Spurious Regression Research Articles

HOW IMPORTANT IS HUMAN CAPITAL FOR GROWTH IN REFORMING ECONOMIES? / ŽMOGIŠKOJO KAPITALO SVARBA PEREINAMOSIOS EKONOMIKOS AUGIMUI

The aim of the paper is to broaden the research on human capital providing new evidence that human capital matters for economic growth in reforming economies. We propose a new model for measuring human capital. An advantage of the proposed model consists in international comparability; money metric scale and more importantly provide solid evidence on human capital significance for economic growth. This new approach in measuring human capital proved robust to the spurious regression problem involving human capital. Study results shows that human capital is important for growth and that large educational investments are essential to boost accumulation. Santrauka Šio straipsnio tikslas – išplėsti mokslinius tyrimus apie žmogiškąjį kapitalą ir pateikti įrodymų, kad jis yra svarbus reformuojamos ekonomikos augimui. Siūloma nauja žmogiškojo kapitalo vertinimo metodologija, kurios pranašumai – tarptautinis lyginamumas, monetarinis vertinimas ir žmogiškojo kapitalo reikšmės ekonomikos augimui akcentavimas. Naujoji metodologija įrodė savo patikimumą vertinant žmogiškojo kapitalo kintamuosius. Empiriniai rezultatai rodo, kad žmogiškasis kapitalas yra svarbus augimui, ir tam reikia didelių investicijų švietimo srityje.

Unbalanced Regressions and Spurious Inference

Spurious regression has been extensively studied in time series econometrics since Granger and Newbold’s seminal paper. Recently, it has been advanced that this phenomenon is due to a mistreatment of short-range autocorrelation in the residuals of the regression when at least one of the variables in a bivariate regression is stationary. HAC errors, feasible GLS and Cochrane-Orcutt-type procedures are then proposed to draw correct inference. Such a proposal should be cautiously considered, since nonsense inference might also be due to deterministic trend mechanisms, structural breaks, and long range dependence. In these cases, standard autocorrelation correction procedures would not solve the problem of spurious regression. We aim to make the later argument clear.

Spurious Regressions and Near-Multicollinearity, with an Application to Aid, Policies and Growth

In multiple regressions, explanatory variables with simple correlation coefficients with the dependent variable below 0.1 in absolute value (such as aid with economic growth) may have very large and statistically significant estimated parameters which are unfortunately driven and spurious. This is obtained by including another regressor which is highly correlated with the initial regressor, such as a lag, a square or interaction terms of this regressor. The analysis is applied on the Botswana outliers driven Burnside and Dollar [2000] article which found that aid had an effect on growth only for countries achieving good macroeconomic policies.

A comment on ‘Is the spurious regression problem spurious?’

McCallum (2010) presented evidence that the spurious regression problem can be solved by standard means. We show using finite-sample evidence that the spurious regression problem cannot always be fixed using standard autocorrelation correction procedures and remains, therefore, a not-so-spurious problem.

Spurious Fixed Effects Regression*

AbstractThis article shows that spurious regression results can occur for a fixed effects model with weak time series variation in the regressor and/or strong time series variation in the regression errors when the first‐differenced and Within‐OLS estimators are used. Asymptotic properties of these estimators and the related t‐tests and model selection criteria are studied by sending the number of cross‐sectional observations to infinity. This article shows that the first‐differenced and Within‐OLS estimators diverge in probability, that the related t‐tests are inconsistent, that R2s converge to zero in probability and that AIC and BIC diverge to −∞ in probability. The results of the article warn that one should not jump to the use of fixed effects regressions without considering the degree of time series variations in the data.

Spurious regression and lurking variables

We present asymptotic and finite-sample arguments to study the spurious regression problem. This problem may be solved by introducing a lurking variable in the specification even if it is merely a proxy variable. Moreover, this approach is also valid if the lurking variable is a trending mechanism, as when the spurious regression is due to nonstationarities in the variables.

Spurious regressions driven by excessive volatility

This paper shows that the excessive volatility results in spurious regressions. The spuriousness can be driven by persistency in the error variances unlike the conventional spurious regressions that are generated by the persistency in the level of regression errors.

Augmented Dickey Fuller Test

Testing data for stationarity is very important in research where the underlying variables based on time. Moreover time series data analysis has many applications in many areas including studying the relationship between wages and house prices, profits and dividends, and consumption and GDP. An important econometric task is determining the most appropriate form of the trend in the data. Many economic and financial time series exhibit trending behavior or non-stationarity in the mean. Leading examples are asset prices, exchange rates and the levels of macroeconomic aggregates like real GDP. In the beginning of the decade 1970s there was a great debate about this topic. Granger and Newbold (1974) were the researchers, who give the idea that the macroeconomic data as a rule contained stochastic trends, and this data is characterized by unit root, they also suggest that using these variables in econometric models may lead towards spurious regressions. So testing for stationarity is very important because the whole results of the regression might be fabricated. In simple words we can say that trended series is called non-stationary and with unit root and on the other hand non-trended series is a stationary series characterized by without unit root.

The Feldstein-Horioka Puzzle Reconsidered for OECD Countries

This paper investigates the savings-investment relationship, also known as the Feldstein-Horioka puzzle, for a panel of 30 OECD countries over 1960-2006. It utilizes the recently-developed panel cointegration techniques to test and estimate the long-run equilibrium relationship between savings and investment. Investment and savings rates are found to have unit roots and to be cointegrated, based on 5 different panel unit root tests and 3 types of panel cointegration tests. The estimated coefficients on the savings rate employing CCR, DOLS, and FMOLS techniques, exhibit a declining trend over subsample periods. It suggests that international capital mobility in the OECD economies almost quadrupled over 1960-2006 and substantially increased in the 1990s and 2000s. Moreover, the magnitude of the estimated saving-retention coefficients is much smaller than those reported by Feldstein and Horioka, who did not consider the nonstationarity of data and the resulting spurious regression problem. We also find that 21 original OECD members had a much greater increasing trend in capital mobility than 9 developing new members over 1990-2006, presenting evidence against the scale effect of country size. The empirical findings in this paper provide strong evidence against the Feldstein-Horioka puzzle in OECD countries over 1960-2006.

An evaluation of Malaysian capital controls

PurposeThis research has been carried out to look into the long run impact of the controls on capital inflows imposed during the years 1998‐2001 in Malaysia. The paper intends to capture the long‐term impact of capital controls in changing the composition of capital flows into Malaysia and to examine whether the controls have been able to divert the short‐term capital inflows to longer‐term investments.Design/methodology/approachThe autoregressive first differenced ordinary least square models have been used to examine whether the controls have been able to divert the short‐term capital inflows to longer‐term investments.FindingsThe capital controls have been successful in the short run in switching some of the short‐term capital inflows into longer‐term portfolio investments, without jeopardizing the Malaysian investment environment in the longer‐term. Such controls did not have an impact on the decisions of foreign investors in the long run even if the rating agencies downgraded the Malaysian investments immediately after the controls were imposed. This paper suggests that capital flows into Malaysia were more a result of interest rate differentials between the domestic and the US interest rates and hardly depended on the Malaysian risk adjusted returns.Research limitations/implicationsOne of the limitations of this research is the ephemeral nature of the econometric analysis. All the variables, except government spending, are first differenced, in order to overcome the problem of spurious regression. However, while taking the first difference, there is a possibility of losing valuable long‐term relationship between the capital flows and the explanatory variables. Further, the analysis was carried out without much reference to the derivative market, which might have disguised some of the capital flows.Social implicationsCapital controls are adopted to prevent the volatility in domestic markets caused due to capital flight. The capital flight has huge macroeconomic implications on a society, including unemployment, interest rate volatility and subsequent economic slowdown and recession. If adopted with an intention to provide a temporary breathing space, it might help the countries manage their domestic imbalances.Originality/valueThis paper provides a fresh look at the implications of capital controls with longer‐term data that also include the period after the controls were withdrawn. The study is expected to be independent of market distortions, which might arise with narrow time frames that cover periods during and/or immediately after the crisis.

Spurious spatial regression and heteroscedasticity

A two-step Lagrange Multiplier test strategy has recently been suggested as a device to reveal spatial nonstationarity and spurious spatial regression. The present paper generalises this procedure by incorporating control for unobserved heteroscedasticity. Using Monte Carlo simulation, the behaviour of several relevant tests for nonstationarity and/or heteroscedasticity is investigated. The two-step Lagrange Multiplier test for spatial nonstationarity turns out to be robust towards heteroscedasticity. While several tests for heteroscedasticity prove inconclusive under certain circumstances, it is shown that a Lagrange Multiplier test for heteroscedasticity based on spatially differenced variables serves well as an indication of heteroscedasticity irrespective of stationarity status.

Challenges in constructing time series models from process data

Correlated input and output sequences of industrial processes are often autocorrelated. Analysts who wish to construct models for such processes from input and output sequences alone must be careful as the autocorrelations in individual time series can masquerade as cross-correlations. Several different models may appear equally plausible, depending on how the process had been operated. In this paper we study the input and output sequences from two industrial case studies using various time series tools. The results of our study illustrate that in feedback situations, where the current input is adjusted—either automatically or manually—on the basis of past output, different models may fit the data equally well. Which of these models describe the actual transfer function is unclear, unless a known dither signal can be added to the input to allow for an unambiguous identification of the transfer function. This problem is related to spurious regression and is of interest to econometricians who often deal with time series where feedback, known or unknown, may be responsible for misleading interpretations. Copyright © 2010 John Wiley & Sons, Ltd.

Spurious regression: A higher-order problem

This paper investigates solving the spurious regression problem using an autocorrelation correction. It is shown that if the relevant data generation processes contain higher-order terms, this solution is not as effective as in the first-order case.

An empirical investigation of spot prices in tanker market using dynamic multiple regression models

The aim of this paper is to investigate spot prices of tanker market following an extensive empirical analysis using dynamic multiple regressions models via autoregressive distributed lags (ADL). These models constitute the most widely used pattern for empirical analysis since they are more suitable to ceteris paribus analysis offering much more flexibility in the formation of general functional form relationships. Also, they can be used to build better predicting models in order to support policy makers’ decisions. This paper focuses in an extensive testing of stationarity and time trend issues in order to overcome the problem of spurious regression. The estimated models have been also used to generate ex-post and ex-ante forecasts in order to evaluate both econometric specification and predicting accuracy of dynamic multiple regression models. Results reveal that spot prices of each ship type market are affected by different sets of independent variables and the estimated models generate quite accurate predictions.

CLIOMETRICS AND TIME SERIES ECONOMETRICS: SOME THEORY AND APPLICATIONS

Abstract The paper discusses a range of modern time series methods that have become popular in the past 20 years and considers their usefulness for cliometrics research both in theory and via a range of applications. Issues such as, spurious regression, unit roots, cointegration, persistence, causality, structural time series methods, including time varying parameter models, are introduced as are the estimation and testing implications that they involve. Applications include a discussion of the timing and potential causes of the British Industrial Revolution, income ‘convergence’ and the long‐run behaviour of English real wages 1264–1913. Finally some new and potentially useful developments are discussed including the mildly explosive processes; graphical modelling and long memory.

Forecasting volatilities in equity, bond and money markets: A market-based approach

This study examines the forecasting power of the most popular volatility forecasting models in the S&P 500 index market, the Eurodollar futures market, and the 30-year US T-Bond futures market at a daily level using a market-based option-pricing error approach. Comparison has been made between two methods including and excluding implied volatility in option-pricing error approach in forecasting next-day volatilities. To remove any advantage to option-implied volatility, the analysis is performed in two steps. Spurious regression biases and biases in the measurement of volatility forecasts are controlled for.The evidence from this paper supports the use of implied volatility as a proxy for market volatility, as it works best in forecasting next-day realized volatility in all the three US markets. The appropriateness of including implied volatility in option-pricing error approach is also discussed.

Asymptotics for Panel Models with Common Shocks - Extended Version

This paper develops a novel asymptotic theory for panel models with common shocks. We assume that contemporaneous correlation can be generated by both the presence of common regressors among units and weak spatial dependence among the error terms. Several characteristics of the panel are considered: cross-sectional and time-series dimensions can either be fixed or large; factors can either be observable or unobservable; the factor model can describe either a cointegration relationship or a spurious regression, and we also consider the stationary case. We derive the rate of convergence and the limit distributions for the ordinary least squares (OLS) estimates of the model parameters under all the aforementioned cases.

Spurious spatial regression with equal weights

This note studies the Lee and Yu ( 2009) spurious regression model for the special case where the weight matrix is normalized and has equal elements, and where the nonstationarity is caused by near unit roots. It shows that spurious spatial regression will not occur in a spatially autoregressive (SAR) model when the spatial weight matrix is row-normalized and has equal weights. In fact, the asymptotic distribution of the OLS estimate will always converge to its true value zero. The only condition required is that the spatial coefficients of the dependent and independent variables be both less than 1, which is a requirement for the SAR model to be an equilibrium model.

International Capital Mobility: A Panel Analysis for OECD Countries

This paper investigates the savings-investment relationship, also known as the Feldstein-Horioka puzzle, for a panel of 30 OECD countries over 1960-2006. It utilizes the recently-developed panel cointegration techniques to test and estimate the long-run equilibrium relationship between savings and investment. Investment and savings rates are found to have unit roots and to be cointegrated, based on 5 different panel unit root tests and 3 types of panel cointegration tests. The estimated coefficients on the savings rate employing CCR, DOLS, and FMOLS techniques, exhibit a declining trend over subsample periods. Moreover, the magnitude of the estimated saving-retention coefficients is much smaller than those reported by Feldstein and Horioka (1980), who did not consider the nonstationarity of data and the resulting spurious regression problem. It suggests that international capital mobility in the OECD economies has almost quadrupled over 1960-2006 and substantially increased in the 1990s and 2000s. The empirical findings in this paper provide evidence against the Feldstein-Horioka puzzle in OECD countries over 1960-2006.

: OECD (International Capital Mobility: A Panel Analysis for OECD Countries)

Korean Abstract: 본고에서는 1960~2006년 기간 중 OECD 30개국의 패널 자료를 사용하여 Feldstein-Horioka puzzle로 알려진 저축-투자 상관관계를 조사한다. 본연구는 최근 개발된 패널 공적분 기법들을 활용하여 OECD 국가들의 국내 저축률 및 투자율간의 장기 균형관계 를 검정하고 추정한다. 저축률과 투자율 변수들은, 5 종의 패널 단위근 검정과 3 종의 패널 공적분 검정에 근거하여, 단위근이 존재하고 공적분되어 있다는 것이 발견된다. CCR, DOLS 및 FMOLS 기법들을 사용한 저축유지율 계수 추정치들은 표본기간 중 하 향 추세를 보여 왔음이 판명되었다. 본고에서 저축유지율 계수 추정치들의 크기는, 통계 자료의 비정상성과 그로 인한 가성회귀 문제를 고려하지 않은 Feldstein and Horioka (1980) 보다 훨씬 작게 나타났다. 본고의 실증 분석 결과는 OECD 회원국에서 국제 자 본이동성이 1960~2006년 기간 중 거의네 배가 되었고,특히 1990년대에 and 2000년대에 크게 증가하였음을 보여준다. 본고의 실증 분석 결과는 1960~2006년 기간 중 30개 OECD 국가들에서 Feldstein-Horioka puzzle과 반대되는 증거를 제시한다. English Abstract:This paper investigates the savings-investment relationship, also known as the Feldstein-Horioka puzzle, for a panel of 30 OECD countries over 1960-2006. It utilizes the recently-developed panel cointegration techniques to test and estimate the long-run equilibrium relationship between savings and investment. Investment and savings rates are found to have unit roots and to be cointegrated, based on 5 different panel unit root tests and 3 types of panel cointegration tests. The estimated coefficients on the savings rate employing CCR, DOLS, and FMOLS techniques, exhibit a declining trend over subsample periods. Moreover, the magnitude of the estimated saving-retention coefficients is much smaller than those reported by Feldstein and Horioka (1980), who did not consider the nonstationarity of data and the resulting spurious regression problem. It suggests that international capital mobility in the OECD economies has almost quadrupled over 1960-2006 and substantially increased in the 1990s and 2000s. The empirical findings in this paper provide evidence against the Feldstein-Horioka puzzle in OECD countries over 1960-2006.