I used White's test to test for heteroskedasticity but could not reject the null hypothesis of homoskedastic
disturbances at [alpha] = 0.
I analyse the empirical performance of the CAPM and test for the following implications: the residuals of the regression (1) should be serially uncorrelated, homoskedastic
and normal, the systematic relationship between portfolio return and market returns should be linear, and the estimate of beta should be time invariant.
Alternative III: baseline model with assumption that errors are homoskedastic
McFadden's method assumes that the error terms in the model are independent and homoskedastic
2] denotes the White's test statistic to test for homoskedastic
errors; figures in round parentheses indicate t- statistics, whereas those in square brackets refer to p values.
The authors performed conditional moment tests for heteroskedasticity and the null hypothesis of homoskedastic
disturbances could not be rejected at conventional levels of significance.
WLS rather than IV is used here because IV estimation is based on the assumption that the error terms in Equations (5)-(7) are homoskedastic
, whereas we consider the assumption of heteroskedasticity to be more appropriate.
Both PC Gets and Hoover and Perez require residuals to be normal, homoskedastic
, without autocorrelations, and temporally stable, both in and out of sample.
If the covariance matrix of the structural errors is homoskedastic
and stable over time, forecasts from biased coefficients would be superior to those from structural parameters.
I have estimated many different specifications for the benefit society IV probit equation, but I never could find one that yields homoskedastic
t] is a serially uncorrelated, homoskedastic
random error term.
The results, which are available from the authors on request, do suggest that, after controlling for autocorrelation and introducing country-specific effects, it is indeed correct to assume an homoskedastic