Abstract
A new panel unit root by Chang (Journal of Econometrics, 110, 261–92, 2002) is employed on a set of financial ratios with a view to improving the power of unit root tests when applied to a relatively small number of observations (in the present case 38 annual observations). The test is innovative in that it allows for cross-sectional dependencies and the asymptotic distribution of the test is standard. Although standard Dickey–Fuller tests suggest that individual financial ratio series are nonstationary, panel unit root tests strongly reject the null hypothesis of a joint unit root in the ratios. Taken together the evidence from the proposed new analysis implies strong persistence in the ratios but that their characterization as I(1) processes may be misleading. These findings have important implications for accounting and finance researchers who employ financial ratios as explanatory variables.
Acknowledgements
D. Peel and I. Venetis gratefully acknowledge financial support from ESRC grant L/138/25/1004.
Notes
1 Panel unit root procedures such as that of Im, Pesaran and Shin (IPS, 1997) have become popular in recent years to analyse issues such as convergence and PPP. The IPS procedure assumes i.i.d. errors. When this assumption is violated, and where the residuals are contemporaneously correlated, a size distortion arises which depends on the magnitude of cross-correlation coefficients, their variability and the number of series in the panel. Demeaning will not eliminate the size problem caused by the variation of cross-correlations (see Strauss and Yigit, Citation2002).
2 The authors are grateful to Tippett, M., and Whittington, G., for providing the data.
3 For technical details see Chang (Citation2002) and references cited therein.
4 These results are available on request from the authors.