{smcl}
{* 10Mar2008}{...}

cmd:help movestay}
{hline}

{title:Title}

{p2colset 5 20 22 2}{...}
{p2col :{hi: movestay} {hline 2}}Maximum-likelihood estimation of endogenous switching regression model{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 17 2}
{cmd:movestay}
({it:{help depvar:depvar0}} [=] {varlist:0}) ({it:depvar1 [=] varlist1})
{ifin}
{weight}
{cmd:,}
{cmdab:sel:ect:(}{it:depvar_s} [{cmd:=}] {it:varlist_s}{cmd:)}
[{it:{help movestay##options:options}}]


{title:Syntax for predict}

{p 8 16 2}
{cmd:predict}
{dtype}
{it:{help newvar}}
{ifin}
[{cmd:,} {it:statistic}]

{synoptset 11 tabbed}{...}
{synopthdr :statistic}
{synoptline}
{syntab :Main}
{synopt :{opt ps:el}} the probability of being in regime 1{p_end}
{synopt :{opt xb0}} fitted values for regime 0{p_end}
{synopt :{opt xb1}} fitted values for regime 1{p_end}
{synopt :{opt yc0}} fitted values for regime 1{p_end}
{synopt :{opt yc1}} fitted values for regime 1{p_end}
{synopt :{opt mills0}} Mills' ratio for regime 0{p_end}
{synopt :{opt mills1}} Mills' ratio for regime 1{p_end}
{synoptline}
{p2colreset}{...}


{synoptset 20 tabbed}{...}
{marker options}{...}
{synopthdr}
{synoptline}
{syntab :Model}
{synopt :{opt select()}} specify selection equation: dependent and independent variables{p_end}
{synopt :{opt col:linear}} keep collinear variables{p_end}

{syntab :SE/Robust}
{synopt :{opt r:obust}}robust estimator of variance{p_end}
{synopt :{opth cl:uster(varname)}}adjust standard errors for intragroup correlation{p_end}

{syntab :Reporting}
{synopt :{opt l:evel(#)}}set confidence level; default is {cmd:level(95)}{p_end}

{syntab :Max option}
{synopt :{it:{help movestay##maximize_options:maximize_options}}}control the maximization process;{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
{opt fweight}s, {opt iweight}s, and {opt pweight}s are allowed;see {help weight}.{p_end}


{title:Description}

{pstd}
{opt movestay} uses the maximum likelihood method to estimate the endogenous switching regression model.
It is implemented using the {cmd:d2} evaluator to calculate the overall log
likelihood together with its first and second derivatives.

{p 4 4 2}
{cmd:movestay} estimates all of the parameters in the model:

{p 8 8 2}(regression equation for regime 0: y0 is {it:depvar0}, x1 is {it:varlist0}){p_end}
{p 16 16 2}y0 = x0 * b0 + e_0

{p 8 8 2}(regression equation for regime 1: y1 is {it:depvar1}, x1 is {it:varlist1}){p_end}
{p 16 16 2}y1 = x1 * b1 + e_1

{p 8 8 2}(selection equation: Z is {it:varlist_s}){p_end}
{p 16 16 2}y0 observed if Zg + u <= 0{p_end}
{p 16 16 2}y1 observed if Zg + u > 0{p_end}


{p 8 8 2}where:{p_end}
{p 16 16 2}e_0 ~ N(0, sigma0){p_end}
{p 16 16 2}e_1 ~ N(0, sigma1){p_end}
{p 16 16 2}u   ~ N(0, 1){p_end}
{p 16 16 2}corr(e_0, u) = rho_0{p_end}
{p 16 16 2}corr(e_1, u) = rho_1{p_end}

{p 4 4 2}Here {it:depvar0}, {it:depvar1} and {it:varlist0}, {it:varlist1}
are the
dependent variables and regressors for the underlying regression models
(y0, y1 = xb), and {it:varlist_s} specifies the variables Z thought to determine
which regime is observed.


{title:Options}

{dlgtab:Model}

{phang}
{opt select()} specifies variables in the selection equation. {it:varlist_s}
includes the set of instruments that help identify the model.  This option is
an integral part of the {cmd:movestay} estimation and is required. The
selection equation is estimated based on all exogenous variables specified in
the continuous equations plus instruments.  If there are no instrumental
variables in the model, {it:depvar_s} must be specified.  In that case the
model will be identified by non-linearities and the selection equation will
contain all the independent variables that enter in the continuous equations.

{phang}
{opt collinear} see {help estimation options}.

{dlgtab:SE/Robust}

{phang}
{opt robust} specifies that the Huber/White/sandwich estimator of the
variance is to be used in place of the conventional MLE variance estimator.
{opt robust} combined with {opt cluster} further allows observations which
are not independent within cluster (although they must be independent between
clusters).

{pmore}
If you specify {cmd:pweight}s, {cmd:robust} is implied.
See {hi:[U] 23.14 Obtaining robust variance estimates}.

{phang}
{opth cluster(varname)} specifies that the observations are
independent across groups (clusters) but not necessarily within groups.
{it:varname} specifies to which group each observation belongs; e.g.,
{opt cluster(personid)} in data with repeated observations on individuals.
{opt cluster()} affects the estimated standard errors and variance-covariance
matrix of the estimators (VCE), but not the estimated coefficients.
{cmd:cluster()} can be used with {help pweight}s to produce estimates for
unstratified cluster-sampled data.  Specifying {cmd:cluster()} implies
{cmd:robust}.

{dlgtab:Reporting}

{phang}
{opt level(#)}; see {help estimation options}.

{marker maximize_options}{...}

{dlgtab:Max options}

{phang}
{it:maximize_options} control the maximization process; see
{help maximize}.  With the possible exception of {cmd:iterate(0)} and
{cmd:trace}, you should only have to specify them if the model is unstable.
The maximization uses option {cmd:difficult} by default. This option need not be specified.


{dlgtab: predict options}

{phang}
{opt psel} calculates the probability of being in regime 1.

{phang}
{opt xb0} calculates the linear prediction for equation 0.

{phang}
{opt xb1} calculates the linear prediction for equation 1.

{phang}
{opt yc0} returns the predicted value of the dependent variable(s) in the regime 0. For example,
if earning function is modeled for two sectors (regimes), then this option predicts the wage rate
in sector one for all individuals in the sample.

{phang}
{opt yc1} returns the predicted value of the dependent variable(s) in the regime 1.

{phang}
{opt mills0} and {opt mills1} calculate corresponding Mills' ratios for two regimes




{title:Examples}

{p 4 4 2}To obtain full ML estimates:

{p 6 6 2} Using instruments:

{p 8 8 2}{cmd:. movestay y1 x1 x2 x3 x4, select(regime1=z1 z2)}

{p 8 8 2}{cmd:. movestay (y1= x1 x2 x3 x4) (y1= x1 x2 x3 x5), select(regime1=z1 z2)}

{p 6 6 2}Model is identified through non-linearities:

{p 8 8 2}{cmd:. movestay (y1= x1 x2 x3 x4) (y1= x1 x2 x3 x5), select(regime1)}

{p 4 4 2}To define and use each equation separately:

{p 8 8 2}{cmd:. global wage_eqn y x1 x2 x3 x4}
{break}{cmd:. global select_eqn regime z1 z2}

{p 8 8 2}{cmd:. movestay ($wage_eqn), select($select_equn)}

{p 4 4 2}To use options:

{p 8 8 2}{cmd:. movestay y= x1 x2 x3 x4 if region=1 [w= hhweight], select(regime= z1 z2)}

{p 8 8 2}{cmd:. movestay (y= x1 x2 x3 x4) if region=1, select(regime= z1 z2) tech("dfp")}

{p 4 4 2}Prediction:

{p 8 8 2}{cmd:. movestay y x1 x2 x3 x4, select(regime= z1 z2)}

{p 8 8 2}{cmd:. predict yexpected, xb}

{p 8 8 2}{cmd:. predict mymills1, mills1}

{p 4 4 2}Example from the {it:Stata Journal}:

{p 8 8 2}{stata `"do http://siteresources.worldbank.org/INTPOVRES/Resources/movestay_example.do"': . movestay lmo_wage age age2 edu13 edu4 edu5 reg2 reg3 reg4, select(private =m_s1 job_hold)}


{title:Authors}

{p 4 4 2}M. Lokshin (DECRG, The World Bank) and Z. Sajaia (Stanford University).


{title:Also see}

{p 4 13 2}
Online:  help for {help regress}, {help heckman}, {help ml}