I was trying to calculate the association between children's Height for age Z score and number of under five children in the family. When i tabulate the variable hv014, it gives following result:

number of

children 5

and under

(de jure) Freq. Percent Cum.

0 22,077 23.01 23.01

1 23,493 24.48 47.49

2 30,452 31.74 79.23

3 15,197 15.84 95.07

4 3,147 3.28 98.35

5 985 1.03 99.38

6 417 0.43 99.81

7 106 0.11 99.92

8 37 0.04 99.96

9 18 0.02 99.98

10 20 0.02 100.00

Total 95,949 100.00

In this case, what does the zero "0" number of children mean? if i want to categorize the response into "0" "1-2" and ">2" children how should i interpret the result? or should i simply exclude the observations with zero children in this case? Can someone please guide me on this? Any help will be really appreciated.

Thank you very much.

Best Regards]]>

Sorry for the confusion and thank you for your reply.

I am using the PR file from Nepal Demographic and Health Survey (NDHS 2011)

use "C:\Users..............\NPPR60FL.DTA"

*Declaring Survey data

gen finalwt=hv005/1000000

svyset hv001 [pweight=finalwt], strata(hv022) vce(linearized) singleunit(missing) || hv002

*DEPENDENT VARIABLE

* Calculation of Stunting (Height for Age)

gen HAZ=hc70

replace HAZ=. if HAZ>=9996

gen stunting= HAZ

replace stunting=0 if HAZ ~=.

replace stunting=1 if HAZ<-200

svy: tab hv014 stunting if hv103==1

Which gives result,

number of

children

5 and

under (de stunting

jure) 0 1 Total

0 .0352 .0105 .0457

1 .2659 .1641 .43

2 .2236 .1709 .3946

3 .0541 .0505 .1046

4 .0144 .0086 .023

5 .0017 4.1e-04 .0021

Total .595 .405 1

Now i am confused about the correct interpretation of the first row of the table (distribution of stunting among the family with "0" under five children) and i need help.

Thank you for your help.

Best,

]]>