ADF Unit Root Test Research Articles

Impact of Population Growth on Unemployment in Nigeria: Dynamic OLS Approach

This empirical research examined the impact of population growth on unemployment in Nigeria. The study applied annual time series data from 1991 to 2017. The data on population, unemployment, consumer price index, exchange rate and foreign direct investment were tested for unit root using ADF, PP and KPSS unit root tests. The results from the ADF and PP tests revealed that all the variables were stationary at first difference except CPI that is stationary at level. While the KPSS units root test result shows that all the variables are stationary at level. The variables were co-integrated as shown by the Johansen Juselius test for co-integration. The Dynamic Ordinary Least Squares (DOLS) were used in the process of estimating the model. The main results disclosed that population and exchange rate impacted positively with unemployment. Whereas consumer price index, GDP per capita and foreign direct investment impacted negatively thereby reducing the rate of unemployment in the long-run. Government should focus more on attracting foreign direct investment, increasing GDP per capita and the desired rate of consumer price index in order to control the rate of unemployment in the country. Keywords: Population Growth, Unemployment, Dynamic Ordinary Least Squares, Co-integration test, GDP per capita, Consumer Price Index, Foreign Direct Investment. DOI : 10.7176/JESD/10-22-09 Publication date: November 30 th 2019

Determinants of Economic Growth in Ethiopia: Evidence from ARDL Approach Analysis

Ensuring sustained real growth in national income is a primary concern to both developed and developing countries. It is that sustained growth in real national income to potentially explain an economy’s development path and people’s wellbeing. Though Ethiopia records double digit growth rate for last few years, it has been found to be unstable due to various internal and emerging global influences. Besides, recent home side political condition is also another challenge to the economic sector of the country at large. The present study examines factors potentially explaining the economic growth of Ethiopia using annual time series observations for the period running from 1981 to 2016. Individual variables were all subjected to both the ADF and PP unit root tests; and that, the existence of mixed order of integration has been confirmed with both approaches. For Cointegration issues, the ARDL approach was employed and the existence of long run relationship among variables entered the growth model has been confirmed too. Besides, none of the diagnostic tests was revealed invalid thereby ensuring the relevance of inferences made based on the ARDL estimates. The current and lagged impact of foreign aids is found to be important in explaining the economic growth of Ethiopia. Its current period impact was estimated to be positive and significant too as expected. Besides, the last year economic status of the country has also been suggested significant determinant of the current economic growth rate. Therefore, economic benefit of aids should be recognized and policy focus must be directed towards its efficient utilization. Keywords: , ARDL, Cointegration, Determinant Economic Growth, Ethiopia, Stationarity DOI : 10.7176/DCS/9-1-05

Fiscal Policy and Balance of Payments in Nigeria

The paper examined the impact of fiscal policy on balance of payments in Nigeria. The objectives of the study were to; examine the impact of government capital expenditure, corporate tax and external debt on BOPs. Time series data from 1980 to 2015 was collected from CBN statistical bulletin. The applied the techniques of ADF unit root test, co-integration and vector error correction model. The results of the estimated model showed that all the time series were stationary at order one. Also, the dynamic model depicted by the co-integration result showed that there is a long run equilibrium relationship among the variables. Similarly, the vector error correction result showed that the coefficient of ECM has the hypothesized negative sign and statistically significant at 5% level. The current year’s value of government capital expenditure showed that a percentage increase in government capital expenditure causes a favorable balance in BOPs by 65.5%. Moreover, the current year’s value of corporate tax showed that a percentage increase in corporate tax decreases the balance in BOPs by 164.4%. The estimated VECM result further showed that a percentage increase in government external debt causes an increase in BOPs by 77.1%. From the discussion so far, it is obvious that fiscal policy measures are effective in achieving a favorable balance of payments in Nigeria. Based on these findings, the following recommendations amongst others were made; Expansionary policies on fiscal policy measures especially in government capital spending and corporate tax policy should be encouraged as they play vital role in the growth of industrial production and help to improve the BOPs in Nigeria. Also, government should avoid superfluous and uncreative borrowing that will serve as a leakage to the economy.

Energy consumption and agricultural economic growth in Pakistan: is there a nexus?

PurposeThis study aims to empirically examine the relationship between energy consumption and agricultural economic growth in Pakistan over the period from 1984 to 2016.Design/methodology/approachThis study used the autoregressive distributed lag (ARDL) bounds testing approach to cointegration to investigate the long-run and short-run determinants of agricultural economic growth in Pakistan.FindingsThe results of the ARDL bounds testing approach to cointegration revealed that long-run linkage exists among the study variables. The findings of this paper showed that agricultural economic growth is positively affected by gas consumption and electricity consumption both in the long-run and short run. The long-run and short-run coefficients of gas consumption and electricity consumption were estimated to be 0.906, 0.421, 0.595 and 0.276, respectively. The estimated equation remains stable during the period from 1984 to 2016 as analyzed by the stability tests.Originality/valueThis study considers the relationship between energy consumption and agricultural economic growth in Pakistan by using an ARDL bounds testing approach to cointegration. The study has three contributions to economic literature:this study used different unit root tests to test stationarity of the variables such as ADF unit root test by Dicky and Fuller and P-P unit root test by Philip and Perron; the ARDL bounds testing approach to cointegration is applied to test the existence of long-run analysis between energy consumption and agricultural economic growth; and to check the robustness, the authors used the Johansen cointegration test to examine the long-run relationship between dependent and independent variables.

Oil Price Volatility, Exchange Rate Movements and Stock Market Reaction: The Nigerian Experience (1985-2017)

Given the observed volatility in crude oil prices in the international oil market and the role which oil and gas play in the Nigerian economy, this paper is an attempt to investigate the impact of crude oil prices and foreign exchange rate movements on stock market prices in Nigeria. In addition, the paper examined whether there is any volatility pass-through between the dollar price of Nigerian crude oil, foreign exchange rate of the Naira and stock market prices respectively. Data employed for the study are monthly values of the Nigerian Stock Exchange (NSE) All-Share Index (ASI), Dollar price of Nigerian Crude Oil (DPO) and the Official Exchange Rate of the Naira to the US Dollar (FXR) from January, 1985 to August, 2017. The methodology adopted for the study include the ADF unit root tests, Johansen co-integration tests, the ECM technique, Granger causality tests, variance decomposition as well as the GARCH(1,1) to model the volatility relationships among the variables. Findings reveal that there is one long-run dynamic co-integrating relationship among the variables ASI, DPO and FXR while the ECM results indicate that Crude oil price (DPO) significantly impact on Stock market prices. The Granger causality test reports a bi-directional causality relationship between ASI and DPO and a unidirectional causality running from FXR to ASI. The ARCH-GARCH volatility analysis demonstrates vividly that stock market prices in the NSE exhibit ARCH effect with a significant and positive first order ARCH term. The GARCH term is also positive and significant indicating that previous month’s stock market price volatility significantly influences current stock market volatility in the NSE. In addition, findings show that the volatility of dollar price of Nigerian oil (DPO) in the world oil market is significantly transmitted to the volatility of stock market prices in Nigeria. The pass-through effect of the volatility of exchange rate (FXR) to the volatility of stock market prices is also positive and significant. These findings offer significant informational signal to policy makers, portfolio managers/advisors and the investing public in achieving optimal asset and portfolio profile.

Türkiye de İktisat Politikasında Kurumsal Değişim ve Politika Koordinasyonu

Aim of this study is to investigate instiutional change of economic policies and to examine whether policies are well coordinated or not for the 1980-2016 period of Turkey. The coordination between economic policies may succeed in through trust, coordination and complementarity between institutions. Turkish economy transformed planned economy to free market system and institutional structure has changed dramatically in that period. Moreover in that period Turkey had exposed to several structural changes and economic crises too. The analysis can be significant when the suitable methods are used for these datas. This is the main reason why non linearity is tested by Harvey, Leybourne and Xiao (2008) and results supports that series are nonlinear. Fourier ADF unit root test is used nonlinear variables and Kapetanios, Shin and Snell (2003) cointegration test is applied for to analyze long run relations between variables. The empirical findings support that there is no relationship between monetary and fiscal policy variables. Secondly, Arby and Hanif (2010) methodology is used for calculating a coordination coefficient for Turkey. The low coordination coefficient supports that coordination institutions has not worked efficiently.

Further evidence on the validity of purchasing power parity in selected African countries

This article extended previous studies on testing the validity of purchasing power parity (PPP) in 16 African countries between 1970 M01 and 2017 M01. We employed these approaches: first, we investigated for the presence of unit roots in the real exchange rates (RERs) using the nonlinear ADF unit root test and the modified Wald-type test under an exponential smooth threshold autoregressive (ESTAR) framework; second, we used the detrended fluctuation analysis (DFA) to find out if RERs were mean- reverting by analyzing Hurst estimates of the RERs in absolute form and in a rolling window form. Finally, we used a nonlinear cointegration rank and score test to investigate if nominal exchange rates and relative prices are cointegrated. Our findings showed that RERs of each of the 16 countries in absolute form had unit roots and were not mean reverting. Also, nominal exchange rates and relative prices were not cointegrated. These findings indicate strong evidence against PPP theory in these countries. We, therefore, cannot use PPP as a basis for determining equilibrium exchange rates for these 16 countries. However, a time-varying DFA method on RERs provided mixed conclusions about the validity of PPP in these countries.

Structural Breaks and Energy Consumption in the Gulf Cooperation Council Countries: Are Random Shocks Transitory or Permanent?

The impact of random shocks on the energy consumption of the Gulf Cooperation Council countries is essentially an empirical question which cannot be determined a priori without properly testing the integration properties of this variable. To this aim, we perform testing the unit root properties of this variable using both traditional unit root tests and the recently developed technique of the Fourier transformation function or simply known as the FADF test developed by Enders and Lee (2012), which not only takes into account for the existence of structural breaks but also that of non‐linearity in the energy consumption series of these countries. The results from the traditional unit root tests fail to reject the null hypothesis of non‐stationarity while that of the Fourier ADF unit root test which is more powerful has strongly rejected the null hypothesis of unit root for all the countries except Bahrain and Qatar. In sum, the results from this test indicate that the energy consumption variables of these countries are characterised by a stationary process and this has important policy implications. This suggests that these random shocks will have only a transitory effect on the energy consumption per capita of these countries.

Determinants of exchange rate volatility: empirical evidence for Turkey

Purpose- In the literature the effect of exchange rate volatility on various macroeconomic variables has been extensively studied but there are not enough studies about the reasons of exchange rate volatility. The aim of the research is to present the theoretical framework about the determinants of exchange rate volatility and to determine the factors affecting exchange rate volatility in Turkey for a period from 1974 to 2016. Methodology- In this research the stationary analysis of the series is determined by the Augmented Dickey Fuller Test (ADF) and the PP (Phillips-Perron test) unit root tests. In addition the GARCH model is used to calculate the real effective exchange rate volatility. The Johansen cointegration test is used to determine whether there is a long-term relationship between variables. The coefficients of the long-run relationship between the variables are estimated by the FMOLS method. Findings- The ADF and PP unit root test results show that the series are stationary at first difference. According to Johansen cointegration test results, it has been found that there is a long-run relationship between the variables involved in the analysis. Results from the FMOLS method for determining the direction and severity of the long-term relationship between the variables reveal that LGFCF, LMONEY and LTRADE positively affects significantly, while LFDI, LGDPC, LGGEXP negatively affects real effective exchange rate volatility. Conclusion- The rise in domestic investment (LGFCF), money supply (LMONEY) and trade openness (LTRADE) increases the real effective exchange rate volatility, while the rise in foreign direct investment (LFDI), output (LGDPC) and government expenditures (LGGEXP) also reduces the real effective exchange rate volatility.

Contributions of the Productive Sectors’ to the Nigeria Economic Performance

The study empirically examined the contributions of the productive sectors’ to the Nigeria economic performance from 1981 to 2016. The study gathered time-series data majorly from the Central Bank of Nigeria Statistical Bulletin. The model in the study specified total gross domestic product of Nigeria as a function of the contributions of the manufacturing, agricultural, oil and gas, building, transport and trading sectors in the Nigerian economy. Employing the classical Ordinary Least Square estimates, ADF unit root test, Johansen Co-integration estimation techniques and Error Correction Modelling to analyse the data obtained. Based on the parsimonious error correction result, the study empirically explored that the ECM is correctly signed and significant and all the explanatory variables were positively and significantly related to the total GDP a proxy of economic performance in Nigeria. The study concluded that the productive sectors in Nigeria exert positive and significant influence on the Nigerian economy for the period under investigation. The study recommended, inter alia, that the government and all other stakeholders should channel huge economic resources into investing more in the productive sectors, so that these sectors will bring about the desired level of economic growth in Nigeria, as witnessed in the European world.

Economic Analysis of Rubber Production in Malaysia Using Ardl Model

The study applies the Autoregressive Distributed Lag (ARDL) Model approach to cointegration analysis and Error Correction Model (ECM) to examine the relationships between the explanatory variables with rubber production in Malaysia and to determine factors influencing the rubber production in Malaysia. The cumulative sum of recursive residuals (CUSUM) were used to test for structural stability of the model. The findings of the study illustrate that the ADF unit root tests indicate that the independent variables at first difference are stationary. The results of estimated long run coefficients using the ARDL Approach for the Rubber Export and Area planted are positively significant. ARDL bounds tests suggest that the independent variable series are co-integrated. The ECM also reveals that the independent variables have significant causative implications for rubber production and able to readjust 56.12% to long-run equilibrium.

Government Expenditure and Poverty Reduction in Nigeria

<p><em>This research investigates the relevance of government expenditure on poverty reduction in Nigeria. The main objective is thus to investigate whether the poverty reduction efforts through government spending has actually translated into a reduction in the poverty level. The study covered the period between 1980 and 2016. The ECM model and cointegration models of the OLS as well as the granger causality techniques were used to analyze the data. The result of the ADF unit root test indicates that all the variables are I(1). The result of the Johansen cointegration indicates the existence of a long run equilibrium relationship among the variables. The result of the parsimonious ECM indicates that though the one period lag government expenditure on health has a significant and positive impact on the per capita income, it has a low elasticity. The result indicates further that government expenditure on education has a significant and positive impact on the per capita income. The result indicates further that government expenditure on building and construction has a significant and positive impact on the per capita income, the elasticity is however very low. The granger causality test result indicates no causality between government expenditure on health and education. A bicausal relationship however exists between government expenditure on education and per capita income. The result shows no causality between government expenditure on building and construction and the per capita income. The result recommends amongst others an increment and proper monitoring of government spending which could be enhanced through public private partnership.</em></p>

BİST Endeksleri ile Kurumsal Yönetim Endeksi Arasındaki Volatilite İlişkisinin İncelenmesi - Investigation of Volatility Relation Between BIST Indexes and Corporate Governance Index

This study tests the volatility spread and long-term relationship between Borsa Istanbul indexes and Corporate Governance Index (XKURY). The long-run relationship between the indexes is analyzed by the Johansen Cointegration test and the stationarity of time series is investigated by ADF and PP unit root tests. According to the study results, the index with the highest return is XKURY and the index with the highest volatility is BIST 30. The cointegration relations between XKURY, BIST100, BIST50 and BIST30 indexes are separately estimated. According to the estimation results, the variables with the highest speed of adjustment (cointegration) are XKURY and BIST50. According to the results of Granger Causality, XKURY is not the Granger cause of BIST100 but BIST100 is the Granger cause of XKURY. Among other variables, there is a two-way causality. Firms included in the corporate governance index have relatively higher return and lower volatility.

A Quarter Century of Inflation Targeting & Exchange Rate Pass-Through: Evidence from the First Three Movers

This study has analysed the implications of Inflation Targeting for the Exchange Rate Pass-Through (ERPT) to inflation and trade balance. In this endeavour, we have focused on the first three movers i.e. New Zealand, UK and Canada. Drawing on the monthly data from October 1976 to September 2017, we employed a Time-Varying Structural Vector Auto-regressive framework in which the sources of time variation were both the coefficients and variance-covariance matrix of the innovations. Our key findings suggest that there is significant evidence of time-variation in the ERPT to inflation and trade balance in all three countries. In specific to inflation, the results showed that contrary to the notion that the ERPT to inflation has decreased in the Inflation Targeting economies, in fact, there is strong evidence that if there is anything, it is the other way around. The results using the ADF unit root test with a structural break (with innovation and additive outliers) suggested that the coefficients for inflation showed a decrease in oscillations which corresponded with the start of inflation targeting. However, this coincident cannot lead to infer that the ERPT has lost its significance. There is also a considerable amount of heterogeneity in the ERPT in the under-analysis countries. Specifically, in response to the positive Real Effective Exchange Rate (REER) shock, the inflation fell in the UK and New Zealand whereas, in Canada, it had the opposite effect. On the ERPT to the Trade Balance, the results on the UK showed a clear evidence of J-curve whereas in Canada, the impact was rather instantaneous and the trade balance quickly deteriorated. In New Zealand, the trade balance also showed deterioration in response to the REER shocks, although comparatively there was milder response than Canada and UK. Our findings have profound implications for monetary policy formulation under inflation targeting regimes and the influence of EPRT on price stability and external balance.

Jevons Paradox:An Econometric Analysis on Energy Efficiency and Rebound Effect

In this study, the effects of energy efficiency, rebound effect, on energy production, consumption, saving, import as well as inflation and current account deficit are examined using time series analysis in the period of 1967-2015 in Turkish economy. Firstly, in order to determine the stationary level of the variables ADF and PP unit root tests are used and the results show that all of the variables considered within the model are stationary at the first difference level. Second, the finding of Johansen-Juselius cointegration analyze reveals the existence of long-run relationships among variables, and Granger causality analysis reflects at least the validity of one-way causal links among variables. The findings of the VEC analysis point out that the Jevons Paradox or rebound effect is valid in the Turkish economy, which means that energy consumption rises as energy efficiency and production increases. In addition, the findings show that depending on increasing energy consumption energy import level rises and therefore current account deficit and inflation begin to deteriorate, also.

Role of Industrialization on Economic Growth: The Experience of Senegal (1960-2017)

The aim of this study is to contribute to the investigation of the impact of industrialization on economic growth by analyzing the Senegalese manufacturing firms. The paper utilized the secondary data drawn from the World Bank (WDI 2015) and the National Agency of Statistic and Demography in Senegal (ANSD) and covered the period between 1960 and 2017. It will employ the Ordinary Least Square (OLS) techniques in estimating the relationship between industrial output, inflation rate, FDI, Foreign Exchange Rate and economic growth, after which ADF unit root test was conducted using Breusch-Godfrey serial correlation LM test and Breusch-Pagan-Godfrey heteroskedasticity test. The econometric analysis has shown that the increase of industrial output will increase economic growth in Senegal. Therefore, there is significant relationship between industrial development and Senegalese economy growth. However, the result revealed that industrialization will go a long way in stimulating economic growth. Based on these results, we have recommended some policy measures in order to boost industrial output by improving the overall productivity of all the sectors and ensure sustainable development.

The Impact of Exchange Rate Dynamics on Agricultural Output Performance in Nigeria

The study investigated the possible asymmetric effect of real exchange rate dynamics on agricultural output performance in Nigeria over the period of 1981 to 2016 by collecting data from secondary sources. The study employed a combination of stationary and nonstationary variables as was found out through the ADF unit root test. Based on the Bounds test for cointegration, a long-run relationship was absent between real exchange rate and agricultural output, irrespective of specifications. Generally, the result of model estimation showed that the significant drivers of agricultural output are real exchange rate (log-levels), real appreciation and depreciation (after some lags), industrial capacity utilization rate, and government expenditure on agriculture (after some lags). ACGSF loan exerted positive and insignificant influence on agricultural output. In addition, though the effect of real appreciation was larger than that of real depreciation, the present study could not find any evidence in support of the asymmetric effect of real exchange rate dynamics on agricultural output performance in the Nigerian economy. It is therefore suggested that fiscal and monetary authorities in Nigeria should work in unison at ensuring that the full potentials of the agricultural sector are harnessed for the growth and development of the country.

Prognostic Ability of Beta in Predicting Stock Returns in Asymmetrical Stock Market -Indian Context

Investors invest in shares by expecting the future prices to go up or down or to remain constant. The main aim of a potential investor will be to attain the highest return by considering the lowest risk. Predicting the future prices of a share can be found difficult and often impossible. Efforts have been made in developing models that will better help in predicting the future prices of shares. This paper looks at one such model, the Capital Asset Pricing Model (CAPM), and wants to test whether the beta calculated based on daily returns or monthly returns is more reliable in predicting the expected returns of a stock according to CAPM. The study considers six stocks divided as two low-cap stocks, two mid-cap stocks and two high-cap stocks from National Stock Exchange (NSE) and the prices of each stock have been considered for a period of 1 year. The data was mined from secondary sources, and the stationarity of the data has been validated by ADF Unit Root test and GARCH model. The results reveal that beta calculated using daily returns is more accurate in predicting the future prices of the share than beta calculated using monthly returns.

Financial fraud and the effect of insider abuse in Nigerian banking sector

The fundamental objective of this study is to scrutinize the effect of insider abuse in the Nigerian banking sector along with its rudimental causes. The Classical Linear Regression Model (CLRM) was adopted along with secondary data extracted from the Nigeria deposit insurance corporations (NDIC) annual account report 2000-2016. The Ordinary Least Square technique signifies the prime technique of analysis as recommended by the ADF unit root test result. The ADF unit test revealed dataset stationarity at first order difference I(1). The R2 explains that 76.32% of the variation in the dependent variable is explained by the principal regressors. Total cases of fraud and amount involved were established to have a positive link with the total expected loss while, staff involvement, and total expected loss established negative and non-significant link. The study established that fraud in relation to insider abuse is not peculiarly Nigerian. The results bare that insider abuse are breed where there is weak and faulty internal control, lack of job security and reward for excellence. Recommendations are that financial institutions must review their internal control system, along with staff salary, the quality of staffs recruited and the audit system of the bank

Econometric Analysis Of Budget Deficits Determinants: Example of Turkey (2006-2015)

The aim of this study is to reveal the effects of budget deficits in 2006-2015 on growth, inflation, employment, unemployment and foreign exchange deficits through econometric analyzes. In the study, the stability of the series is examined with the ADF unit root test and stagnation can be achieved in budget deficits, growth and inflation , but not in employment, unemployment and exchange rate. For this reason, budget deficits continue to be driven by growth and inflation. After stabilization, the Johansen cointegration test is used to investigate the cointegration relationship between budget deficits and growth and inflation. According to the results obtained, cointegration relation between budget deficits and growth and inflation was found. An error correction model (VECM) has been applied in order to find the causality relation due to the cointegration relation. According to the results of the amprical application; Long-term relationship between budget deficits and inflation was bi-directional, while budget deficits and growth were growing without one-way causality relation to budget deficits.