A Comparison Between Ordinary Least Square And Robust Regression And Its Application In Macroeconomic Variables

This thesis investigates the relationship between stock market price and macroeconomic variables in Malaysia. There are six macroeconomic factors selected for this study namely Gross Domestic Product (GDP), Exchange Rate (ER), Money Supply (MI), Inflation Rate (IR) and Based Lending Rate (BLR)....

Full description

Saved in:
Bibliographic Details
Main Author: Siti Nor Syazwani Binti Ab Shatar
Format: Thesis
Language:English
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This thesis investigates the relationship between stock market price and macroeconomic variables in Malaysia. There are six macroeconomic factors selected for this study namely Gross Domestic Product (GDP), Exchange Rate (ER), Money Supply (MI), Inflation Rate (IR) and Based Lending Rate (BLR). The widely adopted method in examining this relationship is regression analysis in which the Ordinary Least Square (OLS) method is applied. OLS however has a limitation since the economic data is subjected to the influence of outliers. To overcome such problem, a robust regression is employed by using M-estimation and comparison is made to the OLS procedure. The results demonstrate that the robust regression procedure is able to generate reliable results as well as diagnosing a few outliers in the analysis. The findings are substantiated with diagnostic procedures, which include leverage identification, standardized residual, studentized residual, DFFITS and Cook's Distance in order to identify the presence of outliers in the model.