Q2. What future works have the authors mentioned in the paper "The relationship between return and market value of common stocks*" ?
Further research should consider the relationship between size and other factors such as the dividend yield effect, and the tests should be expanded to include OTC stocks as well. The past ( 19261976 ) and the future ( 1977-2000 ) ( Fmanctal Analysis Research Foundation ) Klem, Roger W. and ViJay S. Bawa, 1977, The effect of hmited mformation and estimation risk on optimal portfoho diversificatton, Journal of Fmanctal Economics 5, Aug., 89-111. “ Klein and Bawa ( 1977, p 102 ) 16A slmllar result can be obtamed with the Introduction of lixed holdmg costs which lead to hmlted chverslficatlon as well.
Q3. How long are the betas used for the estimation of the security?
Five years of data are used for the estimation of the security beta; the next five years’ data are used for the reestimation of the portfolio betas.
Q4. How many years are the btas rebalanced?
Simple equally weighted portfolios are used rather than more sophisticated minimum variance portfolios to demonstrate that the size effect is not due to some quirk in the covariance matrix.‘*No ex post sample btas IS Introduced, smce monthly rebalancmg includes stocks d&ted durmg the five years.
Q5. Does the grouping procedure lead to substantially different results?
Revising the grouping procedure - ranking on the basis of beta first, then ranking on the basis of market proportion - also does not lead to substantially different results.
Q6. What is the method for estimating the gammas?
As Then (1971, p. 610) has pointed out, this method leads to unbiased maximum likelihood estimators for the gammas as long as the error in the standard error of beta is small and the standard assumptions of the simple errors-in-variables model are met.
Q7. Why do betas change when the weights change?
This is due to two factors: first, even if the true covariance structure is stationary, betas with respect to a value-weighted index change whenever the weights change, since the weighted average of the betas is constrained to be equal to one.
Q8. What is the probability limit of f2 -yz?
The probability limit of f2 -yz is [Levi (1973)]plim ($2-y2)= (a,2 ‘0i2 .yi)/D.The authors find that the bias in f2 depends on the covariance between p and 4 and the sign of ;‘,.
Q9. What is the effect of the size effect on the returns of small firms?
lack of information about small firms leads to limited diversification and therefore to higher returns for the ‘undesirable’ stocks of small firms.
Q10. What is the importance of the diagonal model?
it is very important that the diagonal model is the correct specification of the return-generating process, since the residual variance assumes a critical position in this procedure.
Q11. What is the meaning of the term market effciency?
He chooses to interpret his findings as evidence of market inefficiency but as Ball (1978) points out, market efftciency tests are often joint tests of the efficient market hypothesis and a particular equilibrium relationship.
Q12. Does the choice of a proxy for the market index affect the results?
at least within the context of this study, the choice of a proxy for the market portfolio does not seem to affect the results and allowing for heteroscedastic disturbances does not lead to significantly more efficient estimators.