An empirical study of the power of the F test in normal populations with variances proportional to the cell means is reported. The results indicate that the power of the test can be approximated by the noncentral F distribution with a modified parameter of noncentrality. (Author/CM)

A revised version of Kaiser's Measure of Sampling Adequacy for factor-analytic data matrices is presented. (Author)

Results suggested that once a performance-equated age range of nonretarded Ss was isolated with parity to the mildly retarded standard, a number of nonretarded comparison groups, matched on a preestablished performance standard, may be consistently generated. (Author)

Explains why an econometric practice introduced by J.C. Soper cannot eliminate the problems caused by multicollinearity. The author suggests that it can be a useful technique in that it forces researchers to pay more attention to the specifications of their models. (AM)

Argues that standards protecting human subjects in psychology experiments undermine the freedom and dignity of the researchers. Suggests a simple procedure to relieve the work load of the Human Subjects Committee. (KC)

Argues that Baumrind (1982), in her discussion of studies employing Bem Sex Role Inventory (BSRI) and Personal Attitudes Questionnaire, confuses theories proposed by Bem (1974) and by Spence and Helmreich (1978, 1979), which are based on different assumptions and have different implications. Outlines differences between the two and points out…

The development of an extensive body of research information pertaining to visually handicapped persons is hindered by small, heterogeneous, population samples and by the small number of studies. Four approaches to data synthesis are explored as one means of integrating and synthesizing the limited information available. (Author)

Proposes criteria for evaluating research reviews. (FL)

Reviews 28 studies comparing adolescent self-report of smoking with biological indicators. Identifies four factors limiting agreement: biases in self-report due to limitations of biological measures; limitations of self-report measures; social desirability; and analytic and statistical issues. Concludes that, with optimal measurement, self-report…

Ninnes and Burnett's quantitative analysis of the contribution of poststructuralism to comparative education is flawed in that its selection of poststructuralist scholars is not representative, and it looks for these largely French-speaking scholars in English-language journals. Ninnes and Burnett's under-specification of methodological principles…

Presents a transcript of a speech given by Cyril Burt in 1964 that establishes his access to research findings of others at this later point in his life and strengthens the argument that accusations against Burt of scientific fraud are not proven. (SLD)

Theoretically and methodologically critiques LaPiere's seminal research into attitude-behavior relationship. Asserts that actual discrepancy uncovered was between true attitude (tendency to act in certain way) and that which is measured by attitude questionnaire. LaPiere's primary concern was to point out danger of assuming that…

Used data from nursing homes (n=33) to analyze nursing homes' response to requests to participate in field study. Multiple organizational characteristics predicted responsiveness. Facilities with greater financial resources were more likely to grant access. Stable administration and local facility control predicted higher response rates of nurses.…

Notes that existence of substantial correlation between two or more independent variables creates problems of multicollinearity in multiple regression. Discusses multicollinearity problem in social work research in which independent variables are usually intercorrelated. Clarifies problems created by multicollinearity, explains detection of…

Used census data for U.S. metropolitan area African Americans to examine relationships of measures of sex ratio to each other and to indicators of family formation and family structure. Found that, when measures of sex ratio were properly formulated, they had strong associations with marriage prevalence; nonmarital fertility ratios; and prevalence…