sts_graph.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}
{* 22mar2005}{...}
{cmd:sts graph} {right:dialog:  {bf:{dialog stsgraph:sts graph}}}
{hline}

{title:Title}

{p2colset 5 23 25 2}{...}
{p2col :{hi:[ST] sts graph} {hline 2}}Graph the survivor and cumulative hazard functions{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 21 2}{cmd:sts} {opt g:raph} {ifin} [{cmd:,} {it:options}]

{synoptset 34 tabbed}{...}
{synopthdr}
{synoptline}
{syntab:Main}
{synopt :{opt f:ailure}}graph Kaplan-Meier failure function; default is the survivor function{p_end}
{synopt :{opt na}}graph Nelson-Aalen cumulative hazard function{p_end}
{synopt :{opt h:azard}}graph smoothed hazard estimate{p_end}
{synopt :{opt per(#)}}units to be used in reported rates{p_end}
{synopt :{opth by(varlist)}}calculate separately on different groups of {it:varlist}{p_end}
{synopt :{opth ad:justfor(varlist)}}adjust the estimates to zero values of {it:varlist}{p_end}
{synopt :{opth st:rata(varlist)}}calculate separately on different groups of {it:varlist}{p_end}
{synopt :{opt sep:arate}}show curves on separate graphs; default is to show curves on top of another{p_end}
{synopt :{opt g:wood}}show pointwise Greenwood confidence bands around the survivor (failure) function{p_end}
{synopt :{opt cna}}show pointwise confidence bands around cumulative hazard function{p_end}
{synopt :{opt cih:azard}}show pointwise confidence bands around smoothed hazard function{p_end}


{syntab:Options}
{synopt :{opt l:evel(#)}}set confidence level; default is {cmd:level(95)}{p_end}
{synopt :{opt nosh:ow}}do not show st setting information{p_end}
{synopt :{opt lost}}show number lost{p_end}
{synopt :{opt e:nter}}show number entered and number lost{p_end}
{synopt :{opt atr:isk}}show numbers at risk at beginning of each time interval{p_end}
{synopt :{cmdab:cen:sored(}{opt s:ingle)}}show one tick at each censoring time, not matter what number is censored{p_end}
{synopt :{cmdab:cen:sored(}{opt n:umber)}}show one tick at each censoring time and number censored above tick{p_end}
{synopt :{cmdab:cen:sored(}{opt m:ultiple)}}show multiple tick marks for multiple censoring at the same time{p_end}
{synopt :{opth lostop:ts(marker_label_options)}}affect how numbers lost are rendered{p_end}
{synopt :{opth atriskop:ts(marker_label_options)}}affect how numbers at risk are rendered{p_end}

{syntab:More options}
{synopt :{opt tma:x(#)}}show graph for t<={it:#}{p_end}
{synopt :{opt tmi:n(#)}}show graph for t>={it:#}{p_end}
{synopt :{opt noori:gin}}begin survival (failure) curve at first exit time; default is begin at t=0{p_end}
{synopt :{cmd:width(}{it:#}[{it:#}...]{cmd:)}}override "optimal" widths{p_end}
{synopt :{opt k:ernel(kernel)}}use {it:kernel} to calculate weighted kernel-density estimate{p_end}

{syntab:Plot}
{synopt :{it:{help cline_options}}}affect rendition of plotted lines{p_end}

{syntab:CI plot}
{synopt :{opth ciop:ts(cline_options)}}affect rendition of confidence bands{p_end}

{syntab:Add plot}
{synopt :{opth "addplot(addplot_option:plot)"}}add other plots to the generated graph{p_end}

{syntab:Y-Axis, X-Axis, Title, Caption, Legend, Overall}
{synopt :{it:{help twoway_options}}}any options documented in {bind:{bf:[G] {it:twoway_options}}}{p_end}
{synoptline}
{p2colreset}{...}
{p 4 6 2}
You must {cmd:stset} your data before using {cmd:sts graph}; see {helpb stset}.{p_end}
{p 4 6 2}
Note that {opt fweight}s, {opt iweight}s, and {opt pweight}s may be specified using {cmd:stset}; see {helpb stset}.


{title:Description}

{pstd}
{cmd:sts graph} graphs the estimated survivor (failure) function, or
Nelson-Aalen estimated cumulative (integrated) hazard function, or the
estimated hazard function.

{pstd}
{cmd:sts graph} can be used with single- or multiple-record or single- or
multiple-failure st data.


{title:Options}

{dlgtab:Main}

{phang}
{opt failure} specifies that the failure function 1-S(t+0) be graphed.

{phang}
{opt na} specifies that the Nelson-Aalen estimate of the cumulative hazard
function be plotted.

{phang}
{opt hazard} specifies that an estimate of the hazard function be plotted.
This estimate is calculated as a weighted kernel-density estimate utilizing
the estimated hazard contributions.  These hazard contributions are the same
as those obtained by {cmd:sts generate} {newvar} {cmd:= h}.

{phang}
{opt per(#)} specifies the units used to report the survival or failure rates.
For example, if the analysis time is in years, specifying {cmd:per(100)}
results in rates per 100 person-years.

{phang}
{opth by(varlist)} produces separate survivor, cumulative hazard, or hazard
functions by making separate calculations for each group identified by equal
values of the variables in {it:varlist}.

{pmore}
If you type {cmd:sts graph}, the single survivor function for all the
data{hline 2}the Kaplan-Meier estimate{hline 2}is plotted.  If you type
{cmd:sts graph, by(sex)}, the survivor functions for each sex{hline 2}separate
Kaplan-Meier estimates{hline 2}are graphed (on the same axes).

{pmore}
Similarly, if you type {cmd:sts graph, na}, the Nelson-Aalen cumulative hazard
function for all the data is plotted.  If you type {cmd:sts graph, na by(sex)},
the Nelson-Aalen cumulative hazard function for each sex is graphed (on the
same axes).

{pmore}
If you type {cmd:sts graph, hazard}, the estimated hazard is plotted.  If you
type {cmd:sts graph, hazard by(sex)}, the estimated hazard for each sex is
graphed (on the same axes).

{pmore}
Typically, you specify a single {opt by()} variable, such as {cmd:by(sex)},
but you can specify up to five.  {cmd:sts graph} often restricts you to one
{opt by()} variable, depending on the other options specified because labeling
multiple groups on a graph becomes an impossible problem.

{pmore}
If you have more than one {opt by} variable but need only one, use {cmd:egen}
to create it; see {helpb egen}.

{phang}
{opth adjustfor(varlist)} adjusts the estimate of the survivor function to
that for 0 values of the {it:varlist} specified.  This option is not available
with {cmd:na}.

{pmore}
The following commands

{phang3}
{cmd:. sts graph, by(group) adjustfor(age)}

{pmore}
and

{phang3}
{cmd:. sts graph, strata(group) adjustfor(age)}

{pmore}
graph the survivor functions for each group.  The functions graphed would be
adjusted for age, meaning that an attempt has been made to remove the
differences in the functions due to age.  How {cmd:sts} does this depends on
whether you specify {opt by()} or {opt strata()}.  See {bf:[ST] sts} for
details, but here is a quick review.

{pmore}
If you specify {opt strata()}, {cmd:sts} performs the adjustment by fitting
a stratified-on-group Cox regression model using {opt adjustfor()} as the
covariates.  The stratified, baseline survivor function is then retrieved.

{pmore}
If you specify {opt by()}, {cmd:sts} fits separate Cox regression models for
each group and retrieves the separately calculated baseline survivor functions.

{pmore}
Be aware that, regardless of method employed, the survivor function is
adjusted to 0 values of the covariates.  Say you are adjusting for age and
assume the ages of patients in your sample are 40 to 60.  Then

{phang3}{cmd:. sts graph, strata(group) adjustfor(age)}

{pmore}
will graph results adjusted to age 0.  If you want to adjust the function to
age 40, type

{phang3}{cmd:. gen age40 = age - 40}{p_end}
{phang3}{cmd:. sts graph, strata(group) adjustfor(age40)}

{phang}
{opt strata(varlist)} is a subtle alternative to {opt by()}.  You may
not specify {opt strata()} unless you also specify {opt adjustfor()}, whereas
you may specify {opt by()} in either case.  Thus {opt strata()} amounts to a
modifier of {opt adjustfor()}.  This option is not available for the
{cmd:na} option.

{phang}
{opt separate} is meaningful only with {opt by()} or {opt strata()}; it
requests that each group be placed on its own graph rather than one on top of
the other.  Sometimes curves have to be placed on separate graphs{hline 2}such