Integrated marked Poisson processes with application to image correlation spectroscopy

Image correlation spectroscopy (ICS) is an experimental technique used in the study of cell tissue, specifically to obtain information about protein aggregates. This paper discusses a filtered Poisson process model of ICS, and uses this to obtain the sampling distribution of an estimator of interest, using spectral methods. Integrals of third- and fourth-order spectra are involved, and methods proposed in the literature are studied numerically. They are found to be infeasible methods, requiring months of computing time. An alternative method is proposed and is illustrated on some actual ICS experiments. A novel feature in this study is the use of a SIMD-class parallel computer, a MasPar MP-2 machine, to obtain some statistical properties of the estimation method.     

Computer generated simple random samples

Three computer methods, namely the Random Draw, the Sequential and the Reservoir Methods, to obtain a simple random sample without replacement are reviewed. Several implementations of each method are given and criteria for the selection of an implementation are discussed. The most promising ones are compared for efficiency in their execution times. It is concluded that for small sampling fractions, Ernvall and Nevalainen's (1982) implementation of the Random Draw Method is most efficient when N, the population size, is known. When N is unknown, an Algorithm Z of Vitter (1985), an implementation of the Reservoir Method, is recommended. For larger sampling the algorithm of Bissell (1986) and Vitter (1984) is quite efficient.     

Differences in Life Expectancy Between Self-Employed Workers and Paid Employees when Retirement Pensioners: Evidence from Spanish Social Security Records

European Journal of Population - The aim of this paper is to examine differences in life expectancy (LE) between self-employed (SE) and paid employee (PE) workers when they become retirement...     

Properties of a fourier bootstrap method for time series

A method for bootstrapping stationary Gaussian sequences is studied. The FFT is applied to the original data, randomized in the frequency domain, and the inverse FFT is applied. The result is a sequence whose second order properties are similar to those of the original sequence. Conditions under which the method is valid are given.     

A month carlo approximation of the distributions of the maximum of various brownjan bridges

A Brownian bridge of order a is the weak limit of a residual partial sum obtained from regression fitting. When q=0, the process is teh usual Brownian bridge, and the distribution of the maximum is known analytically. For q>1, the reflection principle does not easily apply. The supremum distributions are approximated by a Monte Carlo technique. Tables of these distributions, as well as a finite sample size correction are given.     

Assessing trunk roads—The conservationist viewpoint

The economic, social and environmental impacts of trunk roads have, to say the least, created much heated discussion and perhaps too little considered evaluation. This paper puts forward a methodology for effectively examining the Trunk Roads Programme from the environmentalist's viewpoint. The authors rightly concentrate on the fact that the road programme has, to some extent at least, become a paradigm for the whole consumer based system. They pursue the argument further than the elementary conflict between competing systems of public transport and pursue the difficult, but important, questions of the dichotomy between the desire for individual mobility (and its assumptions of human liberty) and the need to evaluate external costs which are rarely levied in full upon the beneficiaries. Whilst much of the article concentrates on the principles of a cost benefit evaluation, it brings out some rather important and long term aspects of the construction of these arteries of society which can be described as either scars upon the earth or liberating and effective avenues of mobility. The question remains a vital one for society at large.     

On random grouping in goodness of fit tests of discrete distributions

We consider the problem of random grouping of data from discrete distributions to form χ² goodness of fit tests. In general the random partitions need not converge to the partition one gets using the true distribution function and the same partitioning scheme. We present a method of guaranteeing the convergence of the random partition and yielding the usual χ² asymptotics.     

Statistical inference for some Volterra population processes in a random environment

We study the problem of maximum-likelihood estimation in some random-environment population models, defined through nonlinear ltǒ stochastic differential equations. It is shown that a criticality parameter can be estimated consistently. The asymptotic behavior of the estimators is analyzed, and a goodness-of-fit test is proposed.