Article

The common structure of statistical models of truncation

Authors:
To read the full-text of this research, you can request a copy directly from the author.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... Unfortunately, the requirement for linear regression cannot be usually met in practical applications. In general, output data whose value exceeds the limit of the recording device cannot be observed [J. J. Heckman. (1976); Powell, J. L. (1984); Bottai, M., & Zhang, J. (2010)]. In other words, the output data whose values lie in a certain range are available. Actually, the censored regression can be seen as a nonlinear regression model which includes a saturated nonlinearity model and linear system [Liu, Z., & Li, C. (2017)]. This type of model has been a ...
... sed and wrong estimates ]. Recently, in an attempt to deal with the censored regression problem, numerous algorithms have been proposed. In reference [Cook, J., & Mcdonald, J. (2013)], researches proposed the maximum likelihood algorithm which processes the desirable properties. However, this algorithm holds a heavy computational burden. Reference [J. J. Heckman. (1976)] proposed the Heckman two-step algorithm which consists of two steps: the first step is estimating the bias and the second one is fitting the original linear model. Then, reference [Powell, J. L. (1984)] proposed the least absolute deviation method to address the robust censored regression. To solve online censored regression problems, ...
... on model is widely used in signal processing, communications, and lots of other fields, where observed data are assumed to be available completely. To Unfortunately, the requirement for linear regression cannot be usually met in practical applications. In general, output data whose value exceeds the limit of the recording device cannot be observed [J. J. Heckman. (1976);Powell, J. L. (1984); Bottai, M., & Zhang, J. (2010)]. In other words, the output data whose values lie in a certain range are available. Actually, the censored regression can be seen as a nonlinear regression model which includes a saturated nonlinearity model and linear system [Liu, Z., & Li, C. (2017)]. This type of model has been att ...
Article
In numerous practical applications, the censored observations often occur. Using traditional adaptive algorithms to identify the system of this type may lead to the performance degradation. To address this problem, the distributed censored regression algorithms have been proposed. However, distributed Least Mean Square (D-LMS) based on censored regression has a slow convergence speed. To solve this problem, a variable step size LMS based on censored regression (CR-VSS-LMS) is proposed in this paper.
... The key difference from multiple imputation approaches is that this estimator allows errors to be correlated across the selection and outcome equations. This particular estimator has a motivation similar to the two-stage Heckman estimator (Heckman 1976), although it is less reliant on a particular functional form assumption. ...
... The seventh row presents results from an inverse proportional weighting model that weights observed outcomes in a manner inversely proportional to their probability of being observed (Glynn et al. 2010). The eighth row presents results from Heckman's well-know selection model (Heckman 1976). ...
... If X 2i is not fully observed, the errors in the selection and outcome equations may be correlated. Heckman (1976) models such correlated errors by assuming that the errors in the two equations are distributed as bivariate normal random variables. This allows us to derive the value of the error term in the outcome equation conditional on being observed. ...
Article
Full-text available
To date, field experiments on campaign tactics have focused overwhelmingly on mobilization and voter turnout, with far more limited attention to persuasion and vote choice. In this paper, we analyze a field experiment with 56,000 Wisconsin voters designed to measure the persuasive effects of canvassing, phone calls, and mailings during the 2008 presidential election. Focusing on the canvassing treatment, we find that persuasive appeals had two unintended consequences. First, they reduced responsiveness to a follow-up survey among infrequent voters, a substantively meaningful behavioral response that has the potential to induce bias in estimates of persuasion effects as well. Second, the persuasive appeals possibly reduced candidate support and almost certainly did not increase it. This counterintuitive finding is reinforced by multiple statistical methods and suggests that contact by a political campaign may engender a backlash.
... Unfortunately, the requirement for linear regression may not be usually met in many practical applications. In general, output data whose value exceeds the limit of the recording device cannot be observed [3,15,29]. In other words, the output data whose values lie in a certain range are available. ...
... Since the output data of the censored regression may lose significant information, using the traditional algorithms to identify this type of model may result in biased and wrong estimates [22]. Recently, in an attempt to deal with the censored regression problem, numerous algorithms have been proposed, such as maximum likelihood (ML) methods [8], two-step estimator [15], least absolute deviation [29] To solve online censored regression problems, Liu et al. [24] proposed the adaptive Heckman two-step algorithm (TSA) which significantly outperforms the conventional adaptive algorithms while the output data is censored. ...
... In other words, whend n < 0, the datad n is missing, which leads to the bias and the inequality E[d n |u T n w o ] u T n w o . To compensate the bias, firstly, it is necessary to correct the sample selection bias using FRMS in censored observations, which is inspired by the Heckman two-stage approach [15]. Due to the left-censored property of d n , only positive values of d n can be correctly obtained. ...
Article
Full-text available
In reality, the range of sensor response is limited in many sensor systems due to the saturation characteristics of the sensor. That is, the value exceeding the sensor response range is not observed. Using traditional adaptive algorithms to identify the system of this type may lead to the performance degradation. To address this problem, the censored regression algorithms have been proposed. However, when the mixed sub-Gaussian and super-Gaussian/impulsive noises occur, these algorithms may fail to work. To overcome these drawbacks, a family of robust M-shaped (FRMS) functions for censored regression (CR-FRMS) is proposed in this paper. When the system to be identified exhibits a certain degree of sparsity, the CR-FRMS algorithm cannot fully utilize the characteristics of the sparse system. Therefore, in this paper, proportionate FRMS (PFRMS) algorithm based on \( l_{0} \)-norm constraint for censored regression (\( l_{0} \)-CRPFRMS) is also proposed accordingly. The simulations using Gaussian white noise as the input signal and the non-Gaussian mixed noise as the background noise show that the proposed algorithm performs better than other algorithms.
... si en otro caso 0 0 (7) Una vía alternativa, propuesta por Heckman (1976), sugiere que, dado que los trabajadores no constituyen una extracción aleatoria de la población, se pueden estimar funciones de oferta de trabajo exclusivamente con los datos sobre ocupados, pero teniendo en cuenta el problema de autoselección muestral existente. ...
... Respecto a estos resultados, la elasticidad renta aparece, normalmente, con signo negativo, salvo en Schultz (1980) y Aaberge et al. (2000). Además otros autores -como Aaberge et al. (1999), Trussell y Abowd (1980), Heckman (1980) y Robinson y Tomes (1985)-presentan elasticidades renta que son aproximadamente cero. Por tanto, la mayoría de los estudios presentan elasticidades renta para las mujeres con signo negativo o valores muy cercanos a cero. ...
... En cuanto al efecto sustitución (elasticidad compensada) se observa un rango de valores muy amplio (incluso con valores negativos) y tiene como máximo 14,79 (Heckman, 1980). Asimismo, se observan elasticidades compensadas positivas muy próximas a cero (Duncan y Jones,1994). ...
Book
Full-text available
SIRPIEF es una herramienta que evalúa el impacto de reformas de imposición sobre la renta en España, desarrollada por la Unidad de Microsimulación del Instituto de Estudios Fiscales (UMIEF). Los miembros de la UMIEF son José Félix Sanz (director), Juan Manuel Castañer, Desiderio Romero, Juan Prieto y Francisco José Fernández. El uso de esta publicación y el software asociado para fines académicos, docentes, de consultoría o de cualquier otra índole debe mencionarse expresamente del siguiente modo: “Los resultados que se presentan en este trabajo se derivan del uso del Simulador del Impuesto sobre la Renta Personal del Instituto de Estudios Fiscales (SIRPIEF). Para la documentación de esta herramienta consúltese: Sanz J.F.,Castañer J.M., Romero D., Prieto J. y Fernández F.J. (2004). Microsimulación y Comportamiento Laboral en las Reformas de la Imposición sobre la Renta Personal. El Simulador del Impuesto sobre la Renta Personal del Instituto de Estudios Fiscales (SIRPIEF). Madrid: Instituto de Estudios Fiscales.”
... C'est moins l'exactitude de la mesure du phénomène que le type d'effet qu'il engendre qui nous intéresse ici 47 . La prise en compte du paramètreθ dans l'équation d'indemnité de justice s'apparente à la procédure de correction des biais de sélection proposé par Heckman(Heckman (1976),Heckman (1979)). Le coefficient de régression associé au terme correctifθ est une covariance pondérée entre les erreurs des différents postes d'indemnités et le terme d'erreur de l'indemnité totale.Cette variable explicative additionnelle a ainsi pour mission de corriger le biais dû à la probable corrélation, du fait de l'hétérogénéité, entre chaque terme d'erreur des postes d'indemnités et celui de l'indemnité totale. ...
... C'est moins l'exactitude de la mesure du phénomène que le type d'effet qu'il engendre qui nous intéresse ici 47 . La prise en compte du paramètreθ dans l'équation d'indemnité de justice s'apparente à la procédure de correction des biais de sélection proposé par Heckman(Heckman (1976),Heckman (1979)). Le coefficient de régression associé au terme correctifθ est une covariance pondérée entre les erreurs des différents postes d'indemnités et le terme d'erreur de l'indemnité totale.Cette variable explicative additionnelle a ainsi pour mission de corriger le biais dû à la probable corrélation, du fait de l'hétérogénéité, entre chaque terme d'erreur des postes d'indemnités et celui de l'indemnité totale. ...
Article
Full-text available
In most economic models of damage compensation, the indemnity is proportional to the fault and victims have to file the claim. Contrary to the tort law approach, a growing number of reparation mechanisms choose to ignore the fault ("no-fault law") to compensate damages in their entirety. The Badinter law, which regulates the compensation of damages from traffic accidents in France, is a perfect example. One particular feature of this setting is that the party paying for the damages is likely to have imperfect information on the actual value of the loss and has to make an out-of-court offer. In turn, the victim has the option to accept the offer or to go to court. This study develops a model with these particular features based on the fact that unobserved component of the damages are correlated with observed ones. Estimation of the model is conducted on AGIRA files for all settlement between 2004 to 2006. We find a negative correlation between observed and unobserved dimensions of damages. The model explains the fact that compensations for each component of the damage is higher in out-of-court settlements, while the global indemnity is higher for in-court settlements and is mainly chosen by the most injured.
... Failure to do so leads to selection bias, which will generate faulty and misleading conclusions. This selection bias arises because farmers who would obtain lower than average net returns from the adoption of mineral fertiliser, given price and fixed factors, choose not to adopt the technology and this truncates the observed distribution of the net return function (Pit 1983;Heckman, 1976). Selection bias also occurs when unobserved factors influence both error terms of the adoption Eq. ...
... The most commonly used econometric methods in the literature include the propensity score matching (PSM) method and the instrumental variable approach. It is argued that the propensity score matching approach is unable to account for unobservable factors that affect the adoption process (Heckman, 1976). For this reason, the instrumental variable approach is highly recommended since it can address both observable and unobservable characteristics associated with the adoption decision process. ...
Article
Poor soil fertility emanating from land degradation is one of the causes of low crop productivity in Sub-Saharan Africa. Therefore, the issues of food insecurity and poverty have become prevalent in these countries. It is however imperative to explore agricultural innovations such as mineral fertiliser to improve soil fertility of the arable lands in Africa including Nigeria. In this study, we analyse the adoption of mineral fertiliser and its economic impacts on the livelihoods of 400 rural farmers in Nigeria. We apply the endogenous switching regression and propensity score matching approaches in the empirical analyses. We find that the adoption of mineral fertiliser increases cassava yields and net revenues of rural farmers. The enhanced cassava yields and net revenues have implications on the transformation of rural economy by reducing food insecurity, minimising poverty, and improving the overall well-being of rural farmers. The results also show that farmer age and leasing negatively influence the adoption of fertiliser whereas farmer education, experience in cassava farming, household size, keeping of farm record, location differential, access to credit, membership of farmer association, and herbicides show positive effects. To achieve higher adoption of fertiliser among rural farmers, we recommend that agricultural policies could target the aforementioned key factors.
... In addition, we run Heckman models (Heckman, 1976(Heckman, , 1979 to control for sample selection in Model I and Model II. The new estimates are supposed to capture unobserved factors which could increase the likelihood of (i) having smartphone ownership and being in better health/mental health and more integrated, and (ii) using m-Integration applications and being in better health/mental health and more integrated. ...
... In Sections 8a-8c we examined associations between the number of m-Integration applications in use and the level of immigrants' integration, health and mental health by restricting the sample to smartphone owners. Running Heckman models (Heckman, 1976(Heckman, , 1979 to control for potential sample selection the presented outcomes (in Sections 8a-8c) are found to be held. Associations are estimated between the number of m-Integration applications in use and increased levels of integration (0.082, p < 0.01, or 4.6%), better health (2.203, p < 0.01, or 5.7%) and decreased adverse mental health symptoms (− 1.260, p < 0.01, or − 13.0%). ...
Article
Using panel data on immigrant populations from European, Asian and African countries the study estimates positive associations between the number of mobile applications in use aiming to facilitate immigrants’ societal integration (m-Integration) and increased level of integration (Ethnosizer), good overall health (EQ-VAS) and mental health (CESD-20). It is estimated that the patterns are gender sensitive. In addition, it is found that m-Integration applications in relation to translation and voice assistants, public services, and medical services provide the highest returns on immigrants’ level of integration, health/mental health status. For instance, translation and voice assistant applications are associated with a 4% increase in integration and a 0.8% increase in good overall health. Moreover, m-Integration applications aided by artificial intelligence (AI) are associated with increased health/mental health and integration levels among immigrants. We indicate that AI by providing customized search results, peer reviewed e-learning, professional coaching on pronunciation, real-time translations, and virtual communication for finding possible explanations for health conditions might bring better quality services facilitating immigrants’ needs. This is the first known study to introduce the term ‘m-Integration’, quantify associations between applications, health/mental health and integration for immigrants, and assess AI’s role in enhancing the aforementioned outcomes.
... The study of research and development (R&D) determinants is a classic topic in industrial organization. From a theoretical point of view, these studies are generally supported on Dorfman-Steiner-type (1954) models, in which profit-maximizing firms choose the level of R&D investment that equalizes the marginal revenue effect and the marginal cost effect of R&D expenditure (Kamien and Schwartz, 1970, 1976, 1978, 1982Needham, 1975;Scherer, 1980). 1 The specific relation among the key variables depends on whether the R&D investment is considered a demand-increasing strategy and/or a cost-reducing strategy. In particular, Cohen and Levin (1989) emphasize that the impact of price elasticity of demand will be ambiguous in empirical studies that do not distinguish between product and process innovation: the gains from process innovation, which is associated with cost-reducing strategies, will be larger the more elastic demand is (Kamien and Schwartz, 1970), while the gains from product innovation, which is related to demand-increasing strategies, will be larger the more inelastic demand is, given that inelastic demand could amplify the gains from a rightward shift in the demand curve (Spence, 1975). ...
... For this reason, both equations are usually estimated as a generalized Tobit model by maximum likelihood 19 Sometimes this first block involves just one equation when the sample refers to innovative firms. (Heckman, 1976(Heckman, , 1979. In the original paper, the innovative effort is approached by the research-technological capital per employee. ...
Chapter
This chapter (Chapter 18) is devoted to the empirical models of firms’ R&D. This literature is still growing due to the increasing availability of micro-data. Taking this fact into account, the main purpose of this chapter is to provide an overview of three important topics covered by the recent literature: the determinants of firms’ R&D investment, the link between R&D, innovation and productivity, and the analysis of the R&D black box. This chapter is presented as an invitation to industrial organization practitioners, both theorists and applied, to cross the bridge (and to change sides) between theory and applications.
... The study of research and development (R&D) determinants is a classic topic in industrial organization. From a theoretical point of view, these studies are generally supported on Dorfman-Steiner-type (1954) models, in which profit-maximizing firms choose the level of R&D investment that equalizes the marginal revenue effect and the marginal cost effect of R&D expenditure (Kamien and Schwartz, 1970, 1976, 1978, 1982Needham, 1975;Scherer, 1980). 1 The specific relation among the key variables depends on whether the R&D investment is considered a demand-increasing strategy and/or a cost-reducing strategy. In particular, Cohen and Levin (1989) emphasize that the impact of price elasticity of demand will be ambiguous in empirical studies that do not distinguish between product and process innovation: the gains from process innovation, which is associated with cost-reducing strategies, will be larger the more elastic demand is (Kamien and Schwartz, 1970), while the gains from product innovation, which is related to demand-increasing strategies, will be larger the more inelastic demand is, given that inelastic demand could amplify the gains from a rightward shift in the demand curve (Spence, 1975). ...
... For this reason, both equations are usually estimated as a generalized Tobit model by maximum likelihood 19 Sometimes this first block involves just one equation when the sample refers to innovative firms. (Heckman, 1976(Heckman, , 1979. In the original paper, the innovative effort is approached by the research-technological capital per employee. ...
... It should be noted that although the incidentally truncated regression model (Heckman 1976) has been applied in a wide variety of areas (see e.g., Maddala 1983;Uggen 1999;Wynand and van Praag 1981), this is the first time it has been used in the study of plea bargaining. Our analysis also offers an important methodological innovation: we decompose ρ into constituent covariation terms in order to assess whether the miscarriage of justice contributes to the empirically estimated value of ρ. ...
... Therefore, IPW is inappropriate a priori because it imposes restrictions that are unnecessarily strong. Instead, we draw on the incidentally truncated regression model (ITM) (Heckman 1976), in which the outcome variable is dichotomous rather than continuous (Wynand and van Praag 1981), and which, in contrast to IPW, does not assume that unobservables in selection are ignorable. Nevertheless, we compare results obtained by IPW, which are sensitive to hidden confounders, with results obtained by our preferred methodology. ...
Article
Full-text available
Objectives We examine whether, on average, plea bargaining encourages guilty pleas among defendants who are factually innocent. Methods We develop a formal theory of plea bargaining in which defendants take into account the possibility of false convictions or acquittals when making plea-bargain decisions. We use an incidentally truncated bivariate probit model to test the theory, which predicts that if innocent defendants plead guilty, the correlation (ρ) between the unobserved heterogeneity regarding selection into trial and regarding conviction at trial should be sufficiently positive. The method does not require knowledge of whether individual defendants are factually guilty or innocent. Since ρ is also predicted to vary directly with the unobserved toughness of prosecutors, we develop a decomposition theorem to distinguish between the effects of defendants and prosecutors in plea bargain decisions. Results Using data on 2012 criminal cases decided in Israeli courts from 2010 to 2011, we find that ρ is large and positive. Hence, defendants who did not plea bargain were positively selected in terms of conviction. This means that defendants who accepted plea bargains had smaller counterfactual conviction probabilities than observationally similar defendants who went to trial. Conclusions The results indicate that, on average, factually innocent defendants in Israel during this period took plea bargains instead of going to trial. This contradicts “innocence effect” theory, which predicts that factually innocent defendants, on average, reject plea bargains. Our findings are important for research on shadow trial theory, since they show that selection into plea bargains cannot be ignored when inferring counterfactual trial outcomes for plea bargainers.
... To deal with this challenge, we use a two-stage selection model à la Heckman (1976Heckman ( , 1979 to identify the impact of foreign workers on (i) the export mode decision of the firm, and (ii) its export value which is conditional on its export mode. In other words, the Heckman selection model allows us to estimate the probability of a firm to be classified in one of the two groups of exporters (indirect or direct exporters), and to then use the estimated probability to analyse the firm's export value. ...
... To deal with this challenge, we use a two-stage selection model à la Heckman (1976Heckman ( , 1979 to identify the impact of foreign workers on (i) the export mode decision of the firm, and (ii) its export value which is conditional on its export mode. In other words, the Heckman selection model allows us to estimate the probability of a firm to be classified in one of the two groups of exporters (indirect or direct exporters), and to then use the estimated probability to analyse the firm's export value. ...
Article
Full-text available
This paper explores the link between the use of trade intermediaries and foreign employment and its implications for Vietnamese firms. The role of trade intermediaries – who “purchase from suppliers for resale to buyers or [...] help buyers and sellers to meet and transact” (Spulber, 1996) – is closely related to the export-enhancing role of foreign workers. We use a heterogeneous firm model to show that foreign employment favours the selection of firms into indirect exports as long as the gain realised by indirectly accessing all destinations is higher than the advantage to directly export to the destination of interest. We use a sample of foreign and domestic firms derived from the Viet Nam Industry Investor Survey 2010 by UNIDO. Using a two-stage Heckman selection model, we find evidence of a positive impact of foreign employment on the probability to export indirectly and – conditional on the export mode – on the export value. Our results suggest that the employment of foreign workers eases access to trade intermediaries.
... Ruf et al. (2001) argue that possible reasons for inconclusive results include improper methodology, no theoretical background, poor measurement of CSR, mismatch between measures of CSR and firm value, and small sample size. Wu and Shen (2013) propose the use of an extended version of the Heckman's (1976) two-step regression to examine the association between CSR and financial performance. The first step uses a multinomial logit model, and the second step estimates the performance equation with the inverse Mills's (1926) ratio from the first step. ...
Article
Full-text available
Purpose Corporate social responsibility (CSR) has several dimensions that are inherently unobservable or measured with errors. Due to measurement errors of CSR proxies, regression analysis seems inappropriate for investigating the relationship between CSR and firm value. Accounting for CSR measurement errors, this study therefore uses a latent variable analysis to examine whether CSR affects firm value. Design/methodology/approach This study applies a latent variable model that directly takes into account the measurement errors of CSR proxies. Moreover, the inclusion of firm-fixed effects in the model controls for time-invariant unobservable firm-specific characteristics that may drive both CSR and firm value. CSR is measured by environmental, social, and corporate governance activities. Findings Based on data of US firms between 2002 and 2014, this study finds conflicting evidence of a direct association between each CSR proxy and firm value. When all CSR proxies are incorporated into a latent variable model, CSR significantly positively impacts firm value. Therefore, CSR strategies based on a single measure of CSR or the equal weighting of CSR measures tend to underestimate the influence of CSR on firm value. Practical implications .Corporate managers should enhance firm value by simultaneously engaging in environmental, social, and corporate governance activities because there is a synergistic effect with firm value. Furthermore, investors who downplay CSR factors in firm valuation can lead to significant errors in making equity investment choices. Originality/value This study presents a novel examination of the price-earnings ratio in the CSR valuation by using the latent variable model with firm-fixed effects.
... In the presence of sample selection, OLS estimation of box office equations could yield biased and inconsistent estimators (Gronau, 1974;Heckman 1974;Heckman, 1976;Heckman, 1979). It is widely recognized that the standard Heckman procedure is susceptible to identification problems and sensitivity of results to model specification and distributional assumption (Vella, 1998). ...
... Çeşitli kayıtdışı çalışma tanımlarını uygulayarak farklı işgücü piyasası konumlarını karşılaştırdılar: Kendi başına çalışanlar, 10'dan az işçinin bulunduğu işletmelerde çalışanlar, 10'dan fazla işçinin çalıştığı firmada kayıtlı çalışanlar ile aynı büyüklükteki firmada kayıtdışı çalışanlar. Pages ve Madrigal (2008), sadece çalışanlara odaklanılmasından dolayı meydana gelen seçilim sapmasından kurtulmak için iki aşamalı Heckman düzeltme yöntemini (Heckman, 1976) kullandılar. Birinci aşamada işgücüne katılma denklemi, ikinci aşamada ise iş memnuniyeti denklemi tahmin edildi. ...
Article
Full-text available
The economic modernization theory (Lewis, 1954) predicts that when any given developing economy completes the necessary stages for economic progress, its dual economic structure will be radically transformed. Throughout this transformation, the dual economic structure, which is characterized by the coexistence of formal and informal sectors, gradually disappears and is replaced by the modern formal sector. One consequence of economic modernization is expected to be the elimination of informal employment arrangements. In the second decade of the twenty-first century, however, it appears that this prediction has failed, in the sense that informal employment is a permanent feature of not only developing economies, but also developed ones. Furthermore, for any given labor market, although informal employment is still important in terms of its size, its composition is becoming more diverse. Indeed, the informal sector continues to provide job opportunities for low-skilled and poor individuals. In addition, high-skilled individuals or those with different preferences regarding work-life balance are increasingly placing themselves in informal jobs. Thus, because of its permanent and changing characteristics, researchers have become increasingly interested in the causes and consequences of informal employment. When aiming to gauge the economic and social consequences of informal employment, it is essential to understand the theoretical approaches that can explain the mechanisms that allocate individuals between formal and informal employment. This is because driving forces of these mechanisms determine the direction of predictions regarding how informal employment is related to individuals’ economic and social welfare. There are two main theoretical approaches: The perfectly competitive market approach and the segmented market approach. According to the perfectly competitive approach, individuals’ ability, skills, and human and social capital can be decisive factors in their choice between informal and formal employment. In this choice-based framework, based on their comparative advantages, individuals perform cost-benefit calculations and then decide whether to work in informal jobs. Therefore, the perfectly competitive market approach states that when all relevant individual characteristics are taken into account, the effect of informal employment is expected to be zero. This zero-effect is considered to hold for both monetary outcomes, such as wages, and nonmonetary outcomes, such as life or job satisfaction. In contrast, according to the segmented market approach, those who are excluded from the formal labor market have to work in informal jobs. Here, informal employment provides individuals necessary means to cover their basic expenditures. Therefore, unlike the competitive market approach, where informal employment is considered as a voluntary form of employment, the segmented market approach conceptualizes informal employment as an involuntary form of employment. For this reason, the segmented market approach predicts that there might be negative welfare consequences of informal employment. In reality, it is likely that informal employment can be a mix of both voluntary and involuntary employment. In this regard, among those who are working informally, the relative shares of voluntary and involuntary employment determine the net effects of informal employment on individuals’ outcomes. Thus, the relation between informal employment and individuals’ wellbeing remains to be determined empirically, which constitutes the main purpose of this study. Adopting this framework, for Turkey, this is the fırst study to ask the question of whether the divide between life and job satisfaction measures among salaried workers occurs along with the formal-informal employment divide. Conducting an association analysis with data from the Turkey Life Satisfaction Survey for the 2004-2012 time period, Ordered Probit and Ordinary Least Squares Methods were implemented to estimate the impact of informal employment on various measures of satisfaction. Estimation results suggest that informal employment is negatively related to the life and job satisfaction measures. This negative association remains robust across different specifications and estimation procedures. Furthermore, the study also evaluates the extent to which the negative associations between informal employment and satisfaction measures differ across gender, age, and education groups. The analysis highlights that the adverse consequences of informal employment are prevalent in all sub-groups. For some satisfaction measures, however, these negative consequences appear to be weaker among women, university graduates, and older individuals. As a concluding remark, it remains to be determined empirically whether estimated negative effects found in this study reflect the causal relationship between informal employment and satisfaction measures or whether these effects are simply driven by identification problems, such as sample selection, omitted variables, reverse causality, or measurement error. Future works with more sophisticated data sets and estimation methods are needed to address these problems.
... Heckman, 1976 :) ( 2 ) ‫یوی‬ ‫الگیییی‬ ‫پروبيت‬ k k k Z B X V    , 1, 2,..., k n  1 k Z  , if * 0 k Y  0 k Z  , if * 0 k Y  ( 0 ) ‫یوی‬ ‫الگیییی‬ ‫خطی‬ ‫رگرسيون‬ k k k k Y B X e      ,‫طيف‬ 1 ‫شامل‬ ‫ای‬ ‫گزینه‬ : ‫هيچ‬ ( 3 ) ‫ک‬ ‫خيلی‬ ، ( 6 ) ‫ک‬ ، ( 2 ) ‫متوسط‬ ، ( 0 ) ‫،زیاد‬ ( 1 ) ‫زیاد‬ ‫خيلی‬ ، ( 5 .)Six point spectrum: none (0), very low (1), low (2), medium (3), high (4), very high (5). ...
Article
Full-text available
Gonabad Township in Khorasan Razavi province is one of the largest saffron producers in Iran. Unfortunately, the yield of saffron farms in Gonabad has decreased drastically in recent years. Evidences and the opinions of agricultural engineers suggest that high-density planting can be considered as one of the main reasons of yield decreases. With high-density planting, the operation period of saffron farms will start sooner. However, it will decrease the length of operation period tremendously. Furthermore, the farm won’t be suitable for saffron cultivation for a long time. Therefore, the present study was conducted with the aim of investigating the effect of high-density planting on yield of saffron farms and determining socio-economic factors affecting unsustainable system of high-density planting. Data of the first 6-years of farms (2011-2016) were collected and in order to analyze the data, a two-stage Heckman model which include a Probit model and a linear regression model was used. Our study findings show that farmers' age, awareness towards factors that reduce yield of saffron farms, and attending training courses are three factors that have a negative and significant impact on planting density. In the other word, these three factors could prevent planting of saffron in high density. Farmers' income and their level of education are two factors which are considered to have a positive and significant impact on planting density. Finally, crop insurance doesn't have a significant impact in none of two models. Therefore, we strongly recommend that farmers should be warned of factors that cause yield decreases throughout training courses. Also, we recommend using of the experience of old and experienced farmers in order to prevent planting saffron in high densities.
... Harford and Uyasal (2014)), we adopt a different approach to tackle endogeneity using linear regression with endogenous treatment effects, a methodology proposed by Maddala (1983) 13 For detailed definitions see section 2.2. based on Heckman (1976Heckman ( , 1978. The overall estimation structure is described below. ...
Article
Full-text available
We investigate hold-up problems in debt financing among publicly traded firms with apparently limited information asymmetries. Based on the prediction by Rajan (1992), we examine how changes in short-term bank loan ratio affect firm investment behavior. We confirm that, while investment by bank-dependent firms reduces with increasing ratio of short-term loans, this negative effect is mitigated or offset for firms with access to the public debt market. Consistent with Rajan (1992), this finding suggests that, as many Japanese firms lack access to the public market because of the absence of public debt issuance under the BBB rating, even publicly traded firms face potential hold-up problems in their relationships with banks. The results presented here help explain why firms without access to public debt have consistently lower investment rates than firms with such access, and suggest that the former face an underinvestment problem.
... First, we control for variables that prior studies have shown to influence investment levels (Hulse & Livingstone, 2010;Richardson, 2006;Shin & Kim, 2002). Second, to determine whether making DTD-investments is more beneficial for some firms than for others, and whether firms that do make such investments also have higher overall levels of investment, we control for the impact of a possible self-selection bias on the results by using the Heckman two step procedure (Heckman, 1976). We explain the procedure in 6 The firms that have missing values for 2011, on average invested more in 2009 and 2010, were more profitable and used the regulation more often. ...
Article
Full-text available
Prior studies have shown limited impact of the US bonus depreciation rules on firm investments during economic downturns. In this article we study the effects of a set of more flexible rules – discretionary tax depreciation (DTD) – introduced in the Netherlands during the 2009–2011 economic crisis. Our simulation results show DTD, which allows firms to accelerate and also to postpone depreciation, to be much more effective than bonus depreciation in reducing the expected value of tax payments, especially in crisis periods. Using a sample of 325 clients of a single office of a Dutch accounting firm, we show that DTD has led to higher investments in assets qualifying for discretionary depreciation for firms that faced the highest marginal tax rate. For other firms, the additional investments crowd out investments in assets that do not qualify for DTD. Our analysis on the actual depreciation choices reveals that firms postpone depreciation when facing losses or loss carry forwards, or to smooth taxable income under the progressive tax system. Our results suggest that a fiscal policy that permits firms to postpone depreciation, as well as to accelerate, may stimulate investment.
... An important question regarding sample selection bias across waves of the survey is whether respondents who drop out of the study share characteristics that are associated with the study outcome (Heckman, 1976). Attrition bias is a problem if respondents with incomplete data have different trajectories from those who remain in the sample. ...
... In comparison, Rodgers (2001) emphasised estimation methods and the need to control for unobserved heterogeneity with panel data modelling, which has subsequently been echoed in Cohn and Johnson (2006) and Andrietti and Velasco (2015). Alternatively, Horn et al. (2011) proposed the heckit model (Heckman 1976) to correct for sample selection bias. Mixed results were obtained across these studies with respect to finding a statistically significant effect of attendance on grades. ...
Article
Full-text available
One of the more noticeable changes to tertiary teaching over the past decade has been the widespread adoption of digital technologies, in particular eLearning platforms and lecture capture technology. However, much of the current knowledge of how students utilise these new technologies and their effect on traditional lecture attendance is simply derived from student surveys rather than comprehensive independent analyses. In this study, we use cluster analysis to identify common lecture resource utilisation patterns for students in four large first-year business subjects. While common usage patterns with respect to lecture attendance, video lecture recording access and download of lecture notes are identified across our subjects, the proportion of students within each of the utilisation clusters varies widely. Business statistics students are much more likely to either attend lectures or view video recordings compared to economics students, many of whom rely solely on the download of lecture notes. In order to gain insight into how student characteristics may affect these utilisation patterns, we develop a predictive model, quantifying the influences of prior academic performance, gender, age, distance from campus and international student status using statistical modelling. We find a strong role for students’ previous academic performance in explaining lecture resource utilisation patterns. Students’ commuting distance to campus is also established as a factor dissuading physical lecture attendance. Contrary to initial expectations, we also found that females and older students tend to rely more heavily on digital resources rather than lecture attendance. It is hoped that these findings can help first-year instructors and University administrators understand the heterogeneity of student lecture engagement patterns within the first-year experience.
... In sensitivity analysis, missing data will be treated as failure to achieve the desired outcome. If data are missing not at random (MNAR), we will employ sensitivity analysis, using selection [98] or pattern mixture [99,100] models. ...
Article
Full-text available
Background Among those at highest risk for COVID-19 exposure is the large population of frontline essential workers in occupations such food service, retail, personal care, and in-home health services, among whom Black and Latino/Hispanic persons are over-represented. For those not vaccinated and at risk for exposure to COVID-19, including frontline essential workers, regular (approximately weekly) COVID-19 testing is recommended. However, Black and Latino/Hispanic frontline essential workers in these occupations experience serious impediments to COVID-19 testing at individual/attitudinal- (e.g., lack of knowledge of guidelines), social- (e.g., social norms), and structural-levels of influence (e.g., poor access), and rates of testing for COVID-19 are insufficient. Methods/design The proposed community-engaged study uses the multiphase optimization strategy (MOST) framework and an efficient factorial design to test four candidate behavioral intervention components informed by an integrated conceptual model that combines critical race theory, harm reduction, and self-determination theory. They are A) motivational interview counseling, B) text messaging grounded in behavioral economics, C) peer education, and D) access to testing (via navigation to an appointment vs. a self-test kit). All participants receive health education on COVID-19. The specific aims are to: identify which components contribute meaningfully to improvement in the primary outcome, COVID-19 testing confirmed with documentary evidence, with the most effective combination of components comprising an “optimized” intervention that strategically balances effectiveness against affordability, scalability, and efficiency (Aim 1); identify mediators and moderators of the effects of components (Aim 2); and use a mixed-methods approach to explore relationships among COVID-19 testing and vaccination (Aim 3). Participants will be N = 448 Black and Latino/Hispanic frontline essential workers not tested for COVID-19 in the past six months and not fully vaccinated for COVID-19, randomly assigned to one of 16 intervention conditions, and assessed at 6- and 12-weeks post-baseline. Last, N = 50 participants will engage in qualitative in-depth interviews. Discussion This optimization trial is designed to yield an effective, affordable, and efficient behavioral intervention that can be rapidly scaled in community settings. Further, it will advance the literature on intervention approaches for social inequities such as those evident in the COVID-19 pandemic. Trial registration ClinicalTrials.gov: NCT05139927 ; Registered on 11/29/2021. Protocol version 1.0. May 2, 2022, Version 1.0
... To overcome these restrictive assumptions, alternative studies in agricultural economics literature have used the Heckman's selection model (Heckman, 1976). Mujawamariya and D'Haese (2011), analysed determinants of choice for interlocking in the gum Arabic sector in Senegal and the effect of interlocking on gum production and market participation. ...
Article
Full-text available
Linking smallholder farmers to modern value chains through contract agriculture (CA) is one of the rural development strategies being promoted to address the challenge of smallholders’ integration in markets. However, the conditions under which CA enhances smallholders’ prospects for inclusion in modern value chains is still debatable. This paper examines the determinants of smallholders’ participation in Zambian dairy markets through interlocked contractual arrangements (ICAs). A multi-stage sampling design was used to select 266 households from milk shed areas from three districts in Lusaka and Central provinces of Zambia. A double-hurdle model was estimated from data collected through semi-structured questionnaires, key informant interviews and focus group discussions. Key determinants of smallholders’ participation in ICAs included ownership of improved breed animals, MCC milk price, access to dairy marketing information, income from other sources and landholding size. While most of these factors also affected the proportion of milk sold, the following were also important: household head education level, cattle rearing culture, extent of supplier’s dependency on buyer and trust in the exchange relationship. To enhance smallholders’ market participation, there is need to facilitate their access to extension services, infrastructure (breeding centres, MCCs and water) and affordable stock feed, and to offer them an effective milk price that is higher than the spot market price. Promotion efforts should target smallholders that are literate, from a cattle rearing culture, and particularly encourage youth and women participation. There is also need for building trust in the exchange relationship and judicious use of power by processors.
... Various studies have applied Heckman correction methods (Heckman, 1976(Heckman, , 1979 or instrumental variables techniques to test for and correct for sample selection and simultaneity bias in the estimation of the pest-control outcome equation (1) (Burrows, 1983;Rejesus et al., 2009;Carlberg et al., 2014;Fernandez-Cornejo and Ferraioli, 1999;Hall and Duncan, 1984;Fernandez-Cornejo et al., 1994;Carrión Yaguana et al., 2016;Ricker-Gilbert et al., 2008;Isoto et al., 2008). A challenge in applying these methods is to be able to identify a variable in equation (2) that (1) effects IPM adoption, but (2) does not affect the outcome variable y directly, but only through the IPM adoption decision. ...
Chapter
There are two reasons the economics of assessing integrated pest management (IPM) is of interest. First, in addition to reducing health and ecological risks of pest control, IPM seeks to increase farm income and maintain the economic viability of farm operations. So, economic as well as environmental and health outcomes are major goals of IPM. Second, economic constraints can act as barriers to the adoption of IPM practices. An understanding of how IPM affects the farm ‘bottom line’ and more broadly, farm household well-being is crucial to efforts to encourage IPM. Unlike earlier reviews, this chapter provides greater in-depth discussion of Farmer Field School (FFS) programs. These are collective, participatory education programs. Their initial focus was IPM adoption in Asia, but their topical and regional scopes have since expanded (Braun et al., 2006; Van den Berg and Jiggins, 2007). The performance of FFS programs and the evaluation of their performance have been controversial. This chapter discusses recent findings on FFS programs.
... For example, Powell's censored least absolute deviations (CLAD) and symmetrically trimmed least squares (STLS) estimators are well-known non-density based estimators [30,31]. Similarly, Heckman [16] and Khan and Powell [22] present two-step non-density based estimators as alternative to CLAD for the CR model. In the density based estimation procedure, the unknown parameters are estimated based on an underlying error distribution [10]. ...
Article
It is well-known that classical Tobit estimator of the parameters of the censored regression (CR) model is inefficient in case of non-normal error terms. In this paper, we propose to use the modified maximum likelihood (MML) estimator under the Jones and Faddy's skew t-error distribution, which covers a wide range of skew and symmetric distributions, for the CR model. The MML estimators, providing an alternative to the Tobit estimator, are explicitly expressed and they are asymptotically equivalent to the maximum likelihood estimator. A simulation study is conducted to compare the efficiencies of the MML estimators with the classical estimators such as the ordinary least squares, Tobit, censored least absolute deviations and symmetrically trimmed least squares estimators. The results of the simulation study show that the MML estimators work well among the others with respect to the root mean square error criterion for the CR model. A real life example is also provided to show the suitability of the MML methodology.
... From an econometric point of view, a Heckman selection model is a feasible alternative [76,77]. The Heckman selection model was used for the first time to estimate LOS by [30]. ...
Article
Full-text available
There is evidence that increasing the Length of Stay (LOS) contributes to the sustainability of destinations. This paper analyzes LOS determinants in the Schist Villages Network (SVN) in Portugal, where almost half of the visitors are same-day visitors. Given that these visitors generate more environmental impacts, an increase in LOS would help guide tourism towards more sustainable standards. The analysis was performed using several Heckman selection models. Unlike the findings of previous studies, LOS depended mainly on the characteristics of the trip and the destination—not on visitor profile—and can therefore be considered a highly specific form of tourism. Comparatively, motivations associated with rest, residents’ hospitality, and local produce consumption encourage visitors to extend their stay, thereby boosting tourism sustainability. The SVN is also shown to have various cultural and heritage resources that are currently highly valued. However, the leisure offer is insufficient to increase LOS. Furthermore, conventional advertising was not shown to be effective in raising LOS compared with word-of-mouth (WOM). The paper concludes that measures should be adopted to increase the local produce offer, retain population, maintain traditional village activities, and attract visitors from nearby regions. These actions could increase overnight stays and LOS, contributing to more sustainable development.
... Nevertheless, it remains possible that other, unobserved characteristics are influencing the decision whether or not to incarcerate, and also what sentence length to award (Bushway, Johnson and Slocum, 2007). To further mitigate the potential impacts of selection bias, our models therefore also include the Inverse Mills Ratio (Heckman, 1976). 4 ...
Article
Full-text available
Empirical research has repeatedly focused on the potential existence of sentencing disparities. In particular, a growing number of studies have used multilevel models to quantify the extent that ‘similar’ offences are treated alike in different courts. This reliance on multilevel models has resulted in a natural focus on differences in the mean sentence awarded between courts, with the amount of within-group variability generally assumed to be the same in each court. In this paper, we show how multilevel models can be extended by allowing the magnitude of within-court differences to be different in each court. This provides a natural framework to connect between-court disparities with the sentencing differences that are thought to originate between judges operating within the same court, particularly in the absence of more fine-grained sentencing data about the judge residing in each case. Focusing specifically on cases of assault sentenced in 2011, we show that there are substantial differences in the range of sentences awarded in different courts, with the range almost twice as large in some courts. We also find that it is those courts that appear to show the traits of more homogeneous sentencing that sentence more harshly and that offences involving the presence of a weapon or evidence of good character and/or exemplary conduct were associated with higher levels of internal consistency.
... After data merging due to missing values, we lost a number of observations from the EFES dataset, which might lead to representation bias. Thus, following past research (Freeman et al. 2010), we used Heckman selection correction (Heckman 1976). From the EFES dataset, we included organizational size, industry-year dummies, and country dummies in the first stage of the analysis. ...
Article
Full-text available
Did publicly traded European firms with employee ownership (EO) realize higher firm performance during or after the Great Recession? Contributing to the growing interest in exploring the association between EO and firm performance during and after the 2008 economic crisis, we draw on a longitudinal sample of 4,259 firm‐years representing 892 publicly traded firms from 28 European countries. The results show that compared to firms without EO, those with EO experienced higher firm performance during or after the recession, albeit with small effect size. Consistent with past findings, we found that firms with EO were less likely to lower their employee count during or after the recession. Findings are robust to controlling for contemporaneous endogeneity and alternate specifications. Our results indicate that publicly traded European firms with EO, on average, realized higher firm performance in the face of the Great Recession.
... Most of the literature on gender wage gaps, using decomposition methods such as the Blinder-Oaxaca decomposition, typically ignores selection bias. But some of the studies on this topic have tried to control for self-selection of individuals in the labour market, e.g. by using two-step Heckman procedure (Heckman, 1976;1979). In this case the correction for sample-selection bias will be included in the wage equation whose initial form is as follows: ...
... Therefore, it is better to select a batch of "non-HSR cities" whose characteristics are "as similar as possible" to the treated group as the control group before DID processing. The propensity score matching (PSM) developed by econometric economists such as Heckman [34], and Rosenbaum and Rubin [35] can eliminate sample selection bias. Consistent with Baier et al. [36], this paper establishes a Logit regression model to calculate the propensity scores. ...
Article
Full-text available
The rapid development of the high-speed rail (HSR) network enhanced the regional accessibility between cities, drove the rise in cities’ investment levels, and expanded the activity radius of the labor force, causing changes in housing prices along the rail lines. Based on panel data of 285 cities in China from 2008–2016, this study used the difference-in-difference based on propensity score matching (PSM-DID) method to calculate the impact of HSR on housing prices. The conclusions of the study indicated that, at the regional level, HSR significantly promoted the rise in housing prices in HSR cities along the rail line. HSR had a positive effect on housing prices, where the coefficient of HSR influence was 0.1511 and passed a 1% significance test. From the perspective of the combination of sub-regional and sub-city scales, HSR mainly played a significant role in promoting housing prices in “small and medium-sized cities” and “central and western cities”, especially in small and medium-sized cities in the central and western regions; in general, HSR can narrow the housing price gap between “small and medium-sized HSR cities” in the central and western regions and large HSR cities in the east region. Lastly, the results of the intermediary mechanism test showed that the income level of residents and employment levels played an intermediary role in the influence of HSR on the housing prices of cities along the rail line. Thus, this paper suggests that the Chinese government needs to formulate housing price control policies that suit local conditions according to the characteristics of different cities.
... As the decision to offer loans is conditional on the decision to apply The Impact of Access to Credit on Household Welfare in Rural Vietnam for loans, it is necessary to separate these two stages: first households decide whether to apply for loans and then lenders decide whether to offer or reject the applications. We employ the Heckman approach (see Heckman, 1976, Heckman, & Ashenfelter, 1974, in which the probability of a household receiving a loan depends first on it has a demand for credit and then on whether its application is accepted by the lender (see similar framework, for example, Zeller, 1994). The first-stage model takes the form below: ...
... When conducting PSM, it is important to note that the "unbiased inference" in PSM is based on the assumption that outcomes are independent of assignment to the treatment group on the basis of observable characteristics [20]. In order to have valid results, it is important that between the propensity scores of treatment and control groups, there exists an area of "common-support" [21]. ...
Article
Full-text available
Background Previous research has shown that developing countries account for the majority of maternal deaths around the world. Relatively high maternal mortality in developing countries has been linked to high HIV prevalence rates in these countries. Several studies have shown that women living with HIV are more vulnerable and are thus more likely to die during maternity than those who are not. Although there has been increased focus on this subject in contemporary research, the relationship between HIV status and maternal-care-utilization is not very well understood. It is not clear whether factors associated with professional maternal care utilization during antenatal, delivery and postnatal periods are similar for HIV positive and HIV negative women. It is also not known whether being HIV positive has an impact on the choice of care (professional care or traditional birth attendants). Thus the aim of this study is to investigate the differences in factors affecting choice of care during antenatal, delivery and postnatal periods between HIV positive and HIV negative women. We also investigate the effect of HIV positive status on choice of care. Methods By using the 2013–2014 Zambia Demographic Health Survey Data (ZDHS), we performed two different quantitative analyses. a) Regression analysis: to identify and compare factors associated with the likelihood of utilizing professional care during antenatal, at birth and postnatal periods between HIV positive and HIV negative women. b) Propensity score matching: to investigate the effect of being HIV positive on the choice of care (Professional care or TBAs). Results Our results show that reasons for choosing professional care during antenatal, at birth, and postnatal periods are the same for both HIV positive and HIV negative women. Further, we also showed that although the probability of utilizing professional care is slightly higher for HIV positive women, the difference is negligible. Conclusion We demonstrated that in Zambia, utilization of professional care among HIV positive women is not particularly high. We also demonstrate that although institutional care is desirable and an ideal solution for HIV positive women, insisting on institutional care when the health facilities lack adequate trained personnel, drugs, and equipment is counterproductive.
... Most of the literature on gender wage gaps, using decomposition methods such as the Blinder-Oaxaca decomposition, typically ignores selection bias. But some of the studies on this topic have tried to control for self-selection of individuals in the labour market, e.g. by using two-step Heckman procedure (Heckman, 1976;1979). In this case the correction for sample-selection bias will be included in the wage equation whose initial form is as follows: ...
Article
Full-text available
In this paper, we compare the income distributions for women and men in Poland. The gender wage gap can only be partially explained by different men’s and women’s characteristics. The unexplained part of the gap is usually attributed to the wage discrimination. The objective of the study is to extend the Oaxaca-Blinder decomposition procedure for the pay gap along the whole income distribution. To describe differences between two distributions of incomes we use a semiparametric reweighting approach (DiNardo, Fortin, Lemieux, 1996). The reweighting factor is computed for each observation by estimating a logit model for probabilities of belonging to men’s or women’s group. Then, we estimate probability density functions, including the counterfactual density function, using kernel density methods. This allows us to decompose the inequalities into the explained and unexplained components. The analysis is based on the EU-SILC data for Poland in 2014.
... Based on the findings, adopting appropriate strategies for familiarizing saffron farmers with sustainable agricultural practices, building trust of reliable and experienced farmers to reduce the use of chemical fertilizers, and reforming the structure of agricultural insurance system play a decisive role in improving the farmers' consumption pattern of chemical fertilizers. Heckman, 1976 ) : ...
Article
Full-text available
The use of chemical inputs seriously threaten the sustainability of crop production due to the erosion and destruction of soil health, in such a way that it has been always put into question and concerns for it have been growing. The present study was conducted to investigate factors affecting the application of chemical fertilizers in saffron farms in Gonabad county. To this end, the descriptive-correlation research method was used. The study population consisted of all saffron farmers in Gonabad. Proportional random sampling procedure was used in which 105 saffron farmers were selected. The data collection tool was a questionnaire. Face validity of questionnaire was confirmed by the professors of agricultural economics. Also, the reliability of questions related to attitude towards sustainable agriculture was evaluated by conducting a pilot study in which the Cronbach’s alpha coefficient was calculated as 0.698. Afterwards, a two-stage Heckman model was carried out to investigate factors affecting the use of chemical fertilizers. Based on the results, the coefficient of attitude towards sustainable agriculture in both stages was negative and significant, which represents that improvement of farmers' attitude effectively reduces the use of chemical fertilizers. While the coefficients of variables of farmers' income, age, education level, and agricultural insurance are positive and significant in both stages and increase the probability and amount of using fertilizers by farmers. Based on the findings, adopting appropriate strategies for familiarizing saffron farmers with sustainable agricultural practices, gaining trust of reliable and experienced farmers to reduce the use of chemical fertilizers, and reforming the structure of agricultural insurance system play a decisive role in improving the farmers’ consumption pattern of chemical fertilizers.
Article
Two common sources of violence rates are police data and hospital data on injuries. It is unclear, however, if violence rates calculated using these sources have the same meaning across location types like rural, suburban, and urban areas. We know that characteristics of assault victims and incidents are associated with whether or not the victim reports the incident to the police. If community type moderates this help-seeking behavior—for example, if the impact of sex, age, race, victim–offender relationship, or injury severity on reporting to the police or being treated in an emergency room (ER) is different in rural relative to urban areas—then this selection bias is problematic for comparisons across location type and for including different location types in the same sample. The goal of this study was to determine which victim and incident characteristics are associated with police notification and ER treatment and to see if these characteristics are the same across rural, suburban, and urban areas. We used National Crime Victimization Survey data on reporting serious assaults to the police and being treated in an ER as a result of a serious assault. Results revealed that (1) police notification is much more likely to occur than ER treatment, (2) a majority of victim and incident characteristics are significantly associated with police notification, (3) few victim and incident characteristics are significantly associated with ER treatment, and (4) there is only chance moderation by location type. Findings suggest that both police and hospital data on serious assaults can be used to make comparisons across rural, suburban, and urban communities without being limited by disproportionate inclusion or exclusion of incidents associated with victim and incident characteristics. However, comparisons between the two data sources should be made with caution due to the different victim and incident characteristics associated with police notification and ER treatment.
Article
Delaware hedge funds exhibit significant differences in contractual structure in terms of higher management and incentive fees. Delaware funds are more likely to use high watermark provisions and less likely to invest their personal capital. Both the redemption notice periods and lock up periods are significantly longer for Delaware hedge funds. While Delaware hedge funds do not outperform or underperform funds registered elsewhere, fund flows are more sensitive to Delaware funds' prior performance and Delaware funds are more likely to be liquidated due to poor performance. Further, Delaware funds are more likely to increase risk after poor absolute performance.
Article
Full-text available
Americans work more than Europeans. Using micro-data from the United States and 17 European countries, we document that women are typically the largest contributors to the cross-country differences in work hours. We also show that there is a negative relation between taxes and annual hours worked, driven by men, and a positive relation between divorce rates and annual hours worked, driven by women. In a calibrated life-cycle model with heterogeneous agents, marriage and divorce, we find that the divorce and tax mechanisms together can explain 45% of the variation in labor supply between the United States and the European countries.
Article
Distributed estimation over sensor networks has received a lot of attention due to its great promise for broad applicability. In many cases, sensors have constraints on the range of data they can measure. This may cause that the measurements or observations are censored, and hence the value of a measurement or observation could be only partially known. This paper focuses on distributed censored regression over networks and develops a diffusion-based algorithm for the censored regression. The proposed algorithm first adopts an adaptive bias-corrected estimator based on a probit regression model to reduce the adverse effect of censoring on estimation results, and afterwards carries out the least squares procedure to find the estimate of the parameter of interest in a collaborative manner between every node and its neighbors. The theoretical study of convergence in the mean and mean-square sense reveals that the proposed algorithm is asymptotically unbiased and stable under some conditions. Moreover, simulation results show the effectiveness of the proposed algorithm.
Article
Investment banks and issuers of Chinese domestic IPOs became fully responsible for IPO offer prices only on June 10, 2009. Before this regulatory reform, the optimistic bias in post-IPO earnings forecasts is highly comparable across affiliated and unaffiliated analysts. Afterward, the forecasts of affiliated analysts are 33 percentage points more positively distorted on average. In the first 90 days after an IPO, this relative forecast bias even increases to 63 percentage points and enlarges further when the issuer's stock price drops in the aftermarket. Affiliated analysts distort especially their forecasts for fiscal years further away from the forecast release date.
Article
We derive simple, multi-step estimation methods for a linear model with heterogeneous coefficients when there are both continuous and discrete endogenous explanatory variables. We consider both cross-sectional and panel data settings. When we extend our model to panel data, we use the Chamberlain-Mundlak device to allow heterogeneity to be correlated with time-varying explanatory variables. We apply the panel data methods we propose to estimation of a housing budget share equation where a homeownership dummy variable plays the role of the endogenous regime, and total expenditure plays the role of a continuous endogenous explanatory variable. We find that the constant coefficient model seems sufficient, and that the estimation methods we propose produce rather plausible estimates of the model parameters.
Article
Full-text available
Theories of sentencing have pointed out the association between the sentence and the courtroom workgroup’s joint assessment of defendants’ risk and culpability. One of the most important indicators of risk and culpability is prior criminal records. Types of crimes and pattern of prior criminal events are an important part of the legal discourse around sentencing. This discussion is conceptually similar to the criminal career concept of criminal specialization. In the present study, latent class analysis (LCA) is used to measure criminal specialization. The cumulative disadvantage perspective is incorporated into the article to model how specialization predicts a series of case processing outcomes—dismissal, charge reduction, incarceration, and length of incarceration. The analysis found specialists of the current crime—robbery defendants who specialized in robbery and larceny defendants who specialized in larceny—generally received less favorable outcomes.
Chapter
This article describes empirical methods for estimating dynamic economic systems using time-series data. By design, the methods target specific feature of the dynamic system and do not require a complete specification of the time-series evolution. The resulting generalized-method-of-moments estimation and inference methods use estimating equations implied by some components of a dynamic economic system. This entry describes the statistical methods and some applications of these methods.
Article
Censored observations are encountered naturally in many engineering tasks. Conventional estimation algorithms may suffer from significant performance degradation when the observations are undesirably censored. This work focuses on adaptively estimating the regression parameter in a censored regression model. We first consider that the noise variance and censored thresholds are known a priori, and solve the online censored regression problem by computing the maximumlikelihood estimate in an expectation-maximization framework. This strategy yields a recursive least-squares algorithm for the censored regression (CR-RLS), and we prove its convergence and present analytical results for the steady state error. Next, we extend the CR-RLS to the case of unknown noise variance and censored thresholds. Theoretical analysis and numerical simulation indicate that the CR-RLS performs significantly better than other competing algorithms in terms of both the estimation accuracy and convergence rate. Especially, for different censored thresholds, the CR-RLS can always achieve good performance, and its steady-state solution is almost as accurate as that of the RLS algorithm with the uncensored (complete) observations.
Article
Full-text available
Background More than half of persons living with HIV (PLWH) in the United States are insufficiently engaged in HIV primary care and not taking antiretroviral therapy (ART), mainly African Americans/Blacks and Hispanics. In the proposed project, a potent and innovative research methodology, the multiphase optimization strategy (MOST), will be employed to develop a highly efficacious, efficient, scalable, and cost-effective intervention to increase engagement along the HIV care continuum. Whereas randomized controlled trials are valuable for evaluating the efficacy of multi-component interventions as a package, they are not designed to evaluate which specific components contribute to efficacy. MOST, a pioneering, engineering-inspired framework, addresses this problem through highly efficient randomized experimentation to assess the performance of individual intervention components and their interactions. We propose to use MOST to engineer an intervention to increase engagement along the HIV care continuum for African American/Black and Hispanic PLWH not well engaged in care and not taking ART. Further, the intervention will be optimized for cost-effectiveness. A similar set of multi-level factors impede both HIV care and ART initiation for African American/Black and Hispanic PLWH, primary among them individual- (e.g., substance use, distrust, fear), social- (e.g., stigma), and structural-level barriers (e.g., difficulties accessing ancillary services). Guided by a multi-level social cognitive theory, and using the motivational interviewing approach, the study will evaluate five distinct culturally based intervention components (i.e., counseling sessions, pre-adherence preparation, support groups, peer mentorship, and patient navigation), each designed to address a specific barrier to HIV care and ART initiation. These components are well-grounded in the empirical literature and were found acceptable, feasible, and promising with respect to efficacy in a preliminary study. Methods/design Study aims are: 1) using a highly efficient fractional factorial experimental design, identify which of five intervention components contribute meaningfully to improvement in HIV viral suppression, and secondary outcomes of ART adherence and engagement in HIV primary care; 2) identify mediators and moderators of intervention component efficacy; and 3) using a mathematical modeling approach, build the most cost-effective and efficient intervention package from the efficacious components. A heterogeneous sample of African American/Black and Hispanic PLWH (with respect to age, substance use, and sexual minority status) will be recruited with a proven hybrid sampling method using targeted sampling in community settings and peer recruitment (N = 512). Discussion This is the first study to apply the MOST framework in the field of HIV prevention and treatment. This innovative study will produce a culturally based HIV care continuum intervention for the nation’s most vulnerable PLWH, optimized for cost-effectiveness, and with exceptional levels of efficacy, efficiency, and scalability. Trial registration ClinicalTrials.gov, NCT02801747, Registered June 8, 2016.
Article
Citizens’ perceptions of the police have been recognized as a long-standing issue of significant importance. Positive perceptions of the police, especially as they relate to legitimacy, are not only critical for fostering healthy police/community relationships but also for enhancing community safety. A large body of research has examined the predicates of legitimacy by studying residents’ general police perceptions as well as their perceptions in specific contexts, primarily traffic stops. Much less is known, however, about the sources of police legitimacy in the context of street stop encounters. Consequently, the current study uses data from the 2011 Police Public Contact Survey to examine the role of procedural justice, along with key sociodemographic characteristics—race and class—in shaping perceptions of legitimacy during non-traffic-related police–citizen street encounters. Findings indicate that officer behavior and levels of respect afforded to citizens during these encounters significantly influence perceptions of legitimacy. Implications and policy recommendations are discussed in detail.
Article
We investigate the impact of household air pollution on household health outcomes using the Uganda National Household Survey (2017) and employ a probit model with selection. Results reveal that exposure to household air pollution is significantly associated with cough and fever incidences among household members, with the young ones being more vulnerable. Also, low education level of household head, cooking indoors in a living house, and poverty significantly increases chances of contracting cough and fever. Also, findings show that having a separate indoor built kitchen, high education, being male, residing in urban areas and staying in the northern and western regions significantly reduce the likelihood of contracting cough and fever. Thus, strategies for behavioural interventions such as promoting outdoor cooking and raising awareness of the health hazards associated with household air pollution, good household planning and adoption of clean fuel could be a promising path for policy makers.
Article
In this paper we present a methodology for studying the desired number of additional children. Our methodology involves a generalization of our earlier work. and an application of the estimator proposed by Heckman and the two-stage simultaneous Tobit estimator proposed by Nelson and Olson.
Article
This study examines the effects of corporate governance and corporate social responsibility (CSR) on credit ratings for firms in Taiwan. We examine this causal relationship using ordered logit regressions with two-stage least-squares estimates. We document that CSR performance demonstrates both moderation and partial mediation effects in the relationship between corporate governance and credit rating. Our results indicate that a firm should practice good corporate governance and engage in CSR activities to improve its credit rating. This study further shows that family firms with strong corporate governance and good CSR performance do not benefit from higher credit ratings. However, large firms with good corporate governance practices benefit from higher credit ratings.
Article
Full-text available
This article investigates the factors affecting access to formal credit by micro and small enterprises in Uganda using the Gender Enterprise Survey that was funded by the IDRC. The study employed a probit model. The findings show that firm sales, owner’s education level, belonging to a business association, belonging to business group, use of internet, owning a personal and business bank account, and gender of the owner are positively associated with access to formal credit. We also find that experienced firms are less likely to apply for credit hence reduce the probability to receive formal bank credit. Our results provide insights on the existing gaps in designing supportive policies for micro and small enterprise to enable them increase their access to credit especially from the formal financial institutions.
Conference Paper
The Financial sector expanded whilst remaining stable despite challenging market conditions both globally and domestically and continued to support the growth momentum in the economy. The Banking sector is the dominant sub sector within the financial sector....
ResearchGate has not been able to resolve any references for this publication.