For nonnegative integer category counts with fixed total , the multinomial likelihood is
Use for zero-count factors. For , its maximum-likelihood estimator on the closed probability simplex is . Maximizing under the sum constraint gives this result; an observed zero category has fitted probability zero. If strict positivity is required for every , a zero observed count can place the optimum on an excluded boundary, yielding a supremum rather than an attained maximum.
For counts the fitted probabilities are . The corresponding likelihood is . When , every count is zero and the likelihood is identically one for every allowed probability vector. There is then no unique fitted vector, and the formula is undefined. The fixed-total sampling experiment differs from independent Poisson distribution cell sampling, although the Poisson trick connects their likelihoods under appropriate nuisance-rate treatment.
For counts with a multinomial distribution, this is twice the log likelihood ratio of the saturated cell-probability estimate to fixed probabilities . Zero-count terms have limiting value zero. Simulation under the specified probabilities gives a direct reference distribution when asymptotic approximations are unsuitable.

Articles by others on the same topic (0)

There are currently no matching articles.