ca_postestimation.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}
{* 04may2005}{...}
{cmd:help ca postestimation}{...}
{right:dialogs:  {bf:{dialog ca_p:predict}  {dialog ca_estat:estat}}{space 8}}
{right:{bf:{dialog cabiplot}  {dialog caprojection}}}
{right:also see:  {bf:{help ca}}{space 20}}
{hline}

{title:Title}

{p 4 32 2}
{hi:[MV] ca postestimation} {hline 2} Postestimation tools for {cmd:ca} and
{cmd:camat}


{title:Description}

{pstd}
The following postestimation commands are of special interest after {cmd:ca}
and {cmd:camat}.

{synoptset 21 tabbed}{...}
{p2coldent:command}description{p_end}
{synoptline}
{synopt:{helpb ca postestimation##cabiplot:cabiplot}}biplot of row and column
	points{p_end}
{synopt:{helpb ca postestimation##caprojection:caprojection}}CA dimension
	projection plot{p_end}
{synopt:{helpb ca postestimation##estat:estat coordinates}}display row and
	column coordinates{p_end}
{synopt:{helpb ca postestimation##estat:estat distances}}display chi-squared
	distances between row and column profiles{p_end}
{synopt:{helpb ca postestimation##estat:estat inertia}}display inertia
	contributions of the individual cells{p_end}
{synopt:{helpb ca postestimation##estat:estat profiles}}display row and column
	profiles{p_end}
{p2coldent:+ {helpb ca postestimation##estat:estat summarize}}estimation sample
	summary{p_end}
{synopt:{helpb ca postestimation##estat:estat table}}display fitted
	correspondence table{p_end}
{synopt:{helpb screeplot}}plot singular values{p_end}
{synoptline}
{p 4 6 2}
+ {cmd:estat summarize} is not available after {cmd:camat}.

{pstd}
In addition, the following standard postestimation commands are available:

{p2coldent:command}description{p_end}
{synoptline}
{p2coldent:* {helpb estimates}}cataloging estimation results{p_end}
{p2coldent:+ {helpb ca postestimation##predict:predict}}fitted values, row
	coordinates, or column coordinates{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
* All {cmd:estimates} subcommands except {opt table} and {opt stats} are
available.
{p_end}
{p 4 6 2}
+ {cmd:predict} is not available after {cmd:camat}.


{title:Special-interest postestimation commands}

{pstd}
{cmd:cabiplot}
produces a plot of the row points, column points, or a biplot of the row and
column points.  In this plot, the (Euclidean) distances between row (column)
points approximates the chi-squared distances between the associated row
(column) profiles if the CA is properly normalized.  Similarly, the
association between a row and column point is approximated by the inner
product of vectors from the origin to the respective points (see {helpb ca}).

{pstd}
{cmd:caprojection}
produces a line plot of the row and column coordinates.  The goal of this
graph is to show the ordering of row and column categories on each principal
dimension of the analysis.  Each principal dimension is represented by a
vertical line; markers are plotted on the lines where the row and column
categories project onto the dimensions.

{pstd}
{cmd:estat coordinates}
displays the row and column coordinates.

{pstd}
{cmd:estat distances}
displays the chi-squared distances between the row profiles and between the
column profiles.  In addition, the chi-squared distances between the row and
column profiles to the respective centers (marginal distributions) are
displayed.  The fitted profiles rather than the observed profiles
are used.

{pstd}
{cmd:estat inertia}
displays the inertia (= chi2/N) contributions of the individual cells.

{pstd}
{cmd:estat profiles}
displays the row and column profiles; the row (column) profile is the
conditional distribution of the row (column) given the column (row).  This is
equivalent to specifying the {cmd:row} and {cmd:column} options with the
{helpb tabulate} command.

{pstd}
{cmd:estat summarize}
displays summary information about the row and column variables over the
estimation sample.

{pstd}
{cmd:estat table}
displays the fitted correspondence table.  Optionally the observed
"correspondence table" and the expected table under independence are
displayed.


{marker predict}{...}
{title:Syntax for predict}

{p 8 16 2}
{cmd:predict} {dtype} {newvar} {ifin} [{cmd:,} {it:statistic} ]

{synoptset 15 tabbed}{...}
{synopthdr:statistic}
{synoptline}
{syntab:Main}
{synopt:{opt f:it}}fitted values; the default{p_end}
{synopt:{opt row:score(#)}}row score for dimension {it:#}{p_end}
{synopt:{opt col:score(#)}}column score for dimension {it:#}{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
{cmd:predict} is available after {cmd:ca} only, not {cmd:camat}.


{title:Options for predict}

{dlgtab:Main}

{phang}{opt fit}
specifies that fitted values for the correspondence analysis model are
computed.  {opt fit} is the default.

{phang}{opt rowscore(#)}
generates the row score for dimension {it:#}, i.e., the appropriate elements
from the normalized row coordinates.

{phang}{opt colscore(#)}
generates the column score for dimension {it:#}, i.e., the appropriate
elements from the normalized column coordinates.


{marker estat}{...}
{title:Syntax for estat}

{pstd}
Display row and column coordinates

{p 8 14 2}
{cmd:estat} {opt co:ordinates} [{cmd:,} {opt norow} {opt nocol:umn}
	{opth for:mat(%fmt)} ]

{pstd}
Display chi-squared distances between row and column profiles

{p 8 14 2}
{cmd:estat} {opt di:stances} [{cmd:,} {opt norow} {opt nocol:umn}
	{opt ap:prox} {opth for:mat(%fmt)} ]

{pstd}
Display inertia contributions of cells

{p 8 14 2}
{cmd:estat} {opt in:ertia} [{cmd:,} {opt to:tal} {opt nosc:ale}
	{opth for:mat(%fmt)} ]

{pstd}
Display row and column profiles

{p 8 14 2}
{cmd:estat} {opt pr:ofiles} [{cmd:,} {opt norow} {opt nocol:umn}
	{opth for:mat(%fmt)} ]

{pstd}
Display summary information

{p 8 14 2}
{cmd:estat} {opt su:mmarize} [{cmd:,} {opt lab:els} {opt nohea:der}
	{opt nowei:ghts} ]

{pstd}
Display fitted correspondence table

{p 8 14 2}
{cmd:estat} {opt ta:ble} [{cmd:,}
	{opt fit} {opt obs} {opt in:dependence} {opt nosc:ale}
	{opth for:mat(%fmt)} ]

{synoptset 16 tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Main}
{synopt:{opt norow}}suppress display of row results{p_end}
{synopt:{opt nocol:umn}}suppress display of column results{p_end}
{synopt:{opth for:mat(%fmt)}}display format; default is
	{cmd:format(%9.4f)}{p_end}
{synopt:{opt ap:prox}}display distances between fitted (approximated)
	profiles{p_end}
{synopt:{opt to:tal}}add row and column margins{p_end}
{synopt:{opt nosc:ale}}display chi-squared
	contributions; default is inertias = chi2/N 
	(with {cmd:estat inertia}) {p_end}
{synopt:{opt lab:els}}display variable labels{p_end}
{synopt:{opt nohea:der}}suppress the header{p_end}
{synopt:{opt nowei:ghts}}ignore weights{p_end}
{synopt:{opt fit}}display fitted values from CA model{p_end}
{synopt:{opt obs}}display correspondence table ("observed table"){p_end}
{synopt:{opt in:dependence}}display expected values under independence{p_end}
{synopt:{opt nosc:ale}}suppress scaling of entries
	to 1 (with {cmd:estat table}) {p_end}
{synoptline}
{p2colreset}{...}


{title:Options for estat}

{dlgtab:Main}

{phang}{opt norow},
an option used with {cmd:estat coordinates}, {cmd:estat distances}, and
{cmd:estat profiles}, suppresses the display of row results.

{phang}{opt nocolumn},
an option used with {cmd:estat coordinates}, {cmd:estat distances}, and
{cmd:estat profiles}, suppresses the display of column results.

{phang}{opth format(%fmt)},
an option used with many of the subcommands of {\tt estat}, specifies the
display format for the matrix, e.g., {cmd:format(%8.3f)}.  The default is
{cmd:format(%9.4f)}.

{phang}{opt approx},
an option used with {cmd:estat distances}, computes distances between the
fitted profiles.  The default is to compute distances between the observed
profiles.

{phang}{opt total},
an option used with {cmd:estat inertia}, adds row and column margins to the
table of inertia or chi-squared (chi-squared/N) contributions.

{phang}{opt noscale},
as an option used with {cmd:estat inertia}, displays chi-squared contributions
rather than inertia (= chi-squared/N) contributions.  (See below for the
description of {opt noscale} with {cmd:estat table}.)

{phang}{opt labels},
an option used with {cmd:estat summarize}, displays variable labels.

{phang}{opt noheader},
an option used with {cmd:estat summarize}, suppresses the header.

{phang}{opt noweights},
an option used with {cmd:estat summarize}, ignores the weights, if any.  The
default when weights are present is to perform a weighted {cmd:summarize} on
all variables except the weight variable itself.  An unweighted
{cmd:summarize} is performed on the weight variable.

{phang}{opt fit},
an option used with {cmd:estat table},
displays the fitted values for the correspondence analysis model.
{cmd:fit} is implied if {cmd:obs} and {cmd:independence} are not specified.

{phang}{opt obs},
an option used with {cmd:estat table}, displays the observed table with
non-negative entries (the "correspondence table").

{phang}{opt independence},
an option used with {cmd:estat table}, displays the expected values p(ij)
assuming independence of the rows and columns, p(ij) = r(i) c(j), where r(i)
is the mass of row i and c(j) is the mass of column j.

{phang}{opt noscale},
as an option used with {cmd:estat table}, normalizes the displayed tables to