This paper examines and analyzes the use of Multivariate Regression Analysis (MRA) as a forecasting tool. The authors attempt to test the capability of the multivariate regression model to forecast the prices of stocks classified as `A-Group' by the Bombay Stock Exchange (BSE). Researchers in the past have applied numerous variables to forecast stock prices; the authors in this study use three variables, namely stock price, operating cash flow and risk-free rate of interest. The results of the study are encouraging and the average variation of 173 stocks is less than 4%. The findings suggest that stock markets do not follow a random walk and there exists a possibility of forecasting stock prices by using operating cash flows and risk-free rate of returns. The authors opine that it is possible to capture nonlinearities contained in the stock prices by using MRA. If MRA is used judiciously, it is possible to forecast stock prices fairly well and this could bring transparency in stock trading and benefit the investors.

The history of regression goes back to the 18^th century. The earliest form of regression was the method of least squares, which was published by Adrien Marie Legendre in 1805 and by Carl Friedrich Gauss in 1809. According to Dunteman (1984), Multivariate Regression Analysis (MRA) considers the simultaneous effects of many variables taken together. A crucial role is played by multivariate normal distribution, which allows simplifying assumptions to be made, which makes it feasible to develop appropriate models.

A common use of multivariate analysis is to reduce a large number of inter-correlated variables into a much smaller number of variables, preserving as much as possible of the original variation, whilst also having useful statistical properties such as independence. In the case of regression analysis, R² measures the strength of the relationship, but an additional R² statistic called the adjusted R² is computed to counter the basis that will induce the R² to keep increasing as more independent variables are added to the regression. Multivariate regression is a powerful tool that allows examining the determinants of any response variable.

Accounting Research and Audit Practices Bombay Stock Exchange, BSE, Multivariate Regression Analysis, MRA, Statistical Properties, Regression Analysis, Efficient Market Hypothesis, EMH, Cash Flow, Vector Autoregressive, VAR, Electronic Data Information Filing and Retrieval System, EDIFAR.