Credit risk management and performance of deposit money banks in nigeria
Download 61.14 Kb.
|
- Navigate this page:
- CHAPTER FOUR DATA ANALYSIS AND PRESENTATION OF RESULTS 4.1 Introduction
- 4.2 Panel Unit Root Tests
| 3.6 Method of Data Analysis
Three main methods are used in the analysis of this study. They are the panel unit root test, correlation coefficient and the fully modified ordinary least square technique. The Levin, Lin & Chu t and ADF-Fisher Chi-square were used to conduct the panel unit root tests in order to ascertain the stationarity of the variables used. The reason for this is to avoid spurious regression results. The correlation coefficient was used to ascertain the background characteristics among the data set. The Fully Modified Least Squares (FMOLS) regression model was employed in order to evaluate the impact of credit risk management on the performance of deposit money banks in Nigeria. The fully modified least squares regression was originally designed in the work of Phillips and Hansen (1990) to provide optimal estimates of cointegrating regressions. The method modifies least squares to account for serial correlation effects and for the endogeneity in the regressors that results from the existence of a cointegrating relationship. The coefficients obtained from the estimation are then used to verify the working hypotheses of the study. The eview 9.0 is used for the analysis of the study. CHAPTER FOUR DATA ANALYSIS AND PRESENTATION OF RESULTS 4.1 Introduction In this chapter, we implement the method of data analysis earlier stated in chapter three with respect to the fully modified ordinary least square (FMOLS) econometric technique. First, in order to provide a rich background characterization of the data for investigating credit risk management and performance of deposit money banks (DMBS) in Nigeria, the correlation coefficient was employed in this regard. Next, we performed the panel unit root test and the fully modified ordinary least square (FMOLS) for the main analysis of the study. 4.2 Panel Unit Root Tests A time series is stated as non-stationary if the mean and variance is dependent over time. On the other hand, a time series is stated as stationary if the mean and variance is constant over time (Gordon, 1995). In this section, we present the unit root tests for the integration properties of the variables in the model using different panel unit root tests analysis. The results are obtained by using Levin, Lin & Chu t (LLC) and Fisher Chi-square-ADF. The result for the unit root test at levels (including ROA and ROE) is presented in Table 4.1. It is evidently clear that LLC, Fisher and ADF test were stationary at levels while others were not. Download 61.14 Kb. Share with your friends:
|