{smcl} {* documented: June 12, 2007}{...} {* revised: February 12, 2012}{...} {cmd:help fmm postestimation} {right:also see: {helpb fmm} } {hline} {title:Title} {hi:fmm postestimation} {hline 2} Postestimation tools for {cmd:fmm} {title:Description} {pstd} The following postestimation commands are available for {opt fmm}: {synoptset 11}{...} {p2coldent :command}description{p_end} {synoptline} INCLUDE help post_estat INCLUDE help post_estimates INCLUDE help post_lincom INCLUDE help post_lrtest INCLUDE help post_margins INCLUDE help post_nlcom {synopt :{helpb fmm postestimation##predict:predict}}predictions including component probabilities{p_end} INCLUDE help post_test INCLUDE help post_testnl {synoptline} {p2colreset}{...} {marker predict}{...} {title:Syntax for predict} {p 8 16 2} {cmd:predict} {dtype} {newvar} {ifin} [{cmd:,} {it:statistic} {opt eq:uation(component#)}] {synoptset 11 tabbed}{...} {synopthdr :statistic} {synoptline} {syntab :Main} {synopt :{opt me:an}}predicted mean; the default{p_end} {synopt :{opt pri:or}}prior component probability{p_end} {synopt :{opt pos:terior}}posterior component probability{p_end} {synoptline} {p2colreset}{...} {p 4 6 2} Option {opt eq:uation(component#)} is required for {opt pri:or} and {opt pos:terior}. It is also required for {opt me:an} if predicted within-component means are desired. {p_end} INCLUDE help esample {title:Options for predict} {phang} {opt me:an}, the default, calculates the predicted mean. {pmore} To obtain within component means, specify the {opt eq:uation(component#)} option. {phang} {opt pri:or} calculates the prior component probabilities. With {opt prior}, {opt eq:uation(component#)} must also be specified. {phang} {opt pos:terior} calculates the posterior component probabilities. With {opt posterior}, {opt eq:uation(component#)} must also be specified. {title:Marginal effects} {pstd} Marginal effects can be calculated separately for the overall conditional mean as well as for within-component means, prior and posterior probabilities. To calculate marginal effects for within-component means, prior and posterior probabilities, run {cmd:margins} separately for each component, as shown in the examples below. Note that {cmd:fmm} has not been updated to accommodate factor variables. {title:Examples} {pstd}Mixture of normals {phang}{stata "webuse womenwk, clear" : . webuse womenwk, clear} {phang}{stata "fmm wagefull educ age married, mix(normal) comp(2)" : . fmm wagefull educ age married, mix(normal) comp(2)} {phang}{stata "predict wfhat" : . predict wfhat} {phang}{stata "predict wfhat1, eq(component1)" : . predict wfhat1, eq(component1)} {phang}{stata "predict wfhat2, eq(component2)" : . predict wfhat2, eq(component2)} {phang}{stata "predict wfhatpri, prior eq(component1)" : . predict wfhatpri, prior eq(component1)} {phang}{stata "predict wfhatpos, posterior eq(component1)" : . predict wfhatpos, posterior eq(component1)} {phang}{stata "sum wagefull wfhat*" : . sum wagefull wfhat*} {phang}{stata "drop wfhat*" : . drop wfhat*} {pstd}Mixture of Negative Binomials (Type 2) {phang}{stata "webuse medpar, clear" : . webuse medpar, clear} {phang}{stata "gen los0 = los - 1" : . gen los0 = los - 1} {phang}{stata "fmm los0 died hmo type2-type3, mix(negbin2) comp(2)" : . fmm exlos died hmo type2-type3, mix(negbin2) comp(2) comp(2)} {phang}{stata "predict wfhat" : . predict wfhat} {phang}{stata "predict l0hat1, eq(component1)" : . predict l0hat1, eq(component1)} {phang}{stata "predict l0hat2, eq(component2)" : . predict l0hat2, eq(component2)} {phang}{stata "predict l0hatpri, prior eq(component1)" : . predict l0hatpri, prior eq(component1)} {phang}{stata "predict l0hatpos, posterior eq(component1)" : . predict l0hatpos, posterior eq(component1)} {phang}{stata "sum los0 l0hat*" : . sum los0 l0hat*} {phang}{stata "drop l0hat*" : . drop l0hat*} {phang}{stata "margins, dydx(*) predict(eq(component1))" : . margins, dydx(*) predict(eq(component1))} {phang}{stata "margins, dydx(*) predict(eq(component2))" : . margins, dydx(*) predict(eq(component2))} {phang}{stata "margins, dydx(*)" : . margins, dydx(*)} {title:Also see} {psee} {helpb fmm}; {helpb estimates}, {helpb lincom}, {helpb lrtest}, {helpb margins}, {helpb nlcom}, {helpb predictnl}, {helpb suest}, {helpb test}, {helpb testnl} {p_end}