On the estimation of parameter of weighted sums of exponential distribution (Q463206)

Summary: The random variable \(Z_{n,\alpha}=Y_1+2^{\alpha}Y_2+\dots+n^{\alpha}Y_n\), with \(\alpha\in\mathbb{R}\) and \(Y_1,Y_2,\dots\) being independent exponentially distributed random variables with mean one, is considered. \textit{J. S. H. van Leeuwaarden} and \textit{N. M. Temme} [Stat. Probab. Lett. 81, No. 11, 1571--1579 (2011; Zbl 1245.62010)] attempted to determine good approximation of the distribution of \(Z_{n,\alpha}\). The main problem is estimating the parameter \(\alpha\) that has the main state in applicable research. In this paper we show that estimating the parameter \(\alpha\) by using the relation between \(\alpha\) and mode is available. The mean square error values are obtained for estimating \(\alpha\) by mode, moment method, and maximum likelihood method.