Spurious Regression

Ventosa‐Santaulària, Daniel

doi:10.1155/2009/802975

Cited by 37 publications

(19 citation statements)

References 148 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variables such as GDP and prices (as well as bank loans) are intrinsically nonstationary in growing and inflationary economies such as Turkey. Hence, one needs differencing (or to use growth rates) to induce stationarity and so avoid the spurious regression phenomenon which can occur when the dependent variable is nonstationary and the regressors are either stationary or nonstationary -see, for examples, Stewart (2006) and Ventosa-Santaularia (2009). 24 Whilst there may be cross-sectional heterogeneity in the log-levels of bank loans there does not appear to be significant heterogeneity across banks for the differenced log-levels of bank loans.…”

Section: However It Is Important To Notice That the F-test For The Ementioning

confidence: 99%

Monetary policy and the banking sector in Turkey

Akinci¹,

Matoušek²,

Radic³

et al. 2013

Journal of International Financial Markets, Institutions and Mo

View full text Add to dashboard Cite

We find evidence that monetary policy influenced bank lending in Turkey in the period 1991 -2007 both directly through the money lending channel and indirectly through the bank lending channel. The bank lending channel is shown to depend on two bank characteristics, namely liquidity and capital. We also find that both capital and GDP growth have plausible positive and significant long-run effects on bank loan growth, whereas inflation, bank size and, in particular, efficiency do not have a significant equilibrium relationship with loan growth. This latter result is despite our finding that the efficiency of all Turkish banks improved over the period. It is also evident that domestic banks are, unexpectedly, found to be more efficient, on average, than foreign banks. We discovered no evidence of significant dynamics or fixed-effects in the growth of loans and so prefer to use the pooled OLS estimator over the fixed-effects and Arellano and Bond estimators. We therefore caution against assuming the existence of fixed-effects and dynamics in such models as this may adversely affect inference.

show abstract

Section: However It Is Important To Notice That the F-test For The Ementioning

confidence: 99%

Monetary policy and the banking sector in Turkey

Akinci¹,

Matoušek²,

Radic³

et al. 2013

Journal of International Financial Markets, Institutions and Mo

View full text Add to dashboard Cite

show abstract

“…We will investigate the asymptotic behaviors of the least squares estimators and various statistics defined from our model (4). More precisely, we derive the asymptotic for the OLS estimators for regression coefficient and the t-statistics.…”

Section: Resultsmentioning

confidence: 99%

“…The general null hypothesis on β is routinely formulated as H 0 : β = 0, and tested against the alternative hypothesis H 1 : β 0. However, the nature of the structure mechanism in the dependent and explanatory variables is unknown a prior in model (4). This is mainly due to a lack of economic knowledge on structure mechanism.…”

Section: Resultsmentioning

confidence: 99%

“…For convenience, we denote Mean-Trend, Mean-Difference and Difference-Trend respectively representative of sequences generated by (u t , w t ), (u t , v t ) and (v t , w t ) in regression model (4). Table 1 summarizes the Tsay's (1999) and Jin et al's (2013) results and the above findings.…”

Section: Accepted Manuscriptmentioning

confidence: 94%

“…Our simulation studies is based on samples of size T = 500, 1000, 5000, 10000. For each simulated sample, we calculate the standard least squares estimators and construct the t-statistic in model (4). The percentage of rejections are obtained by 2000 replications at 5% nominal level, i.e., the percentage of t-statistic such that |tβ| > 1.96.…”

Section: Monte Carlo Simulationmentioning

confidence: 99%

See 2 more Smart Citations

Evidence of spurious regression driven by heavy-tailed observations with structural changes

Jin

Zhang

et al. 2016

Communications in Statistics - Simulation and Computation

View full text Add to dashboard Cite

This paper extends the theoretical analysis of spurious relationship and considers the situation where the deterministic components of the processes generating individual series are independent heavy-tailed with structural changes. It shows when those sequences are used in ordinary least squares regression, the convenient t-statistic procedures wrongly indicate that (i) the spurious significance is established when regressing mean-stationary and trend-stationary series with structural changes, (ii) the spurious relationship occurs under broken mean-stationary and difference-stationary sequences and (iii) the extent of spurious regression becomes stronger between difference-stationary and trend-stationary series in the presence of breaks. The spurious phenomenon is present regardless of the sample size and structural breaks taking place at the same points or not. Simulation experiments confirm our asymptotic results and reveal that the spurious effects are not only sensitive to the relative location of structural changes with the sample, but seriously depend on the stable indexes.

show abstract

Spurious Forecasts?

Martínez-Rivera

Ventosa‐Santaulària

Vera-Valdés

2011

Journal of Forecasting

View full text Add to dashboard Cite

Phillips (1998) demonstrated that deterministic trends are a valid representation of an otherwise stochastic trending mechanism; he remained skeptic, however, about the predictive power of such representations. In this paper we prove that forecasts built upon spurious regression may perform (asymptotically) as well as those issued from a correctly specified regression. We derive the order in probability of several in-sample and out-of-sample predictability criteria (F test, root mean square error, Theil's U-statistics and R 2 ) using forecasts based upon a least squares-estimated regression between independent variables generated by a variety of empirically relevant data-generating processes. It is demonstrated that, when the variables are mean stationary or trend stationary, the order in probability of these criteria is the same whether the regression is spurious or not. Simulation experiments confirm our asymptotic results.

show abstract

Spurious Regression

Cited by 37 publications

References 148 publications

Monetary policy and the banking sector in Turkey

Monetary policy and the banking sector in Turkey

Evidence of spurious regression driven by heavy-tailed observations with structural changes

Spurious Forecasts?

Contact Info

Product

Resources

About