Testing for Periodicity Effects in a Panel Data Regression Model

Testing for Periodicity Effects in a Panel Data Regression Model

Authors: O Adeboye and D. A Agunbiade


This research attempts to investigate the effect of periodicity usually occasioned by the presence of serial correlation in panel data, through the estimation of pooled ordinary least square estimator (POLS) of a specified audit fees PDRM. Other analytical techniques employed through derivation are Fixed Effect Least Square dummy variable (where all coefficient vary over time), and Random Effect estimator (REM). A conditional Lagrange multiplier test was developed via a two-way error components model, to examine the presence of serial correlation in the fitted POLS model while Hausman test was used to ascertain the suitability of the LSDV Model over Random effect model and vice-versa. The conditional LM test gave a value of 35.3806 with P-value of 0.0001075 which shows that there is presence of serial correlation among the residuals of the fitted Pooled OLS model, thereby rendered the estimator inconsistent. Both LSDV and RE models captured the goodness of fit better when compared to the Pooled OLS model. However, the hausman test revealed that fixed effect model will be a preferable model since its results support the rejection of null hypothesis.

Keywords: Periodicity, Violation, Serial correlation, Panel Data, Audit Fees Model, Panel Data Regression Model.

Download: N. O Adeboye et al, Carib.j.SciTech, 2017, Vol.5, 040-050