{smcl} {* 19June2002}{...} {hline} help for {hi:survtime}{right:(see also: {hi:[R] stset})} {hline} {title:Survival Time for use in stset} {p 8 17}{cmd:survtime} [{cmd:if} {it:exp}] [{cmd:in} {it:range}] {cmd:,} {cmdab:e:vents(}{it:varlist}{cmd:)} {cmdab:c:ensors(}{it:varlist}{cmd:)} [{cmdab:g:enerate(}{it:newvarname}{cmd:)} {cmdab:s:equential} {cmdab:o:rigin(}{it:varlist}{cmd:)} {cmdab:a:ddone}] {p 2 4}NOTE: if {cmdab:g:enerate(}{it:newvarname}{cmd:)} is not used {cmd:survtime} will create or overwrite two variables called {it:event_d}: the first occurring date & {it:event_i}: the corresponding event indicator. {title:Description} {p 0 4}{cmd:survtime} finds the first occurring date of a list of events and censor dates and creates one variable {it:event_d} (or {it:newvariable_d}) for the date and a second variable {it:event_i} (or {it:newvariable}) indicating the status of that date as an event (1,2,...) or a censor (0) of types provided in {cmdab:e:vents(}{it:varlist}{cmd:)} and {cmdab:c:ensors(}{it:varlist}{cmd:)}, respectively.{p_end} {p 0 4}{cmd:survtime} was written with meaningful date (see {help dates}) variables in mind. There is no check made for compatible numeric variables specified in {cmdab:e:vents(}{it:varlist}{cmd:)}, {cmdab:c:ensors(}{it:varlist}{cmd:)}, or {cmdab:o:rigin(}{it:varname}{cmd:)}.{p_end} {p 2 4}{cmd:stset} will use the resulting variable and event indicator. Example syntax of {help stset} following {cmd:survtime}: {p 8 16}{cmd:stset} {it:event_d} [{cmd:if} {it:exp}] [{cmd:in} {it:range}] [{cmd:,} {cmdab:f:ail(}{it:event_i==}{it:numlist}{cmd:)} {cmdab:o:rigin(}{it:varname}{cmd:)} {cmdab:s:cale(}{it:#}{cmd:)} {cmdab:id:(}{it:varname}{cmd:)}]. {title:Options} {p 0 4}{cmdab:g:enerate(}{it:newvarname}{cmd:)} specifies that new variables be created. The date will have the suffix _d added. The event indicator will have no suffix added. By default {it:event_d} and {it:event_i} will be created or overwritten. {p 0 4}{cmdab:s:equential} specifies that the {cmdab:e:vents(}{it:varlist}{cmd:)} are in descending order of interest and values 1,2,... will be so assigned and labeled indicating which event occurs first. Tied events will take the preceding event type. If {cmdab:s:equential} is not specified all {cmdab:e:vents(}{it:varlist}{cmd:)} get the value, 1. {p 0 4}{cmdab:o:rigin(}{it:varname}{cmd:)} specifies that the number of elapsed days be found from this origin. It will contain the number gotten by subtracting the provided origin from the event or censor date. The resulting variable will reflect this in its label. If this option is used it is not necessary to use the origin() option in {cmd:stset}. {p 0 4}{cmdab:a:ddone} specifies that one be added to the interval. If this option is specified without {cmdab:o:rigin(}{it:varname}{cmd:)}, zero is used as the origin. {p 0 4}[{cmd:if} {it:exp}] [{cmd:in} {it:range}] options result in missing values for records excluded thereby. In general, it is recommend that the analysis set be defined in {help stset}, or by some other means, rather than in {cmd:survtime}. If {it:timevar} in {cmd:stset} contains missing values {cmd:stset} responds by indicating {it:probable error}, which can mask substantial information about survival data. This, however, does not matter if {cmd:survtime} is used without {cmd:stset} to find observation time for a certain subset. {title:Example} {p 8 12}{inp:. survtime , e(die dmarrel) c(dlast cutoff) gen(dfs) seq }{p_end} {p 8 12}{inp:. stset dfs_d, failure(dfs==1/2) origin(begin_d) scale(365) id(idnumber)}{p_end} {p 8 12}{inp:. survtime , e(die dmarrel) c(dlast cutoff) gen(dfs) }{p_end} {p 8 12}{inp:. stset dfs_d, failure(dfs==1) origin(begin_d) scale(365) id(idnumber)}{p_end} {title:Author} {p 8 12} Allen Buxton, {p_end} {p 8 12} Assistant Statistician {p_end} {p 8 12} Children's Oncology Group {p_end} {p 8 12} Arcadia, CA {p_end} {title:Also see} {p 1 14}Manual: {hi:[R] stset} {p_end} {p 0 19}On-line: help for {help stset} {help survtime} {p_end}