Issues linking PMA Phases 1-3 using FQINSTID

GLOBAL HEALTH
1

Greetings,

I hope you’re doing well.

I’m currently working with the Female Respondents (longitudinal, long format) file for Burkina Faso, Niger, and Côte d’Ivoire, phases 1–3. While reviewing country result briefs for Niger and Côte d’Ivoire, I noticed that although a large proportion of women had completed all three phase counts, in the long file, I seem unable to recover any 3-phase women when I use the variable FQINSTID. Specifically, when inspecting the variable through duplicate reports for each country, I notice that there are a maximum of two copies of observations rather than three, which is odd since it is reported that in both regions, there are 3 phases available under the variable PHASE.

Considering the challenges I am facing in two key areas, 1) linking women across all three phases and 2) creating consecutive intervals for phases 1-2 and 2-3, I would be grateful for any insight or coding tips you can offer to help me achieve my goal.

Please note that I also noticed a possible small coding typo under the variable PHASE for Niger. Specifically, it appears that only phases 1, 2, and 4 are available for this region. However, after comparing the data collection year and interview dates in the dataset with those reported by PMA for phase 4, I noticed a discrepancy. The dates provided in the dataset seem to correspond with those for the Phase 3 data collection.

Thank you for your help.

2

Thank you for reaching out and sharing your findings. You’re correct that there is an error in the PHASE variable for Niger: observations coded as phase 4 are actually from phase 3. This will be fixed by the IPUMS Global Health team in the next data release.

To simplify the linking process, I recommend using the wide form longitudinal samples. These can be accessed from the Select Samples page by checking Longitudinal and then selecting the Wide option. Wide form provides pre-linked data that merges variables from across time onto the same row of the panel woman. As a result, there is one record per woman across all survey phases (see the user note on longitudinal formats for more information). If you prefer working with the long form data, you may need to first trim any leading or trailing whitespace from FQINSTID in order to link women across all three survey phases. See strtrim() if working in Stata or trimws() for R.