586 – Weighting and Variance Estimation
A Comparison of Variance Estimates Using Random Group and Taylor Series Methods for a Large National Survey of Businesses
Sadeq R. Chowdhury
Agency for Healthcare Research and Quality
David Kashihara
Agency for Healthcare Research and Quality
The random group (RG) method of variance estimation has been used in the Medical Expenditure Panel Survey - Insurance Component (MEPS-IC) since the beginning of the survey in 1996. However, this method was found to be less reliable for certain types of estimates so the variance estimation method was changed to the Taylor Series Expansion (TS) method starting in 2014. This paper will present a comparison of standard error estimates using the RG and TS methods for a variety of MEPS-IC estimates and will discuss the situations where the RG method may be less reliable than the TS method.