Purchase Solution

CAPM and significance of low value of R-square in regression

Not what you're looking for?

Ask Custom Question

Capital Asset Pricing Model (CAPM) is used to calculate the required return from a stock. To calculate the required return from ABC stock, a regression was run between the S&P Index daily retun over risk free rate and ABC daily returns over risk free rate on the historical data for 500 days. The R square value of the regression is 20%. What does this value represent. What does a low value of R square mean. Could you find some possible reasons for low R sqaure. Since the R square value is only 20%, can we conclude CAPM is not a good model to calculate the required rate of return.

Purchase this Solution
Solution Summary

This posting explains how to interpret the value of r-square obtained in a regression analysis mainly in the context of beta calculations for using CAPM. Whether a low value of R-square is always bad or a higher value of r-square is always good? Such questions are answered.

Solution Preview

See the attached file for complete solution. The text here may not be copied exactly as some of the symbols / tables may not print. Thanks

No. R square of the time series regression is really irrelevant. It is a bit meaningful in that low R square leads to imprecisely estimated alphas and betas, but we have separate t statistics to evaluate that question. High R2 only matters if you are interpreting the regression as an APT, but then we'd have other factors and not the market on the right hand side, and portfolios on the left.

R2 is a statistic that measures the percentage of variation in the dependent variable that is explained for by all the explanatory variables in the model. Thus, R2 provides a measure of the overall goodness-of-fit of the regression model. The R2 ...

Purchase this Solution
Free BrainMass Quizzes
Learning Lean

This quiz will help you understand the basic concepts of Lean.

Introduction to Finance

This quiz test introductory finance topics.

Transformational Leadership

This quiz covers the topic of transformational leadership. Specifically, this quiz covers the theories proposed by James MacGregor Burns and Bernard Bass. Students familiar with transformational leadership should easily be able to answer the questions detailed below.

Organizational Behavior (OB)

The organizational behavior (OB) quiz will help you better understand organizational behavior through the lens of managers including workforce diversity.

Income Streams

In our ever changing world, developing secondary income streams is becoming more important. This quiz provides a brief overview of income sources.

View More Free Quizzes
Related BrainMass Solutions

  • Linear Regression Analysis

    This is based on the value of: Adjusted R Square= 0.875 Adjusted R Square 0.875 indicates that 87.5 % of the variation in Y is explained by the regression line. 4) Discuss the strength of the regression model.

  • Regression Analysis with Excel

    Excel file - with the data and the regression results SUMMARY OUTPUT Regression Statistics Multiple R 0.95636229 R Square 0.914628829 Adjusted R Square 0.903613194 Standard Error 0.022471973

  • Interpreting Summary Output for Simple Linear Regression

    F =146.773 is very high and Significance F corresponding to this value of F=7.10E-07 is very low. p = .05 is very high compared to 7.10E-07 which means that the correlation coefficient is significant at p < .05 8.

  • AIU's survey: Regression Analysis- Benefits & Intrinsic

    The low level of linearity is reflected in the very low R square of .17, which is almost too low to be usable. For overall scores, we have a positive slope.

  • Linear regression

    From the tables Adjusted R Square 0.8171 F = 36.730 Significance F = 0.0001 Adjusted R Square value is 0.8171 . This means that 81.71 % of the variation in Y is explained by the regression line.

  • Regression analysis and 5-Step Hypothesis Test

    Step 5: Interpret result We can say that there is no significant positive correlation between no. of TVs and price 2. A) R = 0.47399607 The value of correlation coefficient is 0.474, which is very low.

  • Excel Formula

    Since the p-value < 0.05, we reject the null hypothesis and conclude that the relationship is significant. C) Here the R-Square value is 0.7438. This means that, the estimated regression equation explained 74.38% of variability in Price.

  • multicollinearity

    The R-square will be overestimated and will show a higher value than it should be in reality.

  • Correlation and Simple Linear Regression

    Regression Statistics Multiple R 0.95624857 R Square 0.914411327 Adjusted R Square 0.897293593 Standard Error 5.089839735 Observations 7 R Square 0.914411327 percent of the variation in y (dependent

View More Related Solutions