## Examining Relationships Between Where Students Start and How Rapidly They Progress: Implications for Constructing Indicators That Help Illuminate the Distribution of Achievement Within Schools (2001)

Venue: | University of California, National Center for |

Citations: | 13 - 1 self |

### BibTeX

@TECHREPORT{Seltzer01examiningrelationships,

author = {Michael Seltzer and Michael Seltzer and Kilchan Choi and Kilchan Choi and Yeow Meng Thum and Yeow Meng Thum},

title = {Examining Relationships Between Where Students Start and How Rapidly They Progress: Implications for Constructing Indicators That Help Illuminate the Distribution of Achievement Within Schools},

institution = {University of California, National Center for},

year = {2001}

}

### OpenURL

### Abstract

Attending to school mean rates of change and to differences in rates of change for various demographic groups is of central importance in monitoring school performance.

### Citations

1240 | Bayesian Data Analysis - Gelman, Carlin, et al. - 1995 |

281 | Bayes and Empirical Bayes Methods for Data Analysis - Carlin, Louis - 2000 |

264 | Hierarchical linear models: Applications and data analysis methods - Bryk, Raudenbush - 1992 |

162 | Illustration of Bayesian Inference in Normal Data Models Using Gibbs Sampling - Gelfand, Hills, et al. - 1990 |

53 | Application of Hierarchical Linear Models to Assessing Change - Bryk, Raudenbush - 1987 |

33 | HLM5: Hierarchical linear and nonlinear modeling - Raudenbush, Bryk, et al. - 2001 |

31 | General longitudinal modeling of individual differences in experimental designs: A latent variable framework for analysis and power estimation - Muthén, Curran - 1997 |

31 | Bayesian Output Analysis Program (BOA), User’s Manual, Version 1.1,” technical report
- Smith
- 2004
(Show Context)
Citation Context ...e quite good in our applications, and convergence was rapid. While various diagnostics are available in WinBUGS (e.g., trace plots, ACF plots), the programs CODA (Best, Cowles & Vines, 1995) and BOA (=-=Smith, 2000-=-) provide users with a comprehensive set of diagnostic tools. CODA can be downloaded from the BUGS website, and BOA can be downloaded from the Web as well. The resulting marginal posterior medians and... |

27 | The Tennessee Value-Added Assessment System (TVAAS): Mixed-model methodology in educational assessment - Sanders, Horn - 1994 |

21 | Toward a More Appropriate Conceptualization of Research on School Effects: A Three-Level Hierarchical Linear Model - Bryk, Raudenbush - 1988 |

16 | Analysis of longitudinal data using latent variable models with varying parameters - Muthén, B - 1991 |

16 | Myths about longitudinal research - Rogosa - 1988 |

16 |
Questions and answers in the measurement of change
- Willett
- 1988
(Show Context)
Citation Context ...ints in time to analyses and summaries of student growth. To be sure, the notion of growth in knowledge and skills lies at the heart of definitions of learning and education (Bryk & Raudenbush, 1988; =-=Willett, 1988-=-, p. 346). However, rather than focus exclusively on changes in student achievement over time (e.g., estimates of growth rates), we feel that it is also often important to consider levels of student a... |

13 |
Longitudinal studies of achievement growth using latent variable modeling. Learning and Individual Differences, Special issue: Latent growth curve analysis
- Muthén, Khoo
- 1998
(Show Context)
Citation Context ...ble regression coefficients. In addition to WinBUGS, a variety of other software packages can be used to fit such models, including HLM5 (Raudenbush, Bryk, Cheong & Congdon, 2000) and Mplus (Muthen & =-=Muthen, 1998-=-). We discuss various software possibilities in the final section of our paper. Before moving on, we wish to comment briefly on several other features of the above between-student model. First, as in ... |

12 |
Tools for Statistical Inference, 3rd ed
- Tanner
- 1996
(Show Context)
Citation Context ...or parameters of interest in a wide-range of complex modeling settings (see, e.g., Carlin & Louis, 1996; Gelfand, Hills, Racine-Poon & Smith, 1990; Gelman, Carlin, Stern & Rubin, 1995; Seltzer, 1993; =-=Tanner, 1996-=-). In technical parlance, these iterative techniques provide a means of simulating the marginal posterior distributions of parameters of interest. Thus, for example, the Gibbs sampler could be used to... |

10 | Convergence Diagnosis and Output Analysis Software for Gibbs Sampling Output, Version 0.30 - Best, Cowles, et al. - 1995 |

10 |
Sensitivity analysis for fixed effects in the hierarchical model: A Gibbs sampling approach
- Seltzer
- 1993
(Show Context)
Citation Context ...and intervals for parameters of interest in a wide-range of complex modeling settings (see, e.g., Carlin & Louis, 1996; Gelfand, Hills, Racine-Poon & Smith, 1990; Gelman, Carlin, Stern & Rubin, 1995; =-=Seltzer, 1993-=-; Tanner, 1996). In technical parlance, these iterative techniques provide a means of simulating the marginal posterior distributions of parameters of interest. Thus, for example, the Gibbs sampler co... |

8 | Measuring Progress Toward a Goal. Estimating Teacher Productivity Using a Multivariate Multilevel Model for Value-Added Analysis
- Thum
(Show Context)
Citation Context ...pe is that the kinds of summaries and analyses illustrated above can, in conjunction with various measures of school performance (see, e.g., Bryk, Thum, Easton & Luppescu, 1998; Sanders & Horn, 1994; =-=Thum, 2001-=-; Willms, 1992), help stimulate fruitful discussion among school personnel regarding possible areas of concern. For example, suppose that there is evidence of a strong positive relationship between in... |

6 | Assessing School Academic Productivity: The Case of Chicago School Reform. Social Psychology of Education - Bryk, Thum, et al. - 1998 |

5 |
The statistical analysis of data from nonequivalent group designs
- Reichardt
- 1979
(Show Context)
Citation Context ...or a discussion of centering level-2 predictors). In the case of classic ANCOVA models, covariates such as pretest scores (e.g., Xi) are typically deviated from their grand means (Xi −X.) (see, e.g.=-=, Reichardt, 1979). Sim-=-ilarly, in the model for growth rates in Equation 6, our covariate (π0i) is deviated from its grand mean (i.e., π0i − β00). As a result, β10 now represents the expected rate of change for a male... |

4 | Assessing program effects in the presence of treatment-baseline interactions: A latent curve approach - Khoo - 2001 |

4 | The metric matters: The sensitivity of conclusions about growth in student achievement to choice of metric. Educational Evaluation and Policy Analysis - Seltzer, Frank, et al. - 1994 |

3 | Multiple Group IRT - Bock, Zimovski - 1997 |

3 |
Mplus user’s guide. Los Angeles: Muthén & Muthén. (Available from Muthén
- Muthén, Muthén
- 1998
(Show Context)
Citation Context ...ble regression coefficients. In addition to WinBUGS, a variety of other software packages can be used to fit such models, including HLM5 (Raudenbush, Bryk, Cheong & Congdon, 2000) and Mplus (Muthen & =-=Muthen, 1998-=-). We discuss various software possibilities in the final section of our paper. Before moving on, we wish to comment briefly on several other features of the above between-student model. First, as in ... |

3 | Assessing direct and indirect associations in multilevel designs with latent variables. Sociological Methods and Research - Raudenbush - 1999 |

3 | Latent variable modeling in the hierarchical modeling framework: Exploring initial status treatment interactions in 8 studies - Seltzer, Choi, et al. - 2002 |