stata里面有oprobit命令

help oprobit                                                                        dialogs:  oprobit  svy: oprobit
                                                                                   also see:  oprobit postestimation
--------------------------------------------------------------------------------------------------------------------

Title

    [R] oprobit -- Ordered probit regression

Syntax

        oprobit depvar [indepvars] [if] [in] [weight] [, options]

    options               description
    --------------------------------------------------------------------------------------------------------------
    Model
      offset(varname)     include varname in model with coefficient constrained to 1

    SE/Robust
      vce(vcetype)        vcetype may be oim, robust, cluster clustvar, bootstrap, or jackknife

    Reporting
      level(#)            set confidence level; default is level(95)

    Max option
      maximize_options    control the maximization process; seldom used
    --------------------------------------------------------------------------------------------------------------
    bootstrap, by, jackknife, nestreg, rolling, statsby, stepwise, svy, and xi are allowed; see prefix.
    Weights are not allowed with the bootstrap prefix.
    vce() and weights are not allowed with the svy prefix.
    fweights, iweights, and pweights are allowed; see weight.
    See [R] oprobit postestimation for features available after estimation.

Description

    oprobit fits ordered probit models of ordinal variable depvar on the independent variables indepvars.  The
    actual values taken on by the dependent variable are irrelevant, except that larger values are assumed to
    correspond to "higher" outcomes.  Up to 50 outcomes are allowed in Stata/MP, Stata/SE, and Stata/IC, and up to
    20 outcomes in Small Stata.

    See logistic estimation commands for a list of related estimation commands.

Options

        +-------+
    ----+ Model +-------------------------------------------------------------------------------------------------

    offset(varname); see [R] estimation options.

        +-----------+
    ----+ SE/Robust +---------------------------------------------------------------------------------------------

    vce(vcetype) specifies the type of standard error reported, which includes types that are derived from
        asymptotic theory, that are robust to some kinds of misspecification, that allow for intragroup
        correlation, and that use bootstrap or jackknife methods; see [R] vce_option.

        +-----------+
    ----+ Reporting +---------------------------------------------------------------------------------------------

    level(#); see [R] estimation options.

        +-------------+
    ----+ Max options +-------------------------------------------------------------------------------------------

    maximize_options:  iterate(#), [no]log, trace, tolerance(#), ltolerance(#), nrtolerance(#), nonrtolerance; see
        >  [R] maximize.  These options are seldom used.

Example

    ----------------------------------------------------------------------------------------------------------------
    Setup
        . webuse fullauto

    Ordered probit regression
        . oprobit rep77 foreign length mpg

    ----------------------------------------------------------------------------------------------------------------
    Setup
        . webuse nhanes2f
        . svyset psuid [pw=finalwgt], strata(stratid)

    Ordered probit regression using survey data
        . svy: oprobit health female black age age2
    ----------------------------------------------------------------------------------------------------------------

Saved Results

    oprobit saves the following in e():

    Scalars  
      e(N)           number of observations
      e(k_cat)       number of categories
      e(N_cd)        number of completely determined observations
      e(k_eq)        number of equations in e(b)
      e(k_aux)       number of auxiliary parameters
      e(df_m)        model degrees of freedom
      e(r2_p)        pseudo-R-squared
      e(ll)          log likelihood
      e(ll_0)        log likelihood, constant-only model
      e(N_clust)     number of clusters
      e(chi2)        chi-squared
      e(converged)   1 if converged, 0 otherwise

    Macros   
      e(cmd)         oprobit
      e(cmdline)     command as typed
      e(depvar)      name of dependent variable
      e(wtype)       weight type
      e(wexp)        weight expression
      e(title)       title in estimation output
      e(clustvar)    name of cluster variable
      e(offset)      offset
      e(chi2type)    Wald or LR; type of model chi-squared test
      e(crittype)    optimization criterion
      e(vce)         vcetype specified in vce()
      e(vcetype)     title used to label Std. Err.
      e(predict)     program used to implement predict
      e(properties)  b V

    Matrices 
      e(b)           coefficient vector
      e(cat)         category values
      e(V)           variance-covariance matrix of the estimators

    Functions
      e(sample)      marks estimation sample

Also see

    Manual:  [R] oprobit

    Online:  [R] oprobit postestimation;
             [R] logistic, [R] mlogit, [R] mprobit, [R] ologit, [R] probit, [SVY] svy estimation