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

Title

    [R] mlogit -- Multinomial (polytomous) logistic regression


Syntax

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

    options                 description
    -----------------------------------------------------------------------------------------------------------
    Main
      noconstant            suppress constant term
      baseoutcome(#)        value of depvar that will be the base outcome
      constraints(clist)    apply specified linear constraints; clist has the form #[-#][,#[-#] ... ]
      collinear             keep collinear variables

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

    Reporting
      level(#)              set confidence level; default is level(95)
      rrr                   report relative-risk ratios
      nocnsreport           do not display constraints
      display_options       control spacing and display of omitted variables and base and empty cells

    Maximization
      maximize_options      control the maximization process; seldom used

    + coeflegend            display coefficients' legend instead of coefficient table
    -----------------------------------------------------------------------------------------------------------
    + coeflegend does not appear in the dialog box.
    indepvars may contain factor variables; see fvvarlist.
    indepvars may contain time-series operators; see tsvarlist.
    bootstrap, by, fracpoly, jackknife, mfp, mi estimate, rolling, statsby, and svy are allowed; see prefix.
    vce(bootstrap) and vce(jackknife) are not allowed with the mi estimate 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] mlogit postestimation for features available after estimation.


Menu

    Statistics > Categorical outcomes > Multinomial logistic regression


Description

    mlogit fits maximum-likelihood multinomial logit models, also known as polytomous logistic regression.  You
    can define constraints to perform constrained estimation.  Some people refer to conditional logistic
    regression as multinomial logit.  If you are one of them, see [R] clogit.

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


Options

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

    noconstant; see [R] estimation options.

    baseoutcome(#) specifies the value of depvar to be treated as the base outcome.  The default is to choose
        the most frequent outcome.

    constraints(clist), collinear; 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.

        If specifying vce(bootstrap) or vce(jackknife), you must also specify baseoutcome().

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

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

    rrr reports the estimated coefficients transformed to relative-risk ratios, i.e., exp(b) rather than b.
        Standard errors and confidence intervals are similarly transformed.  This option affects how results
        are displayed, not how they are estimated.  rrr may be specified at estimation or when replaying
        previously estimated results.

    nocnsreport; see [R] estimation options.

    display_options:  noomitted, vsquish, noemptycells, baselevels, allbaselevels; see [R] estimation options.

        +--------------+
    ----+ Maximization +---------------------------------------------------------------------------------------

    maximize_options:  difficult, technique(algorithm_spec), iterate(#), [no]log, trace, gradient, showstep,
        hessian, showtolerance, tolerance(#), ltolerance(#), nrtolerance(#), nonrtolerance, from(init_specs);
        see [R] maximize.  These options are seldom used.

    The following option is available with mlogit but is not shown in the dialog box:

    coeflegend; see [R] estimation options.


Examples

    Setup
        . webuse sysdsn1

    Fit multinomial logistic regression model
        . mlogit insure age male nonwhite i.site

    Same as above, but use 2 as the base outcome
        . mlogit insure age male nonwhite i.site, base(2)

    Replay, reporting relative-risk ratios
        . mlogit, rrr

    Setup
        . constraint 1 [Uninsure]
        . constraint 2 [Prepaid]: 2.site 3.site

    Fit multinomial logistic regression model with constraints
        . mlogit insure age male nonwhite i.site, constraint(1)
        . mlogit insure age male nonwhite i.site, constraint(2)
        . mlogit insure age male nonwhite i.site, constraint(1/2)