Nonparametric Change-Point Estimation
Carlstein, E.
Ann. Statist., Tome 16 (1988) no. 1, p. 188-197 / Harvested from Project Euclid
Consider a sequence of independent random variables $\{X_i: 1 \leq i \leq n\}$ having cdf $F$ for $i \leq \theta n$ and cdf $G$ otherwise. A class of strongly consistent estimators for the change-point $\theta \in (0, 1)$ is proposed. The estimators require no knowledge of the functional forms or parametric families of $F$ and $G$. Furthermore, $F$ and $G$ need not differ in their means (or other measure of location). The only requirement is that $F$ and $G$ differ on a set of positive probability. The proof of consistency provides rates of convergence and bounds on the error probability for the estimators. The estimators are applied to two well-known data sets, in both cases yielding results in close agreement with previous parametric analyses. A simulation study is conducted, showing that the estimators perform well even when $F$ and $G$ share the same mean, variance and skewness.
Publié le : 1988-03-14
Classification:  Cramer-von Mises,  distribution-free,  Kolmogorov-Smirnov,  62G05,  60F15
@article{1176350699,
     author = {Carlstein, E.},
     title = {Nonparametric Change-Point Estimation},
     journal = {Ann. Statist.},
     volume = {16},
     number = {1},
     year = {1988},
     pages = { 188-197},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176350699}
}
Carlstein, E. Nonparametric Change-Point Estimation. Ann. Statist., Tome 16 (1988) no. 1, pp.  188-197. http://gdmltest.u-ga.fr/item/1176350699/