Borrowing Strength from Images to Facilitate Exploratory Structural Analysis of Binary Variables
This paper concerns exploratory structural analysis of relations among binary variables. Some new methods are described and illustrated, methods that appear to hold promise for general improvements in binary structural analysis. Standard common factor theory and methods, including image analysis, are used in combination with methods for data smoothing, to construct an alternative data system at the outset of analysis. Most of the new algorithms are relatively fast, easy to explain and to program, and appear to work as intended, at least for initial applications with real and simulated data. Given various advances in statistical theory and methods for prediction, as well as increasingly powerful and convenient computing facilities, there are a number of ways to extend the methods discussed here beyond the current framework.
KeywordsBinary Variable Coefficient Matrice Factor Coefficient Tetrachoric Correlation Apply Psychological Measurement
Unable to display preview. Download preview PDF.
- Chen, C. (1979) Bayesian inference for a normal dispersion matrix and its applications to stochastic multiple regression. Journal of the Royal Statistical Society, Series B, 41, 235 —248.Google Scholar
- Harris, C.W. (1962). Some Rao-Guttman relationships. Psychometrika, 27, 247 –263.Google Scholar
- Pruzek, R.M. and Lepak, G. (1992) Weighted structural regression: A broad class of adaptive methods for improving linear prediction. Multivariate Behavioral Research, 27, 95 – 129.Google Scholar
- Rabinowitz, S.N., Rule, D. and Pruzek, R.M. (1998) Some new regression methods for predictive and construct validation. Social Indicators Research, 45, 201– 231.Google Scholar
- Tucker, L. R. (1983) Searching for structure in binary data. In H. Wainer and S. Messick (Eds.), Principals of Modern Psychological Measurement, 215 – 235. Erlbaum and Associates, Hillsdale, N.J.Google Scholar
- Wailer, N. (2000) MicroFACT user’s manual 2.0. Assessment Systems Corp., St. Paul.Google Scholar