Testing for predictability in panels of any time series dimension

Research output: Contribution to journalArticle

Standard

Testing for predictability in panels of any time series dimension. / Westerlund, Joakim; Narayan, Paresh.

In: International Journal of Forecasting, Vol. 32, No. 4, 2016, p. 1162–1177.

Research output: Contribution to journalArticle

Harvard

APA

CBE

MLA

Vancouver

Author

RIS

TY - JOUR

T1 - Testing for predictability in panels of any time series dimension

AU - Westerlund, Joakim

AU - Narayan, Paresh

PY - 2016

Y1 - 2016

N2 - The few panel data tests for predictability of returns that exist are based on the prerequisite that both the number of time series observations, $T$, and the number of cross-section units, $N$, are large. As a result, these tests are impossible for stock markets where lengthy time series data are scarce. In response to this, the current paper develops a new test for predictability in panels where $N$ is large and $T \geq 2$ can be small or large, or indeed anything in between the two extremes. This consideration represents an advancement when compared to the usual large-$N$ and large-$T$ requirement. The new test is also very general, especially when it comes to the allowable predictors, and it is easy to implement. As an illustration, we consider the Chinese stock market, for which data is only available for 17 years but where the number firms is relatively large, 160.

AB - The few panel data tests for predictability of returns that exist are based on the prerequisite that both the number of time series observations, $T$, and the number of cross-section units, $N$, are large. As a result, these tests are impossible for stock markets where lengthy time series data are scarce. In response to this, the current paper develops a new test for predictability in panels where $N$ is large and $T \geq 2$ can be small or large, or indeed anything in between the two extremes. This consideration represents an advancement when compared to the usual large-$N$ and large-$T$ requirement. The new test is also very general, especially when it comes to the allowable predictors, and it is easy to implement. As an illustration, we consider the Chinese stock market, for which data is only available for 17 years but where the number firms is relatively large, 160.

KW - Panel data

KW - Predictive regression

KW - Stock return predictability

KW - China

U2 - 10.1016/j.ijforecast.2016.02.009

DO - 10.1016/j.ijforecast.2016.02.009

M3 - Article

VL - 32

SP - 1162

EP - 1177

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 1872-8200

IS - 4

ER -