vec_postestimation.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* 28mar2005}{...}
{cmd:help vec postestimation}{right:dialog:  {bf:{dialog vec_p:predict}}}
{right:also see:  {helpb vec}    }
{hline}

{title:Title}

{p2colset 5 32 34 2}{...}
{p2col :{hi:[TS] vec postestimation} {hline 2}}Postestimation tools for vec{p_end}
{p2colreset}{...}


{title:Description}

{pstd}
The following postestimation commands are of special interest after {cmd:vec}:

{synoptset}{...}
{p2col :command}description{p_end}
{synoptline}
{synopt :{helpb fcast compute}}obtain dynamic forecasts{p_end}
{synopt :{helpb fcast graph}}graph dynamic forecasts obtained from 
{cmd:fcast compute}{p_end}
{synopt :{helpb irf}}create and analyze IRFs and FEVDs{p_end}
{synopt :{helpb veclmar}}LM test for autocorrelation in residuals{p_end}
{synopt :{helpb vecnorm}}test for normally distributed residuals{p_end}
{synopt :{helpb vecstable}}check stability condition of estimates{p_end}
{synoptline}
{p2colreset}{...}

{pstd}
In addition, the following standard postestimation commands are available:

{synoptset}{...}
{p2col :command}description{p_end}
{synoptline}
INCLUDE help post_estat
INCLUDE help post_estimates
INCLUDE help post_lincom
INCLUDE help post_lrtest
INCLUDE help post_nlcom
{synopt :{helpb vec postestimation##predict:predict}}predictions, residuals, 
influence, statistics, and other diagnostic measures{p_end}
{synopt :{helpb predictnl}}point estimates, standard errors, testing, and
inference for generalized predictions{p_end}
INCLUDE help post_test
INCLUDE help post_testnl
{synoptline}
{p2colreset}{...}


{marker predict}{...}
{title:Syntax}

{p 8 19 2}
{cmd:predict} {dtype} {newvar} {ifin} 
  [{cmd:,} {opt eq:uation}{cmd:(}{it:eqno}|{it:eqname}{cmd:)} 
  {it:statistic}]

{synoptset}{...}
{synopthdr:statistic}
{synoptline}
{synopt :{cmd:xb}}fitted value for the specified equation; the default{p_end}
{synopt :{cmd:stdp}}standard error of the linear prediction{p_end}
{synopt :{opt r:esiduals}}residuals{p_end}
{synopt :{cmd:ce}}calculate the predicted value of the specified 
  cointegrating equation{p_end}
{synopt :{opt l:evels}}one-step prediction of the level of the endogenous 
  variable{p_end}
{synopt :{opt u:sece(varlist_ce)}}compute the predictions using previously 
  predicted cointegrating equations{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}These statistics are available both in and out of sample; type
{cmd:predict} {it:...} {cmd:if} {cmd:e(sample)} {it:...} if wanted only for
the estimation sample.


{title:Options for predict}

{phang}
{opt equation(eqno|eqname)} specifies to which equation you are referring.

{pmore}
{opt equation()} is filled in with one {it:eqno} or {it:eqname} for options
{opt xb}, {opt residuals}, {opt stdp}, {opt ce}, and {opt levels}.
{cmd:equation(#1}) would mean that the calculation is to be made for the first
equation, {cmd:equation(#2)} would mean the second, and so on.  Alternatively,
you could refer to the equation by its name.  {cmd:equation(D_income)} would
refer to the equation named D_income and {cmd:equation(_ce1)} to the first
cointegrating equation, which is named _ce1 by {cmd:vec}.

{pmore}
If you do not specify {opt equation()}, the results are as if you specified
{cmd:equation(#1)}.

{phang}
{opt xb}, the default, calculates the fitted values for the specified
equation of the VECM.  The form of the VECM implies that these fitted values
are the one-step predictions for the first-differenced variables.

{phang}
{opt stdp} calculates the standard error of the linear prediction for the
specified equation.

{phang}
{opt residuals} calculates the residuals from the specified equation of the
VECM. 

{phang}
{opt ce} calculates the predicted value of the specified cointegrating
equation.

{phang}
{opt levels} calculates the one-step prediction of the level of the endogenous
variable in the requested equation.

{phang}
{opt usece(varlist_ce)} specifies that previously predicted cointegrating
equations saved under the names in {it:varlist_ce} be used to compute the
predictions.  The number of variables in the {it:varlist_ce} must equal the
number of cointegrating equations specified in the model.

{phang}
For more information on using {cmd:predict} after multiple-equation estimation
commands, see {help predict}.


{title:Examples}

{phang}{cmd:. vec missouri indiana kentucky illinois, trend(rconstant) rank(2)}{p_end}
{phang}{cmd:. vecnorm}{p_end}
{phang}{cmd:. veclmar}{p_end}
{phang}{cmd:. vecstable}{p_end}
{phang}{cmd:. irf create myirfs, set(results, replace)}{p_end}
{phang}{cmd:. irf graph oirf}{p_end}
{phang}{cmd:. predict ce1, ce equation(#1)}{p_end}


{title:Also see}

{psee}
Manual:  {bf:[TS] vec postestimation}{p_end}

{psee}
Online:  {helpb vec};{break} 
{helpb estimates}, {helpb fcast compute}, {helpb fcast graph}, {helpb irf}, 
{helpb lincom}, {helpb lrtest}, {helpb nlcom}, {helpb predictnl}, 
{helpb test}, {helpb testnl}, {helpb veclmar}, {helpb vecnorm}, 
{helpb vecstable}{p_end}