Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Testing for predictability in panels of any time series dimension

Westerlund, Joakim LU and Narayan, Paresh (2016) In International Journal of Forecasting 32(4). p.1162-1177
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Panel data, Predictive regression, Stock return predictability, China
in
International Journal of Forecasting
volume
32
issue
4
pages
16 pages
publisher
Elsevier
external identifiers
  • scopus:84971655211
  • wos:000384778200005
ISSN
1872-8200
DOI
10.1016/j.ijforecast.2016.02.009
language
English
LU publication?
yes
id
2415caf5-fdbe-47fe-9ea6-ec2a926b0105 (old id 8603524)
date added to LUP
2016-04-01 10:26:10
date last changed
2022-03-12 05:40:16
@article{2415caf5-fdbe-47fe-9ea6-ec2a926b0105,
  abstract     = {{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.}},
  author       = {{Westerlund, Joakim and Narayan, Paresh}},
  issn         = {{1872-8200}},
  keywords     = {{Panel data; Predictive regression; Stock return predictability; China}},
  language     = {{eng}},
  number       = {{4}},
  pages        = {{1162--1177}},
  publisher    = {{Elsevier}},
  series       = {{International Journal of Forecasting}},
  title        = {{Testing for predictability in panels of any time series dimension}},
  url          = {{http://dx.doi.org/10.1016/j.ijforecast.2016.02.009}},
  doi          = {{10.1016/j.ijforecast.2016.02.009}},
  volume       = {{32}},
  year         = {{2016}},
}