Long-horizon regressions: theoretical results and applications

Valkanov, Rossen

doi:10.1016/s0304-405x(03)00065-5

Cited by 457 publications

(397 citation statements)

References 33 publications

Supporting

Mentioning

370

Contrasting

Unclassified

Order By: Relevance

“…Thus, inference based on the asymptotic normal p-values reported in Table VII is likely to be highly deceptive. Valkanov (2003) suggests another reason as to why inference based on the normal distribution is likely to be inappropriate when testing the unit slope hypothesis. He argues that the use of timeaggregated data, as is the case with compounded interest rate series, may alter the convergence rate of routinely computed t-ratios with massive size distortions as a result.…”

Section: The Full Fisher Effectmentioning

confidence: 99%

Panel cointegration tests of the Fisher effect

Westerlund

2007

J of Applied Econometrics

813

429

View full text Add to dashboard Cite

SUMMARYMost empirical evidence suggests that the Fisher effect, stating that inflation and nominal interest rates should cointegrate with a unit slope on inflation, does not hold, a finding at odds with many theoretical models. This paper argues that these results can be attributed in part to the low power of univariate tests, and that the use of panel data can generate more powerful tests. For this purpose, we propose two new panel cointegration tests that can be applied under very general conditions, and that are shown by simulation to be more powerful than other existing tests. These tests are applied to a panel of quarterly data covering 20 OECD countries between 1980 and 2004. The evidence suggest that the Fisher effect cannot be rejected once the panel evidence on cointegration has been taken into account.

show abstract

Section: The Full Fisher Effectmentioning

confidence: 99%

Panel cointegration tests of the Fisher effect

Westerlund

2007

J of Applied Econometrics

813

429

View full text Add to dashboard Cite

show abstract

“…The dependant variable can therefore suffer from serious autocorrelation. Valkanov (2003) finds that regressions using long horizon returns can have poor statistical power due to the autocorrelation inherent in the data. This is can be dealt with using the Newey-West (1987) heteroskedasticity and autocorrelation consistent (HAC) standard errors as in Evans and Lyons (2005) who examine exchange rate forecasting.…”

Section: Datamentioning

confidence: 99%

Rationality in precious metals forward markets: Evidence of behavioural deviations in the gold markets

Aggarwal

Lucey

O’Connor

2014

Journal of Multinational Financial Management

View full text Add to dashboard Cite

“…Another worrisome point is the summation of logarithmic one-period returns. Even though white noise in theory, Valkanov (2003) shows that concatenating logarithmic one-period stock returns leads to almost unit root processes in the long-run and hence spurious regression results. Valkanov suggests an adjustment to the conventional t-statistic to overcome this obstacle.…”

Section: Incomplete Consumption Risk Sharing and Common Factors In Cumentioning

confidence: 99%

“…Repeating this procedure sufficiently many times and calculating the value of the t-statistic for the significance level at which the null hypothesis is tested should give a good indication of the predictor's true forecasting. Table 3 reports Newey-West (Newey and West (1987)) corrected t-statistics in parenthesis as well as Valkanov (2003) corrected t-statistics in brackets 3 below the regression estimates.…”

Section: Incomplete Consumption Risk Sharing and Common Factors In Cumentioning

confidence: 99%

“…The regressor, , is the temporary deviation from the long-term trend in the ratio of residential housing wealth and disposable income in the Euro Area as calculated in Nitschka (2008) The forecast horizon, h, is in quarters. T-statistics in parenthesis are NeweyWest corrected (Newey and West (1987)), t-statistics in brackets are Valkanov (2003) corrected. Both appear below the regressor estimates.…”

Section: Incomplete Consumption Risk Sharing and Common Factors In Cumentioning

confidence: 99%

See 1 more Smart Citation

Idiosyncratic consumption risk and predictability of the carry trade premium: Euro-Area evidence

Nitschka

2009

Financ Mark Portf Manag

View full text Add to dashboard Cite

The empirical failure of the uncovered interest rate parity condition seems to be the reflection of risk premia on foreign currencies. After the formation of foreign currency portfolios according to interest rate differentials or forward discounts, recent studies suggest that either consumption-or currency return-based pricing factors explain the cross-section of foreign currency portfolio returns. The contribution of this paper is twofold. It shows that the returnbased explanation applies to foreign currency portfolios sorted from the perspective of a Euro Area investor. Secondly, the main results of this paper suggest that the decisive pricing factor, the so called carry trade premium, mirrors business cycle related risks. Times of relatively large amounts of uninsured Euro Area consumption growth risk are associated with an expected increase of the carry trade premium. JEL: F31, G10, G15

show abstract

Long-horizon regressions: theoretical results and applications

Cited by 457 publications

References 33 publications

Panel cointegration tests of the Fisher effect

Panel cointegration tests of the Fisher effect

Rationality in precious metals forward markets: Evidence of behavioural deviations in the gold markets

Idiosyncratic consumption risk and predictability of the carry trade premium: Euro-Area evidence

Contact Info

Product

Resources

About