%0 Research article
%T Some aspects of the sampling distribution of the Apportionment Index and related inference
%A Koskela, Laura
%A Sinha, Bikas K.
%A Nummi, Tapio
%D 2007
%J Silva Fennica
%V 41
%N 4
%R doi:10.14214/sf.277
%U https://silvafennica.fi/article/277
%X As customer-oriented production strategies have gained ground in the  sawmill industry, proper measurement of the fit between the log demand  and log output distributions has become of crucial importance. The  prevailing means of measuring the outcome is the so-called Apportionment  Index (AI), which is calculated from the relative proportions of the  observed and required distributions. Although some statistical  properties of the AI have recently been examined and alternative means  of measuring the bucking outcome have been suggested, properties of the  sampling distribution of the AI have not yet been widely studied. In  this article we examine the asymptotic sampling distribution for the AI  by assuming a multinomial distribution for the outcome. Our results are  based mainly on large-sample normal approximations. Also some studies of  the determination of the number of logs needed to obtain a specified  level of accuracy of the AI have been carried out.