Skip to main content

Table 4 Illustrations of data arrangements

From: Survival analysis of Rural Clinical School of Western Australia graduates: the long-term work of building a long-term rural medical workforce

Participant Original format   New format for SAS PROC PHREG analysis
CollectionYear RuralPractice StartYear EndYear CensorStatus
1 2011 No 0 2 1
1 2012 No    
1 2013 Yes 2 4 2
1 2014 Yes    
1 2015 No 4 5 1
  1. Calendar years were converted to simple time (yearly) units, with 0 indicating (end of) year 2010, and 5 indicating (end of) year 2015
  2. This was necessary to preserve the correct duration, or the number of years, that the participatnt contributed to the study. For example, the maximum time period in this study is 5 years (2011 through 2015 inclusive). However, 2015–2011 (or in code 5–1) equals 4 years only
  3. CensorStatus = 1 indicates censoring or a non-event (ie no rural practice). CensorStatus = 2 indicates an event (ie rural practice)
  4. Grey-shaded rows of data did not exist in the new format