{smcl}
{* 2mar2013}{...}
{hline}
help for {hi:alignmicro}{right:Jinjing Li (2 Mar 2014)}
{hline}

{title:Stata module to perform alignment in microsimulation}

{p 4 12}{cmd:alignmicro} {it:varname} [{cmd:if} {it:exp}]
	{cmd:,} {cmdab:target(}{it:number}{cmd:)} {cmdab:outcome(}{it:varname}{cmd:)} 
	{cmdab:method(}{it:name}{cmd:)}


{title:Description}

{p}{cmd:alignmicro} implements some common microsimulation alignment algorithms for binary variables as described in Li and O'Donoghue (2014).
The command creates a binary variable as an output, based on the observation's original probability, overall target probability, and the alignment method selected.

{title:Options}

{p 0 4}{cmd:varname} specifies the original probability variable. 

{p 0 4}{cmd:target(}{it:number}{cmd:)} specifies the alignment target. If the target is a probability value (0~1), the specified proportion of the 
observations will be selected. If the target is an integer value greater than one, the specified number of observations will be selected.

{p 0 4}{cmd:outcome(}{it:varname}{cmd:)} specifies the outcome variable name.

{p 0 4}{cmd:method(}{it:varname}{cmd:)} specifies the alignment method. The following methods are supported.

{p 4 4} {it:ms}: multiplicative scaling {break}
{it:sidewalk}: Sidewalk method (original) {break}
{it:sidewalknl}: Sidewalk method with non-linear adjustment (eta = 0.5, lambda = 0.03){break}
{it:clt}: Central limit theorem approach {break}
{it:sbp}: Sort by predicted probability {break}
{it:sbd}: Sort by the difference between predicted probability and random number {break}
{it:sbdl}: Sort by the difference between logistic adjusted predicted probability and random number

{title:Return Values}

{p 4 4} {it:r(ctime)} reports the total number of seconds used in the alignment operation. {break}
 {it:r(method)} reports the method used.
{break}

{title:Examples}

{p 8 8 2}{inp:clear}{break}{inp:set obs 1000}{break}
{inp:gen simprob = uniform()}{break}
{inp: alignmicro simprob, target(0.8) outcome(out) method(sbp)}{break}
{inp:alignmicro simprob, target(200) outcome(out2) method(sbdl)}


{title:Author}

{p 4 4}Jinjing Li, The National Centre for Social and Economic Modelling (NATSEM), The Institute for Governance and Policy Analysis (IGPA), University of Canberra, Australia{break}
{browse "mailto:jinjing.li@canberra.edu.au"}


{title:Reference}

{p 4 8} Li, J., & O'Donoghue, C. (2014). Evaluating Binary Alignment Methods in Dynamic Microsimulation Models. 
{it:Journal of Artificial Society and Simulation}, 17(1) {break}
{browse "http://ideas.repec.org/a/jas/jasssj/2013-16-3.html"}