No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Residual based tests for co integration in models with regime shifts
... Tests of co-integration were developed for the first order co-integrated series I(1) by Shin (1994), based on the stationary test in Kwiatkowski, Phillips, Schmidt and Shin (1992), as well as by Saikkonen and Luukkonen (1993), Xiao and Phillips (2002), and others. Specifically, Gregory and Hansen (1996) developed residual-based tests for cointegration in models with regime shifts. These tests seem to be suitable to our empirical study in view of the presence of a structural break in our data series due to the crisis and empirically proved by Zivot and Andrews's unit root test. ...
... Where the unrevealed parameter ) 1 , 0 ( indicates the timing of the breakpoint. In this context, Gregory and Hansen (1996) ...
... The Gregory and Hansen (1996) test consists of null hypotheses of no co-integration against the alternatives in the three last models presented above. The methodology proposed to treat regime shift is inspired from Banerjee et al. (1992) and Zivot and Andrews (1992). ...
This paper examines the contagion effect caused by the European debt crisis on the Saudi Arabian stock market and the effect's spread to the real economy. Firstly, the presented analysis tests the hypothesis about the contagion effect and interdependence between the markets by means of Gregory and Hansen's co-integration in presence of structural breaks, as well as the test for common trends proposed by Stock and Watson (1988). Next, to identify the transmission channel of the European financial crisis to the Saudi Arabia real economy, we estimate a model with a dummy variable. Finally, we estimate a stylized Phillips curve to investigate the impact of the crisis on Saudi inflation rate. The empirical results indicate that Saudi Arabian stock market has been notably affected by the European crisis. The dummy variable model demonstrates that the primary transmission channel of the financial crisis to the Saudi Arabian output is international trading. In conclusion, the estimated stylized Phillips curve remains unchanged after the crisis. This finding indicates that the crisis has not affected the structure of the relationship between inflation and output.
... The results from Ref. (Hatemi-J, 2008) co-integration test with break in level and slope is reported in Table 5. Since (Hatemi-J, 2008) suggests three residual based test statistics (namely the modified ADF (ADF*) test and the two modified Phillips (Z a *and Z t *) tests), our analysis will depend on Z t * test statistics (Gregory & Hansen, 1996). 3 As can be TB 1 and TB 2 are the first and second optimal time breaks, respectively. ...
... Several studies in the literature shows that conventional tests techniques for co-integration have low power and provide spurious results in the presence of a regime shift in data that is not taken into account (Gregory & Hansen, 1996;Uddin et al., 2013). Therefore, this study uses the Autoregressive Distributed Lag (ARDL) bounds testing approach developed by Refs. ...
... Like unit root tests, standard co-integration tests mostly used in the literature, namely (Engle & Granger, 1987;Granger, 1981;Granger, 1983) and (Johansen, 1991) do not take into account for a possible existence of structural regimes in long run relationship. However, when one or more structural breaks exist in the data, these standard co-integration tests may not be acceptable and a co-integration test with structural regimes shifts should be performed (Gregory & Hansen, 1996;Westerlund & Edgerton, 2007). ...
This paper examined the effect of external factors on economic growth in Tunisia. The economic analysis was carried out using recent quantitative technique of annual time series data from 1976 to 2017. Based on co-integration test with unknown structural breaks and ARDL bound testing we investigated importance of each factor in stimulating economic growth. Our results show that in the long run FDI does not affect economic growth. Remittances and imports negatively affect economic growth. Exports promote economic growth such that a 1% increase stimulates economic activity by 0.702%. In the short term, our estimates emphasize a structural break in 1988 linked to the structural adjustment program. Likewise, FDI does not have a significant effect on economic growth while remittances and imports slow economic growth significantly at the conventional level. On the other hand, exports form a relevant engine of economic growth. So, our conclusions imply that political decision-makers in Tunisia must guarantee certain level of training and infrastructure to ensure the gain of transfers of new technologies and experiences related to the FDI. Thus, Tunisia must encourage peoples living aboard to create new investment opportunities instead of just supporting their families for consumption. In addition, the state must develop financial system capable of transferring funds for investment in order to better benefit from remittances. Finally, the government must restrict import of consumer goods and allow import of equipment and machinery goods that promote production and economic growth.
... Also, the world economy has undergone various changes and shocks; hence, it is recommended that the time data should also be tested for structural break the period of the study. If significant structural break is identified, the authors can employ Gregory andHansen (1996a, 1996b) method of co-integration with structural break. Previous studies have mainly focused on the analysis of oil prices without consideration of the structural changes that happened during the period 1994-2015. ...
... Also, the world economy has undergone various changes and shocks; hence, it is recommended that the time data should also be tested for structural break the period of the study. If significant structural break is identified, the authors can employ Gregory andHansen (1996a, 1996b) method of co-integration with structural break. Previous studies have mainly focused on the analysis of oil prices without consideration of the structural changes that happened during the period 1994-2015. ...
... a) Importance of the study This research focuses on discussing the possible factors that determine crude oil prices taking into account the structural changes that influence the study period, using recent empirical and theoretical literature. Zivot and Andrews (1992) and Perron (1997) unit root test with structural break test for stationarity of the time series is used and for the test of co-integration in the presence of structural changes, the Gregory andHansen (1996a, 1996b) method of co-integration. Establishing the presence of co-integration, we apply the evaluation of Granger causality by using vector error-correction model (VECM). ...
As the world economy has undergone various changes and shocks, the oil market went through significant fluctuations during the period 1994–2015. This study focuses on discussing the possible factors that determine crude oil prices, which include world economic growth, market power of Organization of the Petroleum Exporting Countries (OPEC), non-OPEC supply and the value of dollar, taking into account the structural changes that influence the study period, which is quarterly data for the period of 1994.Q1–2015.Q3. For time series stationarity tests, Zivot and Andrews (1992) and Perron (1997) unit root test with structural break is used. To test the existence of a long relationship in the presence of structural changes, the Gregory and Hansen (1996a, 1996b) method of co-integration is used. For long-run coefficient, we proceed to estimate fully modified least squares. The result shows a significant influence of non-OPEC supply, the dollar appreciation and world gross domestic product growth, but OPEC did not have a significant effect on the price of oil, which is indicated by the structural break for OPEC capacity utilisation at 2002.Q1, that indicates the starting point of the loss of OPEC power. Establishing the presence of co-integration, we apply the evaluation of Granger causality for co-integrated data, using vector error-correction model.
... As the first order log difference of exchange rates contained all specific time series properties, exhibit ergodicity, exchange rates can also be modeled as a stationary stochastic process, and thus, made the comparison possible. Johansen (1991) and Gregory-Hansen (1996) test of co-integration and advanced multivariate dynamic conditional correlation (DCC) Generalized Autoregressive Conditional Heteroskedastic (GARCH) model (Engle, 2002) has also been used in this paper. Univariate GARCH models were initially introduced by Bollerslev (1988); later on multivariate advance versions of this have been employed for assessing co-movements and co-integration among stock and foreign exchange markets. ...
... If the null hypothesis is rejected, the T S associated with ADF* becomes T n S . Since, in large systems, Johansen test results may give incorrect inferences about the presence of co-integration Lee, 1998, 2000) or are rendered too sensitive to the lag length included in the VAR (Hall, 1991), we applied an additional test called GH co-integration methodology (Gregory and Hansen, 1996) to validate the results of Johansen's test. Likewise, for each possible date of structural break, T S , the basic "level shift" model was augmented to develop a combined regime shift model for each T S and is expressed as follows: ...
... Critical values of ADF taken from MacKinnon (1996) are −4.10 at the 0.05 (5 percent) level, for zero lag length. Critical values of ADF* obtained from Gregory and Hansen (1996) are −5.56, −5.28, −4.92, −4.16 at the 0.05 (5 percent) level, for the level shift model and −6.41, −6.00, −5.50, −4.95 at the 0.05 (5 percent) level, for the regime shift model, for 4, 3, 2, 1 regressors, respectively. ...
Purpose
– The purpose of this paper is to econometrically investigate the level of financial co-integration of the least developed countries (LDCs) of Asia and Pacific region. In addition, the paper also tested the co-integration of LDCs with the world’s second largest economy “China.” For this, the paper employed the foreign exchange data sets of respective LDCs. It also aimed to assess the dynamic conditional correlation (DCC) between the foreign exchange rates of LDCs and China, and further, examined the past and current level of their co-relational dependence.
Design/methodology/approach
– The authors created data sets namely LDCs of Asia and Pacific, LDCs of SAARC, LDCs of ASEAN, LDCs of Pacific, LDCs of SAARC and ASEAN, LDCs of ASEAN and Pacific, and LDCs of SAARC and Pacific. In addition, the authors tested the co-integration of these seven groups with China, and thus, making a total of 14 data sets. The analysis was carried out using the Johansen and Gregory-Hansen multivariate co-integration econometric techniques. To assess the DCC, multivariate DCC GARCH model was employed.
Findings
– It was found that at the intra-regional level, exchange rates of LDCs of SAARC, ASEAN and Pacific were co-integrated and showed the existence of 1-3 co-integrating equations. At inter-regional level SAARC-ASEAN, ASEAN-Pacific and SAARC-Pacific were also co-integrated and showed 1-3 co-integrated equations. However, on the inclusion of China in the study, the degree of co-integration of exchange rate of China with LDCs of SAARC and ASEAN increased, while with Pacific, the result was mixed. Conditional correlation estimated of multivariate DCC GARCH model suggested that except for Afghanistan, there was an upward shift in the correlation dynamics of exchange rates of LDCs with China, post global financial crisis.
Practical implications
– Asia and Pacific region constituted of 53 countries, of which 13 were LDCs. Enhanced financial integration among LDCs of Asia-Pacific region and also between LDCs and major economies of the region like China will strengthen economic and financial integration efforts in the region.
Originality/value
– The present paper attempted a comparative assessment of the co-movements of the foreign exchange markets of LDCs, the countries which have remained largely neglected in academic discourses on financial integration.
... Phillips-Perron tests for unit root, the Gregory and Hanson (1996a;1996b) cointegration test to capture endogenous structural breaks in the cointegrating vectors of Nigerian long-run money demand function, cumulative sum of recursive residuals (CUSUM) and cumulative sum of recursive residuals squares (CUSUMSQ) tests for structural stability proposed by Brown et al. (1975). In estimating the canonical specification models, extended specifications are also presented. ...
... where β 0 is the constant term U t is the error term, β 1 > 0 , β 2 < 0, β 3 <0, β 4 < 0, β 5 < 0 or > 0, The Gregory and Hanson (1996a;1996b) ...
... The Gregory and Hanson (1996a;1996b) cointegration test was employed on the demand for money function in Nigeria. The results of the GH test are reported in table 2 below. ...
... However, a limitation of conventional Engle-Granger (1987) cointegration test is that it does not take into account the effect of a structural break in the cointegration relationship. Gregory and Hansen (1996) developed residual-based cointegration tests allow for an endogenous structural break in the cointegration relationship. The regime shift (C/S) model of Gregory and Hansen (1996) is considered since our aim is to capture the change both in the intercept and slope which takes the form: ...
... Gregory and Hansen (1996) developed residual-based cointegration tests allow for an endogenous structural break in the cointegration relationship. The regime shift (C/S) model of Gregory and Hansen (1996) is considered since our aim is to capture the change both in the intercept and slope which takes the form: ...
... If the residuals are stationary, the two series are said to be cointegrated. Gregory and Hansen (1996) propose three test statistics to examine the null hypothesis of no cointegration. These statistics are the ADF test statistics and extensions of the Z test statistics (Z t and Z α ). ...
This paper examines the validity of Fisher hypothesis in Turkey for the time period 1987Q1-2010Q3. For this purpose, we employ cointegration test with a structural break as well as time varying parameters approach (TVP) that takes into account the effects of regime or policy changes on the relation between interest rate and inflation rate. The empirical results show that weak form of the Fisher hypothesis holds in Turkish economy.
... The existence of structural breaks has been tested by implementing the procedure proposed by Gregory and Hansen (1996), who consider co-integration processes allowing intercepts and/or slope coefficients to break at an unknown point over the period under scrutiny. In formulas we have ...
... The tests work as follows: when considering the long run relationship between exports and exchange rates, the procedure allows us to identify possible breaks; when this occurs, it tests the null hypothesis of absence of change in the long run relationship. Under the alternative hypothesis, there is movement towards a new long run equilibrium (Gregory and Hansen, 1996). The test is based on an extension of the ADF, Z t and Z a test-statistics for co-integration and allows us to detect the stability of co-integration over time in the presence of structural change, if any. 12 Table 6 shows the results for the test constructed to search for a change in constant (equation 3). ...
... . For details, see Gregory and Hansen (1996). 2004. ...
The empirical literature on trade imbalances does not make currency tensions easy to understand, because tensions across traders originate from the assumption that export-price elasticity is high. This paper provides new evidence by analysing the export-behaviour of China, France, Germany, Italy, Japan, UK, and the USA from 1990 to 2012. Estimates of export-price elasticities have been made using panel data techniques for non-stationary data. Long run relationships are stable to any structural break and indicate that exports are heavily dependent on world income, with long run income elasticity significantly higher than unity in many cases (China, Japan, Germany, UK and USA). Conversely, exports are price inelastic for most of the countries in the sample, in both the long and short runs. The exception is France, whose exports in the long run would increase by 2 percent if the country experienced a 1 percent depreciation of its real exchange rate.
... A potential disadvantage of pursuing this method exists if there is a structural break in the cointegrating relationship. Research by Gregory and Hansen (1996) and Inoue (1999) has shown that one or more breaks can yield misleading results on cointegration. ...
... This research will adopt the methodology developed by Inoue (1999) for determining a potential structural break endogenously within a multivariate cointegrated system. This is in preference to the Gregory and Hansen (1996) approach, which is a two-step procedure along a similar line to the original Engle and Granger (1987) two-step methodology that requires a prior specification of the left-and right-hand side variables. The Inoue (1999) procedure allows for a test of cointegrating rank within the presence of a mean-and/or trend-break. ...
... They allowed for two structural breaks: the Gulf War in 1990 and the Asian crisis in 1997-1999. However, the specific time points for the breaks were guessed by the authors without using formal tests; this ad hoc choice can lead to bias and errors in results and conclusions (see Gregory and Hansen, 1996). ...
... Hence, Philips-Perron unit root test was also conducted to overcome the limitations of ADF test. Engle-Granger (1987) and Gregory-Hansen's (1996) bivariate co-integration tests and Johansen (1988) multivariate co-integration test were used to investigate how spatially distant livestock markets are linked together via prices. Price dynamics were portrayed by the Vector Error Correction (VEC) model. ...
... The test was also criticized for testing multiple co-integration relationship and large bias in small sample. Gregory-Hansen (1996) co-integration test was also used to allow any structural changes in the price series due to major policy change or other kinds of shocks. Co-integrating relationships can be changed by the structural break in the price series. ...
... Hence, Philips-Perron unit root test was also conducted to overcome the limitations of ADF test. Engle-Granger (1987) and Gregory-Hansen's (1996) bivariate co-integration tests and Johansen (1988) multivariate co-integration test were used to investigate how spatially distant livestock markets are linked together via prices. Price dynamics were portrayed by the Vector Error Correction (VEC) model. ...
... The test was also criticized for testing multiple co-integration relationship and large bias in small sample. Gregory-Hansen (1996) co-integration test was also used to allow any structural changes in the price series due to major policy change or other kinds of shocks. Co-integrating relationships can be changed by the structural break in the price series. ...
This study examines livestock market integration and price dynamics in the United
States using weekly price series of five major livestock market from October 2005
to March 2015. Engle-Granger and Gregory-Hansen bivariate co-integration tests
and Johansen multivariate co-integration test were employed to measure integration
among spatially separated markets. Price dynamics among livestock markets were
investigated by the Vector Error Correction model. The result indicates that all
markets are co-integrated with sharing a common stochastic trend suggesting the
‘Law of One Price’. The long-run and short-run dynamics of price suggest that the
transmission of price changes from one market to another market during the same
week is very fast. Livestock markets in the United States are well integrated
reflecting satisfactory level of price discovery and market efficiency.
... Regression analysis showed that there was adverse impact of bank credit on economic growth in Pakistan. Olowofeso, Adeleke and Udoji (2015) ascertained the impacts of private sector credit on economic growth in Nigeria using the Gregory and Hansen (1996) co-integration test. The method was applied to quarterly data spanning 2000:Q1 to 2014:Q4, while the fully modified ordinary least squares procedure was employed to estimate the model coefficients. ...
... All the empirical literature reviewed showed that bank lending has positive impact on economic development and growth except for a contrary result of Ojeaga, Odejimi, Okhiku and Ojeaga (2014). These literatures adopted various econometric tools such granger causality test, Johansen co-integration, vector error correction model and Gregory and Hansen (1996) co-integration test among others to make their conclusion. ...
... We also perform the Gregory and Hansen (1996) test that allows for an endogenous structural break in the estimated relationship. The regime shift (C/S) model of Gregory andHansen (1996)captures the change in both the intercept and slope. For instance, in terms of Equation 6, we get: ...
... The null hypothesis of Gregory and Hansen tests that the residuals contain a unit root and hence there is no estimation with a break, whereas the alternative hypothesis is that the residuals are stationary and hence there is a relationship between the variables. Gregory andHansen (1996)propose three test statistics to examine the null hypothesis. These statistics are the ADF test statistic and extensions of the Z-test statistics (Z t and Z α ).Table 2reports the results of the estimation of the system of Equations 3–7. ...
... This paper investigates the relationship between domestic saving (S) and investment (I) to assess degree of capital mobility for G7 countries during the period 1960-2007. To this end, Engle-Granger (1987) and Gregory-Hansen (1996) residual based cointegration tests was firstly applied for each of the G7 countries, but we did not find any evidence of a long-run relationship between S and I. Extending the analysis to time varying parameters (TVP) approach to see changes in the capital mobility over time, the findings suggest that there is no significant increase in capital mobility in the sense of Feldstein-Horioka (1980). ...
... If the residuals from the co-integration regression are stationary, this would indicate that I and S are co-integrated. However, as pointed out by Gregory and Hansen (1996) (GH), the power of the conventional co-integration tests decreases in the presence of a structural break. Unlike the standard co-integration tests, GH (1996) approach allows for an endogenous structural break in the long relationship. ...
This paper investigates the relationship between domestic saving (S) and investment (I) to assess degree of capital mobility for G7 countries during the period 1960- 2007. To this end, Engle-Granger (1987) and Gregory-Hansen (1996) residual based co-integration tests was firstly applied for each of the G7 countries, but we did not find any evidence of a long-run relationship between S and I. Extending the analysis to time varying parameters (TVP) approach to see changes in the capital mobility over time, the findings suggest that there is no significant increase in capital mobility in the sense of Feldstein-Horioka (1980).
... The analysis starts by performing the panel unit root test proposed by Levin et al. (2002) and the panel cointegration test of Westerlund (2007). In addition, we use the Gregory and Hansen (1996) test for checking the structural stability of each time series. After performing these tests, we proceed by using Year ...
... The existence of structural breaks was detected using the Gregory and Hansen (1996) test, who consider cointegration processes allowing intercepts and/or slope coefficients to break at an unknown time point. We have the following formulas: ...
This paper provides new evidence on export price elasticities by analyzing the cases of China, France, Germany, Italy, Japan, UK and the USA over the period 1990 –2012. Estimates have been made using panel data techniques for non-stationary data. After demonstrating that long-run relationships are stable to any structural break, it is found that exports are significantly determined by foreign demand, with long-run income elasticity significantly higherthan unity for China, Japan, Germany, the UK and the USA. Conversely, exports are price inelastic for most of the countries in the sample, in both the long run and the short run. The exception is France, whose export price elasticity is lower (higher) than unity in the short run (long run).
... Co-integration has been detected by referring also to the Johansen test (1991). Moreover, the Gregory and Hansen (1996) test is used for checking the structural stability. Structural breaks can affect model parameters, thereby inducing different policy implications. ...
... The existence of structural breaks was detected with the Gregory and Hansen (1996) test (hereafter GH), which considers co-integration processes allowing intercepts and/or slope coefficients to break at an unknown time-point. Formulas for exports (X t ) are as follows: ...
This paper focuses on trade elasticities by analysing the case of China, France, Germany, Italy, Japan, UK, and the USA over the period 1990-2012. While the empirical setting mainly refers to panel data techniques for non-stationary data, the VECM model complements the analysis at single-country level. After having shown that long-run relationships are stable to any structural break, it is found that exports and imports are price inelastic for most of the countries in the sample. Furthermore, exports and imports are determined by domestic and foreign income, with asymmetric income elasticities. This helps to explain why global trade imbalances are persistent.
... In the second stage, co-integration test was carried out in order to analyse whether the variables were co-integrated or moved jointly in the long run. This was done using parameter instability test following the procedures of Furuoka and Munir (2011);Geda et al.,( 2006); Kungi-Vetenskapsakademien ( 2003); Gregory and Hansen (1996); Philips and Hansen (1990). ...
... The t-statistic (-2.651) showed there is existence of a weak relationship and hence cannot be used for further analysis. The series at first difference level gave residuals which were integrated of order one i.e. 1(1) as a result of the t-statistic of the PP (-16.248) which was significant at 1% probability level as shown in Table 3. (2010) variables (Gujarati and Sangeetha 2007;Nto and Mbanasor, 2011;Johansen and Juselius, (1990) Gregory and Hansen, 1996;Philips and Hansen, 1990). Co-integrating procedure which adopted parameter instability test was used. ...
The study examined the influence of monetary policy variables on banks’ credit supply to small and medium scale enterprises (SMEs) in Nigeria. Time series data which were collected on quarterly basis were elicited from the Central Bank of Nigeria (CBN) Statistical bulletin and financial statements for five commercial banks. The data covered a period of 1995-2010 and were analyzed using Fully Modified Least Squares (FMOLS). Considering the time series properties of the variables, unit root test was done with Philips Perron test to establish stationarity prior to actual analysis. The result of the FMOLS indicated that policies on interest rate and liquidity ratio were negatively and positively significant at 1 percent probability level respectively. Based on the results, it was recommended that government through CBN should strengthen existing policies on the adjustment of interest rates and liquidity ratio so as to increase and stabilize credit supply to SMEs.
... However, the structural breaks in the time-series (somehow ad hoc) choices to be made about the prior model specification like choice of the deterministic parts, lag length selection, and innovation process distribution may impact the model estimation of the study (Ghouse et al., 2018). Hence, further robustness check was carried out for structural breaks, Gregory-Hansen (G-H) co-integration test (Gregory & Hansen, 1996a, 1996b), and Bayer and Hanck (2013 test of non-cointegration test (available on request from the authors). The analysis shows that our VEC model specification is robust to structural breaks. ...
This paper analyses the dynamic roles of remittance on the process of economic growth of Nepal using time-series annual data for 37 years from 1981-2017. The basic tools of data analysis are vector error correction model, long-run structural modeling, Granger causality test, generalized impulse response functions, persistence profile, and variance decomposition analysis. The paper shows that the remittance inflow and economic growth have bidirectional relationship in the long run, but there is no relationship in the short run. Remittance affects the dynamics of other variables like investment, financial development, and investment on human capital which indirectly affect the performance of the economy through these variables. Findings indicate that remittance could promote financial development in the short run. It also shows the possibility of negative shocks in remittance flow could have a permanent negative effect on educational attainment. It concludes that an environment for investment should be created for enhancing the role of remittance on economic growth. Policies promoting flow of remittance through formal channels and financial literacy should be effective tools for channelizing remittance for economic growth. The government should prioritize the educational sector to prevent dropout of the students from schools when the households are hit negatively due to remittance shocks.
... The assumption of stability in the long-run relationships is not necessarily warranted either as "linkages may be time-varying and episodic". One proposal to account for the potential time-variance in co-integration studies has been suggested by Gregory & Hanson (1996), whose method detects structural breaks in the data, revealing support of long-run relationships not captured by static tests. According to Maddala & Kim (1998), Johansen's procedure is also highly sensitive to the assumption that errors are independent and normally distributed. ...
In this paper we highlight an important yet often neglected issue that arises within the context of the broader set of concerns set out in Keynes’s seminal critique of Tinbergen’s early work in econometrics and that is the problem of “trend” in the dataset. We use the example of conforming data to achieve stationarity to solve a problem of unit roots to highlight that Keynes concerns with the “logical issues” regarding the “conditions which the economic material must satisfy” still gains little attention in theory and practice. There is a lot more discussion of the technical aspects of method than there is reflection on conditions that must be satisfied when methods are applied. Concomitantly, there is a tendency to respond to problems of method by applying fixes rather than addressing the underlying problem. We illustrate various facets of the argument using central bank policy targeting and using examples of differencing, co-integration and Bayesian applications.
... However, these methods assume that the long-run co-integration parameters do not change over time; in other words, it does not take into account structural breaks. Gregory and Hansen (1996) developed a cointegration test that takes into account the structural break to overcome this deficiency of traditional co-integration tests. Recently, Hatemi-J and Hatemi-J (2008) has developed a methodology to provide a co-integration test that estimates two breaks. ...
The phenomenon of migration is an essential component in designing sustainable development policies, and it is valuable to investigate the multidimensional effects of migration. While the current literature focuses more on the economic, social, and political impacts of migration, its impact on the environment is relatively less explored. This paper, which aims to overcome this shortcoming in the literature, examines the relationship between immigration, human capital, economic growth, financial development, energy, and environmental pollution in the USA with the STIRPAT model. We follow unit root and structural breaks co-integration tests, then parameter estimates and causality analysis. According to the results, while migration, financial development, and energy consumption have an increasing effect on environmental pollution, economic growth has a decreasing impact on pollution. There is no statistically significant relationship between human capital and the environment. On the other hand, immigration contributes to human capital accumulation in the long run.
... So, the PP statistic is the modification of the ADF 't' statistic that takes into account the less restrictive nature of the error process. The asymptotic distribution of the PP 't' statistic is the same as the ADF 't' statistic and thus, the Mackinnon (1991 and1996) critical values are still applicable. ...
In this article, we tried to estimate Intra-Industry Trade among the BRICS countries. IIT calculated by employing Grubel and Lloyd IIT Index for static analysis and Thom and McDowell (1999) MIIT index for dynamic analysis. Additionally, the decomposition of IIT carried out to distinguish between Horizontal and Vertical IIT. The unit of analysis selected at one- digit and two-digit SITC Industry level for GL IIT index, Further, to conduct MIIT analysis, industry is defined at two-digit-SITC level data by aggregating four-digit SITC sub-industry level data of IIT of BRICS countries. Further, study analysed the Pre and Post-BRICS trade pattern of IIT. Therefore, this study emphasises that do emerging economies IIT among themselves? On the basis of estimated results of this study revealed that IIT occurs at higher level of aggregation. This signifies that developing countries are trading in the same Industry for love for variety and cost effectiveness. Hence, the empirical result contradicts conventional Krugman (1979, 1985) hypothesis of IIT trade takes place in developed nations (industrialist nations). This implies that BRICS countries should focus on opportunities of trade complementary of intermediates products. This will enhance cost effectiveness of product development or production. Further, this will promote innovation in the BRICS region. To achieve this, countries needs to conduct constructive trade dialogue among the BRICS countries.
... ARDL approach for Co-integration is preferable to other conventional Cointegration techniques such as that of Engle and Granger (1987) and Gregory and Hansen (1996). One of the reasons for preferring the ARDL is that it is applicable irrespective of whether the underlying regressors are purely I(0), I(1), or mutually co-integrated. ...
This study analyzes the long and short run relationship between the Karachi stock market index and a set of macroeconomic variables using the data from 2003 to date of inflation, exchange rate and interest rates; the Auto Regressive Distributed Lag technique is used to find the long-run Co-integration relationship of the model and Ordinary Least Square and Vector Error Correction techniques are applied for the analysis of the long and short-run relationship between the Macroeconomic variables and Karachi Stock Market, the Co-integration and granger casualty test is used to verify the results. Detailed analysis show that long run Co-integration relationship does exist between stock prices and the macroeconomic variables in the Karachi stock market (evidence from the significance of Wald test. While by applying the Error Correction Model the stock market has short run relationship with interest rates and exchange rates. These results confirm that the investor can predict the future behavior of the stock market by analyzing the trends and behavior of these macroeconomic variables. And in future Pakistan's economy will be going through struggling times that will eventually affect the stock market, to retain the investor's confidence. In this major part of the financial sector, government policies regarding the interest rates and controlling the inflation would be of immense importance.
... The economic and financial data usually display structural breaks which poses problems for the validity of conventional Johansen test since the power of the co-integration test is dramatically reduced if a break exists in the co-integration relationship (Gregory & Hansen, 1996). This issue is especially important for the empirical work covering the last two decades because of the massive structural change initiated by the Global Financial Crisis (GFC) of 2007. ...
The aim of this paper is to analyze the impact of the Global Financial Crisis (GFC) on the co-integration relationship between the REIT and stock market indices using a sample of 10 developed countries. The main tool employed for this purpose is the dynamic co-integration approach. The empirical results strongly suggest that the stock and REIT markets were deeply affected by two successive crises. The first crisis was related to the U.S. subprime problems while the second shock emanated from the European insolvency problems. The shocks led to serious structural breaks in the financial data during the 2007-2012 period. As a result of this and the highly variable nature of the co-integration structure during this period, the conventional and static Johansen tests cannot detect the strong co-integration between the REIT and stock markets which were the result of common negative response of both markets to the successive shocks. Dynamic co-integration approach seems to be a more valid tool to capture the dynamics of the co-integration structure after the GFC. The dynamic approach implies that the destruction of diversification benefits between the REIT and stock markets was essentially a shock related outcome which also implies that the diversification potential between these two markets may still be valid in the absence of shocks.
... The present study proposed the technique for model estimation is autoregressive distributed lag (ARDL) for Co-integration Shin, 1995, 1998;Pesaran et al., 1996;Pesaran et al., 2001). Recent empirical studies have indicated that the ARDL approach is more appropriate to other conventional co-integration approaches such as Engle and Granger (1987), and Gregory and Hansen (1996). The basic reason to prefer ARDL is that it is applicable irrespective of whether the underlying regressors are purely I(0), purely I(1) or mutually co-integrated. ...
This study explores the two-way causality between poverty and remittances in Pakistan. The empirical evidence is based upon ARDL double bound approach for the long run relationship between remittances and poverty and VECM was used for direction and magnitude of causation. Furthermore, variance decomposition and Impulse response functions were used to capture the standard deviation shocks. Poverty (head count ratio) and remittances to GDP ratio were used from 1973-2006 for analysis purpose. In the study two equations were used interchangeably as dependent variable. It was found by using the Narayan (2005) test criteria for small sample there is co-integration found between poverty and remittances. The relationship is further supported by long run and short run analysis by ECM. Poverty and remittances are inversely and significantly related in the short run and long run by the estimates of ECM. VECM confirms the results by providing the short run and long run significant estimates. The results are also corroborated with variance decomposition and impulse response function. It could be concluded from the results that remittances are playing a vital role after the foreign direct investment. It is also found that due to altruistic behavior, inflow of remittances is increasing due to the poverty and it provides safety nets to poor and ultimately helping to reduces poverty.
... To carry it out, this paper will firstly use the Engle–Granger and Dickey–Fuller (EG–DF) procedure. Secondly, taking into account the possible presence of any structural break in the series, later this paper will also implement the Gregory–Hansen procedure (Gregory and Hansen, 1996). In implementing the EG–DF procedure, this paper will regress the first difference of residuals from Equation (2) as follows, ...
... Engle-Granger residuals-based tests for the null of no co-integration with critical values at 5% level equal to -26.94 and -3.767. ‡ Gregory-Hansen (1996) residuals-based tests for the null of no co-integration with critical values at 5% level equal to -46.98 and -4.92. ...
This paper studies the interrelation among the volumes of bonds and stocks issued by non-financial firms, and levels of industrial loans outstanding in the US. These aggregates are co-integrated and characterized by asym-metric volatility. Their co-movements are driven by financial indicators such as the yield spread, size of loan market and market volatility. Bond and stock issuance are positively correlated, and even more so during the expansionary phase of the cycle. Loans outstanding and bond issuance are negatively correlated, and they diverge more in periods of economic downturn, highlighting the importance of bond markets to mitigate credit crunches.
... Dolado et al. (2001) note that the parameters of equation (7) may not be constant through time. To deal with the situation, Gregory and Hansen (1996) ...
Purpose
– The purpose of this paper is to investigate if the prevalence of corruption and other unwholesome financial practices in Nigeria contributed substantially to the stunted growth of the capital market in general, and the stock market in particular.
Design/methodology/approach
– The paper employed Gregory–Hansen cointegration approach to test the long-run equilibrium relationship between the occurrence of predatory banking practices and stock market capitalization in Nigeria.
Findings
– There exists a long-run equilibrium relationship between bank fraud and stock market capitalization but with a structural break in 2005.
Practical implications
– There is an urgent need to overhaul and re-assess from time to time the existing systems of internal checks and controls in banks, as well as other financial institutions in Nigeria.
Originality/value
– This paper is the first to empirically test the long-run equilibrium relationship between bank fraud and stock market capitalization in Nigeria.
Artan nüfus ve sanayileşme ile beraber artan çevresel kirlilik, sera gazları, su kirliliği, geri dönüştürülemeyen atıklar giderek endişe uyandırmaktadır. 20. yüzyıl itibari ile hükümetler, politik karar alıcılar, bilim ve iş insanları çevre ve sürdürülebilirlik kavramlarına odaklanmaya başlamıştır. Çevresel endişeler, lojistik sektörüne de yansımaktadır. Yük ve yolcu taşımacılığında kullanılan otomobil, otobüs, kamyon vb. araçlar fosil yakıtlarla çalışmaktadır. Bu yakıtların yanmasıyla ortaya çıkan sera gazları, hava ve çevre kirliliğini yüksek ölçüde etkilemektedir. Bu sorunlar için hem uluslararası hem ulusal, hem de şirket düzeyinde çeşitli önlemler alınmaktadır. Bu çalışmada karayolu taşımacılığı sektöründeki yeşil uygulamalardan bahsedilerek, dünya ve Türkiye özelinde şirket bazlı yeşil uygulama incelemeleri yapılmıştır.
Natural gas is a vital energy resource that is used to produce the national output of Pakistan. On the other hand, since natural gas is a relatively cleaner energy resource compared to oil and coal, enhancing the level of natural gas use can be expected to promote economic growth while improving environmental quality in the process. Hence, it is pertinent to assess the economic growth effects associated with the consumption of comparatively cleaner energy resources. Against this background, the main objective of this paper is to explore the asymmetric effects of natural gas consumption, controlling for financial development, on Pakistan's economic growth level over the 1965-2019 period. The results from the Augmented Dickey-Fuller, Phillips-Perron, and Zivot-Andrews unit root tests confirm a mixed order of integration among the variables. Besides, the bounds test and Gregory-Hansen cointegration analyses reveal evidence of long-run associations between economic growth, natural gas consumption, and financial development in Pakistan. Moreover, the outcomes from the non-linear autoregressive distributed lag model analysis show that in the short-run positive changes in the natural gas consumption levels increase Pakistan’s economic growth. On the other hand, in the long-run, positive and negative changes in natural gas consumption levels increase and decrease the economic growth level, respectively. On the other hand, both positive and negative changes in the financial development level are found to reduce Pakistan’s economic growth level in the long-run. Furthermore, the Hacker-Hatemi-J causality analysis verifies that natural gas consumption influences the economic growth level in Pakistan; thus, the energy consumption-led growth phenomenon is evidenced. In line with these key findings, several policy level suggestions are put forward for Pakistan to boost its natural gas consumption figures in order to enhance its economic growth level in the future.
An important prerequisite for reducing poverty, sustainable development and achievement of the millennium development goal has to some extent been tied to access to electricity. However, the subject matter; 'electricity consumption causing economic growth' has seen conflicting results from the theoretical and empirical front, if indeed a relationship exist at all. The study tests, within a panel context the long-run relationship between electricity consumption and economic growth for 13 African Countries from 2006 to 2017 by employing recently developed panel co-integration techniques. Implementing a three stage approach made up of panel unit root, panel co-integration and Granger causality test to examine the causal relationship between electricity consumption, electricity price, corruption, employment and growth. The study provides empirical evidence that a bidirectional causal relationship between electricity consumption and economic growth exist in the short run, suggesting that lack of electricity could hamper economic growth as well as an investment in electricity infrastructure would in turn improve economic growth. Also reveals that corruption causes the level of electricity consumption and GDP in the short run. On the long-run front electricity consumption and electricity price granger causes GDP and GDP causes electricity consumption.
Bu çalışmada; otomotiv sektörünün ekonomik büyüme üzerindeki etkileri, Türkiye’nin 1963-2018 dönemi yıllık verileri kullanılarak analiz edilmiştir. Çalışmada ekonomik büyüme; kişi başına düşen milli gelir ile temsil edilmiş, otomotiv sektörü; otomobil, otobüs, kamyon ve traktör üretimi şeklinde toplulaştırılmıştır. Her bir sektör için ayrı modeller kurulmuş ve analizler bu dört model yardımıyla gerçekleştirilmiştir. Serilerin durağanlığı Kapetanios (2005) çoklu yapısal kırılmalı birim kök testiyle incelenmiş ve serilerin farklı derecelerde durağan oldukları görülmüştür. Seriler arasındaki eşbütünleşme ilişkileri Maki (2012) çoklu yapısal kırılmalı eşbütünleşme testiyle incelenmiş ve modellerde yer alan serilerin eşbütünleşme içinde oldukları belirlenmiştir. Eşbütünleşme testinden elde edilen yapısal kırılma tarihleri, uzun dönem analizine kukla değişkenlerle dâhil edilmiştir. Uzun dönem analizleri DOLS yöntemiyle gerçekleştirilmiş ve Türkiye’deki kişi başına düşen milli geliri; otomobil üretimindeki %1’lik artışın %0.62, kamyon üretimindeki %1’lik artışın %0.47, traktör üretimindeki %1’lik artışın %1.28 oranında artırdığı, otobüs üretimindeki %1’lik artışın ise %0.36 oranında azalttığı görülmüştür. Seriler arasındaki kısa dönem analizleri de DOLS yöntemi yardımıyla gerçekleştirilmiş ve otobüs üretiminin, uzun dönemdekinin aksine, kısa dönemde kişi başına düşen milli geliri artırdığı görülmüştür. Kamyon üretimi, uzun dönemde olduğu gibi kısa dönemde de milli geliri artırmıştır. Otomobil ve traktör üretiminin milli gelir üzerindeki kısa dönem etkileri pozitif olmakla birlikte, istatistiksel olarak anlamsız bulunmuştur. Bütün modellerin hata düzeltme terimlerinin katsayıları negatif ve istatistiksel olarak anlamlı çıkmıştır. Bu durum; modellerin hata düzeltme mekanizmalarının çalıştığını ve yapılan analizlerin güvenilir olduğunu göstermektedir.
Since the previous periods, poverty reduction has been a big concern for many countries especially in developing countries like Algeria; in this paper, we shall explore the causal relationship between poverty reduction, economic growth and financial development in Algeria during the period of 1970-2017, the aim of this research is to answer the question which sector causes the poverty reduction: real sector or financial sector? Therefore, we employed the modern frequency domain causality presented by Breitung and Candelon (2006) with a comparison with the time domain causality under Lutkepohl (2006) procedure, the results suggest that there is unidirectional causality running from the real sector (economic growth) to poverty rates in the short and long run terms, also, we found that there is an unidirectional causality running from the financial sector to poverty rates only in the long run term, while another causality running from poverty rates to the financial sector but in the short run term. This article aims at contributing to enlarge the literature review by utilizing the frequency domain causality in the field of poverty studies because of its effectiveness to test the causalities in different frequencies.
Climate change is a rising issue for agriculture productivity and topographical area of Pakistan makes it insecure because of environmental changes. Climate change is fundamentally because of expansion in the Greenhouse Gases (GHGs) such as carbon dioxide, methane and nitrous oxide due to fossil fuel burning and other human activates. Greenhouse gases block the sun radiations and increases the earth's general temperature and causes global warming. The aim of study is to take a deep analysis of the climatic effects on citrus fruit production. The study utilizes Auto Regressive Distributed Lag (ARDL) model to assess the effect of climate change on the citrus production in Punjab. For this purpose, annual data from 1989 to 2015 were considered. The result estimated concluded that under climate change it has impact on citrus production. Through variation in the temperature, rainfall it directly affects the citrus production and also profitability of fruit. Consequently, the research also concluded that undoubtedly impact of climate change effects the production. On the contrary, if suitable adaptive and moderate practices in planting and better watering system, new technology and usage of hybrid seeds are applied then it can diminish this recently developing danger of climate change.
In this paper using both annual time-series data at the federal level as well as annual state-level (balanced) panel data from 1980 to 2017 we investigate the relationship between several labor market variables and the federal and state level incarceration rates in the United States. We find a significant empirical association between the incarceration rate, 10th-percentile real-wage rate, and the unemployment rate, as well as the level of inequality. Specifically, the time-series analysis reveals a significant negative correlation between the incarceration rate and the 10th-percentile wage rate. Moreover, in all time-series regressions, the unemployment rate and the 40%-to-10% wage ratios are both positively correlated with the incarceration rate. In the state-level analysis, panel data regressions indicate that the unemployment rate, income inequality, and unemployment duration are positively associated with incarceration whereas the 10th-percentile wage is negatively correlated with the latter.
The contribution of tourism to economic development is an open secret but it is a double-edged sword. The opportunity cost for this significant share is environmental degradation without required measures to protect the environment. Using the Fully Modified Ordinary Least Squared approach from 1995 to 2014, this study aims to explore the nexus between tourism and environmental pollution for three lower middle-income Southeast Asian economies: Indonesia, the Philippines and Vietnam. This paper uses carbon emissions as a proxy for environmental pollution against tourist arrivals with a few control variables for analysis. The Zivot-Andrews unit root test is applied to deal with structural breaks in data and the Gregory-Hansen test for robustness. The results confirm a negative impact of tourism on the environment for Indonesia and the Philippines; however, tourism improves the environmental quality of Vietnam. This implies that the relationship varies for different countries in the same region, depending on the country-specific characteristics and corresponding policies to protect the environment. The impact of governmental policies also differs for high and lower middle-income countries as one size cannot fit all. This study provides a comprehensive milieu of the impact of tourism on the environment. The identified dominant factors can guide Southeast Asian and other developing countries’ governments at all levels in systematically formulating policies; by using these policies, carbon emissions from tourism can be reduced efficiently, resulting in sustainable development in the region.
The contribution of tourism to economic development is an open secret but it is a double-edged
sword. The opportunity cost for this significant share is environmental degradation without
required measures to protect the environment. Using the Fully Modified Ordinary Least Squared
approach from 1995 to 2014, this study aims to explore the nexus between tourism and
environmental pollution for three lower middle-income Southeast Asian economies: Indonesia,
the Philippines and Vietnam. This paper uses carbon emissions as a proxy for environmental
pollution against tourist arrivals with a few control variables for analysis. The Zivot-Andrews
unit root test is applied to deal with structural breaks in data and the Gregory-Hansen test for
robustness. The results confirm a negative impact of tourism on the environment for Indonesia
and the Philippines; however, tourism improves the environmental quality of Vietnam. This
implies that the relationship varies for different countries in the same region, depending on the
country-specific characteristics and corresponding policies to protect the environment. The
impact of governmental policies also differs for high and lower middle-income countries as one
size cannot fit all. This study provides a comprehensive milieu of the impact of tourism on the
environment. The identified dominant factors can guide Southeast Asian and other developing
countries’ governments at all levels in systematically formulating policies; by using these
policies, carbon emissions from tourism can be reduced efficiently, resulting in sustainable
development in the region.
This study investigates the direct impact of government expenditure on poverty reduction in Algeria from 1970 to 2017 so as to be able to find out if the government expenditure is pro-poor people or not, the Gregory-Hansen (1996) co-integration technique allowing for the presence of potential structural breaks in data is applied to examine the long run co-movement between poverty rate and government expenditure, the results shows that there is a structural break in poverty rates in 1989 using the Zivot-Andrews unit root test and in 1972 and 1986 using CMR and LM unit root tests, and there is a co-integration relationship with one break in 1986 among the variables, the results also suggests that there is no evidence of any affect from government expenditure on poverty rate over the period of study both in short run and long run term which means that the government expenditure in Algeria is not pro-poor people and the expenditure efforts presented by the government still very limited to impulse and reduce the poverty rates and to improve the standard living for the poor people.
2018 420 Astract: This analytical review explores the relationship between poverty reduction as measured by the consumption per capita and economic growth in the case of Algeria for the period 1970-2015.we use in this paper the two types of unit root tests; without structural breaks (ADF, PP and Ng-perron) and with structural breaks (Zivot Andrews test (1992) and Clemente-Montanes-Reyes test (1998)), and to test to long run relationship among the variables, the paper apply the Gregory Hansen (1996) procedure to test the co-integration relationship with regime shift to avoid the spurious results from the traditional tests. The results show that all the variables contains structural breaks in different dates, and the results obtained from the Gregory Hansen test indicate that there is a long run relationship among the variables with a regime shift in 2008. This result reveals that the poor people in Algeria benefit from the economic growth which means that the Algerian economic growth is pro-poor. JEL Codes: C33, G21, I32. ممخص : تهدف البحثية الورقة هذه اسة در الى الفترة خالل ائر الجز في االقتصادي النمو و لمفرد باالستهالك المقاس الفقر من الحد بين العالقة 1970-2015. هيكمية ات فجو بدون ؛ الوحدة جذر ات اختبار من نوعين عمى اسة الدر هذه في نعتمد (ADF و PP و Ng-perron) اختبار هيكمية ات بفجو و (Zivot Andrews (1992 اختبار و (Clemente-Montanes-Reye (1998. نموذ الورقة تطبق ج
With the Russian ruble becoming an “oil” currency it is important to study how its behavior is affected by changes in oil prices. The author attempts to trace the relationship between the Brent crude oil price and the dollar price of the Russian ruble using 181 weekly observations between June 2014 and November 2017. An econometric methodology includes testing for structural breaks, stationarity, and weak exogeneity as well as error correction modelling. Two structural breaks were detected, dividing our time series into three regimes: 16/06/2014 - 5/10/2015, 12/10/2015 - 30/01/2017 и 6/02/2017 - 27/11/2017. In regimes 1 and 2 Ruble’s exchange rate and the Brent crude oil price remained cointegrated with the letter being weakly exogenous relative to the former. In regime 3 cointegration collapsed, and a regression model composed of differentiated series proved to be statistically insignificant. Successful efforts by OPEC+ to curb oil production added stability to the market. Other factors began exerting greater influence on Ruble’s exchange rate. Low inflation and high interest rates “orchestrated” by the Bank of Russia stimulated capital inflow. Higher demand for the Russian currency to buy Russian assets, particularly government bonds, resulted in stronger Ruble.
El objetivo de este estudio es mostrar si la industria manufacturera peruana mantiene su liderazgo en el proceso de crecimiento económico y en el aumento de la productividad del trabajo, después de veinticinco años de reformas y política neoliberales. El enfoque del trabajo es kaldorianokeynesiano, según el cual el crecimiento económico está determinado fundamentalmente por factores de demanda. Se evalúan estadística y econométricamente las leyes de Kaldor, según las cuales el crecimiento de la manufactura impulsa el crecimiento del PBI, el crecimiento de la productividad laboral en la propia manufactura y en la economía en su conjunto. El período de análisis cubre 65 años de 1950 a 2015, que incorpora tanto el periodo de industrialización dirigida por el Estado como los veinticinco años de neoliberalismo también dirigido por el Estado.
Promotion of regional stock market integration is critically meaningful for regional development. Since last couple of decades stock markets Integration has been widely seen as the most exciting and promising area for investment, especially because they are expected to generate high returns and to offer good portfolio diversification opportunities. Consequently, these markets have known a considerable expansion. For this motive, we examine the integration of principal Asian equity markets namely; Taiwan, Sri Lanka, Korea, China, Japan, Malaysia, Hong Kong, India, Singapore and Pakistan employing ARDL bounds testing approach to co-integration and VECM. The study employed monthly stock indices data covering from July 1997 to June 2015. For this purpose list of following indices are used to represent the markets: TSEC weighted index for Taiwan, CSE for Sri Lanka, KOSPI composite index for Korea, SSE composite index for China, Nikkei 225 index for Japan, FTSE 100 index for Malaysia, Hang Seng index for Hong Kong, BSE Sensex for India, Strait Time Index for Singapore and KSE 100 index for Pakistan. We investigate null hypothesis (H0) of no long run relationship as well the direction of causality in case of rejection of (H0). Study explore the Asian markets are integrated during sample period of pre- and post-2008 U.S sub-prime crisis which is in line with prior literature, to extent, this study further explore more attractive results of integration among sample indices and concludes that adjustment of (ECT-1) improved expressively in post-crisis period compare to pre-crisis period over sample years. This implies that the strength of long-run relationship among Asian markets increase over the post-crisis period. The overall comparison results of sample Asian stock indices pre- and post U.S sub-prime crisis conclude that, the integration of sample indices are more strengthen in Asian markets after the global financial crisis. It would be interesting to further explore the factors leading for market integration like, trade flow of the countries, foreign institutional/private portfolio investments, previous equity returns and more precisely put on structural breaks to measure the strength of US crisis period. In addition, it would be more strengthen to make sound policy coordination among Asian region to overcome the influence of economic instabilities and financial fluctuations.
The study examines the methods of testing the presence of unit root and co-integration of time series data using those tests that assumes the presence of breaks and those that assumes no breaks. We employed Eliott et-al(1996) DF-GLS for the latter test and Perron(1997) for the former category. In terms of the co-integration tests, we applied both Johansen(1992) andGregory and Hensen (1996a)procedures that allows to check for co-integration in the presence of no structural breaks and the one that assumed the present of shift under alternative hypothesis. The study applied these tests to examine the Real Interest Rate Parity Relationship between Nigeria and her major trading partners namely: China, India and USA. To do this, monthly time series data was collected on interest rates (call rates and 90 days Treasury Bills rates) and Inflation (Consumer Price Index) from the respective statistical institutions of these countries. The following evidences were found: firstly, there is no difference between breaking and non-breaking univariate and multivariate unit root tests. Secondly, there exist a Real Interest Rate Parity (RIRP) between Nigeria, China, India and USA and the direction runs from Nigeria to these countries. Therefore, the study concludes that it is profitable to borrow money in Nigeria and deposit in China, India and USA at prevailing market interest rate.
The study examines the Fisher’s hypothesis using India’s macroeconomic data with main objective of ascertaining the empirical relationship between nominal interest rate and expected inflation. The study collected monthly time series data on interest rate (lending rate) and CPI growth rate (inflation) from Reserve Bank of India’s database spanning from 1990M01 to 2015M03. To achieve the objective, the study first examined the univariate stochastic properties of the series using test that assumed the presence of structural: Zivot and Andrews (J Bus Econ Stat 10(3):251–270, 1992) and Perron (J Econ 80:355–385, 1997) on one hand and those that assumed no break: Elliot et al. (Econometrica 64:813–836, 1996) and Kwiatkowski et al. (J Econom 54:159–178, 1992) on the other hand. The result for the univariate stochastic properties revealed that inflation is level stationary whereas lending rate is differenced stationary. This finding is consistent with the two tests considered as mentioned above. To examined the Fisher’s effect, given the result of the univariate stochastic properties, the study checked the multivariate counterpart using test that assumed break; Gregory and Hensen (J Econom 70:99–126, 1996) and the one that assumed no break; Pesaran et al. (J Appl Econom 16:289–326, 2001). The result reveals the absence of long run equilibrium between nominal interest rate and inflation for the full and sub-samples which is against Fisher’s proposition. This finding can be attributed to the following reasons: firstly, the conduct of monetary policy by RBI is passive; that is, the policy rate response less than proportionate to change in inflation. Secondly, the presence of distortion in the interest rate pass-through channel makes the sign, speed and magnitude of monetary policy uncertain and finally, the dominant of informal financial sector in India that makes short term policy rate ineffective monetary policy instrument. Therefore the study concludes that the conduct of monetary policy is responsible for the rejection of Fisher’s hypothesis in India.
This study investigates the causality link between economic growth and oil consumption using annual data over the years of 1974-2014 by using causality tests and the Engle-Granger and Gregory-Hansen co-integration models for the Turkish economy. The empirical findings support the view that there is no long term co-integration between the level of economic growth and oil consumption level. However, the UVAR, TYVAR and Hsiao's Granger causality tests in the short term show that a positive one-way causality is going from the oil consumption level to the economic growth rate, and oil consumption level stimulates economic growth rate. JEL Classifications: Q43, C32
This study investigates the causality link between economic growth and oil consumption using annual data over the years of 1974-2014 by using causality tests and the Engle-Granger and Gregory-Hansen co-integration models for the Turkish economy. The empirical findings support the view that there is no long term co-integration between the level of economic growth and oil consumption level. However, the UVAR, TYVAR and Hsiao's Granger causality tests in the short term show that a positive one-way causality is going from the oil consumption level to the economic growth rate, and oil consumption level stimulates economic growth rate. JEL Classifications: Q43, C32 ÖZ: Bu çalışmada 1974-2014 dönemi yıllık verilerle Türkiye ekonomisi için ekonomik büyüme ile petrol tüketimi arasındaki ilişkiler kısa dönem nedensellik testleri, uzun dönem Engle-Granger ve Gregory-Hansen eşbütünleşme yöntemleri ile incelenmiştir. Ampirik sonuçlar değişkenler arasında uzun dönemde eşbütünleşme ilişkisinin olmadığını, ancak UVAR, TYVAR ve Hsiao'nun Granger nedensellik testleri kısa dönemde petrol tüketiminden ekonomik büyümeye doğru pozitif, tek yönlü bir nedenselliğin olduğunu, petrol tüketimi arttıkça büyüme hızının arttığını göstermektedir.
This paper studies the interrelation among the volumes of bonds and stocks issued by non-financial firms, and levels of industrial loans outstanding in the US. These aggregates are co-integrated and characterized by asym-metric volatility. Their co-movements are driven by financial indicators such as the yield spread, size of loan market and market volatility. Bond and stock issuance are positively correlated, and even more so during the expansionary phase of the cycle. Loans outstanding and bond issuance are negatively correlated, and they diverge more in periods of economic downturn, highlighting the importance of bond markets to mitigate credit crunches.
This study aims to empirically re-examine Japan's long-run aggregate import demand function using a variety of cointegration tests. The primary contribution of this study is to compare estimates obtained from samples of quarterly, biannual, and annual data for the period 1973 to 2000. The results of bounds test and Johansen's multivariate test show that the quantity of imports, real incomes, and relative import prices are consistently cointegrated regardless of data frequency. In contrast, the Engle-Granger's residual-based and error correction mechanism tests reveal no cointegrating relationship in Japan's aggregate import equation. This study thus concludes that data frequency does not affect estimates of Japan's aggregate import demand function, but that the choice of cointegration techniques does.
Brain drain has long been an important concern particularly for a developing country like Morocco where high-skilled emigration rates are highest. The aim of this paper is to highlight the causes of migration of Moroccan students to France, to offer then some implications. To this end, we apply an ARDL Bounds testing approach and VEC Granger causality test to annual data spanning the period between 1971 and 2011. We show that the quality of higher education measured by French research & development (proxy of French institutions) seem the main determinant of student mobility. The per-capita income differential between France and Morocco also plays an important role on explaining student migration. The uncertainty about future Moroccan inflation (proxy of Moroccan institutions) encourages the departure of students abroad, while the degree of openness via trade and foreign direct investments discourage. Academic exchange agreements and the creation of research centers accredited by the two countries have been recommended to enhance the French economic development from high-skilled migrants without depriving Morocco.
A large proportion of international real estate investment is concentrated in the office markets of the world's largest cities. However, many of these global cities are also key financial services centres, highlighting the possibility of reduced economic diversification from an investor's perspective. This paper assesses the degree of synchronization in cycles across twenty of the world's largest office markets, finding evidence of significant concordance across a large number of markets. The results highlight the problems associated with commonalities in the underlying economic bases of the markets. The concentration of investment also raises the possibility of common flow of funds effects that may further reduce diversification opportunities.
ResearchGate has not been able to resolve any references for this publication.