Dichotomizing the Variables


Return to One-way Page 2

1. Open bdeshc.sav

2.  Select Transform, Recode, Into different variable.

3. Select the variable diaprvfm (diarrhea prevalence male and female) and move to the right. Tab and type the name of the dichotomized variable hldiaprv (high/low diarrhea prevalence) and click on change.

4. Now click on old and new values. Select the button range and type in 0 in the first cell and 14.99 in the second. Now tab to value and type 1, then add.

5. Select range again and type 15 in the first cell and 99 in the second. Tab to value and type 2, then Add.

6. Finally click the button labeled All other values, tab to value and click on System-missing, click Add and then Continue, then OK.

7.  Repeat these steps substituting the variable ditrhw (name the dichotomized variable hlditrhw for high /low diarrhea treatment). Remember the range for the value 1 should be 0 to 19.99 and value 2 should be 20 to 99 for the health worker variable.

8.  To perform a cross-tabulation, select Statistics, Summarize, Crosstabs. Select and move your newly created variables into the row and column cells putting hlditrhw under column and hldiaprv under row and click OK.

 

wpe9.jpg (7444 bytes)

The resulting output looks like this.  Does it look like what you have in SPSS?  There are two categories for the diarrhea treatment by a health worker (HLDITRHW:  represents a high/ low diarrhea treatment by health worker) that are coded 1 for <20% (low) and 2 for >=20% (high).  There are also two categories for prevalence of diarrhea (HLDIAPRV:  represents a variable high/ low prevalence of diarrhea) that is are coded 1 for <15% (low) and 2 for >=15% (high). It is easy now to see how where the deficiencies are in targeting and to re-target the healthworkers from the high coverage/ low prevalence areas to those areas that are high prevalence/ low coverage. This will be the next step.

Return to Top of Page