Introduction to Configural Frequency Analysis :The Search for Types and Antitypes in Cross-Classification ( Environment and Behavior )

Publication subTitle :The Search for Types and Antitypes in Cross-Classification

Publication series :Environment and Behavior

Author: Alexander von Eye  

Publisher: Cambridge University Press‎

Publication year: 1990

E-ISBN: 9781139242738

P-ISBN(Paperback): 9780521380904

Subject: O212.4 Multivariate Analyses

Keyword: 心理学研究方法

Language: ENG

Access to resources Favorite

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Introduction to Configural Frequency Analysis

Description

Configural Frequency Analysis (CFA) is a method for analysis of groups of individuals in cross-classifications. Individuals belong to a type if their particular pattern of characteristics occurs more often than expected, and to an antityte if their particular pattern of characteristics occurs less often than expected. The author's original contribution is his linking of CFA to log-linear modeling and the General Linear Model, enabling the reader to relate CFA to a well-known statistical background. It is shown that CFA and log-linear modeling are methods that complement each other. Introduction to Configural Frequency Analysis covers the latest developments in CFA, and it will be easy to read even for those with only an elementary statistics course as a background.

Chapter

2 Testing for types and antitypes

2.1 The binomial test and its approximations

2.1.1 Approximation of the binomial test using

2.1.2 Approximation of the binomial test using the DeMoivre-Laplace limit theorem

2.1.3 Standard normal approximation of the binomial test

2.1.4 Chi-square approximation of the z-test statistic

2.1.5 Heilmann and Schutt's F-approximation of the binomial test

2.2 Asymptotic CFA tests based on distributional assumptions

2.2.1 Lehmacher's asymptotic hypergeometrical test

2.2.2 Kiichenhoffs continuity correction of Lehmacher's asymptotic test

2.3 Comparison of CFA tests using empirical data

2.4 The problem of simultaneous testing in CFA: procedures for alpha adjustment

2.4.1 Alpha adjustment using Bonferroni's inequality

2.4.2 Holm's method for alpha adjustment

2.4.3 Hommel, Lehmacher, and Perlfs modifications of Holm's method

2.5 Application and comparison of procedures for alpha adjustment in CFA testing

3 Models of CFA: concepts and assumptions

3.1 The hierarchy of global CFA models

3.1.1 Zero order CFA

3.1.2 First order CFA

3.1.3 Second order CFA

3.2 Regional CFA models

3.2.1 Interaction structure analysis

3.2.2 Variations of ISA

3.2.3 CFA of directed relations

3.2.4 Comparison of DCFA, ISA, and PCFA

Part II : Applications and Strategies of CFA

4 Global models of CFA: applications and examples

4.1 Zero order CFA

4.2 First order CFA

4.3 Second and higher order CFA

5 Regional models of CFA: applications and examples

5.1 Interaction structure analysis

5.1.1 Estimation of expected frequencies

5.1.2 Goals of ISA

5.1.3 Models of ISA and data examples

5.2 ISA strategies

5.3 Special ISA application: independence of factorially defined tests

5.4 Prediction CFA

5.5 Application of PCFA: special issues

5.5.1 Conditional prediction CFA: stratifying on a variable

5.5.2 Biprediction CFA

5.5.3 Prediction coefficients

5.6 Comparison of k samples

5.6.1 Two-sample CFA

5.6.2 k-sample CFA

5.6.3. Combination of ISA and k-sample CFA

5.7 CFA of directed relationships

5.8 Aggregation of types and antitypes

Part III : Methods of Longitudinal CFA

6 CFA of change over time

6.1 CFA of differences

6.2 CFA of shifts in location

6.3 CFA of first, second, and higher differences

6.3.1 CFA of first differences between t observation points

6.3.2 CFA of second and higher differences between t observation points

6.4 Considering both level and trend information

6.4.1 CFA of categories of trend and location

6.4.2 CFA of orthogonal polynomial coefficients for equidistant time points

6.4.3 CFA of orthogonal polynomial coefficients for nonequidistant time points

6.5 CFA of time series of different length

6.6 CFA in the analysis of treatment effects

6.7 CFA of treatment effects in control group designs

6.8 CFA of patterns of correlation or of distance sequences

Part IV : Strategies of CFA and computational issues

7 Exploratory and confirmatory search for types and antitypes

7.1 Exploratory and hybrid CFA

7.2 Confirmatory CFA

8 CFA and log-linear models

9 Computational issues

9.1 Programs for pocket calculators

9.2 Programs for microcomputers

9.3 Programs for main frame computers

Appendix A : Computational issues: the estimation of tail probabilities for the standard normal and the F distributions

The estimation of tail probabilities for the z statistic

The estimation of tail probabilities for the F statistic

Appendix B : Estimation of expected frequencies in 2 x 2 x 2 tables under the assumption that main effects and first order interactions exist

Appendix C : Critical alpha levels under Holm adjustment for up to 330 cells and a priori alphas 0.05 and 0.01

References

Subject Index

Author Index