The following four integrative data analysis strategies for mixed-method evaluation designs are derived from and illustrated by empirical practice: (1) data transformation; (2) typology development; (3) extreme case analysis; and (4) data consolidation and merging. Use of these methods to realize the full potential of mixed-method approaches is…

Substruction is the illustration of the infrastructure of a research study--the foundational elements, their relationships, and outcome. It helps researchers increase their knowledge of theoretical, empirical, and descriptive links between a study's conceptual and operational components. (SK)

Argues that a previous study of preservice teachers' beliefs about the nature of science (NOS) was interpretively and methodologically faulty. Contests the finding that teachers learned the NOS through implicit instruction, and questions the methodology leading to the assertion that teachers intended to include NOS instruction in their lessons.…

Answers a critique of a previous study of teachers' beliefs about the nature of science (NOS). Reasserts that teachers in the study learned the NOS through implicit instruction and contends that there was negligible researcher bias in the finding that teachers planned to include NOS instruction in their instruction. Defends the choice of…

Examination of 66 congruence studies, including benchmarking studies with improved methodology, showed that congruence is a sufficient though not a necessary condition for job satisfaction. A paradigmatic shift is needed with diverse research designs and methods, emphasizing experiment and drawing on person-environment psychology. (Contains 142…

Trial-by-trial strategy assessments and a microgenetic design were used to examine the learning of rules for solving balance scale problems by 70 4- and 70 5-year olds. Developmental differences in learning that emerged seemed to reflect both distal and proximal influences. Encoding and initial rule use were related to different learning process…

Focuses on and discusses the common knowledge concerning research design and the statistical analysis of data. (Author/ASK)

Examines differences in the design and execution of two surveys: the 1996 National Household Education Survey (NHES) and the 1994 October Current Population Survey (CPS). These differences may have contributed to disparate estimates of the number and proportion of home-schooled children. Discusses implications for survey research and home…

This article reviews issues in questionnaire design beyond the creation of standardized questions and basic data collection rules. The use of magnitude scales, the application of decision theory, and the use of a questionnaire framework that replicates how choices are made by respondents are among the new design approaches discussed. (SLD)

Examines 10 variables in content analyses of 245 journal articles from the social scientific, interpretive, and critical traditions. Finds that researchers conform highly to expectations associated with ontology, epistemology, data collection, and data analysis, but less so with theory, hypotheses, sampling, verification, and generalization.…

Describes verbal protocols as a useful tool for evaluating computer hardware and software, especially if informed by activity theory. Such protocols cannot, however, stand alone in a thorough evaluation design. (Author/SLD)

Studied, through Monte Carlo simulation, the conditions for which analysis of covariance (ANCOVA) does not maintain adequate Type I error rates and power and evaluated some alternative tests. Discusses differences in ANCOVA robustness for balanced and unbalanced designs. (SLD)

Compared the Type I error rate and the power to detect differences in slopes and additive treatment effects of analysis of covariance (ANCOVA) and randomized block designs through a Monte Carlo simulation. Results show that the more powerful option in almost all simulations for tests of both slope and means was ANCOVA. (SLD)

Describes and compares useful and unified power formulas for analysis of covariance and change-score analyses, indicating the implications of each for sample size requirements. Contains practical recommendations for evaluations and outlines a simple spreadsheet approach. (SLD)

Both quantitative and qualitative methodologies have advantages and disadvantages. Choice of methodology should be determined by the nature of the research objectives. Cooperative education researchers should consider qualitative or combined-methodology inquiries including interviews and action research. (SK)