{smcl}
{* *! version 1.03  2008-02-18}{...}
{cmd:help armadiag}{...}
{right:see also:  {help corrgram} {help ac} {help pac} {help wntestq}}

{hline}

{title:Post-estimation residual diagnostics for time series}


{title:Syntax}

{p 8 25 2}
{cmd:armadiag}
[{varname}]
{ifin}
[{cmd:,} 
{opt a:rch}
{opt d:fc(d)}
{opt h:etrobust}
{opt lag:s(p)}
{opt lev:el(alpha)}
{opt yw}
{opt nog:raph}
{opt t:able}
{opt lin:scale}
{opt force}]

{title:Description}

{p}{cmd:armadiag} is a post-estimation diagnostic tool for use after {cmd:arch}, {cmd:arima}
or {cmd:regress}. The residuals (standardized residuals
with {cmd:arch}) are plotted together with autocorrelations, partial autocorrelations
and p-values of the Ljung-Box Q-statistic. The variable {it:varname} is used instead of
residuals if {it:varname} is specified.

{p}Optionally the square of the variable/residuals/standardized residuals is used to
allow detection of (remaining) ARCH-effects.

{p}The degrees of freedom of the Q-statistic are adjusted for the number of estimated 
ARMA-parameters and/or lags of the dependent variable. When the squared residuals are 
investigated the degrees of freedom are corrected for the number of ARCH-parameters.

{p}Residuals are calculated for the estimation sample unless {it:if} or {it:in} is specified.

{p}You must {cmd:tsset} your data before using {cmd:armadiag}, see {manhelp tsset TS}.

{p}{it:varname} may contain time-series operators; see {help tsvarlist}.

{title:Options}

{synoptset 15}{...}
{synopthdr:option}
{synoptline}

{synopt:{opt a:rch}}Diagnostics for ARCH, i.e. the square of the residuals, 
standardized residuals or variabe is plotted with autocorrelations, partial 
autocorrelations and Q-stat p-values for the square. Degrees of freedom are
adjusted for the number or ARCH-parameters.

{synopt:{opt d:fc(n)}}Override default degrees of freedom correction. The default
is to subtract the number of lagged dependent variables and ARMA terms for models
estimated with {cmd:arch}, {cmd:arima} and {cmd:regress}. If {opt arch} is specified
the number of ARCH-terms are subtracted for models estimated with {cmd:arch}.

{synopt:{opt h:etrobust}}Calculate Q-statistics that are robust to heteroskedasticity
of the ARCH-variety. Milh{c o/}j has shown that the variance of the estimated
autocorrelations is different from 1/T when there is ARCH and {opt hetrobust} 
corrects for this by scaling with a consistent estimate of the variance.

{synopt:{opt lag:s(p)}}The number of lags to calculate statistics for. Default is
min(int(T/2)-2,40)

{synopt:{opt lev:el(alpha)}}Level for "confidence bands" in autocorrelation and partial 
autocorrelation plots. Specified this way for consistency with {cmd:ac} and {cmd:pac} which 
has it wrong. These are not confidence intervals, a confidence interval would be be
centered on the estimate. They are 1-{it:alpha} critical values for testing the null that
the autocorrelation or partial autocorrelation is zero. 
The default is {it:alpha}=95, i.e. 5% critical values.

{synopt:{opt yw}}Calculate partial autocorrelations by using Yule-Walker equations{p_end}

{synopt:{opt nog:raph}}Do not plot results.

{synopt:{opt t:able}}Print results in a table like {cmd:corrgram}

{synopt:{opt lin:scale}}Plot p-values for Q-statistics on a linear scale. By default
the p-values are plotted on what is almost a log scale to make the more interesting, 
small, p-values easier to distinguish.

{synopt:{opt force}}Calculates statistics for residuals from other commands than
{cmd:arch}, {cmd:arima} or {cmd:regress}. 
{it:This may or may not make sense. Use at your own risk}
{synoptline}

{title:References}

{pstd}Milh{c o/}j, A., (1985), "The Moment Structure of ARCH Processes," 
{it:Scandinavian Journal of Statistics}, 12, 281-292.

{title:Examples}

{pstd}Setup{p_end}
{phang2}{cmd:. webuse air2}{p_end}
{phang2}{cmd:. gen lnair = ln(air)}{p_end}

{pstd}Plot data, autocorrelations and partial autocorrelations for model order identification{p_end}
{phang2}{cmd:. armadiag lnair}{p_end}
{phang2}{cmd:. armadiag d.lnair}{p_end}
{phang2}{cmd:. armadiag s12.lnair}{p_end}
{phang2}{cmd:. armadiag ds12.lnair}{p_end}

{pstd}Fit "airline model" and plot residual diagnostics{p_end}
{phang2}{cmd:. arima lnair, arima(0,1,1) sarima(0,1,1,12)}{p_end}
{phang2}{cmd:. armadiag}{p_end}

{pstd}Check for presence of ARCH in residuals{p_end}
{phang2}{cmd:. armadiag, arch}

{title:Author}

{pstd}Sune Karlsson, Örebro University, Sweden{p_end}
{pstd}sune.karlsson@oru.se{p_end}

{title:Also see}

{psee}
{help corrgram} {help ac} {help pac} {help wntestq}