Showing papers on "Reliability (statistics) published in 1968"

A simplified criterion for the reliability of a powder pattern indexing

Abstract: A figure of merit is defined for an indexing of a given pattern as M20 = Q20/2\overline \epsilonN20. Here N20 is the number of different calculated Q values up to Q20, which is the Q value for the 20th observed and indexed line; is the average discrepancy in Q for these 20 lines. From a number of indexings which have been disproved by single-crystal analysis, the conclusion is drawn that M20 10 guarantees that the indexing is substantially correct.

On the importance of different components in a multicomponent system

Abstract: : In a system whose functioning or failure depends on the functioning or failure of its components, some components may play a more important part than others. A quantitative definition of this notion of importance is proposed in the present paper for systems with coherent structures, assuming (1) that only the structure of the system is known, or (2) that also the reliabilities of all components are known. Some theoretical properties of the so defined concepts are discussed, and applications are presented to such problems as allocation of spare parts or appropriation of funds for improvement of component reliability.

Probabilistic Reliability: An Engineering Approach

Abstract: (1969). Probabilistic Reliability: An Engineering Approach. Technometrics: Vol. 11, No. 1, pp. 206-206.

System Reliability Allocation and a Computational Algorithm

Abstract: The detailed allocation method of system reliability discussed in this paper is designed to select the optimal solution in the context of the trade-off analysis. It is noted that the problem may be structured as an n-stage sequential decision problem. A computational algorithm is developed using dynamic programming.

Frequency and Duration Methods for Power System Reliability Calculations: I - Generation System Model

Abstract: As a goal, the evaluation and computation of electric power system reliability requires that a consistent technique be used for all portions?generation, transmission, and distribution. At present, a number of different methods are used for the generation system, while the frequency and duration of outages seems to be developing as a standard measure for the analysis of the distribution system. This paper and a subsequent one will present a reliability calculation method for the generation system that incorporates the frequency and duration of unit outages and includes consideration of the loads. This method leads to calculated generation reliability measures which are the availability, frequency of occurence, and mean duration of reserve states. These are cumulative states in that they specify system reserve conditions of a given magnitude or less. This paper is concerned with the procedure for calculating the availability, frequency, and outage duration for a number of generating units connected in parallel to form a single system. Numerical data are used to illustrate the technique and make comparisons with other methods.

Deriving coefficients of reliability and agreement for ratings.

Abstract: The paper is concerned with the measurement of internal consistency of rating scales and interviewing schedules, with the assessment of bias between different raters and with coefficients for measuring the degree of agreement between them. Analysis of variance models are first employed, but reference is also made to earlier psychometric techniques and to recent work by Armitage et al. and by Fleiss.

Reliability of Structures and Structural Systems

Abstract: The safety and reliability of structures and structural systems are examined within the context of several physically plausible assumptions. Some fundamental results are derived to clarify the consequences of various assumptions pertaining to a system and its components on the reliability of a structure. Among these results are: (1) The risk function of a structure is shown to be a monotonically decreasing function of the number of loads sustained; thus, assuming a constant risk equal to the probability of failure to the first load leads to a safe estimate of the true reliability; (2) recognizing that the member forces in a structural system are always perfectly correlated, the reliability of a structural system is bounded above by the reliability computed on the assumption of perfectly correlated member strengths, and bounded below by the reliability computed on the assumption of statistically independent member strengths; and (3) the reliability computed on the usual assumption that the failure of members are statistically independent events invariably leads to an extremely conservative estimate of the true system reliability. As far as the survival of the original system is concerned, the treatment of statically indeterminate systems is the same as that of determinate systems.

Radiological signs of ulcerative colitis: assessment of their reliability by means of observer variation studies.

Abstract: Since the radiological appearances of ulcerative colitis were described in 1912 by Stierlin, these appearances have evoked much investigation and speculation. Many and varied radiological signs are described as typical of ulcerative colitis and yet very few workers have attempted to analyse these signs in any detail in order to determine their reliability, usefulness, and prognostic significance to the patient. It therefore seems to us particularly relevant to examine our own experience in this field in a highly critical manner. Our investigations have been divided into three parts. We have carried out preliminary observer variation studies in order to determine the reliability of each individual radiological sign. Next we have subjected those of the signs which were found to be reliable to further analysis by a correlation with the clinical state and prognosis of the patient. And finally we have investigated the change in the extent of colitis which has talken place in our patients over a period of years. In this report we shall describe the results of our initial studies, namely, those involving observer variation.

Systems Reliability Subject to Multiple Nonlinear Constraints

Abstract: A simple computational procedure has been developed for maximizing reliability of multistage parallel systems subject to multiple nonlinear constraints. It appears that the procedure can be applied to a variety of optimization problems with separable objective and multiple constraint functions.

Rating Scales as Measures of Clinical Judgment: a Method for Increasing Scale Reliability and Sensitivity

Abstract: Low reliability and uncertain validity are not the only problems encountered with rating scales in clinical research: ratings are also notably influenced by such response sets as &dquo;leniency&dquo; (Guilford, 1954), or &dquo;social desirability&dquo; (Edwards, 1957) ; the range and average level of the behavior being rated can produce marked anchoring effects (Bieri et al., 1966); idiosyncratic tendencies towards polarization or midpoint clustering are common, etc. It is here argued that these faults are not a necessary concomitant of rating scales per se, but instead spring from two main sources: (1) a failure to determine the unidimensionality (or order) of the universe being measured, and (2) a reliance upon absolute, rather than comparative judgments. This paper describes a convenient

Reliability Physics

Abstract: It is the purpose of this paper to introduce the issue of this TRANSACTIONS devoted entirely to reliability physics and to provide a frame of reference for the individual technical papers which follow. The organizers of this issue felt that a paper putting the various elements of reliability physics into proper perspective, and relating them to the prior art and to their proper fields of application could serve as a useful guide to the reader of this issue and to the literature.

An Exploratory Study of Programmed Tests

Abstract: One approach to the reduction of testing time is through the use of “programmed tests,” which are tests based on a sequential system of branching in which a subject is directed to items appropriate to his ability level. The programmed tests considered in the present paper comprised two major sections: (1) A routing section which contains the branching necessary to direct the subject to the appropriate items, and (2) a measurement section which contains a short test with the item difficulties concentrated at the appropriate level for the subject. Four methods were investigated on an existing item data for — 885 students. By using approximately 40 items in the programmed tests it was possible to obtain correlations with the total test score on 190 items that were quite close to the reliability of the 190-item test. However, essentially the same results were achieved for two shortened conventional tests consisting of the 40 or 42 items with the highest point-biserial correlations with the total test score.

A device for rapid recording of positioning responses in two dimensions

Abstract: A device for rapid recording of positioning responses is described. It utilizes an extremely simple, low-cost position transducer and two digital voltmeters or their equivalent. The device has the advantages of rapid, accurate measurement, reliability, ease of reading, and the potential for automatic recording of positional data in two dimensions.

Predicting the future

Abstract: : The author comments on opinion as the basic means of forecasting technological and social developments in the economy.

Advanced Techniques for Fluorescein Angiography

Abstract: THE USE of fluorescent angiophotography is becoming increasingly widespread in the investigation of both clinical and research problems. It is therefore pertinent to reevaluate and improve existing technical methods in order to obtain better results. The purpose of this paper is to describe the modifications of the fundus camera (Zeiss) for rapid serial photography and to discuss the use of an improved filter system and a new mechanical injection system. The utilization of the phenomenon of fluorescent emission in fluorescein angiography of human ocular tissues presents many technical difficulties.1There is, in addition, the problem of ensuring the safety and reliability which is essential to any clinical procedure. The method to be described is presented as one which shows technical improvement without detriment to the well being of the patient. Camera System It is particularly important in dynamic studies of the retinal circulation to have a high initial dye

The study of early maps: Methodology

Abstract: Summary The literature about the history of early maps contains numerous studies in which their reliability has been assessed ‐either directly or implicitly ‐ by a variety of well‐established techniques. On the other hand, few studies have attempted to isolate these methods for the benefit of new researchers or as a basis for a discussion of their validity. The present paper sets down a few skeletal notes on the topic, considering both evidence of reliability on the maps themselves, and some of the external sources which assist in critical interpretation.

A Bayesian Reliability Growth Model

Abstract: A model is presented for the change (growth) in reliability of a system during a test program. Parameters of the model are assumed to be random variables with appropriate prior density functions. Expressions are then derived that enable estimates (in the form of expectations) and precision statements (in the form of variances) to be made of: 1) projected system reliability at time ? after the start of the test program, and 2) system reliability after the observation of failure data. Numerical examples are presented, and extension to multimode failures is indicated.

Distribution System Reliability Performance

Abstract: Techniques are presented for the estimation of service interruptions initiated in the distribution system. Average service interruption rates and restoration times are calculated from failure rate and repair time data for equipment and lines. A quantitative method is suggested for evaluating the economic consequences of service interruptions. Calculations of reliability performance and its economic consequences are made for representative distribution circuits.

An Instrument for Evaluating Experimental Educational Research Report

Abstract: An Instrument for Evaluating Experimental Research Reports was developed after synthesis of the suggestions of experts. In two studies of reliability with articles from the field of elementary mathematics education and raters from that field and from educational psychology, coefficients of Inter-rater agreement of .01 and .04 resulted, while .77 and .58 were the corresponding coefficients of Intra-class reliability. The Instrument is suggested for use not only In evaluation, but also In planning and developing research studies.