{smcl}
{* 11jun2004}{...}
{hline}
help for {cmd:mijoin}, {cmd:misplit}{right:(SJ5-4: st0067_2; SJ5-2: st0067_1; SJ4-3: st0067)}
{hline}

{title:Join or split multiple imputed datasets}


{p 8 17 2}
{c -(}{cmd:mijoin} [{it:filestubname}] | {cmd:misplit}{c )-}{cmd:,}
{cmd:clear}
[{cmd:m(}{it:#}{cmd:)}
{cmdab:imp:id(}{it:varname}{cmd:)}]


{title:Description}

{p 4 4 2}
{cmd:mijoin} converts datasets prepared by Carlin's {helpb miset} routine
to {helpb mvis} format, for analysis by {helpb micombine}. The component
datasets are stacked (joined vertically). If {it:filestubname} is 
specified then the program will look for files called 
{it:filestubname}{cmd:1.dta}, {it:filestubname}{cmd:2.dta},...,
{it:filestubname}{cmd:m.dta} where {cmd:m} is determined by
the {cmd:m()} option.

{p 4 4 2}
{cmd:misplit} converts a dataset prepared by {helpb mvis}
to {helpb miset} format, for analysis
by {helpb mifit} and other utilities. You should {cmd:use}
the dataset first.

{p 4 4 2}
The operations performed by {cmd:mijoin} and {cmd:misplit}
are reciprocal.


{title:Options}

{p 4 8 2}
{cmd:clear} is not optional and confirms that you are willing to replace the
data in memory.

{p 4 8 2}
{cmd:m(}{it:#}{cmd:)} sets the number of imputed datasets to {it:#}.

{p 4 8 2}
{cmd:impid(}{it:varname}{cmd:)} sets the name of the variable identifying the
imputations to {it:varname} (default is {cmd:_j}). {cmd:mijoin} creates
{it:varname} whereas {cmd:misplit} expects it to exist already.


{title:Remarks}

{p 4 4 2}
After {cmd:mijoin} has been executed, the data are ready for immediate use by
{cmd:micombine}. However, to save the data permanently you would
need to issue a {helpb save} command.

{p 4 4 2}
After {cmd:misplit} has been executed, the data are ready for immediate use by
Carlin's routines. However, to save the data permanently you would
need to issue a {helpb misave} command followed by {helpb miset} on the next use.


{title:Examples}

{p 4 8 2}{cmd:. mvis y x1 x2 x3 using imp, m(3)}{p_end}
{p 4 8 2}{cmd:. use imp, clear}{p_end}
{p 4 8 2}{cmd:. misplit, clear}{p_end}
{p 4 8 2}{cmd:. mifit regress y x1 x2 x3}

{p 4 8 2}{cmd:. miset using imp, clear mimps(5)}{p_end}
{p 4 8 2}{cmd:. mijoin, clear}{p_end}
{p 4 8 2}{cmd:. micombine regress y x1 x2 x3}

{p 4 8 2}{cmd:. mijoin imp, clear m(5)}{p_end}
{p 4 8 2}{cmd:. save imp_mvis}{p_end}
{p 4 8 2}{cmd:. micombine regress y x1 x2 x3}


{title:Author}

{p 4 4 2}
Patrick Royston, MRC Clinical Trials Unit, London.
patrick.royston@ctu.mrc.ac.uk


{title:References}

{p 4 8 2}
Carlin, J. B., N. Li, P. Greenwood, and C. Coffey. 2003. 
Tools for analyzing multiple imputed datasets. {it:Stata Journal} 3(3):
226-244.


{title:Also see}

{p 4 13 2}
Online:  {helpb mvis}, {helpb micombine}, {helpb miset} (if installed)
{p_end}