Error Correction Model Estimation Research Articles

REVISITING THE REAL WAGES–UNEMPLOYMENT RELATIONSHIP. NEW RESULTS FROM NON-LINEAR MODELS

We examine the long-run real wages–unemployment relationship for five OECD countries over the period 1960:1–2001:4. Given the theoretical possibility of non-linear equilibrium due to downward real wage rigidity we employ econometric tests that allow for the presence of non-linearities in the long-run equilibrium. We adopt the notion of ‘hidden co-integration’ suggested by Granger and Yoon. This methodology has several advantages with respect to other non-linear models. We find statistical evidence that, in general, there is a long-run positive relation between real wages and unemployment only when both are affected by positive shocks. We also find a negative relationship between unemployment and productivity. The empirical analysis is complemented with the estimation of error correction models for all countries.

Infrastructure and Agricultural Growth in Nigeria

The study considered infrastructure and agricultural growth in Nigeria using a time series data for over four decades and the Parsimonious Error Correction Model estimation technique. It was found that various performance indicators with respect to physical infrastructure used for the study have not been encouraging in Nigeria. The provision of infrastructure in Nigeria, particularly physical infrastructure is characterized by the predominance of public enterprises except for telecommunications sector in recent time. The empirical part of the study revealed different relative response rates of the different component of infrastructure used in the study to the growth of the agricultural sector in Nigeria. There was unidirectional causality between telecommunication facilities and agricultural production. The same result was found between labour and agricultural production. It was recommended that the sectoral specific effects of the various forms of infrastructure should be taken into consideration when designing policy for promoting agricultural growth in Nigeria. Key Words: Infrastructure, Growth of Agriculture and VAR

The dynamic relationship between the US GDP, imports and domestic production of crude oil

This article investigates the dynamic relationship between crude oil imports, gross domestic product (GDP) and domestic crude oil production of the United States using a Vector Error Correction model estimation, generalized impulse response functions, persistence profile and variance decompositions. This article results suggest that the GDP has a leading role in determining oil imports.

Male and Female Labour Force Participation: The Role of Dynamic Adjustments to Changes in Labour Demand, Government Policies and Autonomous Trends

This study investigates the extent and speed of dynamic adjustment of labour supply to changes in labour demand, government policies and autonomous trends. We estimate error-correction models (ECMs) for male and female participation rates in the Netherlands between 1969 and 2004. The results show significant short and long-run effects of labour demand as well as a negative autonomous trend for male participation. In contrast, we find no significant long-run labour-demand effects and a very strong positive autonomous trend for female participation. Including female and male participation as additional explanatory variables in the male and female ECMs, respectively, reveals significant substitution effects between female and male participation. For male participation the substitution effects from female participation account for the negative trend in the basic ECM, while for female participation the substitution effects from male participation counterbalance labour demand effects that are now significant. In addition, we find very significant breakpoints in male and female participation at 1994, which indicate the effects of exogenous participation-promoting policies by the Dutch governments after 1994. The adjustments of the participation rates to changes in labour demand, government policies and autonomous trends are moderately fast.

Endogenous structural breaks, public investment in agriculture and agricultural land productivity in Taiwan

Using time-series data for Taiwan's agricultural sector and with the government's public investment in the agricultural sector serving as a proxy variable for nonfarm current inputs aside from the original labour and capital input variables usually taken into consideration, this article examines the relationship between public investment in agriculture (public investment/land) and agricultural land productivity (output/land) in Taiwan. Our main findings are as follows. First, the cointegration test reveals that public investment in agriculture and the productivity of agricultural land exhibit a significant positive relationship in the long run, where the elasticity of land productivity in relation to public investment in agriculture is 0.55. Second, when controlling for endogenous structural breaks, the long-run equilibrium relationship for the productivity of the agricultural land model is still supported. Third, the results of the weak exogeneity test indicate that a causal relationship exists in the long run between public investment in agriculture and the productivity of land, indicating that the growth of the agricultural sector must in the long run be based on the government's public investment in the agricultural sector. Furthermore, as the agricultural sector grows, this growth is able to stimulate public investment on the part of the government in the agricultural sector, so that the two affect each other. Fourth, from the short-run error correction model estimation, it is found that public investment in agriculture is a major means of adjusting for the disequilibria that occur within the system. Fifth, in the short run, the unidirectional causal relationship in terms of the productivity of agricultural land on public investment in agriculture is established, otherwise it is not established. From this it can be seen that in the short run, the government is unable to reveal the effectiveness of its public investment in agriculture.

Bayesian Estimation and Selection of Nonlinear Vector Error Correction Models: The Case of the Sugar‐Ethanol‐Oil Nexus in Brazil

AbstractNonlinear adjustment toward long‐run price equilibrium relationships in the sugar‐ethanol‐oil nexus in Brazil is examined. We develop generalized bivariate error correction models that allow for cointegration between sugar, ethanol, and oil prices, where dynamic adjustments are potentially nonlinear functions of the disequilibrium errors. A range of models are estimated using Bayesian Monte Carlo Markov Chain algorithms and compared using Bayesian model selection methods. The results suggest that the long‐run drivers of Brazilian sugar prices are oil prices and that there are nonlinearities in the adjustment processes of sugar and ethanol prices to oil price but linear adjustment between ethanol and sugar prices.

Regional productivity and relative prices dynamics: the case of Italy

In this paper, we study the cointegrating space spanned by Italian regional relative prices and per capita GDPs. To this end, we combine panel data with vector error correction model estimation in an innovative approach which is still under development. The results are interesting: regional prices, which seem to persistently deviate from the law of one price (PPP), cointegrate with relative per capita GDPs. The estimated elasticity is not consistent with the Balassa–Samuelson hypothesis but is closer to supporting the classical supply-demand schedule. Weak-causality testing gives further details on linkages between the real and nominal side of Italy’s regionally diversified economy. Homogeneity of the coefficients, lacking at a national level, can be recovered at a more disaggregated macro-area level.

An Empirical Study of Economic Growth and Expanding Role of Government in Ghana: 1965–2004

Wagner's law is tested by using traditional versions and our own versions which account for prices. Results show that Wagner's law exists in Ghana. However, there is no empirical support for the view that increases in government expenditures lead to economic growth. Both traditional Granger causality and autoregressive distributed lag estimates of long-run and error correction models show that economic growth Granger-causes changes in government expenditures, not vice versa. This suggests that while the government might facilitate economic growth in Ghana, it cannot serve as an engine of economic growth.

The role of trades in price convergence: A study of dual-listed Canadian stocks

Abstract We examine the role of trades in restoring price parity for equities trading in multiple markets. Using a sample of stocks trading on the Toronto Stock Exchange and on the NYSE, AMEX or NASDAQ, we contrast price convergence when market makers (a) observe only lagged quotes from both markets and (b) also observe local order flow. Traditional error correction model estimates show that prices in the two markets adjust towards parity in response to quoted price discrepancies, meaning that observation of the cross-market quote helps restore parity. Including order flow in an augmented error correction model, we find that incremental price convergence occurs when trades are routed to the market with the better price, and the importance of quotes in the price convergence process is reduced. Cross-sectional analysis reveals that the importance of order flow in each market is decreasing in firm size and increasing in measures of liquidity. Our findings point to an important, and hitherto unexamined, role for trades in promoting inter-market price convergence.

THE LONG‐RUN RELATIONSHIP BETWEEN DEFENCE EXPENDITURES AND GDP IN TAIWAN

Using the Solow–Swan growth model and the time‐trend included in the aggregate production function, this study applies the multivariate cointegration approach to re‐investigate the long‐run and causal relationships between defence expenditures and GDP while controlling for capital and labour input in Taiwan during the 1955–2002 period. It examines the long‐run causal relationship using the weak exogeneity test and utilizes general impulse response functions to determine whether a shock to defence expenditures affects economic growth or vice versa. Our findings provide substantive evidence in favour of the existence of a long‐run equilibrium cointegrated relationship between defence expenditures, GDP, labour and capital stock. The results of the weak exogeneity test indicate that a bi‐directional causal relationship exists in the long‐run between defence expenditures and GDP. Thus, the main policy implication that emerges from the long‐run results is that increasing defence expenditures in Taiwan is an effective means to boost overall economic performance and, with this improved economy, it should then be able to increase its defence expenditures further. Lastly, from our dynamic vector error correction model estimations, it is found that defence expenditures are a major means of adjusting for disequilibria that occur within the system.

Is foreign direct investment beneficial for Mexico? An empirical analysis, 1960–2001

Summary This paper examines the impact of foreign direct investment (FDI) on labor productivity growth in Mexico. Using cointegration analysis, a dynamic labor productivity function for the 1960–2001 period is estimated that includes, inter alia, the impact of changes in the stock of private and foreign capital per worker. The error correction model (ECM) estimates suggest that increases in both private (lagged) and foreign (lagged) investment per worker have a positive and economically significant effect on the rate of labor productivity growth. However, after taking into account the growing remittances of profits and dividends, there is a marked decrease in the economic effect of foreign capital per worker on the rate of labor productivity growth. The paper assesses the short-term interactions of the relevant variables via impulse response functions (IRFs) and variance decompositions (VDCs) based on a decomposition process that does not depend on the ordering of the variables.

The Role of Seasonality and Monetary Policy in Inflation Forecasting

Adequate modeling of the seasonal structure of consumer prices is essential for inflation forecasting. This paper suggests a new econometric approach for jointly determining inflation forecasts and monetary policy stances, particularly where seasonal fluctuations of economic activity and prices are pronounced. In an application of the framework, the paper characterizes and investigates the stability of the seasonal pattern of consumer prices in the Kyrgyz Republic and estimates optimal money growth and implied exchange rate paths along with a jointly determined inflation forecast. The approach uses two broad specifications of an augmented error-correction model-with and without seasonal components. Findings from the paper confirm empirical superiority (in terms of information content and contributions to policymaking) of augmented error-correction models of inflation over single-equation, Box-Jenkins-type general autoregressive seasonal models. Simulations of the estimated errorcorrection models yield optimal monetary policy paths for achieving inflation targets and demonstrate the empirical significance of seasonality and monetary policy in inflation forecasting.

An alternative approach to estimation of structural vector error correction models with long-run restrictions

This paper presents an alternative approach to two-step maximum likelihood estimation of structural vector error correction models that are partially identified with long-run restrictions. We generalize the existing literature by allowing for over-identifying restrictions.

An examination of regional interaction and super‐regions in Britain: An error correction model approach

Gray D. (2005) An examination of regional interaction and super‐regions in Britain: an error correction model approach, Regional Studies 39 , 619–632. This paper examines spill‐over effects among regions. Estimating error correction models of British rates of unemployment and conducting Granger‐causality tests, it is found that, on a short‐run basis, the West Midlands is a leading territory within a closely knit group of surrounding regions. The paper draws a distinction between a core and a leading region, suggesting the core region, the South East, is a follower, responding to, and magnifying, economic fluctuations. The policy implications are that current regional delineations may not be consistent with the demands of economic coherence at the national level and so is not optimal for the delivery of decentralized spatial economic policy. Indeed, as economic engineering in the high unemployment periphery has consequences for more prosperous areas, it may be better not to allow local administrators too much autonomy as the benefits of a better economic focus may be out‐weighed by destabilizing tendencies that decentralization may impose on the whole system. This problem has consequences for, and may be compounded by, policy initiatives at the European level.

The Impact of Education Expenditures on Economic Growth In Uganda: Evidence From Time Series Data

Does education promote economic growth? Empirical evidence is not conclusive on this question. This paper uses time-series technique to investigate the relationship between government education expenditure per worker and economic growth in Uganda during the period 1965-1999. The empirical results show that education expenditure per worker has a positive and significant impact on economic growth both in the long run and short run. The estimates of error correction model suggest that a 1% increase in average education expenditure per worker will lead to about 0.04% increase in output in the short run. The cointegration estimates show that a 1% increase in average education expenditure per worker will increase output by about 0.6% in the long run.

Government Revenues and Expenditures in Guinea-Bissau: Causality and Cointegration

The paper establishes empirically the temporal causality and long run relationship between government expenditures and government revenues for the case of Guinea-Bissau - a low income country under stress (LICUS) in Africa. A simple macroeconomic model is developed to lay out the hypothesis of a spend-tax behavior in the country's public finances management system. Empirical validation is carried out by means of a traditional Granger-causality test and the estimation of a simple error correction model between expenditures and revenues.

A cointegration approach to the lead–lag effect among size-sorted equity portfolios

We develop a framework which illustrates that lagged information transmission may entail cointegration between the current price of small-firm portfolios and the lagged price of large-firm portfolios. We test for cointegration using data which comprises three sets of monthly prices of equity portfolios for the period 1955–2000. The first two sets contain monthly prices of size-sorted portfolios of different capitalisation size, and the third contains portfolios of the same size. We find evidence of cointegration for both sets of different capitalisation size portfolios and no evidence of cointegration for equal-size portfolios. Large-firm portfolio prices are long-run forcing variables for small-firm portfolio prices, suggesting that capitalisation size is a driving force of the lead–lag effect in the long run. For the two sets of different-size portfolios, we estimate error correction models (ECMs) using the auroregressive distributed lag (ARDL) approach, and obtained out-of-sample forecasts of small-firm portfolios returns. These ECMs are found to have superior forecasting performance relative to models without the error correction term, further highlighting the relevance of cointegration between the lagged price of large-firm portfolios and the current price small-firm portfolios.

A cointegration approach to the lead?lag effect among size-sorted equity portfolios

We develop a framework which illustrates that lagged information transmission may entail cointegration between the current price of small-firm portfolios and the lagged price of large-firm portfolios. We test for cointegration using data which comprises three sets of monthly prices of equity portfolios for the period 1955–2000. The first two sets contain monthly prices of size-sorted portfolios of different capitalisation size, and the third contains portfolios of the same size. We find evidence of cointegration for both sets of different capitalisation size portfolios and no evidence of cointegration for equal-size portfolios. Large-firm portfolio prices are long-run forcing variables for small-firm portfolio prices, suggesting that capitalisation size is a driving force of the lead–lag effect in the long run. For the two sets of different-size portfolios, we estimate error correction models (ECMs) using the auroregressive distributed lag (ARDL) approach, and obtained out-of-sample forecasts of small-firm portfolios returns. These ECMs are found to have superior forecasting performance relative to models without the error correction term, further highlighting the relevance of cointegration between the lagged price of large-firm portfolios and the current price small-firm portfolios.

Estimating residential demand for electricity in Greece

This paper examines the residential demand for electricity in Greece. The issues of structural stability, price and income sensitivity of both long- and short-run residential demand for electricity in Greece were examined employing monthly data over the period 1986–1999. The long-run residential demand for electricity is estimated taking into account changes in weather conditions weighted by the size of the population employing multivariate framework analysis. A long-run residential demand function for electricity, sensitive to real income, price level and weather conditions, is found to exist and the importance of short-run deviations is presented using vector error-correction model (VECM) estimation. The empirical evidence suggests the presence of a stable residential demand for electricity in Greece both in the long- and short-run periods and the policy implications of such a relationship are presented.

Housing Prices, Mortgage Payments and Savings Behavior in Taiwan: A Time Series Analysis

After reaching its peak at the year of 1987, the saving rate of Taiwan dropped quickly in the late 1980s. At the same time, the real average housing prices in Taiwan had increased almost three times from 1987 to 1990. Why did the savings rate in Taiwan drop so quickly after 1987? Does it relate to the dramatic increase in housing prices? Although it has been confirmed that there is a negative wealth effect of housing price appreciation on savings, the estimated wealth effect on savings could be biased if the effect of mortgage payment (also known as forced savings) on saving is neglected. Applying quarterly data from 1981 to 2000 in Taiwan, we employ a time series analysis to compare two saving models, the traditional one and the one with forced saving. As we expected, the negative wealth effect of housing price appreciation on saving is smaller in the forced saving model than in the traditional saving model. By the estimated error correction models (ECMs), ignoring the impact of housing price appreciation on forced saving, the speed of short‐run adjustment in total saving would be significantly slower. For forecasting purposes, the forecast errors in ECM of the forced saving model are smaller than that in the total savings model.