Race/Ethnicity redux

[Bob Schacht-3]

On August 8, I sent a query that was apparently not clear. Several list
members wrote asking for clarifications and examples, so I will attempt to
do both. My apologies for the delay in my response.

As you may recall, I began by pointing out that the Census now allows
respondents to identify with more than one "race" or ethnicity.
In order to measure compliance with norms on service to minorities, Federal
indicators sometimes use the term "non-minority" individuals for
individuals who report themselves exclusively as White, non-Hispanic).

Briefly, the original data on the race or ethnicity of each person came
from two sources:
    * a quarterly file of both active and closed cases, in which the Asian
"race" ("ASIAN-HI) was coded with a letter (e.g., C = China, J = Japan,
etc.), and the Hawaiian-Pacific Islander category ("HAWN-PI-HI") was also
subdivided (e.g., H = Hawaiian, S = Samoan, P=Pacific Islander, etc.).
    * an annual file of closed cases
    * the values for variables AI/AN, BLACK, HISPANIC, and WHITE may be
from either source file, depending on the closure status.
These files were combined, and duplicates were eliminated, keeping only the
most recent quarter of active cases, or the annual "final" closed case
summary. This process has resulted in some anomalies.
    * The race and ethnicity categories were read from the annual file as
numbers. A "1" indicated identification with this race or ethnicity, and
"0" was entered if "not this race/ethnicity,"
    * The race and ethnicity categories were read from the quarterly files
as characters (ASIAN-HI, HAWN-PI-HI) or numbers. These fields contained a
non-missing value only if the person was identified with the race/ethnicity.
    * I am treating the "missing values" as "not this race/ethnicity".
Here's a sample of the file (Font Courier New fixed space). There are
supposed to be 8 columns of data. Two columns, Asian-HI and Hawn-PI-HI, are
character fields and may be blank. The others are numeric fields, and a '0'
means essentially the same thing as a blank (sysmis)

AI/AN   Asian-HI        Asian  Black  Hawn-PI  Hawn-PI-HI  HISPANIC   White

1                       .       .    .                          .       .
.                       .       .    .                          .       1
.                       .       1    .                          .       .
.                       .       .    .                          1       1
.                       .       .    .          H           .           .
0                       0       0    1          H           0           0
.                       .       .    .          P           .           .
0                       0       0    1          P           0           0
0                       0       0    1          S           0           0
.               C               .       .    .                          .
     .
0               C               1       0    0                          0
     0
.               F               .       .    .                          .
     .
0               F               1       0    0                          0
     0
.               J               .       .    .                          .
     .
.               K               .       .    .                          .
     .
0               K               1       0    0                          0
     0
.               O               .       .    .                          .
     .
.               V               .       .    .                          .
     .
0               V               1       0    0                          0
     0

Gene Maguin's suggestion, sent off-list, is the best I've received to date:

>Recode Asian-HI Hawn-PI-HI(' '=0)(else=1) into nAsian-HI nHawn-PI-HI.
>Recode white(sysmis=0).
>Count minority=AI/AN nAsian-HI Asian Black nHawn-PI nHawn-PI-HI HISPANIC(1).
>
>*  check for missing data. (0,0) is the problem.
>Crosstabs minority by white.
>
>*  assume none.
>Recode minority(0=0)(1 thru hi=1).

There was indeed a (0,0) problem, so if Minority and White were both '0', I
recoded it as missing. With that fix, my problem now seems solved.
Thanks to those who responded!

Bob Schacht

Robert M. Schacht, Ph.D. <[hidden email]>
Pacific Basin Rehabilitation Research & Training Center
1268 Young Street, Suite #204
Research Center, University of Hawaii
Honolulu, HI 96814

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD