{smcl}
{* 06.05.2013}{...}
help {hi:lcmc}
{hline}
{title:Title}
{p 8 12 2} Latent class missing covariate model for continous main response, ordinal covariate with missing values, and informative selection
{title:Basic syntax}
{p 8 12 2}{cmd:lcmc} ({it:svar} = {it:varlist1}) ({it:yvar} = {it:varlist2}) ({it:mcvvar} = {it:varlist3}) [{cmd:if}
{it:exp}] [{cmd:in} {it:range}] {p_end}
{title:Full syntax}
{p 8 12 2}{cmd:lcmc} ({it:svar} = {it:varlist1}) ({it:yvar} = {it:varlist2}) ({it:mcvvar} = {it:varlist3}) [{cmd:if}
{it:exp}] [{cmd:in} {it:range}] [{cmd:,} {cmd:rep(#)} {cmdab:sc:ale}(#) {cmdab:hvec:tor}(# # #) {cmdab:meth:od}(#)
{cmdab:from}({it:matrixname}) {cmd:cluster}({it:clustvar})
{cmdab:constr:aints}({it:clist}) {cmdab:thres:ctr} {cmdab:hb:ased} {cmdab:tr:ace}
{cmdab:eval:uate} {cmdab:rob:ust} {cmdab:iter:ate}(#) {cmd:mloptions}]{p_end}
{p 0 0 2} The first equation defines the model for the selection dummy, the second equation defines the model for the main continous response, and the third equation definies the model for the missing ordinal covariate (see description). {p_end}
{marker options}{...}
{synopthdr:options}
{synoptline}
{p2coldent : {opt rep(#)} } Sets the number of random draws that will be used for calculating the simulated likelihood. The default value is 1600. {p_end}
{p2coldent : {opt scale(#)}} Sets the standard deviation of the error terms uy, ux, and us in equation 4 of Miranda & Rabe-Hesketh (2014). The default
value is 0.2. {p_end}
{p2coldent : {opt hvec:tor(# # # #)}} Controls aspects of the simulation, all four numbers must be integers. Two random vectors of size N
are needed to perform the simulation of the likelihood. These two vectors are chosen from a random NxQ matrix, Q>=2. The first number
of {opt hvec} sets Q while the second and third numbers indicate which columns will be used to simulate the likelihood. Finally, the third
number sets the number of rows -from the top row onwards- to be
discarded from the chosen columns. For instance, {opt rep(500)} {opt hvec(2 1 2 100)} asks for a 500x2 random matrix, to take the
first and second columns for the simulation of the likelihood and to discard 100 rows. The resulting 400x2 random matrix is
used for simulating the likelihood. The default values are {opt hvec(2 1 2 100)}.{p_end}
{p2coldent : {cmdab:meth:od}(#)} Type of random draws to be used for simulating the likelihood. Option 1 indicates that Halton sequences shall be used. Option 2 indicates that a Hammersley set should be used.
Finally, option 3 indicates that pseudouniform random numbers should be used. The default value is 1.{p_end}
{p2coldent : {cmdab:from}({it:matname})} Specifies the matrix to be used for the initial values. The matrix may be obtained from a previous
estimation command using e(b). This is useful if the model was first estimated constraining the thresholds to be
cut1