We explore the conditions under which short, comparative interrupted time-series (CITS) designs represent valid alternatives to randomized experiments in educational evaluations. To do so, we conduct three within-study comparisons, each of which uses a unique data set to test the validity of the CITS design by comparing its causal estimates to…

Automated scoring models for the "e-rater"® scoring engine were built and evaluated for the "GRE"® argument and issue-writing tasks. Prompt-specific, generic, and generic with prompt-specific intercept scoring models were built and evaluation statistics such as weighted kappas, Pearson correlations, standardized difference in…

Currently principals are involved with a variety of programs offered in schools, such as IDEA, English Language Learners, Title I remedial services, migrant education, and gifted and talented programs. However, there is a growing recognition that gifted students are being poorly served by most public schools. The purpose of this study was to…

The Panel on Decennial Census Methodology met during the year 1984 to investigate the following technical issues related to the 1990 United States census: (1) adjustment of census counts and characteristics; (2) sampling; and (3) administrative records. A number of recommendations were made. It was suggested that a low priority be given to…