svy_logistic.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}
{* 29mar2005}{...}
{cmd:help svy: logistic}{...}
{right:dialog:  {bf:{dialog svy_logistic}}{space 16}}
{right:also see:  {help "svy: logistic postestimation"}}
{hline}

{title:Title}

{p2colset 5 28 30 2}{...}
{p2col :{hi:[SVY] svy: logistic} {hline 2}}Logistic
regression, reporting odds ratios, for survey data{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 42 2}
{cmd:svy} [{it:vcetype}]
	[{cmd:,} {it:svy_options}]
	{cmd::} {cmd:logistic} {depvar} [{indepvars}] {ifin}
	{bind:[{cmd:,} {it:options}]}


{synoptset 21 tabbed}{...}
INCLUDE help svy_optable


{synopthdr:options}
{synoptline}
{syntab:Model}
{synopt :{opt nocon:stant}}suppress the constant term{p_end}
{synopt :{opt off:set(varname)}}include
	{it:varname} in model with coefficient constrained to 1{p_end}
{synopt :{opt asis}}retain perfect predictor variables{p_end}

{syntab:Reporting}
{synopt :{opt coef}}report estimated coefficients{p_end}

{syntab:Max options}
{synopt :{it:maximize_options}}control
	the maximization process; seldom used{p_end}
{synoptline}
{p2colreset}{...}


{title:Description}

{pstd}
{cmd:svy: logistic} fits logistic regression models for complex survey data.
In the logistic regression model, {it:depvar} is a 0/1 variable (or, more
precisely, a 0/non-0 variable).

{pstd}
See {helpb logistic} for a description of this model involving nonsurvey data,
{helpb "svy: logit"} for logistic regression reporting coefficients,
{helpb "svy: probit"} for probit regression,
{helpb "svy: mlogit"} for multinomial logistic regression,
{helpb "svy: ologit"} for ordered logistic regression, and
{helpb "svy: oprobit"} for ordered probit regression for survey data.


{title:Options}

{phang}
{it:svy_options}; see {helpb svy}.

{dlgtab:Model}

{phang}
{opt noconstant}, {opt offset(varname)};
see {help estimation options}.

{phang}
{opt asis} forces retention of perfect predictor variables and their
associated perfectly predicted observations and may produce instabilities in
maximization; see {hi:[R] probit} (sic).

{dlgtab:Reporting}

{phang}
{opt coef} causes {cmd:svy: logistic} to report the estimated coefficients
rather than the odds ratios (exponentiated coefficients).  {opt coef} may be
specified when the model is fitted or used later to redisplay results.
{opt coef} affects only how the results are displayed and not how they are
estimated.

INCLUDE help svy_internal_maximize_options


{title:Examples}

{phang}
{cmd:. webuse nhanes2d}
{p_end}
{phang}
{cmd:. svydes}
{p_end}
{phang}
{cmd:. matrix h2 = (1, -1 \ 1, 1)}
{p_end}
{phang}
{cmd:. matrix h32 = h2 # h2 # h2 # h2 # h2}
{p_end}
{phang}
{cmd:. svy brr, hadamard(h32) nodots:}
{cmd:logistic highbp height weight age age2 female black}
{p_end}


{title:Also see}

{psee}
Manual:  {bf:[SVY] svy: logistic}

{psee}
Online:  {help "svy: logistic postestimation"};{break}
{helpb logistic},
{helpb "svy: logit"},
{helpb "svy: mlogit"},
{helpb "svy: ologit"},
{helpb "svy: oprobit"},
{helpb "svy: probit"}
{p_end}