Showing papers in "Metrika in 1968"
TL;DR: The concepts of inaccuracy, ent ropy and information have been connected and the concept extended to the case of continuous distributions and its application to coding theory was discussed.
Abstract: N _ _ iment as {qk}k= ~, ~ qk 1 whereas the true probabilities are {pk}N= ~, it k being assumed tha t if Pk = 0, then qk = 0 for some k, if any. We have (i) extended this concept to the case of continuous distributions (ii) int roduced inaccuracy of order a for both the discrete as well as continuous distr ibutions and discussed its application to coding theory. Fur ther , the concepts of inaccuracy, ent ropy and information have been connected.
29 citations
16 citations
14 citations
8 citations
4 citations
TL;DR: In this paper, a conservative distribution-free general procedure for testing the null hypothesis that two distributions differ at most by the value of a parameter is proposed, which is similar to our approach.
Abstract: A conservative distribution-free general procedure is proposed for testing the null hypothesis that two distributions differ at most by the value of a parameter.
3 citations
TL;DR: In this article, a class of frequency distributions consisting of the negative hypergeometric distribution and its limit cases, namely, the negative binomial, binomial and Poisson, gamma, beta, and normal distributions are studied.
Abstract: This paper deals with a class of frequency distributions consisting of the negative hypergeometric distribution and its limit cases, namely, the negative binomial, binomial, Poisson, gamma, beta and normal distributions. In view of the relationships existing between the various members of this class, it is found convenient to discuss jointly for all the distributions certain topics, including additivity properties, a property related to the information measure in point estimation, as well as a comparison of frequency theory and Bayesian theory interpretations of interval estimation.
3 citations
Journal Article•
2 citations
TL;DR: In this paper, an analysis of a system with N 1 components of one type and N 2 components of another type in parallel with uninterrupted running times of each component following exponential distribution and the repair time following arbitrary distribution is given.
Abstract: This paper gives an analysis of a system withN
1 components of one type andN
2 components of another type in parallel with uninterrupted running times of each component following exponential distribution and the repair time following arbitrary distribution. The head of the line and preemptive resume priority disciplines have been imposed on the repair of the components. The busy period process is investigated first using the supplementary variable method. Then the general time dependent process in which busy periods alternate with idle periods has been studied in terms of the busy period probabilities and probability of finding the repair facility idle at timet. Finally, the long-run availability of the system in terms of the steady state probabilities for the two cases of priority disciplines has been obtained.
2 citations
1 citations
TL;DR: Goodman and Khatri as mentioned in this paper considered some aspects of analysis of variance and covariance theory for the complex normal distribution introduced by Goodman and pointed out the similarity between the real and the complex case.
Abstract: In this paper we consider some aspects of analysis of variance and covariance theory for the complex normal distribution introduced byGoodman (1963). The properties which we consider are similar to those in the real case.Goodman (1963), andKhatri (1965) have studied several other properties of the complex normal model and have pointed out the similarity between the real and the complex case.
TL;DR: In this paper, the regret function is defined as the expectation of avoidable costs for a lot of defective units in a sample of sizen, and the usefulness of the sampling plan (n, c) is described by regret function.
Abstract: A lot is accepted if the number of defective units in a sample of sizen does not exceed the acceptance numberc. The usefulness of the sampling plan (n, c) is described by the regret function. This regret functionR(p), depending on the proportionp of defective units in the lot, is the expectation of the avoidable costs. There always exists an optimum sampling plan which minimizes the maximum ofR(p). The dependence of the maxima ofR(p) onn andc is studied and some theorems are given which are useful for calculating the minimax solution, that is the optimum sampling plan.