Walter Zucchini

Georg-August-Universität Göttingen, Göttingen, Lower Saxony, Germany

Are you Walter Zucchini?

Claim your profile

Publications (51)28.42 Total impact

  • N. M. Neykov · P. N. Neytchev · W. Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Stochastic daily precipitation models are commonly used to generate scenarios of climate variability or change on a daily time scale. The standard models consist of two components describing the occurrence and intensity series, respectively. Binary logistic regression is used to fit the occurrence data, and the intensity series is modeled by a continuous-valued right-skewed distribution, such as gamma, Weibull or lognormal. The precipitation series is then modeled using the joint density and standard software for generalized linear models can be used to perform the computations. A drawback of these precipitation models is that they do not produce a sufficiently heavy upper tail for the distribution of daily precipitation amounts; they tend to underestimate the frequency of large storms. In this study we adapted the approach of Furrer and Katz (2008) based on hybrid distributions in order to correct for this shortcoming. In particular we applied hybrid gamma - generalized Pareto (GP) and hybrid Weibull-GP distributions to develop a stochastic precipitation model for daily rainfall at Ihtiman in western Bulgaria. We report the results of simulations designed to compare the models based on the hybrid distributions and those based on the standard distributions. Some potential difficulties are outlined.
    Natural Hazards and Earth System Sciences 01/2014; 2(2). DOI:10.5194/nhessd-2-1223-2014 · 1.74 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We develop estimators for line transect surveys of animals that are stochastically unavailable for detection while within detection range. The detection process is formulated as a hidden Markov model with a binary state-dependent observation model that depends on both perpendicular and forward distances. This provides a parametric method of dealing with availability bias when estimates of availability process parameters are available even if series of availability events themselves are not. We apply the estimators to an aerial and a shipboard survey of whales, and investigate their properties by simulation. They are shown to be more general and more flexible than existing estimators based on parametric models of the availability process. We also find that methods using availability correction factors can be very biased when surveys are not close to being instantaneous, as can estimators that assume temporal independence in availability when there is temporal dependence.
    Biometrics 07/2013; DOI:10.1111/biom.12049 · 1.57 Impact Factor
  • Fred Böker · Stefan Sperlich · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Dieser erste Teil des Buches besteht aus der umfangreichen Aufgabensammlung, die wie eingangs gesagt nach 13 Sektionen untergliedert ist. Selbstverständlich folgt die Gliederung der Lösungen, die allesamt im zweiten Teil dieses Buches aufgeführt werden, exakt derjenigen der Aufgabensammlung im ersten Teil. Obgleich die Bereitstellung der in R verfassten Programme in erster Linie zum besseren Verständnis der Aufgaben und Nachrechnen der Lösungen sowie dem Erlernen der Benutzung der Statistiksoftware R dienen soll, werden auch die meisten derjenigen Programme zur Verfügung gestellt, die zum Verfassen der Aufgabenstellung und der dort, also im ersten Teil, erscheinenden Grafiken benutzt worden sind.
    Statistikübungen für Bachelor- und Masterstudenten, 01/2013: pages 1-170; , ISBN: 978-3-642-34787-0
  • Chapter: Lösungen
    Fred Böker · Stefan Sperlich · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Dieser zweite Teil des Buches besteht aus der Sammlung der zumeist ausführlich dargestellten Lösungen zur Aufgabensammlung aus dem Aufgabenteil dieses Buches. Folglich ist sie ebenso in dieselben 13 Themen untergliedert. Wie bereits mehrfach erwähnt, werden zu den meisten der Lösungen auch die entsprechenden in der Statistiksoftware R geschriebenen Programme zur Verfügung gestellt. Eine Einführung zu dieser Software finden Sie im Anhang dieses Buches und natürlich auch in der online-Hilfe der Software selbst. Um sich den Zugang zu dieser Statistiksoftware zu vereinfachen, lohnt es sich, R auch schlicht als Taschenrechner zu benutzen noch bevor man beginnt, komplexere Probleme damit zu lösen. Sie können die bereitgestellten Programme auch jederzeit beliebig modifizieren und somit spielend den Gebrauch dieser Software erlernen.
    Statistikübungen für Bachelor- und Masterstudenten, 01/2013: pages 171-291; , ISBN: 978-3-642-34787-0
  • Roland Langrock · Iain L. MacDonald · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a number of nonstandard stochastic volatility (SV) models and examine their performance when applied to the series of daily returns on several stocks listed on the New York Stock Exchange. The nonstandard models under investigation extend both the observation process and the volatility-generating process of basic SV models. In particular, we consider dependent as well as independent mixtures of autoregressive components as the log-volatility process, and include in the observation equation a lower bound on the volatility. We also consider an experimental SV model that is based on conditionally gamma-distributed volatilities.Our estimation method is based on the fact that an SV model can be approximated arbitrarily accurately by a hidden Markov model (HMM), whose likelihood is easy to compute and to maximize. The method is close, but not identical, to those of Fridman and Harris (1998), Bartolucci and De Luca (2001, 2003) and Clements et al. (2006), and makes explicit the useful link between HMMs and the methods of those authors. Likelihood-based estimation of the parameters of SV models is usually regarded as challenging because the likelihood is a high-dimensional multiple integral. The HMM approximation is easy to implement and particularly convenient for fitting experimental extensions and variants of SV models such as those we introduce here. In addition, and in contrast to the case of SV models themselves, simple formulae are available for the forecast distributions of HMMs, for computing appropriately defined residuals, and for decoding, i.e. estimating the volatility of the process.
    Journal of Empirical Finance 01/2012; 19(1). DOI:10.1016/j.jempfin.2011.09.003 · 0.84 Impact Factor
  • Source
    Katja Landau · Stephan Klasen · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the accuracy of ex ante assessments of vulnerability to income poverty using cross-sectional data and panel data. We use long-term panel data from Germany and apply different regression models, based on household covariates and previous-year equivalence income, to classify a household as vulnerable or not. Predictive performance is assessed using the Receiver Operating Characteristics (ROC), which takes account of false positive as well as true positive rates. Estimates based on cross-sectional data are much less accurate than those based on panel data, but for Germany, the accuracy of vulnerability predictions is limited even when panel data are used. In part this low accuracy is due to low poverty incidence and high mobility in and out of poverty.
  • Source
    Claudia Fichtel · Walter Zucchini · Roland Hilgartner ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Many animals are organized into social groups and have to synchronize their activities to maintain group cohesion. Although activity budgets, habitat constraints, and group properties may impact on behavioural synchrony, little is known regarding how members of a group reach a consensus on the timing of activities such as foraging bouts. Game theory predicts that pair partners should synchronize their activities when there is an advantage of foraging together. As a result of this synchronization, differences in the energetic reserves of the two players develop spontaneously and the individual with lower reserves emerges as a pacemaker of the synchrony. Here, we studied the behavioral synchrony of pair-living, nocturnal, red-tailed sportive lemurs (Lepilemur ruficaudatus). We observed 8 pairs continuously for ≥1 annual reproductive cycle in Kirindy Forest, Western Madagascar. During focal observations, one observer followed the female of a pair and, simultaneously, another observer followed the male. We recorded the location and behavioral state of the focal individual every 5 min via instantaneous sampling. Although behavioral synchrony of pair partners appeared to be due mainly to endogenous activity patterns, they actively synchronized when they were in visual contact (<10 m). Nevertheless, red-tailed sportive lemurs benefit from synchronizing their activity only for 15% of the time, when they are close together. The lack of an early warning system for predators and weak support for benefits via social information transfer in combination with energetic constraints may explain why red-tailed sportive lemurs do not spend more time together and thus reap the benefits of behavioral synchrony.
    International Journal of Primatology 12/2011; 32(6):1383-1396. DOI:10.1007/s10764-011-9551-6 · 1.99 Impact Factor
  • Source
    Jing Dai · Stefan Sperlich · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: A reliable prediction of unconditional welfare distributions, like income or consumption, is essential for welfare analysis, and in particular for inequality, poverty or development studies. Where observations of expenditures or income are missing, the mean prediction based on available covariates is not just a poor estimator of the unconditional distribution; it fails to predict the required information about tails and quantiles. A new estimation method is introduced which can be combined with any mean prediction model. It is used to calculate the income distribution of a survey based on subsample information, to estimate the unconditional income distribution for the non-responding households, and to predict the household expenditures of a future panel wave. It allows for imputing welfare distributions for a census from a survey or for synthetic populations under specific scenarios. Further inference is straight-forward, including prediction of Lorenz curves, indexes like the Gini, or distribution quantiles, including confidence intervals.
    SSRN Electronic Journal 11/2011; DOI:10.2139/ssrn.1965409
  • Neyko Neykov · Plamen Neytchev · Walter Zucchini · Hristo Hristov ·
    [Show abstract] [Hide abstract]
    ABSTRACT: An eight states non-homogeneous hidden Markov model is developed for linking daily precipitation amounts data at a network of 32 stations broadly covering the territory of Bulgaria to large-scale atmospheric patterns. At each site a 40-year record 1960–2000 of daily October–March precipitation amounts is modeled. The atmospheric data consists of daily sea-level pressure, geopotential height at 500 and 850 hPa, air temperature at 850 hPa and relative humidity at 700 and 850 hPa on a 2.5 × 2.5 grid based on NCEP-NCAR reanalysis data set covering the Europe-Atlantic sector 30W–60E, 20N–70N for the same period. The first 30 years data are used for model fitting purposes while the remaining 10 years are used for model evaluation. Detailed model validation is carried out on various aspects. The proposed model reproduces well the rainfall statistics for the observed and reserved data whereas the identified states are found to be physically interpretable in terms of regional climatology.
    Environmental and Ecological Statistics 11/2011; 19(2). DOI:10.1007/s10651-011-0185-9 · 0.93 Impact Factor
  • Source
    Jing Dai · Walter Zucchini · Stefan Sperlich ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In many countries the demand for health care services is of increasing importance. Especially in the industrialized world with a changing demographic structure social insurances and politics face real challenges. Reliable predictors of those demand functions will therefore become invaluable tools. This article proposes a prediction method for the distribution of the number of visits to the medical doctor for a determined population, given a sample that is not necessarily taken from that population. It uses the estimated conditional sample distribution, and it can be applied for forecast scenarios. The methods are illustrated along data from Sidney. The introduced methodology can be applied as well to any other prediction problem of discrete distributions in real, future or any fictitious population. It is therefore also an excellent tool for future predictions, scenarios and policy evaluation.
    SSRN Electronic Journal 11/2011; DOI:10.2139/ssrn.1964285
  • Source
    Georges Nguefack-Tsague · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Although model selection is routinely used in practice, little is known about its precise effects on any subsequent inference that is carried out. The same goes for the effects induced by the closely related technique of model averaging. This paper is concerned with the use of the same data first to select a model and then to carry out inference, in particular point estimation and point prediction. The properties of the resulting estimator, called a post-model-selection estimator (PMSE), are difficult to derive. Using selection criteria such as hypothesis testing, AIC, BIC, HQ and CP, we illustrate that, in terms of risk function, no single PMSE dominates the others. The same conclusion holds more generally for any penalized likelihood information criterion. We also compare various model averaging schemes and show that no single one dominates the others in terms of risk function. Since PMSEs can be regarded as a special case of model averaging, with 0-1 random weights, we propose a connection between the two theories, in the frequentist approach, by taking account of the selection procedure when performing model averaging. We illustrate the point by simulating a simple linear regression model.
    Pakistan Journal of Statistics and Operation Research 10/2011; 7(2-Sp). DOI:10.18187/pjsor.v7i2-Sp.292
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Adult-onset Still's disease (AOSD) is a potentially crippling or life-threatening rare disease that may be self-limited, intermittent, and chronic. Clinical predictors of outcome are still lacking, as is information on the rate of progress of its chronic course. The main objective is to identify factors that improve our ability to predict the course of AOSD, and factors associated with the rate of progress of its chronic course. A comparison with the literature is included. A retrospective cohort observational study conducted at the tertiary-referral Rheumatology Unit in Ferrara, Italy. Seventy-six patients (44 females and 32 males) referred to the Unit and who satisfied the criteria for AOSD were identified. Our findings on white AOSD patients are largely compatible with those previously published. Ferritin level, as well disease activity score (DAS(28)), is associated with the rate of progression of the articular manifestations of the disease. A polyarthritis persisting over 6 months is associated with the development of a chronic articular course, irrespective of the size of the involved joints. Ferritin, being associated with the course of AOSD, could play a role in the diagnosis of the disease. Together with DAS(28), it might also serve as a useful predictor for the rate of progress of the chronic course of the disease, as measured with simple erosion narrowing score.
    Seminars in arthritis and rheumatism 03/2011; 41(2):279-85. DOI:10.1016/j.semarthrit.2010.12.006 · 3.93 Impact Factor
  • R. Langrock · W. Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: A hidden Markov model (HMM) with a special structure that captures the ‘semi’-property of hidden semi-Markov models (HSMMs) is considered. The proposed model allows arbitrary dwell-time distributions in the states of the Markov chain. For dwell-time distributions with finite support the HMM formulation is exact while for those that have infinite support, e.g. the Poisson, the distribution can be approximated with arbitrary accuracy. A benefit of using the HMM formulation is that it is easy to incorporate covariates, trend and seasonal variation particularly in the hidden component of the model. In addition, the formulae and methods for forecasting, state prediction, decoding and model checking that exist for ordinary HMMs are applicable to the proposed class of models. An HMM with explicitly modeled dwell-time distributions involving seasonality is used to model daily rainfall occurrence for sites in Bulgaria.
    Computational Statistics & Data Analysis 01/2011; 55(1-55):715-724. DOI:10.1016/j.csda.2010.06.015 · 1.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We investigated the feasibility of night-time pulse-oximetry telemedicine. We compared polysomnography (PSG) as the gold standard with simultaneously recorded pulse-oximetry from a wrist pulse-oximeter. The results were evaluated by a sleep specialist and compared with outpatient polygraphy. A total of 135 consecutive patients (mean age 55 years, mean body mass index 31.6 kg/m(2)) were studied. Patients with minor, moderate and severe PSG findings were grouped together and compared to those without PSG findings; the resulting sensitivity was 1 and specificity 0.35. In addition, patients with and without minor PSG findings were grouped together and compared to those with moderate and severe PSG findings; the resulting sensitivity was 0.66 and the specificity was 0.98. The receiver operating characteristic (ROC) of telemedically-evaluated oximetry was superior to that of outpatient polygraphy. In contrast, the automatic assessment of severity based on the Oxygen Desaturation Index was unsatisfactory. For patients suspected of sleep related breathing disorders (SRBD), telemedically-evaluated pulse-oximetry is able to identify those who should be referred to a sleep laboratory for definitive diagnosis and treatment. The technique appears to be suitable for first screening in all patients at risk for SRBD.
    Journal of Telemedicine and Telecare 10/2010; 17(1):15-9. DOI:10.1258/jtt.2010.100205 · 1.54 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Tick-borne encephalitis (TBE) virus can cause severe symptoms in humans. The incidence of this vector-borne pathogen in humans is characterised by spatial and temporal heterogeneity. To explain the variation in reported human TBE cases per county in southern Germany, we designed a time-lagged, spatially-explicit model that incorporates ecological, environmental, and climatic factors. We fitted a logistic regression model to the annual counts of reported human TBE cases in each of 140 counties over an eight year period. The model controlled for spatial autocorrelation and unexplained temporal variation. The occurrence of human TBE was found to be positively correlated with the proportions of broad-leafed, mixed and coniferous forest cover. An index of forest fragmentation was negatively correlated with TBE incidence, suggesting that infection risk is higher in fragmented landscapes. The results contradict previous evidence regarding the relevance of a specific spring-time temperature regime for TBE epidemiology. Hunting bag data of roe deer (Capreolus capreolus) in the previous year was positively correlated with human TBE incidence, and hunting bag density of red fox (Vulpes vulpes) and red deer (Cervus elaphus) in the previous year were negatively correlated with human TBE incidence. Our approach suggests that a combination of landscape and climatic variables as well as host-species dynamics influence TBE infection risk in humans. The model was unable to explain some of the temporal variation, specifically the high counts in 2005 and 2006. Factors such as the exposure of humans to infected ticks and forest rodent population dynamics, for which we have no data, are likely to be explanatory factors. Such information is required to identify the determinants of TBE more reliably. Having records of TBE infection sites at a finer scale would also be necessary.
    International Journal of Health Geographics 08/2010; 9(1):42. DOI:10.1186/1476-072X-9-42 · 2.62 Impact Factor
  • Source
    Georges Nguefack-Tsague · Stephan Klasen · Walter Zucchini ·
    [Show abstract] [Hide abstract]
    ABSTRACT: The Human Development Index (HDI) published in the Human Development Report (HDR) of the United Nations Development Program is calculated as a simple average of the Life Expectancy Index (LEI), the Education Index (EI) and the Gross Domestic Product Index (GDPI). This paper provides statistical support for the use of this seemingly arbitrary equal weighting of the three components by treating human development as a latent concept imperfectly captured by its three component indices. We show that a principal component analysis (PCA) based on the correlation matrix of the components leads to practically the same weights. Specifically we show that, for the period 1975 to 2005, the first principal component accounts for between 78% and 90% of the total variability in the data, and that its coefficients are positive and nearly equal. By normalizing the coefficients, the simple average weighting (1/3, 1/3, 1/3) scheme is obtained. The ranks of countries obtained using the PCA weightings are very similar to those based on the HDI. An advantage of the simple equal weighting is that one can define a simple index to measure the balance of a country\'s development, given its HDI which we show below.
    Journal of Human Development and Capabilities 01/2010; 12(37). DOI:10.1080/19452829.2011.571077 · 0.88 Impact Factor
  • Source
    Walter Zucchini · Andreas Schlegel · Oleg Nenadić · Stefan Sperlich ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Jeder hat eine Vorstellung davon, was man unter Statistik versteht, und viele denken dabei sicherlich zunächst an umfangreiche Tabellen oder grafische Darstellungen, die bestimmte Sachverhalte in komprimierter Weise verdeutlichen. Dies ist jedoch nur ein Teil der Statistik, die sogenannte beschreibende oder deskriptive Statistik, die dazu dient, umfangreiche Datensätze mit Hilfe von Abbildungen und Kennzahlen anschaulich darzustellen. In den meisten Fällen geht die Statistik jedoch weit über die reine Beschreibung von Datensätzen hinaus. In der Regel sind vorliegende Daten nur eine Stichprobe aus einer sogenannten Grundgesamtheit, und man möchte aus der Stichprobe Schlussfolgerungen für die Grundgesamtheit ziehen. Dieser Teil der Statistik wird schließende oder induktive Statistik genannt. Zu Beginn dieses ersten Kapitels werden zunächst einige praktische Anwendungsbeispiele statistischer Methoden vorgestellt, um einen Eindruck von den vielfältigen Anwendungsmöglichkeiten der Statistik zu vermitteln. Im hinteren Teil des Kapitels werden dann einige wichtige Grundbegriffe der Statistik, wie zum Beispiel Stichprobe und Grundgesamtheit, eingeführt.
    04/2009: pages 1-40;
  • Walter Zucchini · Iain L. MacDonald ·

  • Walter Zucchini · Andreas Schlegel · Oleg Nenadić · Stefan Sperlich ·

  • Walter Zucchini · David Raubenheimer · Iain L MacDonald ·
    [Show abstract] [Hide abstract]
    ABSTRACT: We describe a family of models developed for time series of animal feeding behavior. The models incorporate both an unobserved state, which can be interpreted as the motivational state of the animal, and a mechanism for feedback to this state from the observed behavior. We discuss methods for evaluating and maximizing the likelihood of an observed series of behaviors, and thereby estimating parameters, and for inferring the most likely sequence of underlying states. We indicate several extensions of the models, including the incorporation of random effects. We apply these methods in an analysis of the feeding behavior of the caterpillar Helicoverpa armigera, and thereby demonstrate the potential of this family of models as a tool in the investigation of behavior.
    Biometrics 12/2007; 64(3):807-15. DOI:10.1111/j.1541-0420.2007.00939.x · 1.57 Impact Factor

Publication Stats

1k Citations
28.42 Total Impact Points


  • 1997-2014
    • Georg-August-Universität Göttingen
      • • Department of Forest Zoology and Forest Conservation
      • • Institute for Mathematical Stochastics
      Göttingen, Lower Saxony, Germany
  • 2006
    • University of Cape Town
      • Department of Actuarial Science
      Cape Town, Province of the Western Cape, South Africa