Search

This study's aim was to assess the validity of naive subjects' implicit personality theories, the correspondence among the theories, and the influence of social desirability on them. High school girls classified the items from the MMPI Psychopathic Deviate scale into clusters representing different traits. These clusters agreed closely with the factors obtained in previous factor analyses of self-reports to these items and were highly similar for individual subjects. Desirability was substantially related to the clusters, but generally did not mediate their correspondence with the factors or each other. These results indicate that the lay theories possessed validity as well as communality and that desirability had a distinct but limited involvement with the theories. (Author)

The problem of comparing proportions when some data are missing is investigated, and determination is made of what statistical techniques are appropriate under each of several probability models describing the observations likely to be missing. Monte Carlo methods were used to investigate the properties of standard estimators under each of the missing data models. Applying standard techniques which ignore the occurrence of missing observations may yield misleading conclusions. Some tests and estimators are fairly robust to the model for missing data, but others may be seriously affected. If the model for missing observations is complex, the sample information may be insufficient for adequate data analysis. This report is useful since the problem of missing data is recurrent in educational research and may present serious difficulties even for simple problems. (Author/LH)

The Monte Carlo method was used, and the factors considered were (1) level of main effects in the population; (2) level of interaction effects in the population; (3) alpha level used in determining whether to pool; and (4) number of degrees of freedom. The results indicated that when the ratio degrees of freedom (axb)/degrees of freedom (within) was large (1/4), pooling resulted in a disturbance in the actual alpha for the main effect test. The magnitude and nature of the disturbance was dependent on the alpha level employed in testing the interaction effects. The use of an alpha of .25 for the interaction effects resulted in a congruence between actual alpha and nominal alpha, and a slight increase in power. (Author/CK)

Attention has been drawn to the lack of standards for evaluating the degree of goodness of fit of patterns resulting from a principal components analysis of two data sets. An empirical sampling distribution of the statistic average trace (E'E) as E is obtained in the orthogonal procrustes problem, for various orders of A matrices was developed through a Monte Carlo approach. A method is presented which can be used as a guideline in determining whether factor structures obtained from two data sets are congruent. (Author)

Using a computer-based Monte Carlo approach to generate item responses, the results of this study indicate that, when item discrimination indices are considered, item-examinee sampling procedures having the same number of observations have different standard errors in estimating both test mean and test variance. With certain types of tests, a single item-examinee sampling plan would not yield optimal, i.e., smallest standard error, estimates of both mu and sigma squared. That is, one sampling plan would be needed to optimally estimate mu and another to optimally estimate sigma squared. In addition, it was found that single exhaustion of the item set was sufficient for estimating both mu and sigma squared. (Author)

The construction cost estimate, often expressed as an absolute cost, leads to misunderstanding between client, designers, and builders. If estimates are to be used as adequate cost indicators, their probabilistic nature must be recognized and they must be expressed not as absolute numbers but in terms of a number with some indication of the magnitude of the risk that that number may be expected to change by some stated amount. In order to develop this new type of estimate, a model is constructed that assigns a probability distribution to each cost component of the project and ends up with a probability distribution of the total cost of the project rather than a single answer. This bracketing of the cost provides a better in-depth look at the current knowledge of the project cost than does the traditional estimate. (Author)

An investigation is conducted which presents extensive Monte Carlo results which indicate the conditions under which a procedure using the F distribution can be used to study the robustness of the confidence interval procedures for small samples. A review of the literature is presented. Procedure uses a binary data matrix. Results indicate that the procedure is an extremely practical one. (CK)

The applicability of a mathematical theorem designed to trace causality of a three-variable path that consists of an initial cause variable, an intermediate variable, and a final-effect variable with control over other system variables is evaluated. The formula was used with a horizontal rather than a normal distribution, as had been done in an earlier study which successfully demonstrated the theorem. Horizontally-distributed random numbers (200x5) were generated and substituted into five interdependent equations to produce five scores for each of 200 pseudo people. Methods and techniques, data sources, and results are presented. Results indicate that the model is reliable, potentially useful to the practitioner as a multivariate tool in educational research, and a possible instrument for the investigation of causality. (AE)

In some correlational studies it is not reasonable to assume that bivariate observations are uncorrelated. An example would be a configural analysis in which two individuals are correlated across several variables (e.g., Q-technique). The present study was a Monte Carlo investigation of the robustness of techniques used in judging the magnitude of a sample correlation coefficient when observations are correlated. Empirical distributions of r, t, and Fisher's z were generated. Patterns of correlation were found which caused error rates to be as high as 0.20 when the nominal alpha was 0.05. A technique for controlling error rates in certain situations is suggested. (Author)

A paper given at a conference on statistical computation discussed teaching statistics with computers. It concluded that computer-assisted instruction is most appropriately employed in the numerical demonstration of statistical concepts, and for statistical laboratory instruction. The student thus learns simultaneously about the use of computers and those concepts which are best demonstrated through the use of computers--for example, multivariate analysis. In an introductory course on statistical inference, computers are used for weekly laboratory exercises, generating random numbers, empirical theoretical distributions, Monte Carlo studies, means, and the like. However, direct use of the computer in instruction--namely directions and questions included on-line--is at this time too expensive. As cost of computer time decreases it should become more feasible. Future planning centers around more flexible student terminals, and the development of a battery of computer-administered tests to further individual instruction. (BB)

Results showed that the canonical correlations are very stable upon replication. The results also indicated that there is no solid evidence for concluding that components are superior to the coefficients, at least not in terms of being more reliable. (Author/BJG)

Monte Carlo methods were used to investigate the robustness of techniques used in judging the magnitude of a sample correlation coefficient when observations are correlated. Empirical distributions of r, t, and Fisher's z were generated. A technique for controlling error rates in certain situations is suggested. (Author/BJG)

Focuses on three management tools--the Delphi technique, Bayesian statistics, and Monte Carlo simulation--in order to simulate a problem-solving/decision-making situation with which an educational administrator may be faced. (Author)

A computerized library of references to integral neutron experiments has been developed at the Lawrence Radiation Laboratory at Livermore. This library serves as a data base for the systematic retrieval of documents describing diverse critical and bulk nuclear experiments. The evaluation and reduction of the physical parameters of the experiments to a standard numerical format, and their comparison with calculated results using Monte Carlo computer codes and established libraries of neutron cross sections will make routine appraisal easier, and also make possible improvement of neutron transport calculations. The program has four aspects: (1) collection and retrieval of pertinent documents; (2) evaluation of specific experiments; (3) neutronics calculation appropriate to specific experiments; and (4) comparison of the results of the calculations with these experiments, followed by reexamination of the models and cross sections used in the calculations. These four aspects are discussed individually. (Author/SJ)

A large number of correlational models for cross-tabular analysis are available for utilization by social scientists for data description. Criteria for selection (such as levels of measurement and proportional reduction in error) do not lead to conclusive model choice. Moreover, such criteria may be irrelevant. More pertinent criteria are operational characteristics of a model. Operational criteria examined in this research include sensitivity to changes in population convariance; and insensitivity to sample size, table dimensions, and variable distributional characteristics. A complete facit or factorial design of 384 elements is generated to include cross-slassification conditions of typical social science utilization. A Monte Carlo computer program is then utilized to generate a cross-tabulation table as specified by the parameters of each of its design elements. Twenty-five correlational models are then applied to each of the tables. Because the tables are generated by design and their characteristics known, a priori, changes in the value of a given correlation coefficient can be explained. Analysis over all the facits lends to a description of the operational characteristics of each of the models. Finally, a factorial analysis leads to a reduction of the 25 models into four types of correlational models. (Author)

A microeconomic theory is applied in this book to computer services and costs and for the benefit of those who are decision-makers in the selection, financing, and use of computers. Subtopics of the theory discussed include value and demand; revenue and profits; time and risk; and costs, inputs, and outputs. Application of the theory is explained as it refers to the computer industry, to sale and rental of computers, and to cost and effectiveness of computer systems and of memory. A regression analysis is appended. References are given. (MF)

In a primer intended for the administrative professions, for the behavioral sciences, and for education, simulation and its various aspects are defined, illustrated, and explained. Man-model simulation, man-computer simulation, all-computer simulation, and analysis are discussed as techniques for studying object systems (parts of the "real world"). The role of models in simulation is examined. Computer systems, services, languages, and input output equipment are reviewed. An explanation of Monte Carlo techniques and their use in simulation is given. Applications of simulation are reported in almost every imaginable area: among others, computer systems, educational gaming, counseling, educational administration, communication networks, social systems, war and crisis gaming, operational gaming, management games, queuing systems, operations research and management science, business decision making, personnel problems, physical systems, continuous systems, and flight and space activities. (MF)

Describes a dry- lab" experiment for the college freshman laboratory, in which the essential features of Browian motion are given principles, using the Monte Carlo technique. Calculations principles, using the Monte Carlo technique. Calculations are carried out by a computation sheme based on computer language. Bibliography. (LC)

A discussion of the importance and procedures for including probability in the elementary through secondary mathematics curriculum is presented. Many examples and problems are presented which the author feels students can understand and will be motivated to do. Random digits, Monte Carlo methods, combinatorial theory, and Markov chains are included in the suggested curriculum. (JG)

These results indicate that in deciding on the data-gathering design to be used in seeking norm information, attention should be given to item characteristics and test length with particular attention paid to the range of biserial correlations between item response and ability. (Author)

Results provide a first step toward the establishment of guidelines for the experimenter who wishes to use nonmetric multidimensional scaling effectively, especially when an underlying configuration is hypothesized. (Author)

A description is given in which a computer program can be used to illustrate principles of statistical mechanics. The concepts of ensembles, statistical averages, and responses are classified particularly with respect to the role of statistical fluctuations. (DF)

Discusses the different strategies employed by three practical nonmetric multidimensional scaling algorithms using Monte Carlo techniques. (Author/RK)

A major problem in most predictions of school enrollment is the forecaster's failure to express adequately his certainty or uncertainty in his estimates. Describes a method whereby a forecaster can prepare probability distributions of enrollment predictions. The Monte Carlo computer simulation calculates enrollments by the multivariable method, computes probabilities, and prints the output. (Author)

Develops models to systematically forecast the tendency of an educational administrator in charge of personnel selection processes to shift from one decision strategy to another under generally stable environmental conditions. Urges further research on these processes by educational planners. (JF)

Reviews the principles of Monte Carlo calculation and random number generation in an attempt to introduce the direct and the rejection method of sampling techniques as well as the variance-reduction procedures. Indicates that the increasing availability of computers makes it possible for a wider audience to learn about these powerful methods. (CC)

In this paper a method is proposed whereby an investigator may improve the metric qualities of questionnaire and similar kinds of data. (Author)

Bales studied the flow of interaction in groups of various sizes, attempted to describe some of the basic group processes, and found that the initiation rates change so group members become hierarchially arranged according to these rates. This study focuses on the impact of the distribution of positive and negative rewards on the distribution process. (JA)

The increased emphasis on quantitative techniques in business demands that students be instructed in how computers may be used as tools of decision making. (Author)

Ce générateur a pour principe de base la distribution statistique des désintégrations nucléaires. Il est formé de 16 compteurs Geiger-Müller disposés autour d'une source radioactive et reliés par l'intermédiaire de bistables à une entrée numérique digitale de l'ordinateur 1MB 1800. Ce générateur peut être utilisé dans toutes les études faisant appel à la méthode de Monte-Carlo.