Review of Quantitative Finance and Accounting, 24: 423–439, 2005
2005 Springer Science + Business Media, Inc. Manufactured in The Netherlands.
Panel Cointegration Analysis of Audit Pricing Model
WIN LIN CHOU
Department of Economics, The Chinese University of Hong Kong, Tel. (852) 2609-8001
DOMINICA SUK-YEE LEE
School of Accountancy, The Chinese University of Hong Kong, Tel. (852) 2609-7841
Abstract. This paper addresses two issues that arise from testing and estimating cointegration in accounting
research. The ﬁrst issue is the failure to use more powerful cointegration tests by earlier researchers. This has led
to the problem of low test power in the cointegration procedures employed in the earlier accounting literature.
Another issue that has not received much attention in earlier studies of audit pricing is the endogeneity bias
that arises from the endogenous nature of the regressors. Commonly used regressors such as auditee size and
auditee complexity are endogenous and are often related to audit fees through a system of simultaneous equations.
Endogeneity bias suggests that the conventional OLS estimators are biased.
Using more powerful panel sample estimation procedures, we ﬁnd that elasticities of total assets are in general
under-estimated in the earlier studies when the conventional OLS method was used. We also ﬁnd that the earlier
studies tend to under-state the effects of the foreign subsidiary ratio and over-state the effect of the ratio of account
receivables to total assets on audit fees.
Keywords: audit fee model, bias-correction estimation methods, panel cointegration
JEL Classiﬁcation: C33, M41
Since the seminal work of Engle and Granger (1987), there has been immense interest in
testing unit roots and cointegration in economic time-series data. Perhaps due to the lack
of time-series data, much of the earlier accounting research has relied on cross-section
data. With the increased availability of time-series data, time-series models are being used
increasingly in empirical accounting research. In common with Nelson and Plosser (1982)
who ﬁnd that non-stationarity is common in economic time series, Wu, Kao and Lee (1996)
show that most accounting and ﬁnancial time series are non-stationary. The existence of
non-stationarity in accounting and ﬁnancial time series implies that tests of cointegration
between accounting and ﬁnancial variables are necessary in correct modeling.
Indeed, researchers in empirical accounting are aware of the dangers (e.g., spurious re-
gressions, and invalid inferences based on traditional statistical tests) associated with non-
stationarity. For example, Whittington and Tippett (1999) suggest using accounting ratios
to avoid the dangers associated with non-stationary series when they ﬁnd the existence of a
cointegrating relationship between the numerators and denominators of accounting ratios.
Qi, Wu and Xiang (2000) apply the unit root test of Phillips and Perron (1988) to investigate