Econ 457-01: Fall 2008

Due Date: Wednesday, 10/1, 2008

Project 1: Test CAPM

The econometric specification of CAPM model is the following:

This type of model can be estimated with ordinary least squares regression. We assume that the expected value of the error is zero and that it is uncorrelated with the independent variable. We also took expected values of each side of this model:

which looks like the CAPM. But the asset pricing model that we developed imposes the following constraint on expected returns:

The security's expected excess return is linear in the security's beta. The beta represents the risk of security i in the market portfolio -- or the contribution of security i to the variance of the market portfolio. The beta risk is the only type of risk that is rewarded or priced in equilibrium. What makes the CAPM different from the statistical model is that the CAPM imposes the constraint that the intercept or alpha is zero. 1. Time Series Tests of the CAPM 1) Testing method and hypothesis One test of the CAPM is to test whether the alpha of any security or portfolio is statistically different from zero and beta is stable over the time. The null hypothesis is (the CAPM holds) is that the intercept is equal to zero. Under the alternative hypothesis, the intercept or alpha is not equal to zero. The standard test is a t-test on the intercept of the regression. If the intercept is more than 2 standard errors from zero (or having a t-statistic greater than 2), then there is evidence against the null hypothesis (the CAPM).

2) Data to be used:

Tested assets: One stock (IBM) and one portfolio(Dow index) (test them separately) Market portfolio: S&P 500 index Frequency of the data: monthly Risk free return rate: 4-week Treasury bill rate, and before 2001 July, use 3month Treasury bill rate. (Ideally we should use 4-week rate all the time because our test is based on monthly data, however, 4-week Treasury bill rate is only available after 2001 July. So before that, use a proxy, 3-month rate) Time period: January 1965 to January 2005. Divide the whole period into several sub-periods, which last 5 years each. Test the model in each 5-year sub-period, i.e. Jan.1965- Jan.1970, Jan.1970- Jan.1975, and so on.

3) Where to get data: For stock price and index, go to Yahoo! Finance (http://finance.yahoo.com/), enter the stock or index you are looking for in the get quotes window, then click historical prices on the left, choose period and frequency (monthly), click download to spreadsheet (at the bottom of the page). Use adjusted close data. For risk free return data: Go to St. Louis Fed website (http://research.stlouisfed.org/fred2/), find monthly 4-week (1-month) Treasury bill rate, (there are daily, weekly, monthly available, pick monthly), before July 2001, use monthly 3-month treasury rate. Once you find the data, download to spreadsheet. (Attention, these Treasury bill rates are nominal rates, not periodic ones) 4) Testing procedure. Download and organize the data transform price data into return data (which are monthly return) transform nominal risk free rate into periodic rate (i.e. monthly rate too) Run regressions for each 5-year period. Do IBM first, and then Dow. 5) Obtain your results, analyze the results and write your report. Whether alpha =0 in all the sub-periods? Whether beta of IBM and Dow is stable through different 5-year sub-periods? What do the results imply to us about the efficiency of the CPAM model for individual stock (IBM) and portfolio (Dow) respectively?

2. Cross-Sectional Tests of the CAPM 1) Testing method and hypothesis The Capital Asset Pricing Model implies that each security's expected return is linear in its beta. A possible strategy for testing the model is to collect securities' betas at a particular point in time and to see if these betas can explain the cross-sectional differences in average returns. Consider the cross-sectional regression:

In this regression, R represents the returns of many securities at a particular crosssection of time and beta represents the betas on many firms. According to the CAPM, gamma_0 should be equal to zero and gamma_1 should equal the expected excess return on the market portfolio. We can test this. 2) Data to be used: Tested assets: 30 stocks included in Dow index. (find out yourself what these 30 stocks are) Market return: S&P 500 index Risk free return rate: 4-week Treasury bill rate Frequency of the data: monthly Time period: January 2002 to January 2005. 3) Where to get data: the same as the time series test 4) Testing procedure. Download and organize the data. transform price data into return data transform nominal risk free rate into periodic rate Run regressions to obtain beta for each of 30 stocks in this 3-year period. Calculate average monthly return for each of 30 stocks during this 3-year period Thus, you have cross-sectional stocks return data and beta, run the regression suggested above. 5) Obtain your results, analyze results and write your report. Whether gamma_0 =0? Whether gamma_1=market premium? What do your results imply about the efficiency of the CPAM?

You can use Stata, Excel, SPSS or any other statistical software to do this project. Finally, put all your results, analysis and conclusions in the final report and submit the report.