d 'ASREG': module to estimate rolling window regressions. Fama-MacBeth and by(group) regressions
d
d asreg can fit three types of regression models; (1) a model of
d depvar on indepvars using linear regression in a user's defined
d rolling window or recursive window (2) cross-sectional
d regressions or regressions by a grouping variable (3) Fama and
d MacBeth (1973) two-step procedure. asreg is order of magnitude
d faster than estimating rolling window regressions through
d conventional methods such as Stata loops or using the
d Stata's official rolling command. asreg has the same speed
d efficiency as asrol. All the rolling window calculations,
d estimation of regression parameters, and writing of results to
d Stata variables are done in the Mata language. asreg reports most
d commonly used regression statistics such as number of
d observations, r-squared, adjusted r-squared, constant, slope
d coefficients, standard errors of the coefficients, fitted
d values, and regression residuals.
d
d KW: rolling window regression
d KW: recursive window regressions
d KW: by-group regressions
d KW: Fama
d KW: MacBeth
d KW: Newey-West
d KW: storing regression results in memory
d KW: rolling betas
d KW: moving window regressions
d KW: cross-sectional regressions
d
d Requires: Stata version 11
d
d Distribution-Date: 20180731
d
d Author: Attaullah Shah, Institute of Management Sciences
d Support: email attaullah.shah@@imsciences.edu.pk
d
f asreg.ado
f asreg.sthlp
f ../l/lasreg.mlib