Statistische eigenschappen van een vlambeveiliging met behulp van een gasontladingsbuis welke gevoelig is voor ultraviolet licht

Summary  The output voltage of a detector circuit containing a gas-filled tube sensitive to ultraviolet radiation can be used to indicate whether a flame is still burning or not. As long as the flame is burning the random nature of the discharges of the tube leads to random fluctuations in the output voltage, which can be considered as a Markov-process with dependent increments. The problem is to select an alarm level for the output voltage with a suitable chosen probability of exceedance while the flame is burning, in order to limit the probability of false alarm. In this article a method is given for determining upper and lower bounds for the distribution function of the output voltage at any moment, answering the question of the alarm level to be chosen. Results are given for a special circuit.     

Structural Changes in Australian Manufacturing Industry*

The paper uses a neoclassical production function and historical data to test for structural stability in Australian manufacturing industry. The production function is an extended constant elasticity of substitution form in which factor substitution elasticity, returns to scale and market structure in output, capital and labour are testable hypotheses. Tests for structural changes in homogeneity and factor substitution elasticity relations are based on overall and individual tests of covariance analysis and also on a special version of the Swerling-Kalman filtering systems as proposed by Cooley and Prescott. The empirical findings possess desirable statistical properties and indicate the existence of structural instability in the industry. The evidence also repudiates the assumptions of unitary factor substitution elasticity, constant returns to scale and market competitiveness in output and factors of production.