Alternative methods of unit nonresponse weighting adjustments: an application from the 2003 Survey of Small Business Finances

The 2003 Survey of Small Business Finances (SSBF) screening interview had significant unit nonresponse and therefore some type of nonresponse adjustment was deemed necessary. The approach used in the 2003 survey differed from that used in previous surveys. The current paper examines the impact of this technique on weights, point estimates and variance of the estimates by comparing the approach ultimately implemented for the 2003 survey to alternative approaches. The results using the 2003 SSBF hybrid method are very similar to the traditional weighting class method and the propensity stratification methods. Even though the hybrid technique did in some instances increase the variance of the weights over the traditional weighting class adjustment method, the differences were quite small. In addition the hybrid method decreased the variance for the weights as well as the some of the point estimates.