INFOR Information Systems and Operational Research · 1971 · 11 citations · 11 references
Natural SciencesMathematicsProbability TheoryStatistical ModelingStatisticsCensoring MechanismsHypothesis TestingInferential StatisticsProbabilistic ModelingStatistical InferenceCensored Data ModelingEstimation Under CensoringExponential Family DistributionsPredictionProbability Density AnalysisReliability FunctionStructural TheoryTransformations
AbstractStructural inference theory develops the unique probability density function for the parameter of a scale model. This density constitutes a strong basis for statistical inference because no information is required beyond that provided by the classical statistical model. This paper applies structural theory to the one-parameter exponential measurement model. On the basis of the structural density function for the exponential scale parameter, the probability density of the reliability function is derived. Prediction densities are then developed as an alternative class of life test inferences; these densities concern (i) an arbitrary vector of future measurements, (ii) the average of a number of future measurements, and (iii) the smallest and largest of such future measurements. The data transformations are derived which allow the results of this paper to be applied to progressively censored data of types I and II. An example is given to illustrate the structural densities of this paper.RésuméLa théorie de l’inférence structurelle permet d’obtenir, pour le paramétre d’un modéle á l’échelle, la fonction unique de densité de probabilité. Cette densité devient la base solide de l’inférence statistique parce qu’aucun autre renseignement n’est requis au-delá de ce qui est donné par le modéle statistique classique. Cet article applique la théorie structurelle á un modéle uniparamétrique de mesure exponentielle. Sur la base de la fonction de densité structurelle pour un paramétreé échelle exponentielle,la densité probable de la fonction d’endurance est calculée.Des densités prévisibles sont alors reprises comme formant une autre classe d’inérences sur les tests d’endurance; ces densités comprennent: (i) un vecteur arbitraire des mesures futures, (ii) la moyenne d’un nombrede mesures futures, (iii) la plus petite et la plus grande valeur de ces mesures futures.Les transpositions de valeurs sont déterminées pour permettre d’appiiquer les résultats de cet article á des données travaillées de types I et II. Un exemple est présenté pour illustrer les densités structurelles de cet article. Additional informationNotes on contributorsK.V. BuryKarl Bury received his BA SC degree in Engineering Physics from the University of Toronto in 1959. He worked for United Aircraft Company, Montreal, from 1959 to 1962 on the design and development of the PT6 gas turbine. He received an MS degree in Applied Mechanics from the California Institute of Technology in 1963 and an MBA degree in Business Administration from Stanford University in 1965. Karl worked for Hawker-Siddeley Company, Toronto, from 1965 to 1966 on gas turbine problems and received a PH D degree in Industrial Engineering from the University of Toronto in 1968. He is currently assistant professor ofMechanical Engineering at the University of British Columbia, doing researchin Applied Statistics in the fields of reliability and engineering design.B. BernholtzDr B. Bernholtz was born in Toronto and obtained his BA and MA in mathematics at the University of Toronto. He did postgraduate work at the California Institute of Technology where he obtained his PH D in 1952. He then returned to Canada and worked in the ResearchDivision of the Hydro-Electric Power Commission of Ontario first as a consultant in mathematics and statistics and later as an operations research analyst.In 1962, Dr Bernholtz joined the faculty of the University of Toronto as an Associate Professor in Industrial Engineering. In 1966 he became a full Professor and in 1968 was appointed Chairman of the Department of Industrial Engineering.Professor Bernholtz is theauthor of many scientific and technical papers in the Transactions of the American Institute of Electrical Engineers (now the IEEE), the Journal of the Operations Research Society of America, the cORS Journal and the siAM Review in such varied fields as optimal control, mathematical programming, queueing theory, and statistical inference.
11
Benjamin Epstein, Milton Sobel · Journal of the American Statistical Association · 1953 · 324 citations
The fiducial method and invariance
D. A. S. Fraser · Biometrika · 1961 · 131 citations
D. A. S. Fraser · The Annals of Mathematical Statistics · 1961 · 97 citations · Full text
Data Transformations and the Linear Model
D. A. S. Fraser · The Annals of Mathematical Statistics · 1967 · 45 citations · Full text
Structural probability and a generalization
D. A. S. Fraser · Biometrika · 1966 · 44 citations