SIGNIFICANCE OF THE SAMPLE LEAD - SOME THEORETICAL AND EMPIRICAL RESULTS

The paper provides theoretical and experimental results concerning the distribution of the sample lead. They apply to sample lead of one party over another in political opinion polls, one product over another in market research surveys, share of market of one company over another in industrial studies, one class over another in social investigations, one programme over another in TV viewing surveys, etc. The theoretical results include the derivation of the moment and cumulant generating functions. It is shown formally that the sampling distribution approaches normality as sample size increases. Experimental results provide guidelines for the choice of sample size to ensure adequacy of the normal approximation. Calculations based on one of the Central Limit Theorems support the results of the simulation.