The effect of non-normality on estimating the variance of the combined ratio estimate in complex surveys |
| |
| Authors: | Stanley Lemeshow David W Hosmer David Hislop |
| |
| Institution: | University of Massachusetts , Division of Public Health , School of Health Sciences, Amherst, Massachusetts |
| |
| Abstract: | The performance of the balanced half-sample, jackknife and linearization methods for estimating the variance of the combined ratio estimate is studied by means of a computer simulation using artificially generated non-normally distributed populations. The results of this investigation demonstrate that the variance estimates for the combined ratio estimate may be highly biased and unstable when the underlying distributions are non-normal. This is particularly true when the number of observations available from each stratum is small. The jack- |
| |
| Keywords: | balanced half-sample jackknife linearization replication methods multistage sample surveys |
|
