Kamal C. Chanda

Density estimation for linear processes

SummaryLetXt, ...,Xn be random variables forming a realization from a linear process

Chi-Square Goodness-of-Fit Tests Based on Dependent Observations

X_t = \sum\limits_{r = 0}^\infty {g_r Z_{t - r} }

Sampling distribution for a class of estimators for nonregular linear processes

where {Zt} is a sequence of independent and identically distributed random variables with E|Zt|<∞ for some ε>0, andgr→0 asr→∞ at some specified rate. LetX1 have a probability density functionf. It is then established that for every realx, the standard kernel type estimator

Some comments on sample quantiles for dependent observations

\hat f_n (x)

On some nonparametric estimators for the linear markov scheme

based onXt (1≦t≦n) is, under some general regularity conditions, asymptotically normal and converges a.s. tof(x) asn→∞.

Probabilities of Large Deviations of Sample Quantiles

In this paper we introduce the concept of m(n)-decomposability as an alternative to classical mixing concepts. We illustrate how to handle the ensuing technicalities by proving asymptotic normality of L-statistics, based on such a decomposable time series, as a typical example.