Two types of question about time: Methodological issues in the analysis of teacher career path data

Abstract Quantitative researchers studying teacher career paths ask two types of question about time: questions about duration (in which time is the outcome) and questions about change (in which time is a predictor). Although asymmetrical in their conceptual placement of time, both questions ask what happens to individual teachers and how variation across teachers is related to background, training and environment. In this chapter, we develop a conceptual framework that integrates methods for addressing both types of questions. We argue that traditional two- wave methods are fundamentally flawed and that to answer questions about time, researchers must gather multi-wave data. We outline new methods that capitalize on the richness of the longitudinal perspective — proportional hazards modeling and growth modeling.

[1]  Paul D. Allison,et al.  Event History Analysis : Regression for Longitudinal Event Data , 1984 .

[2]  L. Zieve.  Note on the correlation of initial scores with gains. , 1940 .

[3]  J. Willett,et al.  DEMONSTRATING THE RELIABILITY THE DIFFERENCE SCORE IN THE MEASUREMENT OF CHANGE , 1983 .

[4]  D. Cox.  Regression Models and Life-Tables , 1972 .

[5]  R. L. Thorndike.  Intellectual status and intellectual growth. , 1966, Journal of educational psychology.

[6]  C. R. Rao,et al.  Some statistical methods for comparison of growth curves. , 1958 .

[7]  Benjamin S. Bloom,et al.  Stability and change in human characteristics , 1966 .

[8]  W. W. Charters,et al.  Some Factors Affecting Teacher Survival in School Districts1 , 1970 .

[9]  Rupert G. Miller,et al.  Survival Analysis , 2022, The SAGE Encyclopedia of Research Design.

[10]  Phillip C. Schlechty,et al.  Do Academically Able Teachers Leave Education? The North Carolina Case. , 1981 .

[11]  Nancy Brandon Tuma,et al.  Nonparametric and Partially Parametric Approaches to Event-History Analysis , 1982 .

[12]  John B. Willett,et al.  Understanding correlates of change by modeling individual differences in growth , 1985 .

[13]  Robert L. Linn,et al.  The Determination of the Significance of Change Between Pre- and Posttesting Periods , 1977 .

[14]  Barry D. Anderson,et al.  Teacher Survival Rates—A Current Look , 1978 .

[15]  Richard J. Murnane,et al.  The Career Paths of Teachers: Implications for Teacher Supply and Methodological Lessons for Research. , 1988 .

[16]  D. Cox,et al.  Analysis of Survival Data. , 1985 .

[17]  Frederic M. Lord.  The Measurement of Growth , 1956 .

[18]  David Rogosa,et al.  A growth curve approach to the measurement of change. , 1982 .

[19]  S. Kirby,et al.  Teacher attrition : the uphill climb to staff the Nations's schools , 1987 .

[20]  J. Ware.  Linear Models for the Analysis of Longitudinal Studies , 1985 .

[21]  John B. Willett,et al.  Doing Data Analysis with Proportional Hazards Models: Model Building, Interpretation and Diagnosis. , 1988 .

[22]  Barry D. Anderson,et al.  Teacher Survival Rates in St. Louis, 1969–1982 , 1985 .

[23]  Eric A. Hanushek,et al.  Efficient Estimators for Regressing Regression Coefficients , 1974 .

[24]  John B. Willett,et al.  Questions and Answers in the Measurement of Change , 1988 .

[25]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data , 1980 .

[26]  Quinn McNemar,et al.  On Growth Measurement , 1958 .

[27]  Richard J. Murnane,et al.  Implications for Teacher Supply and Methodological Lessons for Research , 1988 .

[28]  John B. Willett,et al.  Detecting Involuntary Layoffs in Teacher Survival Data: The Year of Leaving Dangerously , 1988 .