Home    Contents

Windows in SAS
File management

The SAS Program
Program syntax
Debugging tips

1. Prepare the data set 
   Types of data 
   Example programs    
2. View the data
   SAS Procedures
3. Explore the data  
   Numeric statistics    
   Frequency tables    
4. Manipulate the data  
   Basic techniques    
   New variables
5. Adding Variables and 
Observations to Data Sets
   The SET Statement
   The MERGE Statement

6. Data Processing
   ARRAY Statement
   Do Loops
   By-Group Processing
   RETAIN Statement

 Simulated clinical data 
 Simulated Manitoba Health 

Record Layout for the Simulated Manitoba Health Data Set

This record layout provides the following information, in alphabetical order, for the 33 variables in the simulated Manitoba Health data set.

  • Names assigned to variables.
  • Column numbers, reflecting how much space is required for the values of each variable.
  • Type of variable, denoting whether the values should be read in as numeric (N) or alpha/numeric (A/N).
  • General description of variable.
  • Data values for each variable, including format names and files, where applicable.

Unless otherwise specified, the formats are available in the file titled fmts95.

Variable NameColumnsType Variable DescriptionData Values
ABSTYPE82A/N Abstract type
1 - Adult/child
2 - Pediatric
3 - Obstetric
4 - Newborn/stillborn
5 - Rehab/respiratory
Format:  $ABSTYPEL  
AGE7-9N Patient age at discharge
Range:  0 to 103
CHARYES36-37N Had a high-risk diagnosis (Charlson Index - Charlson et al., 1987)
0 - No
1 - Yes
Format:  $CHARL
CMG71-73A/N CIHI's Case Mix Group - a Canadian version of DRG (somewhat parallel)
Range: 1 to 999
Format labels are in 
CMG93C.FMT file 
DAYSFRPR83-85N Interval in days from discharge date of previous admission to current admission
0 to 365 - number of 
  days from previous 
999 - no previous 
  admission within
  the last year
DAYSTOR86-88N Interval in days from current admission to readmission
0 to 364 - number of
  days to readmission
999 - no readmission 
  within the 
  subsequent year
DEATHSEP55-58N Days from hospital separation to death
0 - died in 
1 to 449 - days 
    to death
9999 - alive as of
  500 days after
DIAG0124-28A/N ICD-9-CM diagnosis code: most responsible diagnosis
Range:  001 to 999.9
Format labels are in
DX93.FMT file
DIAG0229-33A/N ICD-9-CM diagnosis code: second diagnosis
Same as for DIAG01
DISCRE50N Discretionary diagnoses (Anderson et al., 1986)
1 - discretionary
0 - other
Format:  $DISCREL
DRG46-48A/N Diagnosis-Related Group
Range:  1 to 477
Format labels are in
DRG93C.FMT file
DRGRGN59-63A/N DRG Refinement Group Number (RDRG) - a 3-digit DRG followed by a "class" digit
Range:  0010 to 9230
DRGWT40-45N DRG weight: relative weights based on a mainly 65+ population, scaled so that 1.00 is standard (in the U.S., this determines how much hospitals are paid for patients of this type).
Range:  0 to 7.5631
GENDER6A/N Patient gender
1 - male
2 - female
Format: $GENDERL
ICD17BRK89-90A/N ICD-9-CM diagnoses grouped into 17 categories (for the actual diagnostic codes, see DIAG01 and DIAG02).
Range:  1 to 17 
(includes ICD-9-CM 
diagnoses 1 to 999.9,
excluding V- and 
Format: $ICD17L
INCDR53A/N Neighbourhood income quintile, based on mean household income assigned to postal code from aggregate enumeration area data
1-less than or equal
  to $22,300
2-$22,400 to $27,500
3-$27,600 to $33,300
4-$33,400 to $41,200
5-greater than
Format: $INCDRL
LOS10-13N Length of hospital stay
Range: 1 to 902
NCASE1-5A/N Case number (unique identifier)
Range: 1 to 5000
NDAYICU14-17N Number of days in Intensive Care
Range: 0 to 73
OP0120-23A/N ICD-9-CM procedure code: primary operative procedure
Range: 01 to 99.99
Format labels are 
in OP93.FMT file 
RDRGWT65-70N Refined DRG weight: based on LOS data for each DRG, but this has not been scaled (like DRGWT), and is based on a large 1986 US sample mainly age 65+.
Range: 0.1433 to
(the higher the value,
the longer the
expected stay).
REGIONH52A/N Hospital region
1 - central Manitoba
2 - eastern Manitoba
3 - Interlake
4 - northern Manitoba
5 - Parkland
6 - Thompson
7 - Westman
8 - Winnipeg
Format:  $REGIONL
REGIONRE52A/N Patient's region of residence
RISKDRG39A/N Score identifying risk of adverse event associated with admission (see info sheet)
0 - not classified
1 - low risk of 
    adverse event
4 - high risk of
    adverse event
RIW74-80N Resource Intensity Weight: based on 1985 New York cost data, to be used in conjunction with CMGs
Range: 0.1366 to 
SCHEDULE38A/N Scheduled admission (usually elective surgery)
1 - not scheduled
2 - scheduled
Format:  $SCHEDL
SEVRDRG64A/N DRG severity code (the last digit of the DRGRGN variable)
0 - no or minor 
1 - moderate c/c
2 - major c/c
3 - catastrophic c/c
Format: $SEVRL
TOTCHAR34-35A/N Charlson Index score: weighted score on high-risk diagnosis index (Charlson et al., 1987)
Range:  0 to 8
TRANADM18A/N Patient transferred from other institution
0 - no transfer/other
1 - hospital
2 - personal care home
Format:  $TRNADML
TRANDIS19A/N Patient transferred to other location
0 - no transfer/other
1 - another hospital
2 - personal care home
3 - died in hospital
Format:  $TRNDISL
TREATY81A/N Treaty First Nations: defined using municipal code, does not necessarily denote residence
0 - non-Treaty
1 - Treaty 
Format:  $TREATYL
TYPEHSP54A/N Type of hospital
1 - Winnipeg
2 - Winnipeg
3 - other Manitoba
Format:  $TYPEHL
WBURG49A/N Wennberg's variation code (Fisher et al., 1992)
1 - low-variation
    medical condition
2 - surgery
3 - high-variation
    medical condition
4 - obstetric 
   (DRG 370-379)
Format:  $WBURGL

Contact: Charles Burchill       Telephone: (204) 789-3429
Manitoba Centre for Health Policy
Department of Community Health Sciences, University of Manitoba
4th floor Brodie Centre
408 - 727 McDermot Avenue
Winnipeg, Manitoba R3E 3P5       Fax: (204) 789-3910
Last modified on Wednesday, 24-Aug-2005 13:42:25 CDT