estimation_options.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}
{* 08apr2005}{...}
{cmd:help estimation options}
{hline}

{title:Title}

{p2colset 5 31 33 2}{...}
{p2col :{hi:[R] estimation options} {hline 2}}Estimation options{p_end}


{title:Description}

{pstd}
This entry describes the options common to many estimation commands.
Not all the options documented below work with all estimation commands;
see the documentation for the particular estimation command.  If an
option is listed there, it is applicable.


{title:Options}

{dlgtab:Model}

{phang}
{marker noconstant}{...}
{opt noconstant}
suppresses the constant term (intercept) in the model.

{phang}
{marker offset()}{...}
{opth offset(varname)} specifies that {it:varname} be included in the
model with the coefficient constrained to be 1.

{phang}
{marker exposure()}{...}
{opth exposure(varname)}
specifies a variable that reflects the amount of exposure over
which the {depvar} events were observed for each observation;
ln({it:varname}) with coefficient constrained to be 1 is entered into the
log-link function.

{phang}
{marker constraints()}
{cmd:constraints(}{it:{help numlist}}{c |}{it:matname}{cmd:)}
specifies the linear constraints to be applied during estimation.
The default is to perform unconstrained estimation.  
{opt constraints(numlist)} specifies the constraints by number after they
have been defined using the {helpb constraint} command.  
See {helpb reg3} for the use of constraints in multiple-equation contexts.

{pmore}
{opt constraints(matname)} specifies a matrix containing the constraints; 
see {helpb matrix constraint}.

{pmore}
{opt constraints(clist)} is used by some estimation commands, such as
{helpb mlogit}, where {it:clist} has the form
{bind:{it:#}[{cmd:-}{it:#}][{cmd:,}{it:#}[{cmd:-}{it:#}] {it:...} ]}.

{phang}
{marker i()}
{opt i(varname_i)} specifies the variable name that contains the unit to which
the observation belongs.  You can specify the {cmd:i()} option the first time
you estimate, or you can use the {cmd:iis} command to set {cmd:i()}
beforehand.  Note that you need not specify {cmd:i()} if the data have been
previously {cmd:tsset} or if {cmd:iis} has been previously
specified{hline 2}in these cases, the group variable is taken from the
previous setting.  See {help xt}.

{phang}
{marker t()}
{opt t(varname_t)} specifies the variable name that contains the time
period to which the observation belongs.  You can specify the {cmd:t()}
option the first time you estimate, or you can use the {cmd:tis} command to
set {cmd:t()} beforehand.  Note that you need not specify {cmd:t()}
if the data have been previously {cmd:tsset} or if {cmd:tis} has been
previously specified{hline 2}in these cases, the group variable is taken from
the previous setting.  See {help xt}.

{phang}
{marker quad()}
{opt quad(#)} specifies the number of points to use in the quadrature
approximation of the integral.  The number specified must be an integer
between 4 and 30 and {it:#} must be no greater than the number of
observations.  The default is {cmd:quad(12)}.

{phang}
{marker force}
{opt force} specifies that estimation is to be forced even though {opt t()} is
not equally spaced.  This is relevant only for correlation structures that
require knowledge of {opt t()}.  These correlation structures require that
observations be equally spaced so that calculations based on lags correspond
to a constant time change.  If you specify a {opt t()} variable that indicates
observations are not equally spaced, the (time-dependent) model will not be
fitted.  If you also specify {opt force}, the model will be fitted, and it
will be assumed that the lags based on the data ordered by {opt t()} are
appropriate.

{marker corr()}{...}
{dlgtab:Correlation}

{phang}
{opt corr(correlation)} specifies the within-group correlation
structure; the default corresponds to the equal-correlation model,
{cmd:corr(exchangeable)}.

{pmore}
When you specify a correlation structure that requires a lag, you indicate the
lag after the structure's name with or without a blank; e.g., {cmd:corr(ar1)}
or {cmd:corr(ar1)}.

{pmore}
If you specify the fixed correlation structure, you specify the name of the
matrix containing the assumed correlations following the word {cmd:fixed},
e.g., {cmd:corr(fixed myr)}.

{dlgtab:SE/Robust}

{phang}
{marker robust}{...}
{opt robust} specifies that the Huber/White/sandwich estimator of variance be
used in place of the traditional calculation; see 
{bf:[U] 20.14 Obtaining robust variance estimates}. {opt robust} combined
with {opt cluster()} allows observations that are not independent within
cluster (although they must be independent between clusters).

{pmore}
If the command allows {opt pweight}s and you specify them, {opt robust}
is implied; see {bind:{bf:[U] 20.16 Weighted estimation}}.

{pmore}
{cmd:vce(robust)} is a synonym for {cmd:robust}.

{phang}
{marker cluster()}{...}
{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., {cmd:cluster(personid)} in data
with repeated observations on individuals.  {opt cluster()} affects the
estimated standard errors and variance{c -}covariance matrix of the estimators
(VCE), but not the estimated coefficients; see 
{bf:[U] 20.14 Obtaining robust variance estimates}.

{pmore}
{opt cluster()} implies {opt robust}; specifying {opt robust cluster()} is
equivalent to typing {cmd:cluster()} by itself.

{phang}
{marker scale()}
{cmd:scale(x2}|{cmd:dev}|{cmd:phi}|{it:#}{cmd:)} overrides the default
scale parameter.  By default, {cmd:scale(1)} is assumed for the discrete
distributions (binomial, negative binomial, and Poisson), and {cmd:scale(x2)}
is assumed for the continuous distributions (gamma, Gaussian, and inverse
Gaussian).

{pmore}
{cmd:scale(x2)} specifies that the scale parameter be set to the Pearson
chi-squared (or generalized chi-squared) statistic divided by the residual
degrees of freedom, which is recommended by McCullagh and Nelder as a
good general choice for continuous distributions.

{pmore}
{cmd:scale(dev)} sets the scale parameter to the deviance divided by the
residual degrees of freedom. This provides an alternative to {cmd:scale(x2)}
for continuous distributions and for over- or underdispersed discrete
distributions.

{pmore}
{cmd:scale(phi)} specifies that the scale parameter be estimated from the data.
{cmd:xtgee}'s default scaling makes results agree with other estimators and
has been recommended by McCullagh and Nelder in the context of
GLM.  When comparing results with calculations made by other software,
you may find that the other packages do not offer this feature.  In such
cases, specifying {cmd:scale(phi)} should match their results.

{pmore}
{opt scale(#)} sets the scale parameter to {it:#}. For example,
using {cmd:scale(1)} in {cmd:family(gamma)} models results in
exponential-errors regression (if you use assume independent correlation
structure).

{phang}
{marker nmp}
{opt nmp} specifies that the divisor N-P be used instead of the
default N, where N is the total number of observations and P is the
number of coefficients estimated.

{dlgtab:Reporting}

{phang}
{marker level()}{...}
{opt level(#)}
specifies the confidence level, as a percentage, for confidence intervals.
The default is {cmd:level(95)} or as set by {helpb set level}; see
{bf:[U] 20.6 Specifying the width of confidence intervals}.

{phang}
{marker noskip}
{opt noskip} specifies that a full maximum-likelihood model with only a constant
    for the regression equation be fitted.  This model is not displayed but
    is used as the base model to compute a likelihood-ratio test for the model
    test statistic displayed in the estimation header.  By default, the
    overall model test statistic is an asymptotically equivalent Wald test of
    all the parameters in the regression equation being zero (except the
    constant).  For many models, this option can substantially increase
    estimation time.


{title:Also see}

{psee}
Manual:  {bf:[R] estimation options},{break}
	 {bf:[ST] estimation options},{break}
	 {bf:[SVY] estimation options},{break} 
	 {bf:[TS] estimation options},{break}
	 {bf:[XT] estimation options}

{psee}
Online:  {help estimation commands}
{p_end}