Small area variation analysis are often based on area-level data such as the total number of hospital admissions within an area, rather than person-level data. Such analysis often make the assumption that the number of admissions within a small area follow a Poisson distribution. This may not be a reasonable assumption when multiple admissions per person are possible. In this case, the multiple admission factor (MAF) can be used to adjust for the extra variance introduced by multiple admissions. In this article, data from Washington State are used to estimate the multiple admission rate and the MAF for each modifed DRG (M-DRG). Examples are presented which illustrate how these MAF estimates can be used in small area analyses. For many M-DRG's, MAF is close to one and hence adjusting for it has little effect, however MAF is larger than 2 for a number of M-DRG's. The usual Chi-square statistic for these M-DRG's will be more than twice as large as it should be, resulting in anti-conservative tests of the null hypothese of no excess variation.
Cain, Kevin and Diehr, Paula, "The Multiple Admission Factor (MAF) in Small Area Variation Analysis" (December 1992). UW Biostatistics Working Paper Series. Working Paper 116.