THE PENNSYLVANIA STATE UNIVERSITY SCHREYER HONORS COLLEGE DEPARTMENTS OF ECONOMICS AND STATISTICS

Size: px
Start display at page:

Download "THE PENNSYLVANIA STATE UNIVERSITY SCHREYER HONORS COLLEGE DEPARTMENTS OF ECONOMICS AND STATISTICS"

Transcription

1 THE PENNSYLVANIA STATE UNIVERSITY SCHREYER HONORS COLLEGE DEPARTMENTS OF ECONOMICS AND STATISTICS COINTEGRATION AND VAR INNOVATION RESPONSE ANALYSIS OF UNEMPLOYMENT, EXCHANGE RATES, AND INTERNATIONAL TRADE GUANHAO FENG SPRING 2012 A thesis submitted in partial fulfillment of the requirements for baccalaureate degrees in Mathematics and Economics with interdisciplinary honors in Economics and Statistics Reviewed and approved* by the following: Herman J. Bierens Professor of Economics Thesis Supervisor James R. Tybout Professor of Economics Honors Adviser Naomi S. Altman Professor of Statistics Honors Adviser * Signatures are on file in the Schreyer Honors College.

2 1 Abstract: The aim of this honors thesis is to examine whether and how fluctuations in exchange rates and international trade affect the unemployment rate in the United States. In particular, on the basis monthly data and cointegrated or regular vector autoregressive (VAR) models I study the response of unemployment to shocks in exchange rates and international trade from the three largest trade partners of the United States (China, Japan and the Euro zone). To distinguish these effects from domestic causes I also include the index of industrial production in these models. The empirical work is to examine whether the time series involved are stationarity or unit root processes, and to conduct cointegration and VAR innovation response analysis. The results show that there is no significant response of unemployment to innovation shocks in the exchange rates. The same applies to innovation shocks in trade, except for trade with Japan and Germany. In particular, the response of unemployment to a unit shock in import from Japan is negative, which is contrary to what one would expect, whereas in a multi-country model the response of unemployment to a unit shock in exports to Germany is positive. i

3 Contents 1 Abstract: i 2 Introduction and Literature Review: 1 3 Data Analysis Data Selection and Sources Unit Root and Stationarity Tests VAR Innovation Response Analysis and Cointegration Stationary VAR Innovation Response Analysis Cointegration Empirical Results Unemployment and Industrial Production Import, Export and Exchange Rate Effects Japan Euro Zone Import and Export Effects Only Japan China Germany Trade Effects Multi-Country Analysis Joint imports Joint exports Conclusion and Future Research 20 7 References 21 ii

4 8 Appendix 22 iii

5 ACKNOWLEDGEMENTS It is my pleasure to thank those people who helped me to finish this thesis. First and foremost, I am heartily grateful to my thesis supervisor Dr. Herman Bierens for his encouragement, supervision and guidance from the beginning to the end. Most definitions and notations of this thesis follow from lecture notes of Professor Bierens, but any errors are mine. I would also like to record my gratitude to thank Dr. David Shapiro, Dr. Naomi Altman and Dr. Neil Wallace for their generous supports and suggestions on my academic work. In addition, I would like to thank Dr. James Tybout and all friends in the Honors Program of Economics for their helpful discussions, comments and advices during this year. Last but not least, I wish to thank my parents, families and friends for being supporting me all the time. iv

6 2 Introduction and Literature Review: In the aftermath of the financial crisis in 2008, high unemployment of about 9% and low growth, stirred up the discontentment of a large number of people. Figure 1: Unemployment rates There have been debates among economists regarding the global trade between developed countries and developing countries and many of them argued that reducing trade barriers lead to job loss (Amornthum, 2004). There were critics that the long-time unfavorable trade balance was one of the main reasons of current depression and high unemployment in the United States. Some analysts argued that American workers lost their jobs to foreign workers and the government should step in and protect the local manufacturing and employment. Most people would agree that, when the country still continued to figure out how to crawl out of the economic despair, workers could definitely be benefited from the recovery of local manufacturing, which was the key engine of local growth and employment. Therefore, an age-old question is how the production and employment of a country are affected by the international competition through global trade. With the increasing participation of developing countries in the global economy in the last three decades, employment and wages of manufacturing workers in the U.S. had been greatly af- 1

7 fected by the abundance of labor from developing countries. These countries encouraged American companies to move their manufacturing factories abroad by providing many preferential policies and abundance of low-waged and skilled labors. According to Forbes, companies from Apple to Ford Motors to Nike to HJ Heinz to Gap were expanding in mainland China to chase the global growth. In 2009, American companies spend $3.6 billion in foreign direct investment in China, up sharply from the $2.9 billion invested in Particularly, the undervaluation of some foreign currencies, for example the Chinese Yuan and Japanese Yen, has been blamed for the out-sourcing of US manufacturing. Undervaluing the currency of a country will lower its import prices and thus increases its competitiveness in the importing market. On one hand, Revenga (1992) empirically showed that changes in import prices have had large and significant effects on both employment and wages. On the other hand, Bergsten and Williamson (2002) emphasized that the over-valued dollar was causing long-term damage by eroding local manufacturing. In theory, real exchange rates adjust to keep every trading partner equally competitive in the market. No country suffers from any persistent trade deficits or enjoys any persistent trade surpluses (Shaikh, 1996). But Bergsten and Williamson (2002) pointed out that China and Japan were two special policy concerns because they had built large accumulations of foreign reserves, which had blocked the yuan and yen from appreciating. The Chinese government has capital controls to prevent the yuan from appreciating and the Japanese have repeatedly engaged in strategic interventions to gain competitive trade advantages. Burgess and Knetter (1996) conducted an international comparison of employment adjustment against exchange rate fluctuations. They estimated models for industry employment dynamics in fourteen industry categories for the G-7 countries. Their study confirmed that a real appreciation of a nation s currency leads to a decline in manufacturing employment, as expected. In addition, Burgess and Knetter (1996) argued that both the elasticity of employment to exchange rates and the speed of employment adjustment to exchange rate shocks were likely to depend primarily on the market structure and the regulations of international trade and the labor market, all of which 2

8 might vary substantially across countries and industries. This paper investigates the innovation response of US employment adjustment to exchange rate and international trade shocks from the three largest trade partners of the United States, China, Japan and the Euro zone, either on the basis of a cointegrated V ector Error C orrection M odel (VECM) if cointegration is present, or on the basis of a nonstructural V ector AutoRegression (VAR).More formal definitions and detailed discussions are included in section 4. In order to determine whether the monthly time series involved are (trend) stationary or unit root (with drift) processes, I have conducted a range of unit root and stationarity tests, since each test has its advantages and disadvantages. I conclude from these tests that almost all the time series in my analysis are unit root processes. Next, I have conducted Johansen s (1991) cointegration analysis to determine possible cointegration relations between these time series. If so, the innovation response analysis has been conducted with the VECM involved. If not, the time series have been differenced to make them stationary, and then the regular Sims (1980) VAR innovation response analysis have been conducted on the differenced time series. In the next section I will discuss the preliminary data analysis, in particular data selection, transformation and unit root tests. Then, in section 4, I proceed with the cointegration and VAR analysis, and in section 5 I make concluding remarks and suggest avenues for future research in this area. The last section is the appendix containing the (raw) data plots and autocorrelation plots of the differenced time series. The latter are used to determine whether to include seasonal dummy variables in the models. 3

9 3 Data Analysis 3.1 Data Selection and Sources The monthly statistics of industrial production, unemployment rate, imports, exports and exchange rates with respect to China, Japan, Germany and the Euro zone have been collected from the following sources: 1. Census Bureau (monthly data of Exports and Imports with China, Japan and Euro zone) 2. Bureau of Labor Statistics (monthly data of unemployment rates) 3. Federal Reserve Bank of S.T. Louis (Industrial Production Index) 4. Federal Reserve Bank of S.T. Louis (monthly data of exchange rates with China, Japan and Euro zone) Initially, I planned to use real GDP instead of industrial production, but GDP data is only available as quarterly data, which would leave me with an insufficient number of observations for my analysis. The Industrial Production Index, an economic indicator released monthly by the Federal Reserve Board, measures real production output, which includes manufacturing, mining, and utilities. As my focus is on the domestic labor market, the Industrial Production Index (IPI) is a reasonable substitute for real GDP. I have chosen imports and exports indicators separately instead of the trade balance because I use the data after logarithmic transformations. The monthly time series started from January of 1997 to September 2011, except for the exchange rate between the euro and the dollar, which started from January of Unit Root and Stationarity Tests Because unit root processes cannot be bounded, and VECM and VAR models assume multivariate normal errors, all positive valued variables in my analysis have been made unbounded by taking 4

10 logs. The unemployment rate U is bounded between zero and 100. Therefore, the unemployment rate U has been transformed by Y = log(u/(100 U)) to make it unbounded. The time series of unemployment rate and Industrial Production Index are seasonally adjusted, but the other time series were not. I have checked the autocorrelation function (ACF) plots of the differences (log) time series involved, and they show obvious seasonal patterns in the import and export data. See the Appendix. Figure 2: CNY/USD Initially I planned to include the exchange rate with China in my analysis, because China is the largest trading partner of the United States. However, the exchange rates between China and the United States were almost constant before 2005, as seen from Figure 2. However, I will get back to China s case when studying models without exchange rates. Consider an AR(p) model in lag operator form: φ p (L)Y t = β 0 + U t, where φ p (L) = 1 β 1 L β 2 L 2 β p L p with L is the lag operator: LY t = Y t 1. 5

11 Given that the errors U t are stationary white noise, a necessary condition for the stationarity of Y t is that all the roots of the polynomial φ p (z) are greater than one in absolute value. In the case that one of the roots of φ p (z) is equal to one, the lag polynomial φ p (L) can be written as φ p (L) = (1 L)ψ p 1 (L), where ψ p 1 (L) is now a lag polynomial of order p 1. Then the AR(p) model becomes an AR(p 1) model in differences: ψ p 1 (L) Y t = β 0 + U t, where Y t = Y t Y t 1. Thus, in the unit root case we need to difference the time series to make it stationary. If the AR(p) model has a unit root, some tests of parameters restrictions may have different null distributions than in the case of a stationary process. For example, to test the null hypothesis that β 1 = 1 in the AR(1) model Y t = β 0 + β 1 Y t 1 + U t using the usual t-test, the null distribution involved is non-normal (Dickey and Fuller, 1979). Therefore, incorrect applications of classical inference may give incorrect results. I subjected the transformed time series to a series of unit root and stationarity tests, namely the Augmented Dickey-Fuller (ADF) test (Dickey and Fuller, 1981), the Phillips-Perron test (Phillips and Perron, 1988), the Breitung s (2002) nonparametric unit root test, the KPSS stationarity test (Kwiatkowski et al., 1992), and the Bierens-Guo stationarity test (Bierens and Guo, 1993). The unit root tests involved test the null hypothesis that the time series Y t has a unit root (with drift) process against the alternative that Y t has a (trend) stationary process, whereas that stationarity tests reverse these hypotheses. The results for the seasonally adjusted data are the following: 1. Y t = log(unemployment rate/(100 - unemployment rate)) H 0 (unit root) was not rejected at the 10% significance level by the ADF test with lag p = 6. (p = 6 was suggested by information criteria.) H 0 (unit root) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root) was not rejected at neither 5% nor 10% significance levels by Breitung s test. 6

12 H 0 (stationarity) was rejected at the 5% significance level by the KPSS test. H 0 (stationarity) was rejected at the 5% significance level by the Bierens-Guo test. Thus, we conclude that Y t has a unit root process. 2. Y t = log(industrial Production Index) H 0 (unit root with drift) was not rejected at the 10% significance level by the ADF test with lag p = 4. (p = 4 is suggested by Information criteria.) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (trend stationarity) was rejected at the 5% significance levels by the KPSS test. H 0 (trend stationarity) was rejected at the 5% significance level by the Bierens-Guo test. Thus, we conclude that Y t has a unit root process with drift. In the presence of seasonal dummy variables the ADF test and Bierens-Guo tests are no longer applicable. A non-seasonal ARIMA(p,r,q) model for a time series Y t takes the form X t = (1 L) r Y t, φ p (L)X t = β 0 + ψ q (L)U t where X t is a stationary ARMA(p,q) process with stationary white noise U t. However, the Phillips-Perron test, Breitung test and the KPSS test are nonparametric tests and can handle ARIMA models. Therefore, these tests remain valid after the seasonal dummy variables are averaged out by a 12 months moving average transformation: MA(Y t ) = m=0 Y t m. Thus, the tests have been conducted on MA(Y t ). If MA(Y t ) is a unit root process, so is Y t, and 7

13 if MA(Y t ) is stationary, so is Y t. The test results are listed below. Note that the variable trade is the sum of import and export. 1. Y t = log(import from Euro zone)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift)was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (trend stationarity) was rejected at the 5% significance level by the KPSS test. Conclusion: Y t has a unit root process. 2. Y t = log(export to Euro zone)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (trend stationarity) was not rejected at the 5% significance level but rejected at 10% significance level by the KPSS test. In view of the latter I conclude that Y t has a unit root process with drift. 3. Y t = log(import from Japan)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was rejected at the 5% significance levels by Breitung s test. H 0 (trend stationarity) was not rejected at neither 5% nor 10% significance levels by the KPSS test. In view of the latter two results my conclusion is that Y t has a trend stationary process. 4. Y t = log(export to Japan)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron 8

14 test. H 0 (unit root with drift) was rejected at the 5% significance level by Breitung s test. H 0 (trend stationarity) was not rejected at neither 5% nor 10% significance levels by the KPSS test. In view of the latter two results I conclude that Y t has a trend stationary process. 5. Y t = log(eur/usd)) H 0 (unit root) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (stationarity) was rejected at the 5% significance level by the KPSS test. Conclusion: Y t has a unit root process. 6. Y t = log(jpy/usd)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (stationarity) was rejected at the 5% significance levels by the KPSS test. Conclusion: Y t is a unit root process. 7. Y t = log(trade with Euro zone)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was not rejected at neither 5% nor 10% significance levelsby Breitung s test. H 0 (trend stationarity) was not rejected at the 5% significance level but rejected at the 10% significance level by the KPSS test. Despite the latter my conclusion is that Y t is a unit root with drift process. 8. Y t = log(trade with Japan)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron 9

15 test. H 0 (unit root with drift) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (trend stationarity) was rejected at the 5% significance level by the KPSS test. Conclusion: Y t is a unit root with drift process. 9. Y t = log(trade with China)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was not rejected at neither 5% nor 10% significance levels by Breitung s test. H 0 (trend stationarity) was rejected at the 5% significance levels by the KPSS test. Conclusion: Y t is a unit root with drift process. 10. Y t = log(trade with Germany)) H 0 (unit root with drift) was not rejected at the 10% significance level by the Phillips-Perron test. H 0 (unit root with drift) was not rejected at the 5% significant level but rejected at the 10% significance level by Breitung s test. H 0 (trend stationarity) was not rejected at neither 5% nor 10% significance levels by KPSS test. In view of the first two I conclude that Y t is a unit root with drift process. 10

16 4 VAR Innovation Response Analysis and Cointegration 4.1 Stationary VAR Innovation Response Analysis The basic VAR(p) model is: p Y t = η + C s Y t s + U t, s=1 where Y t is a k-variate time series; η is a k-dimensional vector of constants; C s, s = 1, 2, 3,..., p, are k k coefficient matrices; U t is k-variate Gaussian white noise: U t is i.i.d. N k (0, Σ). If the VAR(p) process is stationary then by the Wold decomposition it has an infinite vector moving average, VMA( ), representation: Y t = µ + Γ s U t s, Γ 0 = I k s=1 Moreover, using the Cholesky decomposition Σ = LL, where L is a k k lower-triangular matrix, we can write U t = Le t, where e t = (e 1,t,..., e k,t ) is i.i.d. N k (0, I k ). The components e 1,t,..., e k,t of e t are now the innovations associated to the corresponding components of Y t. It follows now that for m 0, E(Y t+m e t ) = Γ m Le t + µ = Γ m where l i is column i of L. 11 k l i e i,t + µ, i=1

17 The response of Y t+m to a unit shock in the innovation e i,t of component i of Y t is now defined as E(Y t+m e i,t = 1) E(Y t+m ) = Γ m l i. 4.2 Cointegration If all the components of a k-variate time series process Y t are unit root processes, it is possible if there exist one or more linear combinations β Y t that are stationary. This is called cointegration. In this case, and under some regularity conditions, the process Y t can be represented by the following p order vector error correction model, shortly VECM(p): p 1 Y t = π 0 + Π s Y t 1 + αβ Y t p + U t. s=1 Here α and β are k r matrices with linear independent columns, with r k the cointegration rank. If r = 0 then αβ = O, so that the VECM(p) becomes a stationary VAR(p 1) model in the differences Y t, and if r = k then Y t is a stationary VAR(p) process. In the case of cointegration, 1 r < k, we can still use the VECM(p) to conduct innovation response analysis, but in general the innovation responses no longer taper off towards zero, and it is no longer possible to endow the innovation responses with standard errors. Johansen (1991) has proposed two likelihood ratio tests for the cointegration rank r, the lambda-max test and the trace test, under various assumptions about the trend or intercept parameters of the VECM(p) process. The lambda-max test tests the null hypothesis that the cointegration rank is equal to r against the alternative hypothesis that the cointegration rank is greater or equal to r + 1. This test is conducted sequentially for r = 0, 1, 2,..., k 1. The trace test tests the null hypothesis that the cointegration rank is equal to r against the alternative hypothesis that the cointegration rank is k. This test is conducted sequentially in reversed order, for r = k 1, k 2,..., 0. 12

18 5 Empirical Results 5.1 Unemployment and Industrial Production It is obvious that the industrial production index is a major determinant of the unemployment rate. Therefore, all VAR and VECM models below include the unemployment rate and the industrial production index, in the form 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), next to trade and exchange rate variables. Recall that both variables are seasonally adjusted, and that Y 1,t is a unit root without drift process and Y 2,t is a unit root with drift process. To determine whether these two time series are cointegrated, I have conducted Johansen s cointegration tests on the basis of a VECM(p) with a time trend. The reason for the latter is that the two time series veer apart due to the drift in Y 2,t. In particular, the selected option in EasyReg for the deterministic terms in the VECM was intercepts and time trend, without cointegration restrictions on the time trend parameters imposed. The order p was determined on the basis of information criteria. The result was that these two time series are not significantly cointegrated. Consequently, the two variables were differenced to make them stationary, and a VAR(p) was fitted to ( Y 1,t, Y 2,t ). The order p = 4 was chosen on the basis of the Hannan-Quinn information criterion (Hannan and Quinn, 1979). Figure 3 displays the response of Y 1,t+m to a unit shock in the innovation of Y 2,t over a horizon of 18 months: m = 0, 1,..., 18. The dots in this plot represent the one and two times standard error bands. The latter correspond to the 95% confidence intervals. As expected, a positive innovation shock in the growth of industrial production, Y 2,t, has a significant negative effect on the growth of unemployment, for at least 12 months 13

19 Figure 3: Base Model 5.2 Import, Export and Exchange Rate Effects Japan Next to the unemployment and industrial production variables I now include imports exports, the exchange rate with Japan. So, the vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(jpy/usd), 4. Y 4,t = log(import from Japan), 5. Y 5,t = log(export to Japan). Recall that the import and export variables are not seasonally adjusted. To determine whether the time series Y 4,t and Y 5,t have seasonally varying drift, I have plotted the autocorrelation functions for Y 4,t and Y 5,t. See the Appendix. Clearly, these ACF plots display seasonal patterns. Thus, in conducting Johansen s cointegration analysis I have selected the option intercepts and seasonally dummies, without cointegration restrictions imposed for the deterministic variables in the VECM(p). The Hannan-Quinn information criterion suggested p = 2. 14

20 The result of the Johansen s test was conclusive: These five variables are cointegrated, with cointegration rank r = 1, and standardized cointegrating vector β = ( , 1, , , ) corresponding to Y t = (Y 1,t,..., Y 5,t ). Thus, β Y t is stationary. The 18-months innovation response plots involved are presented in the figures labeled IRP 1.1, 1.2 and 1.3. Note that export and exchange rate have no effect on unemployment. However, import from Japan has a negative association on unemployment in the US, which is puzzling. We would expect that an increase in imports will lower the domestic production and thus increases the unemployment rate Euro Zone Similar to the case of Japan, the vector time series Y t in the case of the Euro zone has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(euro/usd), 4. Y 4,t = log(import from Euro zone), 5. Y 5,t = log(export to Euro zone). Again, I applied the Johansen s cointegration test first, with the same option for the deterministic terms in the VECM as in the case of Japan. It turned out that these five variables are not cointegrated. Therefore, I have fitted a VAR(p) model to Y t.the Hannan-Quinn and Schwarz (1978) information criteria suggest p = 2. 15

21 The 18-months innovation response plots are presented in the figures labeled IRP 1.4, 1.5 and 1.6. Clearly, the import, export and exchange rate with the Euro zone have no significant effect on unemployment in the US. 5.3 Import and Export Effects Only Since the exchange rates with Japan and the Euro zone have no effect on unemployment in the US, I will now change my focus to the possible effect of import and export on unemployment. By removing the exchange rate it is now possible to include China in my analysis. Moreover, I will now select Germany as a representative of Euro zone because then I can use more data for the analysis. The updated data set now starts at January I am expecting a positive innovation response of imports and a negative innovation response of exports on unemployment rates Japan The vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(import from Japan), 4. Y 4,t = log(export to Japan). As before, these four time series are cointegrated, with cointegrating rank r = 1 and standardized cointegrating vector β = ( , , 1, ). Thus, β Y t is stationary. The innovation response plots are presented in the figures labeled IRP 2.1 and 2.2. As to be expected, the results are the same as before. 16

22 5.3.2 China The vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(import from China), 4. Y 4,t = log(export to China). Johansen s cointegration tests indicate that these time series are not cointegrated. Therefore the innovation response analysis has been conducted via a VAR(p) model for the first differences Y t, with p = 2 suggested by the Hannan-Quinn information criterion. However, the plots of innovation responses in figures labeled IRP 2.3 and 2.4 do not show any significant effect of import and export on unemployment in the US Germany The vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(import from Germany), 4. Y 4,t = log(export to Germany). In this case these four variables are cointegrated, with cointegrating rank r = 1 and cointegrating vector β = ( , 1, , ) Therefore, the innovation response analysis is conducted on the basis of a VECM(p), with p = 3 suggested by the Hannan-Quinn information criterion. The innovation response plots in figures IRP 2.5 and 2.6 show no substantial effect of import and export on unemployment. 17

23 5.4 Trade Effects I have also tried to conduct innovation response analysis with the variable trade, which is the sum of imports and exports, instead of imports end exports separately. This trade variable was taken in logs. In neither of the cases for Japan, China and Germany I could find cointegration, so that the innovation response analysis was conducted in the basis of VAR s in differences. The results, presented in the figures labeled 3.1, 3.2 and 3.3, show no significant impact of trade on unemployment. 5.5 Multi-Country Analysis Since so far I didn t get many significant results from the single country cases, I have finally tried the case where the imports from and exports to Japan, China and Germany are jointly included in two vector time series, one for imports and one for exports Joint imports The vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(imports from Japan), 4. Y 4,t = log(imports from Germany). 5. Y 5,t = log(imports from China) Johansen s cointegration test showed no cointegration for the vector of these 5 variables, so I used a VAR(p) in differences. The Hannan-Quinn criterion suggested that p = 2. However, the plots of innovation responses in figures IRP 4.1, 4.2 and 4.3 show no significant effects of imports on unemployment. 18

24 5.5.2 Joint exports The vector time series Y t involved has the following components: 1. Y 1,t = log(unemployment rate/(100 - unemployment rate)), 2. Y 2,t = log(industrial Production Index), 3. Y 3,t = log(export to Japan), 4. Y 4,t = log(export to Germany). 5. Y 5,t = log(export to China) The result of Johansen s cointegration analysis is that these time series are cointegrated with one cointegrating vector, β = ( , , , 1, ) The Hannan-Quinn criterion suggested that p = 3 for the VECM(p). In the innovation response plots IRP 4.4, 4.4 and 4.6, the responses of unemployment to unit shocks in exports to Japan and China are negative, as expected. However, in the case of Germany the effect is positive, which constitutes another puzzle. 19

25 6 Conclusion and Future Research Initially, I expected that the overvaluation of the dollar, or the undervaluation of foreign currencies, was one of the main reasons for unemployment in the United States. However, I could not find any significant response of unemployment rates to a unit shock in exchange rates. Thus, I have to conclude that dollar overvaluation is not a significant reason for high unemployment. Next, I changed my focus on the trade part, which is always an important part of domestic production. The case of Japan was interesting because of the positive response of unemployment to a unit shock in the import from Japan, which is contrary to what I expected. However, in the model with several countries, this significance of the innovation response to the imports from Japan disappeared. In fact, the innovation response to imports of any country is insignificant in this model. With respect to the case of exports in the model with several countries, the responses of unemployment were negative to unit shocks in exports to Japan and China as expected, yet positive to a unit shock in exports to Germany, which is interesting for further research. In future research, I will focus on the models with several countries and carry out more empirical analysis. Companies from different countries are competing with American companies with different levels of exports. For example, automobile companies of Japan and Germany are very competitive while imports of China are mainly low level goods. However, if the variables in the VAR model are highly correlated, the effects of multicollinearity might be one of the reasons. The puzzling innovation responses found in this study are interesting topics for further research. 20

26 7 References 1. Amornthum S. (2004): Trade and Unemployment. Retrieved from www2.hawaii.edu/ amornthu/pdf/paper660.pdf 2. Bergsten, C. F. and Williamson, J. (2003): Dollar Overvaluation and the World Economy. Washington: Institute for International Economics 3. Bierens,H.J. and Guo, S. (1993): Testing Stationarity and Trend Stationarity Against the Unit Root Hypothesis. Econometric Reviews 12, Bierens, H. J. (2011): Forecasting, lecture notes for Econ Bierens, H. J. (2011): Model Specification, lecture notes for Econ Bierens, H. J. (2011): Vector auto regressions and innovation response analysis, lecture notes for Econ Bierens, H. J. (2011): The Augmented Dickey-Fuller (ADF) and Phillips-Perron tests, lecture notes for Econ Bierens, H. J. (2011): Cointegration Analysis, lecture notes for Econ Bierens, H. J. (2011): Guided tour on Johansen s cointegration analysis 10. Bierens, H. J. (2011): EasyReg International. hbierens/easyreg.htm 11. Breitung, J. (2002): Nonparametric Tests for Unit Roots and Cointegration. Journal of Econometrics 108, Burgess, S. and Knetter, M. (1998): An international comparison of employment adjustment to exchange rate fluctuations. Review of International Economics, pp Dickey D.A. and Fuller W.A. (1979): Distribution of the estimators for autoregressive times series with a unit root. Journal of the American Statistical Association 74,

27 14. Dickey D.A. and Fuller W.A. (1981): Likelihood ratio statistics for autoregressive time series with a unit root. Econometrica 49, Epstein, G. and Meredith, R. (2010): U.S. Companies That Invest Big In China. Retrieved from Hannan, E. J., and Quinn, B. G. (1979): The Determination of the Order of an Autoregression. Journal of the Royal Statistical Society, B, 41, Johansen, S. (1991): Estimation and Hypothesis Testing of Cointegrating Vectors in Gaussian Vector Autoregressive Models. Econometrica 59, Krugman, P. R. (1993): What Do Undergrads Need to Know About Trade? American Economic Review, 83(2), pp Kwiatkowski, D., Phillips, P.C.B., Schmidt, P. and Shin, Y. (1992): Testing the Null of Stationarity Against the Alternative of a Unit Root. Journal of Econometrics 54, Phillips, P.C.B. and P.Perron (1988): Testing for a Unit Root in Time Series Regression. Biometrica 75, Revenga, A. (1992): Exporting Jobs? the Impact of Import Competition on Employment and Wages in U.S. Manufacturing. Quarterly Journal of Economics, 107(1), pp Schwarz, G. (1978): Estimating the Dimension of a Model. Annals of Statistics, 6, Shaikh, Anwar (1996): Free trade, unemployment and economic policy. Global Unemployment: Loss of jobs in the 90 s, ME Sharpe, Armonk, New York 24. Sims, C.A. (1980): Macroeconomics and Reality. Econometrica 48, Appendix 22

28 (a) IRP 1.1 (b) IRP 1.2 (c) IRP

29 (d) IRP 1.4 (e) IRP 1.5 (f) IRP

30 (g) IRP 2.1 (h) IRP 2.2 (i) IRP 2.3 (j) IRP

31 (k) IRP 2.5 (l) IRP

32 (m) IRP 3.1 (n) IRP 3.2 (o) IRP

33 (p) IRP 4.1 (q) IRP 4.2 (r) IRP4.3 28

34 (s) IRP 4.4 (t) IRP 4.5 (u) IRP

35 Figure 4: Unemployment Rates and Industrial Production Index Figure 5: JPY/USD 30

36 Figure 6: EUR/USD 31

37 (a) Japan Exports/Imports (b) ACF plot of Japan Exports (c) ACF plot of Japan Imports 32

38 (d) Eurozone Exports/Imports (e) ACF plot of Eurozone Exports (f) ACF plot of Eurozone Imports 33

39 (g) China Exports/Imports (h) ACF plot of China Exports (i) ACF plot of China Imports 34

40 (j) Germany Exports/Imports (k) ACF plot of Germany Exports (l) ACF plot of Germany Imports 35

41 Feng, Guanhao (Gavin) 2220 Plaza Drive, State College, PA Tel: (814) Education Background Pennsylvania State University, University Park, PA 8/2009 5/2012(expected) B.S. in Mathematics, B.S. in Economics, Minor in Statistics Enrolled in Integrated Undergrad and Graduate program of M.S. in Statistics Honors: Honors Program of Economics / Schreyer Honors College / Phi Beta Kappa Zhongshan (Sun Yat-sen) University, Guangzhou, China 9/2007 7/2009 B.S. in Insurance (transferred) Honors: Outstanding Student Scholarship in freshman year Research and Teaching Experiences REU Program of Economics in Summer 2010 and Fall /2010 1/2011 Research Assistant for Prof. David Shapiro, Department of Economics Provide empirical work for three forthcoming papers and future research in Demography and Development collecting and manipulating data; creating and fixing datasets in Excel, STATA and SAS; regression analysis; statistics calculation; reading papers and surveys; preparing abstracts, graphs, tables and presentation files Economics Honors Program: Two course essays in Game Theory and Monetary Theory Senior Honors Thesis: Essay of VAR innovation response analysis on domestic unemployment rate in U.S. Thesis Advisor: Prof. Herman J. Bierens Abstract: The aim of this honors thesis is to examine whether and how fluctuations in exchange rates and international trade affect the unemployment rate in the United States. In particular, on the basis monthly data and cointegrated or regular vector autoregressive (VAR) models I study the response of unemployment to shocks in exchange rates and international trade from the three largest trade partners of the United States (China, Japan and the Euro zone). To distinguish these effects from domestic causes I also include the index of industrial production in these models. The empirical work is to examine whether the time series involved are stationarity or unit root processes, and to conduct cointegration and VAR innovation response analysis. The results show that there is no significant response of unemployment to innovation shocks in the exchange rates. The same applies to innovation shocks in trade, except for trade with Japan and Germany. In particular, the response of unemployment to a unit shock in import from Japan is negative, which is contrary to what one would expect, whereas in a multi-country model the response of unemployment to a unit shock in exports to Germany is positive. Computing Projects Computing Skills: STATA, C++, Matlab, SAS, R, LaTex, Microsoft Office (Word, Excel, PowerPoint) A software of Matrix Calculator in C++ with self-written matrix template class library (Intermediate Programming) Numerical Library for solving linear systems of equations using Matlab (Numerical Analysis I) Application of Numerical Ordinary Differential Equation to Passive Linear Filters (Numerical Analysis II)

Oil price and macroeconomy in Russia. Abstract

Oil price and macroeconomy in Russia. Abstract Oil price and macroeconomy in Russia Katsuya Ito Fukuoka University Abstract In this note, using the VEC model we attempt to empirically investigate the effects of oil price and monetary shocks on the

More information

Volume 29, Issue 1. Price and Wage Setting in Japan: An Empirical Investigation

Volume 29, Issue 1. Price and Wage Setting in Japan: An Empirical Investigation Volume 29, Issue 1 Price and Wage Setting in Japan: An Empirical Investigation Shigeyuki Hamori Kobe University Junya Masuda Mitsubishi Research Institute Takeshi Hoshikawa Kinki University Kunihiro Hanabusa

More information

ARDL Cointegration Tests for Beginner

ARDL Cointegration Tests for Beginner ARDL Cointegration Tests for Beginner Tuck Cheong TANG Department of Economics, Faculty of Economics & Administration University of Malaya Email: tangtuckcheong@um.edu.my DURATION: 3 HOURS On completing

More information

THE LONG-RUN DETERMINANTS OF MONEY DEMAND IN SLOVAKIA MARTIN LUKÁČIK - ADRIANA LUKÁČIKOVÁ - KAROL SZOMOLÁNYI

THE LONG-RUN DETERMINANTS OF MONEY DEMAND IN SLOVAKIA MARTIN LUKÁČIK - ADRIANA LUKÁČIKOVÁ - KAROL SZOMOLÁNYI 92 Multiple Criteria Decision Making XIII THE LONG-RUN DETERMINANTS OF MONEY DEMAND IN SLOVAKIA MARTIN LUKÁČIK - ADRIANA LUKÁČIKOVÁ - KAROL SZOMOLÁNYI Abstract: The paper verifies the long-run determinants

More information

A Test of Cointegration Rank Based Title Component Analysis.

A Test of Cointegration Rank Based Title Component Analysis. A Test of Cointegration Rank Based Title Component Analysis Author(s) Chigira, Hiroaki Citation Issue 2006-01 Date Type Technical Report Text Version publisher URL http://hdl.handle.net/10086/13683 Right

More information

TESTING FOR CO-INTEGRATION

TESTING FOR CO-INTEGRATION Bo Sjö 2010-12-05 TESTING FOR CO-INTEGRATION To be used in combination with Sjö (2008) Testing for Unit Roots and Cointegration A Guide. Instructions: Use the Johansen method to test for Purchasing Power

More information

11/18/2008. So run regression in first differences to examine association. 18 November November November 2008

11/18/2008. So run regression in first differences to examine association. 18 November November November 2008 Time Series Econometrics 7 Vijayamohanan Pillai N Unit Root Tests Vijayamohan: CDS M Phil: Time Series 7 1 Vijayamohan: CDS M Phil: Time Series 7 2 R 2 > DW Spurious/Nonsense Regression. Integrated but

More information

The causal relationship between energy consumption and GDP in Turkey

The causal relationship between energy consumption and GDP in Turkey The causal relationship between energy consumption and GDP in Turkey Huseyin Kalyoncu1, Ilhan Ozturk2, Muhittin Kaplan1 1Meliksah University, Faculty of Economics and Administrative Sciences, 38010, Kayseri,

More information

The Dynamic Relationships between Oil Prices and the Japanese Economy: A Frequency Domain Analysis. Wei Yanfeng

The Dynamic Relationships between Oil Prices and the Japanese Economy: A Frequency Domain Analysis. Wei Yanfeng Review of Economics & Finance Submitted on 23/Sept./2012 Article ID: 1923-7529-2013-02-57-11 Wei Yanfeng The Dynamic Relationships between Oil Prices and the Japanese Economy: A Frequency Domain Analysis

More information

Introduction to Modern Time Series Analysis

Introduction to Modern Time Series Analysis Introduction to Modern Time Series Analysis Gebhard Kirchgässner, Jürgen Wolters and Uwe Hassler Second Edition Springer 3 Teaching Material The following figures and tables are from the above book. They

More information

CHAPTER III RESEARCH METHODOLOGY. trade balance performance of selected ASEAN-5 countries and exchange rate

CHAPTER III RESEARCH METHODOLOGY. trade balance performance of selected ASEAN-5 countries and exchange rate CHAPTER III RESEARCH METHODOLOGY 3.1 Research s Object The research object is taking the macroeconomic perspective and focused on selected ASEAN-5 countries. This research is conducted to describe how

More information

TRINITY COLLEGE DEPARTMENT OF ECONOMICS WORKING PAPER 15-08

TRINITY COLLEGE DEPARTMENT OF ECONOMICS WORKING PAPER 15-08 Department of Economics Trinity College Hartford, CT 06106 USA http://www.trincoll.edu/depts/econ/ TRINITY COLLEGE DEPARTMENT OF ECONOMICS WORKING PAPER 15-08 Purchasing Power Parity: A Time Series Analysis

More information

Lecture 5: Unit Roots, Cointegration and Error Correction Models The Spurious Regression Problem

Lecture 5: Unit Roots, Cointegration and Error Correction Models The Spurious Regression Problem Lecture 5: Unit Roots, Cointegration and Error Correction Models The Spurious Regression Problem Prof. Massimo Guidolin 20192 Financial Econometrics Winter/Spring 2018 Overview Stochastic vs. deterministic

More information

International Monetary Policy Spillovers

International Monetary Policy Spillovers International Monetary Policy Spillovers Dennis Nsafoah Department of Economics University of Calgary Canada November 1, 2017 1 Abstract This paper uses monthly data (from January 1997 to April 2017) to

More information

Population Growth and Economic Development: Test for Causality

Population Growth and Economic Development: Test for Causality The Lahore Journal of Economics 11 : 2 (Winter 2006) pp. 71-77 Population Growth and Economic Development: Test for Causality Khalid Mushtaq * Abstract This paper examines the existence of a long-run relationship

More information

Autoregressive Integrated Moving Average Model to Predict Graduate Unemployment in Indonesia

Autoregressive Integrated Moving Average Model to Predict Graduate Unemployment in Indonesia DOI 10.1515/ptse-2017-0005 PTSE 12 (1): 43-50 Autoregressive Integrated Moving Average Model to Predict Graduate Unemployment in Indonesia Umi MAHMUDAH u_mudah@yahoo.com (State Islamic University of Pekalongan,

More information

7. Integrated Processes

7. Integrated Processes 7. Integrated Processes Up to now: Analysis of stationary processes (stationary ARMA(p, q) processes) Problem: Many economic time series exhibit non-stationary patterns over time 226 Example: We consider

More information

A TIME SERIES PARADOX: UNIT ROOT TESTS PERFORM POORLY WHEN DATA ARE COINTEGRATED

A TIME SERIES PARADOX: UNIT ROOT TESTS PERFORM POORLY WHEN DATA ARE COINTEGRATED A TIME SERIES PARADOX: UNIT ROOT TESTS PERFORM POORLY WHEN DATA ARE COINTEGRATED by W. Robert Reed Department of Economics and Finance University of Canterbury, New Zealand Email: bob.reed@canterbury.ac.nz

More information

PubPol 201. Module 3: International Trade Policy. Class 4 Outline. Class 4 Outline. Class 4 China Shock

PubPol 201. Module 3: International Trade Policy. Class 4 Outline. Class 4 Outline. Class 4 China Shock PubPol 201 Module 3: International Trade Policy Class 4 China s growth The The ADH analysis Other sources Class 4 Outline Lecture 4: China 2 China s growth The The ADH analysis Other sources Class 4 Outline

More information

Inflation Revisited: New Evidence from Modified Unit Root Tests

Inflation Revisited: New Evidence from Modified Unit Root Tests 1 Inflation Revisited: New Evidence from Modified Unit Root Tests Walter Enders and Yu Liu * University of Alabama in Tuscaloosa and University of Texas at El Paso Abstract: We propose a simple modification

More information

TERMS OF TRADE: THE AGRICULTURE-INDUSTRY INTERACTION IN THE CARIBBEAN

TERMS OF TRADE: THE AGRICULTURE-INDUSTRY INTERACTION IN THE CARIBBEAN (Draft- February 2004) TERMS OF TRADE: THE AGRICULTURE-INDUSTRY INTERACTION IN THE CARIBBEAN Chandra Sitahal-Aleong Delaware State University, Dover, Delaware, USA John Aleong, University of Vermont, Burlington,

More information

Forecasting Foreign Direct Investment Inflows into India Using ARIMA Model

Forecasting Foreign Direct Investment Inflows into India Using ARIMA Model Forecasting Foreign Direct Investment Inflows into India Using ARIMA Model Dr.K.Nithya Kala & Aruna.P.Remesh, 1 Assistant Professor, PSGR Krishnammal College for Women, Coimbatore, Tamilnadu, India 2 PhD

More information

Econ 423 Lecture Notes: Additional Topics in Time Series 1

Econ 423 Lecture Notes: Additional Topics in Time Series 1 Econ 423 Lecture Notes: Additional Topics in Time Series 1 John C. Chao April 25, 2017 1 These notes are based in large part on Chapter 16 of Stock and Watson (2011). They are for instructional purposes

More information

OUTWARD FDI, DOMESTIC INVESTMENT AND INFORMAL INSTITUTIONS: EVIDENCE FROM CHINA WAQAR AMEER & MOHAMMED SAUD M ALOTAISH

OUTWARD FDI, DOMESTIC INVESTMENT AND INFORMAL INSTITUTIONS: EVIDENCE FROM CHINA WAQAR AMEER & MOHAMMED SAUD M ALOTAISH International Journal of Economics, Commerce and Research (IJECR) ISSN(P): 2250-0006; ISSN(E): 2319-4472 Vol. 7, Issue 1, Feb 2017, 25-30 TJPRC Pvt. Ltd. OUTWARD FDI, DOMESTIC INVESTMENT AND INFORMAL INSTITUTIONS:

More information

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY Time Series Analysis James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY & Contents PREFACE xiii 1 1.1. 1.2. Difference Equations First-Order Difference Equations 1 /?th-order Difference

More information

An Empirical Analysis of RMB Exchange Rate changes impact on PPI of China

An Empirical Analysis of RMB Exchange Rate changes impact on PPI of China 2nd International Conference on Economics, Management Engineering and Education Technology (ICEMEET 206) An Empirical Analysis of RMB Exchange Rate changes impact on PPI of China Chao Li, a and Yonghua

More information

Department of Economics, UCSB UC Santa Barbara

Department of Economics, UCSB UC Santa Barbara Department of Economics, UCSB UC Santa Barbara Title: Past trend versus future expectation: test of exchange rate volatility Author: Sengupta, Jati K., University of California, Santa Barbara Sfeir, Raymond,

More information

7. Integrated Processes

7. Integrated Processes 7. Integrated Processes Up to now: Analysis of stationary processes (stationary ARMA(p, q) processes) Problem: Many economic time series exhibit non-stationary patterns over time 226 Example: We consider

More information

Forecasting Bangladesh's Inflation through Econometric Models

Forecasting Bangladesh's Inflation through Econometric Models American Journal of Economics and Business Administration Original Research Paper Forecasting Bangladesh's Inflation through Econometric Models 1,2 Nazmul Islam 1 Department of Humanities, Bangladesh University

More information

A Horse-Race Contest of Selected Economic Indicators & Their Potential Prediction Abilities on GDP

A Horse-Race Contest of Selected Economic Indicators & Their Potential Prediction Abilities on GDP A Horse-Race Contest of Selected Economic Indicators & Their Potential Prediction Abilities on GDP Tahmoures Afshar, Woodbury University, USA ABSTRACT This paper empirically investigates, in the context

More information

Testing for non-stationarity

Testing for non-stationarity 20 November, 2009 Overview The tests for investigating the non-stationary of a time series falls into four types: 1 Check the null that there is a unit root against stationarity. Within these, there are

More information

APPLIED TIME SERIES ECONOMETRICS

APPLIED TIME SERIES ECONOMETRICS APPLIED TIME SERIES ECONOMETRICS Edited by HELMUT LÜTKEPOHL European University Institute, Florence MARKUS KRÄTZIG Humboldt University, Berlin CAMBRIDGE UNIVERSITY PRESS Contents Preface Notation and Abbreviations

More information

Testing Purchasing Power Parity Hypothesis for Azerbaijan

Testing Purchasing Power Parity Hypothesis for Azerbaijan Khazar Journal of Humanities and Social Sciences Volume 18, Number 3, 2015 Testing Purchasing Power Parity Hypothesis for Azerbaijan Seymur Agazade Recep Tayyip Erdoğan University, Turkey Introduction

More information

Univariate, Nonstationary Processes

Univariate, Nonstationary Processes Univariate, Nonstationary Processes Jamie Monogan University of Georgia March 20, 2018 Jamie Monogan (UGA) Univariate, Nonstationary Processes March 20, 2018 1 / 14 Objectives By the end of this meeting,

More information

BCT Lecture 3. Lukas Vacha.

BCT Lecture 3. Lukas Vacha. BCT Lecture 3 Lukas Vacha vachal@utia.cas.cz Stationarity and Unit Root Testing Why do we need to test for Non-Stationarity? The stationarity or otherwise of a series can strongly influence its behaviour

More information

Empirical Market Microstructure Analysis (EMMA)

Empirical Market Microstructure Analysis (EMMA) Empirical Market Microstructure Analysis (EMMA) Lecture 3: Statistical Building Blocks and Econometric Basics Prof. Dr. Michael Stein michael.stein@vwl.uni-freiburg.de Albert-Ludwigs-University of Freiburg

More information

Forecasting Levels of log Variables in Vector Autoregressions

Forecasting Levels of log Variables in Vector Autoregressions September 24, 200 Forecasting Levels of log Variables in Vector Autoregressions Gunnar Bårdsen Department of Economics, Dragvoll, NTNU, N-749 Trondheim, NORWAY email: gunnar.bardsen@svt.ntnu.no Helmut

More information

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY Time Series Analysis James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY PREFACE xiii 1 Difference Equations 1.1. First-Order Difference Equations 1 1.2. pth-order Difference Equations 7

More information

Analyzing the Spillover effect of Housing Prices

Analyzing the Spillover effect of Housing Prices 3rd International Conference on Humanities, Geography and Economics (ICHGE'013) January 4-5, 013 Bali (Indonesia) Analyzing the Spillover effect of Housing Prices Kyongwook. Choi, Namwon. Hyung, Hyungchol.

More information

Real exchange rate behavior in 4 CEE countries using different unit root tests under PPP paradigm

Real exchange rate behavior in 4 CEE countries using different unit root tests under PPP paradigm 1 Introduction Real exchange rate behavior in 4 CEE countries using different unit root tests under PPP paradigm Ghiba Nicolae 1, Sadoveanu Diana 2, Avadanei Anamaria 3 Abstract. This paper aims to analyze

More information

growth in a time of debt evidence from the uk

growth in a time of debt evidence from the uk growth in a time of debt evidence from the uk Juergen Amann June 22, 2015 ISEO Summer School 2015 Structure Literature & Research Question Data & Methodology Empirics & Results Conclusio 1 literature &

More information

On Consistency of Tests for Stationarity in Autoregressive and Moving Average Models of Different Orders

On Consistency of Tests for Stationarity in Autoregressive and Moving Average Models of Different Orders American Journal of Theoretical and Applied Statistics 2016; 5(3): 146-153 http://www.sciencepublishinggroup.com/j/ajtas doi: 10.11648/j.ajtas.20160503.20 ISSN: 2326-8999 (Print); ISSN: 2326-9006 (Online)

More information

Multivariate Time Series Analysis and Its Applications [Tsay (2005), chapter 8]

Multivariate Time Series Analysis and Its Applications [Tsay (2005), chapter 8] 1 Multivariate Time Series Analysis and Its Applications [Tsay (2005), chapter 8] Insights: Price movements in one market can spread easily and instantly to another market [economic globalization and internet

More information

Modelling of Economic Time Series and the Method of Cointegration

Modelling of Economic Time Series and the Method of Cointegration AUSTRIAN JOURNAL OF STATISTICS Volume 35 (2006), Number 2&3, 307 313 Modelling of Economic Time Series and the Method of Cointegration Jiri Neubauer University of Defence, Brno, Czech Republic Abstract:

More information

EXCHANGE RATE PASS-THROUGH: THE CASE OF BRAZILIAN EXPORTS OF MANUFACTURES

EXCHANGE RATE PASS-THROUGH: THE CASE OF BRAZILIAN EXPORTS OF MANUFACTURES EXCHANGE RATE PASS-THROUGH: THE CASE OF BRAZILIAN EXPORTS OF MANUFACTURES Afonso Ferreira Departamento de Economia - Universidade Federal de Minas Gerais (UFMG) and Centro de Pesquisa em Economia Internacional,

More information

The PPP Hypothesis Revisited

The PPP Hypothesis Revisited 1288 Discussion Papers Deutsches Institut für Wirtschaftsforschung 2013 The PPP Hypothesis Revisited Evidence Using a Multivariate Long-Memory Model Guglielmo Maria Caporale, Luis A.Gil-Alana and Yuliya

More information

Volume 37, Issue 1. Animal spirits, the stock market, and the unemployment rate: Some evidence for German data

Volume 37, Issue 1. Animal spirits, the stock market, and the unemployment rate: Some evidence for German data Volume 37, Issue 1 Animal spirits, the stock market, and the unemployment rate: Some evidence for German data Ulrich Fritsche University Hamburg Christian Pierdzioch Helmut-Schmidt-University Hamburg Abstract

More information

Volume 30, Issue 1. EUAs and CERs: Vector Autoregression, Impulse Response Function and Cointegration Analysis

Volume 30, Issue 1. EUAs and CERs: Vector Autoregression, Impulse Response Function and Cointegration Analysis Volume 30, Issue 1 EUAs and CERs: Vector Autoregression, Impulse Response Function and Cointegration Analysis Julien Chevallier Université Paris Dauphine Abstract EUAs are European Union Allowances traded

More information

Generalized Impulse Response Analysis: General or Extreme?

Generalized Impulse Response Analysis: General or Extreme? Auburn University Department of Economics Working Paper Series Generalized Impulse Response Analysis: General or Extreme? Hyeongwoo Kim Auburn University AUWP 2012-04 This paper can be downloaded without

More information

Economics 618B: Time Series Analysis Department of Economics State University of New York at Binghamton

Economics 618B: Time Series Analysis Department of Economics State University of New York at Binghamton Problem Set #1 1. Generate n =500random numbers from both the uniform 1 (U [0, 1], uniformbetween zero and one) and exponential λ exp ( λx) (set λ =2and let x U [0, 1]) b a distributions. Plot the histograms

More information

Trends and Unit Roots in Greek Real Money Supply, Real GDP and Nominal Interest Rate

Trends and Unit Roots in Greek Real Money Supply, Real GDP and Nominal Interest Rate European Research Studies Volume V, Issue (3-4), 00, pp. 5-43 Trends and Unit Roots in Greek Real Money Supply, Real GDP and Nominal Interest Rate Karpetis Christos & Varelas Erotokritos * Abstract This

More information

Existence of Export-Import Cointegration: A Study on Indonesia and Malaysia

Existence of Export-Import Cointegration: A Study on Indonesia and Malaysia Existence of Export-Import Cointegration: A Study on Indonesia and Malaysia Mohammad Zillur Rahman Assistant Professor, School of Business Studies Southeast University, Plot 64-B, Road#18-B, Banani, Dhaka,

More information

THE IMPACT OF REAL EXCHANGE RATE CHANGES ON SOUTH AFRICAN AGRICULTURAL EXPORTS: AN ERROR CORRECTION MODEL APPROACH

THE IMPACT OF REAL EXCHANGE RATE CHANGES ON SOUTH AFRICAN AGRICULTURAL EXPORTS: AN ERROR CORRECTION MODEL APPROACH THE IMPACT OF REAL EXCHANGE RATE CHANGES ON SOUTH AFRICAN AGRICULTURAL EXPORTS: AN ERROR CORRECTION MODEL APPROACH D. Poonyth and J. van Zyl 1 This study evaluates the long run and short run effects of

More information

Nonstationary Time Series:

Nonstationary Time Series: Nonstationary Time Series: Unit Roots Egon Zakrajšek Division of Monetary Affairs Federal Reserve Board Summer School in Financial Mathematics Faculty of Mathematics & Physics University of Ljubljana September

More information

THE LONG RUN RELATIONSHIP BETWEEN SAVING AND INVESTMENT IN INDIA

THE LONG RUN RELATIONSHIP BETWEEN SAVING AND INVESTMENT IN INDIA THE LONG RUN RELATIONSHIP BETWEEN SAVING AND INVESTMENT IN INDIA Dipendra Sinha Department of Economics Macquarie University Sydney, NSW 2109 AUSTRALIA and Tapen Sinha Center for Statistical Applications

More information

The Connection between the Exchange Rate and the Balance of Payments Accounts in the Czech Republic: An Econometric Approach

The Connection between the Exchange Rate and the Balance of Payments Accounts in the Czech Republic: An Econometric Approach DOI: 10.5817/FAI2017-1-4 No. 1/2017 The Connection between the Exchange Rate and the Balance of Payments Accounts in the Czech Republic: An Econometric Approach Tomáš Urbanovský Masaryk University Faculty

More information

FINANCIAL ECONOMETRICS AND EMPIRICAL FINANCE -MODULE2 Midterm Exam Solutions - March 2015

FINANCIAL ECONOMETRICS AND EMPIRICAL FINANCE -MODULE2 Midterm Exam Solutions - March 2015 FINANCIAL ECONOMETRICS AND EMPIRICAL FINANCE -MODULE2 Midterm Exam Solutions - March 205 Time Allowed: 60 minutes Family Name (Surname) First Name Student Number (Matr.) Please answer all questions by

More information

Generalized Impulse Response Analysis: General or Extreme?

Generalized Impulse Response Analysis: General or Extreme? MPRA Munich Personal RePEc Archive Generalized Impulse Response Analysis: General or Extreme? Kim Hyeongwoo Auburn University April 2009 Online at http://mpra.ub.uni-muenchen.de/17014/ MPRA Paper No. 17014,

More information

Introduction to Regression Analysis. Dr. Devlina Chatterjee 11 th August, 2017

Introduction to Regression Analysis. Dr. Devlina Chatterjee 11 th August, 2017 Introduction to Regression Analysis Dr. Devlina Chatterjee 11 th August, 2017 What is regression analysis? Regression analysis is a statistical technique for studying linear relationships. One dependent

More information

Econ 424 Time Series Concepts

Econ 424 Time Series Concepts Econ 424 Time Series Concepts Eric Zivot January 20 2015 Time Series Processes Stochastic (Random) Process { 1 2 +1 } = { } = sequence of random variables indexed by time Observed time series of length

More information

Modeling Long-Run Relationships

Modeling Long-Run Relationships Modeling Long-Run Relationships Chapter 8 of Chris Brook s Book Christopher Ting http://www.mysmu.edu/faculty/christophert/ Christopher Ting : christopherting@smu.edu.sg : 6828 0364 : LKCSB 5036 April

More information

Frederick Wallace Universidad de Quintana Roo. Abstract

Frederick Wallace Universidad de Quintana Roo. Abstract Nonlinear unit root tests of PPP using long-horizon data Frederick Wallace Universidad de Quintana Roo Abstract The Kapetanios, Shin, and Snell (KSS, 2003) test for a nonlinear unit root is used to study

More information

TESTING FOR CO-INTEGRATION PcGive and EViews 1

TESTING FOR CO-INTEGRATION PcGive and EViews 1 Bo Sjö 203--27 Lab 3 TESTING FOR CO-INTEGRATION PcGive and EViews To be used in combination with Sjö (203) Testing for Unit Roots and Cointegration A Guide and the special instructions below for EViews

More information

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014 Warwick Business School Forecasting System Summary Ana Galvao, Anthony Garratt and James Mitchell November, 21 The main objective of the Warwick Business School Forecasting System is to provide competitive

More information

Introduction to Econometrics

Introduction to Econometrics Introduction to Econometrics STAT-S-301 Introduction to Time Series Regression and Forecasting (2016/2017) Lecturer: Yves Dominicy Teaching Assistant: Elise Petit 1 Introduction to Time Series Regression

More information

ECON 4160, Spring term Lecture 12

ECON 4160, Spring term Lecture 12 ECON 4160, Spring term 2013. Lecture 12 Non-stationarity and co-integration 2/2 Ragnar Nymoen Department of Economics 13 Nov 2013 1 / 53 Introduction I So far we have considered: Stationary VAR, with deterministic

More information

Applied Econometrics and International Development Vol.9-1 (2009)

Applied Econometrics and International Development Vol.9-1 (2009) FUNCTIONAL FORMS AND PPP: THE CASE OF CANADA, THE EU, JAPAN, AND THE U.K. HSING, Yu Abstract This paper applies an extended Box-Cox model to test the functional form of the purchasing power parity hypothesis

More information

Author: Yesuf M. Awel 1c. Affiliation: 1 PhD, Economist-Consultant; P.O Box , Addis Ababa, Ethiopia. c.

Author: Yesuf M. Awel 1c. Affiliation: 1 PhD, Economist-Consultant; P.O Box , Addis Ababa, Ethiopia. c. ISSN: 2415-0304 (Print) ISSN: 2522-2465 (Online) Indexing/Abstracting Forecasting GDP Growth: Application of Autoregressive Integrated Moving Average Model Author: Yesuf M. Awel 1c Affiliation: 1 PhD,

More information

Financial Time Series Analysis: Part II

Financial Time Series Analysis: Part II Department of Mathematics and Statistics, University of Vaasa, Finland Spring 2017 1 Unit root Deterministic trend Stochastic trend Testing for unit root ADF-test (Augmented Dickey-Fuller test) Testing

More information

An Econometric Modeling for India s Imports and exports during

An Econometric Modeling for India s Imports and exports during Inter national Journal of Pure and Applied Mathematics Volume 113 No. 6 2017, 242 250 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu An Econometric

More information

9) Time series econometrics

9) Time series econometrics 30C00200 Econometrics 9) Time series econometrics Timo Kuosmanen Professor Management Science http://nomepre.net/index.php/timokuosmanen 1 Macroeconomic data: GDP Inflation rate Examples of time series

More information

Empirical Approach to Modelling and Forecasting Inflation in Ghana

Empirical Approach to Modelling and Forecasting Inflation in Ghana Current Research Journal of Economic Theory 4(3): 83-87, 2012 ISSN: 2042-485X Maxwell Scientific Organization, 2012 Submitted: April 13, 2012 Accepted: May 06, 2012 Published: June 30, 2012 Empirical Approach

More information

Time Series Forecasting Model for Chinese Future Marketing Price of Copper and Aluminum

Time Series Forecasting Model for Chinese Future Marketing Price of Copper and Aluminum Georgia State University ScholarWorks @ Georgia State University Mathematics Theses Department of Mathematics and Statistics 11-18-2008 Time Series Forecasting Model for Chinese Future Marketing Price

More information

Prof. Dr. Roland Füss Lecture Series in Applied Econometrics Summer Term Introduction to Time Series Analysis

Prof. Dr. Roland Füss Lecture Series in Applied Econometrics Summer Term Introduction to Time Series Analysis Introduction to Time Series Analysis 1 Contents: I. Basics of Time Series Analysis... 4 I.1 Stationarity... 5 I.2 Autocorrelation Function... 9 I.3 Partial Autocorrelation Function (PACF)... 14 I.4 Transformation

More information

Unit Roots, Nonlinear Cointegration and Purchasing Power Parity

Unit Roots, Nonlinear Cointegration and Purchasing Power Parity Unit Roots, Nonlinear Cointegration and Purchasing Power Parity Alfred A. Haug and Syed A. Basher June 10, 2005 Abstract We test long run PPP within a general model of cointegration of linear and nonlinear

More information

1 Regression with Time Series Variables

1 Regression with Time Series Variables 1 Regression with Time Series Variables With time series regression, Y might not only depend on X, but also lags of Y and lags of X Autoregressive Distributed lag (or ADL(p; q)) model has these features:

More information

ARMA MODELS Herman J. Bierens Pennsylvania State University February 23, 2009

ARMA MODELS Herman J. Bierens Pennsylvania State University February 23, 2009 1. Introduction Given a covariance stationary process µ ' E[ ], the Wold decomposition states that where U t ARMA MODELS Herman J. Bierens Pennsylvania State University February 23, 2009 with vanishing

More information

Univariate ARIMA Models

Univariate ARIMA Models Univariate ARIMA Models ARIMA Model Building Steps: Identification: Using graphs, statistics, ACFs and PACFs, transformations, etc. to achieve stationary and tentatively identify patterns and model components.

More information

UPPSALA UNIVERSITY - DEPARTMENT OF STATISTICS MIDAS. Forecasting quarterly GDP using higherfrequency

UPPSALA UNIVERSITY - DEPARTMENT OF STATISTICS MIDAS. Forecasting quarterly GDP using higherfrequency UPPSALA UNIVERSITY - DEPARTMENT OF STATISTICS MIDAS Forecasting quarterly GDP using higherfrequency data Authors: Hanna Lindgren and Victor Nilsson Supervisor: Lars Forsberg January 12, 2015 We forecast

More information

Output correlation and EMU: evidence from European countries

Output correlation and EMU: evidence from European countries 1 Output correlation and EMU: evidence from European countries Kazuyuki Inagaki Graduate School of Economics, Kobe University, Rokkodai, Nada-ku, Kobe, 657-8501, Japan. Abstract This paper examines the

More information

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 This is a four hours closed-book exam (uden hjælpemidler). Please answer all questions. As a guiding principle the questions 1 to 4 have equal

More information

Market efficiency of the bitcoin exchange rate: applications to. U.S. dollar and Euro

Market efficiency of the bitcoin exchange rate: applications to. U.S. dollar and Euro Market efficiency of the bitcoin exchange rate: applications to U.S. dollar and Euro Zheng Nan and Taisei Kaizoji International Christian University 3-10-2 Osawa, Mitaka, Tokyo 181-8585 1 Introduction

More information

Cointegrated VARIMA models: specification and. simulation

Cointegrated VARIMA models: specification and. simulation Cointegrated VARIMA models: specification and simulation José L. Gallego and Carlos Díaz Universidad de Cantabria. Abstract In this note we show how specify cointegrated vector autoregressive-moving average

More information

Relationship between Trade Openness and Economic Growth in. Sri Lanka: a Time Series Analysis

Relationship between Trade Openness and Economic Growth in. Sri Lanka: a Time Series Analysis Relationship between Trade Openness and Economic Growth in Introduction Sri Lanka: a Time Series Analysis K.W.K. Gimhani 1, S. J Francis 2 Sri Lanka became the first South Asian country to liberalise its

More information

Estimates of the Sticky-Information Phillips Curve for the USA with the General to Specific Method

Estimates of the Sticky-Information Phillips Curve for the USA with the General to Specific Method MPRA Munich Personal RePEc Archive Estimates of the Sticky-Information Phillips Curve for the USA with the General to Specific Method Antonio Paradiso and B. Bhaskara Rao and Marco Ventura 12. February

More information

Identifying the Monetary Policy Shock Christiano et al. (1999)

Identifying the Monetary Policy Shock Christiano et al. (1999) Identifying the Monetary Policy Shock Christiano et al. (1999) The question we are asking is: What are the consequences of a monetary policy shock a shock which is purely related to monetary conditions

More information

Darmstadt Discussion Papers in Economics

Darmstadt Discussion Papers in Economics Darmstadt Discussion Papers in Economics The Effect of Linear Time Trends on Cointegration Testing in Single Equations Uwe Hassler Nr. 111 Arbeitspapiere des Instituts für Volkswirtschaftslehre Technische

More information

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Fin. Econometrics / 31

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Fin. Econometrics / 31 Cointegrated VAR s Eduardo Rossi University of Pavia November 2014 Rossi Cointegrated VAR s Fin. Econometrics - 2014 1 / 31 B-N decomposition Give a scalar polynomial α(z) = α 0 + α 1 z +... + α p z p

More information

How Can We Extract a Fundamental Trend from an Economic Time-Series?

How Can We Extract a Fundamental Trend from an Economic Time-Series? How Can We Extract MONETARY a Fundamental AND ECONOMIC Trend from STUDIES/DECEMBER an Economic Time-Series? 1998 How Can We Extract a Fundamental Trend from an Economic Time-Series? Masahiro Higo and Sachiko

More information

Unit root problem, solution of difference equations Simple deterministic model, question of unit root

Unit root problem, solution of difference equations Simple deterministic model, question of unit root Unit root problem, solution of difference equations Simple deterministic model, question of unit root (1 φ 1 L)X t = µ, Solution X t φ 1 X t 1 = µ X t = A + Bz t with unknown z and unknown A (clearly X

More information

Financial Econometrics

Financial Econometrics Financial Econometrics Long-run Relationships in Finance Gerald P. Dwyer Trinity College, Dublin January 2016 Outline 1 Long-Run Relationships Review of Nonstationarity in Mean Cointegration Vector Error

More information

TRADE POLICY AND ECONOMIC GROWTH IN INDONESIA Oleh: Nenny Hendajany 1)

TRADE POLICY AND ECONOMIC GROWTH IN INDONESIA Oleh: Nenny Hendajany 1) EKO-REGIONAL, Vol.10, No.2, September 2015 TRADE POLICY AND ECONOMIC GROWTH IN INDONESIA Oleh: Nenny Hendajany 1) 1) Universitas Sangga Buana Email: nennyhendajany@gmail.com ABSTRACT The paper examines

More information

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Financial Econometrics / 56

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Financial Econometrics / 56 Cointegrated VAR s Eduardo Rossi University of Pavia November 2013 Rossi Cointegrated VAR s Financial Econometrics - 2013 1 / 56 VAR y t = (y 1t,..., y nt ) is (n 1) vector. y t VAR(p): Φ(L)y t = ɛ t The

More information

Cointegration and Tests of Purchasing Parity Anthony Mac Guinness- Senior Sophister

Cointegration and Tests of Purchasing Parity Anthony Mac Guinness- Senior Sophister Cointegration and Tests of Purchasing Parity Anthony Mac Guinness- Senior Sophister Most of us know Purchasing Power Parity as a sensible way of expressing per capita GNP; that is taking local price levels

More information

Empirical Project, part 1, ECO 672

Empirical Project, part 1, ECO 672 Empirical Project, part 1, ECO 672 Due Date: see schedule in syllabus Instruction: The empirical project has two parts. This is part 1, which is worth 15 points. You need to work independently on this

More information

Chapter 12: An introduction to Time Series Analysis. Chapter 12: An introduction to Time Series Analysis

Chapter 12: An introduction to Time Series Analysis. Chapter 12: An introduction to Time Series Analysis Chapter 12: An introduction to Time Series Analysis Introduction In this chapter, we will discuss forecasting with single-series (univariate) Box-Jenkins models. The common name of the models is Auto-Regressive

More information

PhD/MA Econometrics Examination January 2012 PART A

PhD/MA Econometrics Examination January 2012 PART A PhD/MA Econometrics Examination January 2012 PART A ANSWER ANY TWO QUESTIONS IN THIS SECTION NOTE: (1) The indicator function has the properties: (2) Question 1 Let, [defined as if using the indicator

More information

Asitha Kodippili. Deepthika Senaratne. Department of Mathematics and Computer Science,Fayetteville State University, USA.

Asitha Kodippili. Deepthika Senaratne. Department of Mathematics and Computer Science,Fayetteville State University, USA. Forecasting Tourist Arrivals to Sri Lanka Using Seasonal ARIMA Asitha Kodippili Department of Mathematics and Computer Science,Fayetteville State University, USA. akodippili@uncfsu.edu Deepthika Senaratne

More information

LATVIAN GDP: TIME SERIES FORECASTING USING VECTOR AUTO REGRESSION

LATVIAN GDP: TIME SERIES FORECASTING USING VECTOR AUTO REGRESSION LATVIAN GDP: TIME SERIES FORECASTING USING VECTOR AUTO REGRESSION BEZRUCKO Aleksandrs, (LV) Abstract: The target goal of this work is to develop a methodology of forecasting Latvian GDP using ARMA (AutoRegressive-Moving-Average)

More information

Measuring price discovery in agricultural markets

Measuring price discovery in agricultural markets Measuring price discovery in agricultural markets Evgenia Pavlova, Georg-August-University Göttingen, Germany, epavlov@gwdg.de Stephan von Cramon-Taubadel, Georg-August-University Göttingen, Germany, scramon@gwdg.de

More information