# Survey Weighted Regression Without FPC in R

I'm using the svydesign package in R to run survey weighted logit regressions as follows:

sdobj <- svydesign(id = ~0, weights = ~chweight, strata = ~strata, data = svdat)

model1 <- svyglm(formula=formula1,design=sdobj,family = quasibinomial)


However, the documentation states a caveat about regressions without specifying finite population corrections (FPC):

    If fpc is not specified then sampling is assumed to be
with replacement at the top level and only the first stage of
cluster is used in computing variances.


Unfortunately, I do not have sufficient information to specify my populations at each level (of which I sampling very little). Any information on how to specify survey weights without FPC information would be very helpful.

-
 The finite population correction factor is just 1-m/N where m is your sample size and N is your population size. You should be able to specify this. The finite sample would not be well-defined without knowing m and N. – Michael Chernick Aug 21 '12 at 17:46 Unfortunately, I do not (currently) have access to the number of clusters in a region, or the number of households in a cluster, so I am unable to use that information. – mike Aug 21 '12 at 18:18 Okay. But when you actual do a survey you will need that information and wouldn't you think it would be important if you want to construct optimal or nearly optimal weights? – Michael Chernick Aug 21 '12 at 19:11 Right, but I'm not during a survey, I'm analyzing a completed survey which has not provided me with that information. – mike Aug 21 '12 at 21:00 I don't see how you can analyze survey data without that basic information. Are you just given the total number of surveys and the overall response frequencies? – Michael Chernick Aug 21 '12 at 21:15
show 1 more comment