slogit.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* *! version 1.0.0  24may2005}{...}
{cmd:help slogit} {right:dialog:  {bf:{dialog slogit}} {space 14}}
{right:also see:  {help slogit postestimation}}
{hline}

{title:Title}

{p2colset 5 19 21 2}{...}
{p2col:{hi:[R] slogit} {hline 2}}Stereotype logistic regression{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 15 2}
{cmd:slogit}
{depvar}
[{indepvars}]
{ifin}
{weight}
[{cmd:,} {it:options}]

{synoptset 22 tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Model}
{synopt:{opt dim:ension(#)}}dimension of the model; default is
{cmd:dimension(1)}{p_end}
{synopt:{opt b:aseoutcome(#|lbl)}}set the base outcome to {it:#} or {it:lbl};
default is the last outcome{p_end}
{synopt:{opt const:raints(numlist)}}apply specified linear constraints{p_end}
{synopt:{opt nocorn:er}}do not apply the corner constraints to the scale
parameters{p_end}

{syntab:SE/Robust}
{synopt:{opth vce(vcetype)}}{it:vcetype} may be {opt oim}, {opt r:obust},
{opt opg}, {opt boot:strap}, or {opt jack:knife}{p_end}
{synopt:{opt r:obust}}synonym for {cmd:vce(robust)}{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 options}
{synopt:{it:{help slogit##maximize_options:maximize_options}}}control the
maximization process; seldom used{p_end}
{synopt:{opt init:ialize(initype)}}method of initializing scale parameters;
{it:initype} can be {opt constant}, {opt random}, or {opt svd}; see
{helpb slogit##initialize:Options} for details{p_end}
{synopt:{opt nonorm:alize}}do not normalize the numeric variables{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
{cmd:bootstrap}, {cmd:by}, {cmd:jackknife}, {cmd:rolling}, {cmd:statsby}, and
    {cmd:xi} are allowed; see {help prefix}.{p_end}
{p 4 6 2}
{cmd:fweight}s, {cmd:iweight}s, and {cmd:pweight}s are allowed; see {help weight}.{p_end}
{p 4 6 2}
See {help slogit postestimation} for features available after estimation.{p_end}


{title:Description}

{pstd}
{opt slogit} fits maximum-likelihood stereotype regression models.
Like multinomial logistic and ordered logistic models,
stereotype logistic models are for use with categorical dependent variables.
In a multinomial logistic model, the categories cannot be ranked, while in an
ordered logistic model the categories follow a natural ranking scheme.  You
can view stereotype logistic models as a compromise between those two models.
You can use them when you are unsure of the relevance of the ordering, as is
often the case when subjects are asked to assess or judge something.  You can
also use them in place of multinomial logistic models when you suspect some
of the alternatives are similar.  Unlike ordered logistic models, stereotype
logistic models do not impose the proportional odds assumption.


{title:Options}

{dlgtab:Model}

{phang}
{opt dimension(#)} specifies the dimension of the model, which is the number
of equations required to describe the relationship between the dependent
variable and the independent variables.  The maximum dimension is min(m-1,p)
where m is the number of categories of dependent variables and p is the number
of independent variables in the model.  The stereotype model with maximum
dimension is a reparameterization of the multinomial logistic model.

{phang}
{opt baseoutcome(#|lbl)} specifies the outcome level whose scale parameters
and intercept are constrained to be zero.  
Note that the base outcome may be specified as a number or a label.
By default, {opt slogit} assumes the outcome levels are ordered and uses the
largest level of the dependent variable as the base outcome.

{phang}
{opt constraints(numlist)}; see
 {help estimation options##constraints():estimation options}.

{pmore}
By default, the linear equality constraints suggested by Anderson, termed the
corner constraints, are generated for you.  You can add additional constraints
to these, as needed, or you can turn off the corner constraints altogether by
specifying {opt nocorner}.

{phang}
{opt nocorner} specifies that {opt slogit} not generate the corner constraints.
If you specify {opt nocorner}, you must specify
at least {cmd:dimension()}*{cmd:dimension()} 
constraints for the model to be identified.

{dlgtab:SE/Robust}

{phang}
{opth vce(vcetype)}; see {it:{help vce_option}}.

{phang}
{opt robust}, {opth cluster(varname)}; see 
   {help estimation options##robust:estimation options}.

{dlgtab:Reporting}

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

{marker maximize_options}{...}
{dlgtab:Max options}

{phang}
{it:maximize_options}:
{opt diff:icult},
{opt tech:nique(algorithm_spec)},
{opt iter:ate(#)},
[{cmdab:no:}]{opt lo:g},
{opt tr:ace},
{opt grad:ient},
{opt showstep},
{opt hess:ian},
{opt shownr:tolerance},
{opt tol:erance(#)},
{opt ltol:erance(#)},
{opt gtol:erance(#)},
{opt nrtol:erance(#)},
{opt nonrtol:erance(#)},
{opt from(init_specs)};
see {help maximize}.  These options are seldom used.

{marker initialize}{...}
{phang}
{cmd:initialize(}{opt const:ant}|{opt rand:om}|{opt svd}{cmd:)}
specifies how initial estimates are computed.  The default,
{cmd:initialize(constant)}, is to set the scale parameters to the constant
min(.5,1/d), where d is the dimension specified in {cmd:dimension()}.

{phang2}
{cmd:initialize(random)} requests that 
uniformly distributed random numbers between 0 and 1 be used as initial values
for the scale parameters.  If you specify this option, you should also use
{bind:{cmd:set seed}} to ensure that you can replicate your results (see
{helpb generate}).

{phang2}
{cmd:initialize(svd)}
option requests that a singular value decomposition be performed on the matrix
of regression estimates from {opt mlogit} to reduce its rank to the dimension
specified in {opt dimension()}.  {opt slogit} uses the reduced-rank components
of the SVD as initial estimates for the scale and regression coefficients to
initialize the scale parameters to a set of orthonormal vectors that are
orthogonal across dimensions.

{phang}
{opt nonormalize} specifies that the numeric variables not be normalized.
Normalization
of the numeric variables improves numerical stability but consumes more
memory in generating temporary double-precision variables.  Variables that are
of type {opt byte} are not normalized, and if initial estimates are specified
using the {opt from()} option, normalization of variables is not performed.


{title:Examples}

{phang}{cmd:. webuse auto2yr}{p_end}

{phang}{cmd:. slogit repair foreign mpg price gratio}{p_end}


{title:Also see}

{psee}
Manual: {bf:[R] slogit}

{psee}
Online:  {help slogit postestimation};{break}
{helpb mlogit},
{helpb ologit},
{helpb oprobit},
{helpb roc}
{p_end}