{smcl}
{* 10sep2011}{...}
{cmd:help xtfmb}{right:version:  2.0.0}
{hline}

{title:Title}

{p 4 8}{cmd:xtfmb}  -  Fama and MacBeth (1973) procedure{p_end}


{title:Syntax}

{p 4 6 2}
{cmd:xtfmb}
{depvar}
[{indepvars}]
{ifin}
{weight}
[, {opt l:evel(#)}
{opt verb:ose}
{opt lag(#)}]

{title:Notes}

{p 4 6 2}
- You must {helpb tsset} your data before using {opt xtfmb}.{p_end}
{p 4 6 2}
- {opt by}, may be used with {opt xtfmb}; see {help by}.{p_end}
{p 4 6 2}
- {opt aweight}s are allowed; see {help weight}.{p_end}



{title:Description}

{p 4 4 2}
{opt xtfmb} is an implementation of the Fama and MacBeth (1973) two step
procedure. The procedure is as follows: In the first step, for each single time 
period a cross-sectional regression is performed. Then, in the second step, 
the final coefficient estimates are obtained as the average of the first step
coefficient estimates.{p_end}

{p 4 4 2}
If {opt xtfmb} is called without option {opt lag(#)}, then it is possible to 
test for the significance of coefficient combinations. This works because in this 
case the second step of the Fama-MacBeth procedure is implemented by aid of 
Zellner's SUR estimation.{p_end}

{p 4 4 2}
When {opt xtfmb} is called with option {opt lag(#)}, then heteroscedasticity and
autocorrelation consistent Newey-West (1987) standard error estimates are provided.
However, in this case the current implementation of {opt xtfmb} does not allow for
testing the significance of coefficient combinations.{p_end}

{p 4 4 2}
The "avg. R-squared" which is provided in the header of the {opt xtfmb} program
is computed as the average value of the R-squares from the cross-sectional 
regressions in the first step of the Fama-MacBeth procedure. The coefficient 
estimates and R-squares of the first step regressions can be printed out with 
option {opt verb:ose}.{p_end}


{title:Options}

{phang}
{opt level(#)}; see {help estimation options##level():estimation options}.{p_end}

{phang}
{opt verb:ose} lists the coefficient estimates and R-squares of the 
cross-sectional regressions from the first step of the Fama-MacBeth procedure.{p_end}

{phang}
{opt lag(#)} computes heteroscedasticity and autocorrelation consistent 
Newey-West (1987) standard error estimates with a lag length of # periods.{p_end}


{title:Example}

{phang}{stata "webuse grunfeld" : . webuse grunfeld}{p_end}
{phang}{stata "xtfmb invest mvalue kstock, verbose" : . xtfmb invest mvalue kstock, verbose}{p_end}
{phang}{stata "est store FMB" : . est store FMB}{p_end}

{phang}{stata "xtfmb invest mvalue kstock, lag(2)" : . xtfmb invest mvalue kstock, lag(2)}{p_end}
{phang}{stata "est store FMB_Newey" : . est store FMB_Newey}{p_end}

{phang}{stata "reg invest mvalue kstock" : . reg invest mvalue kstock}{p_end}
{phang}{stata "est store OLS" : . est store OLS}{p_end}

{phang}{stata "est table *, b se t" : . est table *, b se t}{p_end}


{title:References}

{p 4 6 2}
 - Fama, E.F., and J.D. MacBeth, 1973, Risk, Return, and Equilibrium:
 Empirical tests, {it:Journal of Political Economy} 81, 607-636.{p_end}

{p 4 6 2} 
 - Newey, W.K., and K.D. West, 1987, A simple, positive semi-definite, heteroskedasticity
and autocorrelation consistent covariance matrix, {it:Econometrica} 55: 703Ð708.{p_end}


{title:Author}

{p 4 4}Daniel Hoechle, University of Basel, daniel.hoechle@unibas.ch{p_end}



{title:Also see}

{psee}
Manual:  {bf:[R] regress}

{psee}
Online:
{helpb tsset}, {helpb regress}, {helpb newey}, {helpb xtreg}, {helpb _robust}
{p_end}