The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » HIV » Mozambique INSIDA 2009 - generating age difference with last sexual partner for AGYW 15-24
Mozambique INSIDA 2009 - generating age difference with last sexual partner for AGYW 15-24 [message #15119] Wed, 06 June 2018 02:34
nlohman is currently offline  nlohman
Messages: 1
Registered: June 2018
Location: Maputo
Member
Hi DHS Forum,

I'm working on an analysis of determinants for HIV infection across Mozambique's 2 most recent HIV prevalence surveys (2015 IMASIDA and 2009 INSIDA).

I'd like to include in my analysis an indicator that, for Adolescent Girls and Young Women (AGYW) aged 15-24, looks at the age difference between the AGYW respondents and their last sexual partner.

The trouble I'm sunning into is that when I generate the agediff variable below and then run univariate analysis, Stata won't produce test statistics and returns the following message: "Note: Missing test statistics because of stratum with single sampling unit."

I'd appreciate any help understanding why there is only a single sampling unit in this stratum, even though I can run a similar analysis directly on the age of the last sexual partner without any issues.

Any suggestions about how to better handle the agediff variable to allow test statistics to be generated would also be very welcome.

Thanks in advance,
Nathaniel

Here is the Stata code I'm using:

gen agediff=.
replace agediff=1 if (v834a-v012)<=5 & (v834a-v012)>=-24
replace agediff=2 if (v834a-v012)>5 & (v834a-v012)<90

svy: tab agediff hiv03 if aidsex==2, ci pearson count
svy: tab agediff hiv03 if aidsex==2, ci pearson row


And, here is the output I get:

. svy: tab agediff hiv03 if aidsex==2, ci pearson count
(running tabulate on estimation sample)

Number of strata = 21 Number of obs = 405
Number of PSUs = 141 Population size = 321.484835
Design df = 120

----------------------------------------
| blood test result
agediff | hiv nega hiv pos Total
----------+-----------------------------
1 | 211.3 34.34 245.6
2 | 65.26 10.62 75.88
|
Total | 276.5 44.95 321.5
----------------------------------------
Key: weighted count

Pearson:
Uncorrected chi2(1) = 0.0000
Design-based F(., .) = . P = .

Note: Missing test statistics because of stratum with single sampling unit.
Note: Missing standard errors because of stratum with single sampling unit.

. svy: tab agediff hiv03 if aidsex==2, ci pearson row
(running tabulate on estimation sample)

Number of strata = 21 Number of obs = 405
Number of PSUs = 141 Population size = 321.484835
Design df = 120

----------------------------------------
| blood test result
agediff | hiv nega hiv pos Total
----------+-----------------------------
1 | .8602 .1398 1
2 | .8601 .1399 1
|
Total | .8602 .1398 1
----------------------------------------
Key: row proportion

Pearson:
Uncorrected chi2(1) = 0.0000
Design-based F(., .) = . P = .

Note: Missing test statistics because of stratum with single sampling unit.
Note: Missing standard errors because of stratum with single sampling unit.


Previous Topic: The Gambia DHS
Next Topic: How do I interpret variable "HIV Weight" (ha69 & hb69)?
Goto Forum:
  


Current Time: Sun Oct 21 06:51:24 Eastern Daylight Time 2018