Robert Cudeck
Biographic Data
| ID | 333807 |
|---|---|
| NAME | Robert Cudeck |
| GIVEN NAMES | Robert |
| FAMILY NAME | Cudeck |
| SIGNATURE | CUDECK R |
| AFFILIATIONS | University of Minnesota |
| VERIFIED | No |
| TOTAL WORKS | 21 |
| TOTAL CITATIONS | 1811 |
| AUTHOR COUNT | 21 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 1977 |
| LATEST PUBLICATION YEAR | 2006 |
| H-INDEX | 3 |
Fitting Partially Nonlinear Random Coefficient Models as SEMs
The nonlinear random coefficient model has become increasingly popular as a method for describing individual differences in longitudinal research. Although promising, the nonlinear model it is not utilized as often as it might be because software options are still somewhat limited. In this article we show that a specialized version of the model can be fit to data using SEM software. The specialization is to a model in which the parameters that en…
A Version of Quadratic Regression with Interpretable Parameters
The quadratic regression model is popular and effective in describing a wide variety of data, but it is based on a function whose parameters are not easy to interpret. We suggest an alternative form of the quadratic model that has the same expectation function, but also has the useful feature that its parameters are interpretable. Examples are provided of a simple regression problem and also of a nonlinear mixed-effects model. The models can be e…
Measurement
Mixed-effects Models in the Study of Individual Differences with Repeated Measures Data
Nonlinear mixed-effects models are used to describe each person's set of scores from a longitudinal design or repeated measures study by a function that includes an overall group effect plus an effect for the individual. The model is ideal for many kinds of behavioral data. Some characteristics of mixed models are reviewed in this article and illustrated by a series of examples
Relationships Among Measurement Models for Dichotomous Variables and Associated Composites
Applications of standard error estimates in unrestricted factor analysis: Significance tests for factor loadings and correlations
Estimates of standard errors of factor loadings and factor correlations in the unrestricted factor analysis model can be computed for oblique or orthogonal solutions under maximum likelihood. This information can be used to test individual coefficients for significance, to evaluate whether an orthogonal or oblique structure is most consistent with sample data, or to compute confidence intervals for single parameters or confidence regions for arbi…
Jeffrey S. Tanaka 1958-1992
Alternative Ways of Assessing Model Fit
This article is concerned with measures of fit of a model. Two types of error involved in fitting a model are considered. The first is error of approximation which involves the fit of the model, with optimally chosen but unknown parameter values, to the population covariance matrix. The second is overall error which involves the fit of the model, with parameter values estimated from the sample, to the population covariance matrix. Measures of the…
Model selection in covariance structures analysis and the "problem" of sample size: A clarification
Model selection in covariance structures analysis and the "problem" of sample size: A clarification
Complex models for covariance matrices are structures that specify many parameters, whereas simple models require only a few. When a set of models of differing complexity is evaluated by means of some goodness of fit indices, structures with many parameters are more likely to be selected when the number of observations is large, regardless of other utility considerations. This is known as the sample size problem in model selection decisions. This…
Single Sample Cross-Validation Indices for Covariance Structures
This article considers single sample approximations for the cross-validation coefficient in the analysis of covariance structures. An adjustment for predictive validity which may be employed in conjunction with any correctly specified discrepancy function is suggested. In the case of maximum likelihood estimation under normality assumptions the coefficient obtained is a simple linear function of the Akaike Information Criterion. Results of a rand…
Analysis of correlation matrices using covariance structure models
It is often assumed that covariance structure models can be arbitrarily applied to sample correlation matrices as readily as to sample covariance matrices. Although this is true in many cases and leads to an analysis that is mostly correct, it is not permissible for all structures. This article reviews three interrelated problems associated with the analysis of structural models using a matrix of sample correlations. Depending upon the model, app…
Binclus: Nonhierarchical Clustering of Binary Data
BINCLUS is a clustering procedure designed for aggregating binary variables into relatively homogenous clusters. It uses any of several indices of binary association and operates by a variation on the "average linkage" principle. It was tried out on a number of sets of artificial data and found to be extremely successful. With real data, where clusters are typically less clearly defined, two modifications were useful in clarifying the results. Re…
A Structural Comparison of Conventional and Adaptive Versions of the Asvab
This paper examines several structural models of similarity between a battery of conventional tests and a battery of computerized adaptive tests designed to measure the same aptitudes. Twelve plausible models are reviewed and are fitted to sample data in a double cross-validation design. Three of the 12 models provided reasonable summaries of the data. One model with a multiplicative structure (Browne, 1984) performed quite well. This model provi…
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets (NSAG) by verskillende bevolkingsgroepe
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets Intermediar G ten opsigte van vier bevolkingsgroepe is ondersoek. Die toetslinge was 13-jarige St. 5-leerlinge: Afrikaanssprekend Wit, Engelssprekend Wit, Engelssprekend Indiër, en Afrikaanssprekend Kleurling. Daar is gesoek na die faktormodel wat vir al die populasies optimaal sou wees wat eenvoud en akkuraatheid betref. Alhoewel daar 'n groot mate van ooreenkoms is tussen die faktorstr…
Cross-Validation Of Covariance Structures
This paper examines methods for comparing the suitability of alternative models for covariance matrices. A cross-validation procedure is suggested and its properties are examined. To motivate the discussion, a series of examples is presented using longitudinal data
Patterns of Crime in a Birth Cohort
Most attempts at developing typologies of criminal behavior have not involved empirical research. This paper describes an exploratory empirical approach to identifying patterns in criminal behavior. Two data-reduction techniques, factor analysis and cluster analysis, are applied to the official arrest records of a Danish birth cohort of 28,879 men. Four factors emerged from the factor analysis: GENERAL CRIME, TRAFFIC OFFENSES, WHITE-COLLAR CRIME,…
Structural Equivalence of an Intelligence Test for Two Language Groups
The factorial equivalence of the New South African Group Test (NSAGT) Intermediate Form G in Afrikaans and English was investigated. The covariance matrices of the six subtests were compared for a group of Afrikaans-speaking students ( N = 319) and a group of English-speaking students ( N = 171). Although the covariance matrices differed significantly, similarity in factor structure for the two groups was found for progressively stringent tests o…
Methods For Estimating Between-Battery Factors
In psychometric research there is often a need to examine factors from several batteries of data. Many models have been proposed to carry out this kind of analysis, but the most frequently used strategy is to apply common factor analysis to all variables, disregarding battery membership. This paper reviews a model for multiple battery factor analysis, and contrasts it with other models which have a similar purpose. Recent methodological developme…
The Evaluation of Diagnostic Models
There are two kinds of diagnostic models used in psychological research. A categorical model is used most commonly, but dimensional models have also been studied (Skinner, 1979; Strauss, 1973). When developing or using a model, it is important to determine when the model is appropriate for a particular setting. Unfortunately, methods for carrying out this kind of evaluation are only applied infrequently, particularly with categorical models. This…
Tailor: A Fortran Procedure for Interactive Tailored Testing
TAILOR, a FORTRAN program for tailored testing, is described. The procedure for a joint ordering of persons and items with no pretesting as the basis for the tailored test is given, and a brief discussion of the computer program is included
Alternative Ways of Assessing Model Fit
This article is concerned with measures of fit of a model. Two types of error involved in fitting a model are considered. The first is error of approximation which involves the fit of the model, with optimally chosen but unknown parameter values, to the population covariance matrix. The second is overall error which involves the fit of the model, with parameter values estimated from the sample, to the population covariance matrix. Measures of the…
Analysis of correlation matrices using covariance structure models
It is often assumed that covariance structure models can be arbitrarily applied to sample correlation matrices as readily as to sample covariance matrices. Although this is true in many cases and leads to an analysis that is mostly correct, it is not permissible for all structures. This article reviews three interrelated problems associated with the analysis of structural models using a matrix of sample correlations. Depending upon the model, app…
Model selection in covariance structures analysis and the "problem" of sample size: A clarification
Complex models for covariance matrices are structures that specify many parameters, whereas simple models require only a few. When a set of models of differing complexity is evaluated by means of some goodness of fit indices, structures with many parameters are more likely to be selected when the number of observations is large, regardless of other utility considerations. This is known as the sample size problem in model selection decisions. This…
Applications of standard error estimates in unrestricted factor analysis: Significance tests for factor loadings and correlations
Estimates of standard errors of factor loadings and factor correlations in the unrestricted factor analysis model can be computed for oblique or orthogonal solutions under maximum likelihood. This information can be used to test individual coefficients for significance, to evaluate whether an orthogonal or oblique structure is most consistent with sample data, or to compute confidence intervals for single parameters or confidence regions for arbi…
Structural Equivalence of an Intelligence Test for Two Language Groups
The factorial equivalence of the New South African Group Test (NSAGT) Intermediate Form G in Afrikaans and English was investigated. The covariance matrices of the six subtests were compared for a group of Afrikaans-speaking students ( N = 319) and a group of English-speaking students ( N = 171). Although the covariance matrices differed significantly, similarity in factor structure for the two groups was found for progressively stringent tests o…
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets (NSAG) by verskillende bevolkingsgroepe
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets Intermediar G ten opsigte van vier bevolkingsgroepe is ondersoek. Die toetslinge was 13-jarige St. 5-leerlinge: Afrikaanssprekend Wit, Engelssprekend Wit, Engelssprekend Indiër, en Afrikaanssprekend Kleurling. Daar is gesoek na die faktormodel wat vir al die populasies optimaal sou wees wat eenvoud en akkuraatheid betref. Alhoewel daar 'n groot mate van ooreenkoms is tussen die faktorstr…
Tailor: A Fortran Procedure for Interactive Tailored Testing
TAILOR, a FORTRAN program for tailored testing, is described. The procedure for a joint ordering of persons and items with no pretesting as the basis for the tailored test is given, and a brief discussion of the computer program is included
Methods For Estimating Between-Battery Factors
In psychometric research there is often a need to examine factors from several batteries of data. Many models have been proposed to carry out this kind of analysis, but the most frequently used strategy is to apply common factor analysis to all variables, disregarding battery membership. This paper reviews a model for multiple battery factor analysis, and contrasts it with other models which have a similar purpose. Recent methodological developme…
The Evaluation of Diagnostic Models
There are two kinds of diagnostic models used in psychological research. A categorical model is used most commonly, but dimensional models have also been studied (Skinner, 1979; Strauss, 1973). When developing or using a model, it is important to determine when the model is appropriate for a particular setting. Unfortunately, methods for carrying out this kind of evaluation are only applied infrequently, particularly with categorical models. This…
Cross-Validation Of Covariance Structures
This paper examines methods for comparing the suitability of alternative models for covariance matrices. A cross-validation procedure is suggested and its properties are examined. To motivate the discussion, a series of examples is presented using longitudinal data
Patterns of Crime in a Birth Cohort
Most attempts at developing typologies of criminal behavior have not involved empirical research. This paper describes an exploratory empirical approach to identifying patterns in criminal behavior. Two data-reduction techniques, factor analysis and cluster analysis, are applied to the official arrest records of a Danish birth cohort of 28,879 men. Four factors emerged from the factor analysis: GENERAL CRIME, TRAFFIC OFFENSES, WHITE-COLLAR CRIME,…
Structural Equivalence of an Intelligence Test for Two Language Groups
The factorial equivalence of the New South African Group Test (NSAGT) Intermediate Form G in Afrikaans and English was investigated. The covariance matrices of the six subtests were compared for a group of Afrikaans-speaking students ( N = 319) and a group of English-speaking students ( N = 171). Although the covariance matrices differed significantly, similarity in factor structure for the two groups was found for progressively stringent tests o…
A Structural Comparison of Conventional and Adaptive Versions of the Asvab
This paper examines several structural models of similarity between a battery of conventional tests and a battery of computerized adaptive tests designed to measure the same aptitudes. Twelve plausible models are reviewed and are fitted to sample data in a double cross-validation design. Three of the 12 models provided reasonable summaries of the data. One model with a multiplicative structure (Browne, 1984) performed quite well. This model provi…
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets (NSAG) by verskillende bevolkingsgroepe
Die faktorstruktuur van die Nuwe Suid-Afrikaanse Groeptoets Intermediar G ten opsigte van vier bevolkingsgroepe is ondersoek. Die toetslinge was 13-jarige St. 5-leerlinge: Afrikaanssprekend Wit, Engelssprekend Wit, Engelssprekend Indiër, en Afrikaanssprekend Kleurling. Daar is gesoek na die faktormodel wat vir al die populasies optimaal sou wees wat eenvoud en akkuraatheid betref. Alhoewel daar 'n groot mate van ooreenkoms is tussen die faktorstr…
Binclus: Nonhierarchical Clustering of Binary Data
BINCLUS is a clustering procedure designed for aggregating binary variables into relatively homogenous clusters. It uses any of several indices of binary association and operates by a variation on the "average linkage" principle. It was tried out on a number of sets of artificial data and found to be extremely successful. With real data, where clusters are typically less clearly defined, two modifications were useful in clarifying the results. Re…
Single Sample Cross-Validation Indices for Covariance Structures
This article considers single sample approximations for the cross-validation coefficient in the analysis of covariance structures. An adjustment for predictive validity which may be employed in conjunction with any correctly specified discrepancy function is suggested. In the case of maximum likelihood estimation under normality assumptions the coefficient obtained is a simple linear function of the Akaike Information Criterion. Results of a rand…
Analysis of correlation matrices using covariance structure models
It is often assumed that covariance structure models can be arbitrarily applied to sample correlation matrices as readily as to sample covariance matrices. Although this is true in many cases and leads to an analysis that is mostly correct, it is not permissible for all structures. This article reviews three interrelated problems associated with the analysis of structural models using a matrix of sample correlations. Depending upon the model, app…
Model selection in covariance structures analysis and the "problem" of sample size: A clarification
Model selection in covariance structures analysis and the "problem" of sample size: A clarification
Complex models for covariance matrices are structures that specify many parameters, whereas simple models require only a few. When a set of models of differing complexity is evaluated by means of some goodness of fit indices, structures with many parameters are more likely to be selected when the number of observations is large, regardless of other utility considerations. This is known as the sample size problem in model selection decisions. This…
Alternative Ways of Assessing Model Fit
This article is concerned with measures of fit of a model. Two types of error involved in fitting a model are considered. The first is error of approximation which involves the fit of the model, with optimally chosen but unknown parameter values, to the population covariance matrix. The second is overall error which involves the fit of the model, with parameter values estimated from the sample, to the population covariance matrix. Measures of the…
Jeffrey S. Tanaka 1958-1992
Applications of standard error estimates in unrestricted factor analysis: Significance tests for factor loadings and correlations
Estimates of standard errors of factor loadings and factor correlations in the unrestricted factor analysis model can be computed for oblique or orthogonal solutions under maximum likelihood. This information can be used to test individual coefficients for significance, to evaluate whether an orthogonal or oblique structure is most consistent with sample data, or to compute confidence intervals for single parameters or confidence regions for arbi…
Relationships Among Measurement Models for Dichotomous Variables and Associated Composites
Mixed-effects Models in the Study of Individual Differences with Repeated Measures Data
Nonlinear mixed-effects models are used to describe each person's set of scores from a longitudinal design or repeated measures study by a function that includes an overall group effect plus an effect for the individual. The model is ideal for many kinds of behavioral data. Some characteristics of mixed models are reviewed in this article and illustrated by a series of examples
Measurement
A Version of Quadratic Regression with Interpretable Parameters
The quadratic regression model is popular and effective in describing a wide variety of data, but it is based on a function whose parameters are not easy to interpret. We suggest an alternative form of the quadratic model that has the same expectation function, but also has the useful feature that its parameters are interpretable. Examples are provided of a simple regression problem and also of a nonlinear mixed-effects model. The models can be e…
Fitting Partially Nonlinear Random Coefficient Models as SEMs
The nonlinear random coefficient model has become increasingly popular as a method for describing individual differences in longitudinal research. Although promising, the nonlinear model it is not utilized as often as it might be because software options are still somewhat limited. In this article we show that a specialized version of the model can be fit to data using SEM software. The specialization is to a model in which the parameters that en…
Mathematics (18 works) · Computer Science (14 works) · Statistics (13 works) · Econometrics (10 works) · Psychology (9 works) · Artificial Intelligence (8 works) · Psychometric Methodologies and Testing (8 works) · Artificial Intelligence (7 works) · Covariance (7 works) · Advanced Statistical Methods and Models (6 works)