Estimation in a model with infinite dimensional nuisance parameter
Zapiski Nauchnykh Seminarov POMI, Probability and statistics. Part 8, Tome 320 (2004), pp. 160-165
Citer cet article
Voir la notice du chapitre de livre provenant de la source Math-Net.Ru
Let $X_1$ be a random variable with density function $f(t)$, $\Psi(t)$ be an increasing absolutely continuous function, $\Phi(t)$ be the inverse function, random variable $X_2$ be defined by $X_2=\Phi(X_1)$. We consider the maximum likelihood estimator for density $\psi$ of function $\Psi$ as we observe two independent samples from the distribution of $X_1$ and $X_2$. Under appropriate conditions on the involved distributions, we prove the consistency of maximum likelihood estimator.
[1] Wing Hung Wong, N. Xiatong Shen, “Probability inequalities and convergence rates of sieve mles”, The Annals of Statistics, 2 (1995), 2555–2591