As complex, sophisticated techniques for statistical analysis become easier to obtain and apply, it becomes increasingly critical for researchers to examine their data prior to analysis to ensure that the data are suitable for analysis. Exploratory Data Analysis provides methods for subjecting data to appropriate pre-analysis scrutiny. (PGD)

In most selection validation research, only the upper and lower tails of the criterion distribution are used, often yielding misleading or incorrect results. Provides formulas and tables which enable the researcher to account more accurately for the distribution of criterion within the middle range of population. (Author/RW)

Defines the "worship of p" as the current phenomenon of attaching major significance to statistical analysis, and contends that such statistical analysis and precision are useful only when viewed as secondary tools in scientific research. (MH)

Methodological problems of experimental control, statistical analysis, and appropriateness of experimental design are discussed. Related article is EA 500 731. (KJ)

Much of educational administration research suffers from lack of conformity between data analysis and research design, inattention to the test/retest stability of measurement instruments, and the use of statistics for nominal or interval data with ordinal data, random-sample statistics with nonrandom samples, and unnecessarily complex statistical…

The normalized mean is developed and discussed as a descriptive measure of central location. The advantages of the normalized mean over the arithmetic mean, median, and trimmed mean are discussed. (Author)

Examines the prevalence of inflated Type I error in counseling research and recommends wider use of multivariate statistics to correct the problem. Type I error becomes inflated beyond acceptable levels when researchers perform individual univariate statistics on each of several dependent variables within a single project. (Author)

Presents the results of a detailed study of errors in a musical database. Provides an equation for estimating the effect of an overall error-rate on arbitrary analytic measures derived from the database. Examines four methods of error detection: manual proof-reading, double-entry method, programed syntactic checking, and programed heuristics. (GEA)

Reviews the role of statistical hypothesis testing in research, discusses the problems with multiple t tests, indicates when they are a problem, and suggests a compromise solution. (one reference) (JL)

Disputes Moon, Dillon, and Sprenkle's (1990) claims regarding advantages of qualitative methods and limitations of quantitative approaches for family therapy research. Supports role of qualitative research in theory development and concurs that exclusive allegiance to standard methods may limit attention to important family therapy processes; but…

Clarifies two sets of issues raised in preceding commentaries. First, interaction effects are undoubtedly salient in resilience research; yet main effect findings can be equally critical from an intervention perspective. Second, although resilience research and prevention science reflect similar broad objectives, the former involves explicit…

Evaluating school-based mental health services for children and youth with emotional disturbance (ED) has been a challenge for researchers. One particular challenge is the study design of using the student as the statistical unit of analysis, which in certain cases may lead to a violation of the "independence of error" assumption.…

In psychological and special education research, group comparison experimental designs are more often used than single subject experimental designs. However, the application of group designs poses many difficulties, such as the collection of large numbers of homogeneous subjects for a particular experimental condition, the averaging of individual…

Three computer simulations were conducted to show that very high aggregate predictive validity coefficients can occur when the across-case variability in absolute score stability occurring in both the predictor and criterion matrices is quite small. In light of the increase in internal consistency reliability achieved by the method of aggregation…

Researchers sometimes use stepwise methods to eliminate variables from analyses when the variables do not appreciably improve the ability to explain or predict inferences about the importance of various predictor variables. It is argued that stepwise methods are usually not appropriate for these purposes for three reasons. First, some researchers…