Page 94 - CITN 2017 Journal

As a diagnostic measure, the formulated model was tested for stationarity using the
Augmented Dickey Fuller Unit root test to be sure that one is not analyzing inconsistent
and spurious relationship. A series that exhibit a stochastic trend, or even simply wanders
around at random will not be stationary and cannot be forecast far in future. A stationary
series will constantly return to a given value and no matter the starting point, in the long-
run, it is expected to attain that value (Hall, 1994).

Table 1: Model Predictions to be tested (Apriori expectation)

Variables Symbol Sign
Effective Tax Rate ETR +
t-n
Leverage LEV -
Profitability ROA +
Size SIZE ±
Liquidity LIQ +
Net Working Capital NWC +
Growth Opportunities MTB +
Capital intensity CIN -

Source: Researchers' Compilation, 2015
The resultant sign of the coefficients obtained which indicate the effect of explanatory
variables on the firm value in Nigeria was compared with the theoretical expectation.

Literature shows that using non-stationary data could yield spurious results. It is important
to determine the time series properties of the variables in the model in order to avoid
spurious regression. Stationarity of the variables was tested using the Augmented Dickey-
Fuller (ADF) by Dickey and Fuller (1979) and the Phillips-Perron (PP) tests. However,
these tests have been criticized for their limited ability to distinguish between series that
are purely non-stationary processes and those with near unit roots. Thus, the KPSS test
which has the null of stationarity was also run (Kwiatkowski, Phillips, Schmidt & Shin,
1992). Furthermore, Sargan Test as developed by Sargan (1958) was employed to test for
over-identifying restrictions for one-step and two-step GMM respectively. Hence, the first
and second order autocorrelation disturbance was also confirmed using the p-values of AR
(1) and AR (2) using Arellano-Bond Serial Correlation Test.

1. RESULT AND DISCUSSION

Descriptive Analysis of the Variables
The descriptive statistics of the variables used in analysis are shown in table 1. Descriptive
statistics show mean, median, minimum, maximum and standard deviation of the variables
and provide a general overview of the characteristics of the data. Moreover, the relatively
low standard deviations for most of the series indicate that the deviations of actual data
from their mean values are very small.

The mean of the dependent variable, firm value (TOBINQ) is 11.92 with a standard
deviation of 13.24% which measure the level of dispersal from the mean which is the
measure of central tendency. The mean value is within the range and above the median
value. The skewness had a positive value of 2.5336 this indicate that the measure of
asymmetry of the distribution of the series around the mean had a long tail towards right
side of the graph. The kurtosis as a measure of the peakness or flatness of the distribution of
a series was 12.874 as indicated in Table 5.1 is far above the standard of 3.0 of a normally
distributed data series. This implies that firm value was leptokurtic peaked. However, the

87