What a multivariate contrast analysis should entail and how such an analysis should be conducted are discussed. The three questions encompassing a contrast analysis are: (1) whether the contrast effects are generalizable; (2) which variables contribute most to the contrast effects; and (3) what is the construct underlying the contrast effects.…

Some issues in defining dropouts and reporting information about them are explored, with reference to the Common Core of Data (CCD) survey of the National Center for Education Statistics. There has not been any uniform national count of how many students leave school, and no commonly accepted definition has been developed that allows a number to…

Contrasting traditional linear media (in which all learners proceed through the instructional materials in an essentially fixed sequence) with interactive technologies and hypermedia (in which two learners may take different paths through the same instructional materials), this paper highlights the importance of recording and analyzing the…

The use of outcome assessment in special education is reviewed. Outcome assessments differ widely in design, measures, and data collection, but they share a common focus on outcomes as individual achievements, statuses, or behaviors. Assessments of special education outcomes often have an evaluative purpose in reflecting how well the special…

This guidebook is designed for data analysts who are working with computer data files that contain records with incomplete data. It indicates choices the analyst must make and the criteria for making those choices in regard to the following questions: (1) What resources are available for performing the imputation? (2) How big is the data file? (3)…

Problems involved in providing practical research experience in research methods courses are discussed. The two points in the research process where time is most critical are selecting measures and data collection. This paper suggests using a data base from previous research and having students conduct simulated studies based on randomly selected…

The choice of methods is part of the overall evaluation design process. The process consists of the following steps: (1) analyzing the problem context; (2) asking a few general questions; (3) selecting the methods (strategies) to use; and (4) selecting the specific techniques (tactics) to use. To operate successfully the evaluator needs to know…

Technological advances in microcomputer hardware and software, including size of memory and increasingly more sophisticated statistical application packages, create a new era in educational research. The alternative to costly main-frame computer data processing and statistical analysis is explored in this paper. In the first section, typical…

This workbook with teacher's guide provides "hand-ons" experience for second language (L2) acquisition researchers in analyzing second language data. The sample data is organized into language categories including morphology, lexicon, phonology, syntax/semantics, spoken and written discourse, foreigner talk discourse, specific purpose acquisition,…

This paper describes a computer support system that eliminated many of the problems associated with the usual methods of transcribing and analyzing questionnaire data. The system was created to support the course evaluation system at Athabasca University, a distance education university in Canada. The courses evaluated were all home study courses,…

Members of the educational community are increasingly concerned that the dropout rate is too high. However, concerned educators and researchers do not agree who should be included in the data to determine the dropout rate. National definitions are needed so that accurate comparisons can be made. There is also a need to assess the effectiveness of…

The Quality Circle project is a problem-solving concept requiring the interaction of a variety of organizational skills. Circle members work together, becoming involved in problem-solving processes. They make decisions and take action based upon the data they collect. The reliablity of those data is crucial to the circle's success. Presented in…

A technique for detecting item bias that is responsive to attitudinal measurement considerations is a maximum likelihood factor analysis procedure comparing multivariate factor structures across various subpopulations, often referred to as SIFASP. The SIFASP technique allows for factorial model comparisons in the testing of various hypotheses…

Literacy trends among Black adults in the Republic of South Africa and in some Black states in southern Africa were determined from data obtained from population census reports from 1946 to 1970. Problems concerning the determination of literacy statistics included differing definitions of literacy and data that were subjective, difficult to…

The structure and documentation of High School and Beyond First Follow-Up data files represent a departure from Base Year practices. The Base Year student file contains data from both the senior and sophomore cohorts. Due to the more complex design of the First Follow-Up and resulting increase in the volume of available data, separate First…