A statistical study on the effect of multicollinearity on parameters estimate

Description

Abstract

A statistical study on the effect of multicollinearity on parameters estimate. This study deals with the effect of multicollinearity on parameters estimate. The purpose of this study is to know the effect of multicollinearity in parameters estimate. The data used in this study is secondary data. There were extracted from the practical manual Guide for Higher National Diploma in Statistics HND II Semester 1 and involve the GDP, foreign direct investment, exchange rate, interest rate and inflation rate for the period of 2 years and 5 months. The data collected were analyzed using three statistical methods the least square method, informal method (total R2) and formal method (the chi-square test). The result obtained from the least square method showed that GDP is jointly determined by foreign direct investment, exchange rate, interest rate and inflation rate. The results obtained further showed that the estimated regression coefficients tend to vary widely from one sample to the next when independent variables are highly correlated. Both formal and informal tests showed that there was a presence of multicollinearity in the chosen model and is several. The total R2 revealed that about 91.12% total variation in GDP associated with the use of foreign direct investment, exchange rate, interest rate and inflation rate. Total R2 also showed that the model of GDP on foreign direct investment, exchange rate, interest rate and the inflation rate is adequate and good for prediction