{smcl}
{* 11june2002/3nov2004}{...}
{hline}
help for {hi:ofrtplot}
{hline}

{title:Plot observed, fitted and residuals versus `time' variable} 

{p 8 17 2}{cmd:ofrtplot} [{it:varname}] 
[ 
{cmd:,} 
{cmd:super} 
{cmd:ofplot(}{it:line_options}{cmd:)} 
{cmd:rplot(}{it:spike_options}{cmd:)} 
{cmd:combine(}{it:graph_options}{cmd:)} 
] 


{title:Description}

{p 4 4 2}{cmd:ofrtplot} plots observed, fitted and residuals from the last
model against a predictor. It is primarily designed for time series models and
by default the predictor is whatever has been {cmd:tsset} as the time variable.
However, other variables may be specified, whether or not data have been
{cmd:tsset}. 

{p 4 4 2}Observed values are for the response or dependent variable from the
last model, fitted values are whatever {cmd:predict} produces by default and
residuals are whatever {cmd:predict, res} produces. The plot is restricted to
the estimation sample. 

{p 4 4 2}By default, the plot has two panels. In the top panel, observed and
fitted are plotted against the predictor. In the bottom panel, residuals are
plotted against the predictor, by default as spikes from zero.


{title:Options}

{p 4 4 2}{cmd:super} specifies that plots are to be superimposed, not separate.
 
{p 4 4 2}{cmd:ofplot()} specifies options of {help twoway line} to tune the 
display of observed and fitted values.  

{p 4 4 2}{cmd:rplot()} specifies options of {help twoway spike} to tune the 
display of residuals. 

{p 4 4 2}{cmd:combine()} specifies options to control the combination 
of the two graphs. This has no effect with {cmd:super}. 


{title:Examples}

{p 4 8 2}{cmd:. tsset time}{p_end}
{p 4 8 2}{cmd:. regress {it:whatever} time}{p_end}
{p 4 8 2}{cmd:. ofrtplot}{p_end}

{p 4 8 2}{cmd:. gen gpm = 1 / mpg}{p_end} 
{p 4 8 2}{cmd:. regress gpm weight}{p_end}  
{p 4 8 2}{cmd:. ofrtplot, ofplot(recast(scatter) ms(Oh none) connect(none l))}


{title:Author}

{p 4 4 2}Nicholas J. Cox, University of Durham, U.K.{break} 
n.j.cox@durham.ac.uk


{title:Acknowledgements} 

{p 4 4 2}Denis de Crombrugghe suggested this program originally. 
Kit Baum made several useful suggestions.


{title:Also see}

{p 4 13 2}On-line: help for {help predict}, {help tsset}, {help modeldiag}