Regency population Indonesia

Dear Ambassador Bob,

thank you very much for your response on my question: “I want to track changes in population of Indonesian regencies across census rounds. IPUMS does not get me there…”.

It was very helpful. Three follow-ups:

  1. You write: “If all you need are population counts then you may wish to look elsewhere.” Indeed, this is all I need: population counts at the regency level, I do not need to do any regressions using the other data that IPUMS provides. But, if that’s the only thing I need, where else could I look? Now that you told me about the WTPER etc., of course I can retrieve the population counts now from IPUMS, but a) that would take slightly more time and b) you mentioned that for small regencies, the standard error can be quite large.

  2. As you write, and as I also found in the link you sent to me, WTPER is 0.51% for the 2005 census round. However, when I download the data, WTPER changes from regency to regency in 2005 (while it is constant at 10 for 2000 and 2010, as also stated in the link). What should I take away here - is 0.51% for all regencies correct or does WTPER really vary across regencies in the 2005 census?

  3. My supervisor found some documentation a while ago which might help you to harmonize level 2 geography by area for Indonesia. The ID variables for regencies used in these pdf files seem to be consistent with the ones from the census data that I downloaded. The weblinks from which my supervisor got the pdf’s do not work any more, but I have the pdf files, so if you give me an email address, I can send them to you.

Thank you for the offer of level2 geography documentation for Indonesia. We would be happy to have a copy. My email address is rmccaa at

Regarding question 2, indeed for the 2005 sample wtper varies from unit to unit. Multiplying by 200 is not advisable. The sample design is described here:

as follows:

“Multistage sample of census blocks using urban/rural status of each regency/municipality.”

For question 1, I assume that Statistics Indonesia has the complete counts on their website:

From the IPUMS-International site, the counts using sample data are readily available for all Indonesian samples 1971-2010. Click “Analyze Data Online”, select Indonesia 1971-2010 and log-in. Then select geo2b_id for the row variable and “sample” for the column. Scroll down to click off “Column” percentaging to keep things simple. Then scroll again to click “Run the table”.

| | |

The table is generated in 20-30 seconds. Weights are automatically applied. The table shows how inconsistent the level 2 codes are from census to census, but you do get the simple weighted counts without having to download the microdata.

Hope this helps.