Problems of estimation and interpretation are discussed that arise when a statistical package, which does not incorporate a dedicated weighted least-squares (WLS) routine, performs WLS regression by misapplication of a case-weighting strategy. A strategy is offered for adjusting WLS regression estimates after a case weighting strategy has been…

Asserts that, despite its growing popularity, there still exists confusion about the nature and proper use of logistic regression in family studies. Presents nontechnical discussion of logistic regression, with illustrations and comparisons to better-known procedures. Concludes that logistic regression can be powerful statistical procedure when…

Use of internal correlation for statistical analysis--as proposed by G. W. Joe and J. L. Mendoza (1989)--is discussed. Use of the bootstrap technique to deal with the distributional problem is questioned. Joe and Mendoza attempt the interpretation of the two linear composites that produce the largest internal correlation. (TJH)

The use of internal correlation for statistical analysis, as proposed by G. W. Joe and J. L. Mendoza (1989), is discussed. The suggestion of using bootstrapping is received well. Applications to collinearity are suggested. (TJH)

Examined 29 salary discrimination court cases to determine how organizations can refute regression analysis that leads to inference of discrimination in compensation. Found it equally effective for organization to introduce its own regression, other statistics, or no statistics. Plaintiff won all cases when discrimination was proven in promotion;…

Beck Scale for Suicide Ideation (BSI) was administered to 121 adolescent inpatients. Twelve characteristics found to be associated with adolescent suicide ideation were entered into multiple regression to estimate BSI scores, along with Beck inventories for anxiety, depression (BDI), and hopelessness (BHS), and Youth Self Report. BHS and BDI were…

Develops random-effects probit model for case in which outcome of interest is series of correlated binary responses, obtained as product of longitudinal response process where individual is repeatedly classified on binary outcome variable or in multilevel or clustered problems in which individuals within groups are considered to share…

Cobb's Cusp Surface Analysis Program (CUSP) provides a way to estimate empirically and test a nonlinear cusp catastrophe model. A model of emotion during problem solving is used to introduce catastrophe theory modeling and is discussed in conjunction with how to run and interpret CUSP. (SLD)

The two symposium articles extend "USA Today" SAT state ranking efforts by examining which states have the highest achievers, add the most value to enrolled students, and use resources most effectively. Dynarski and Gleason show that this test measures educational achievement more than innate ability. Graham and Husted adjust rankings…

The Scholastic Aptitude Test (SAT) is often used to measure educational performance at national, state, and local levels. Because participation rates differ considerably, such comparisons are invalid. This article proposes a regression model framework for adjusting SAT scores. Results are validated by comparing adjusted SAT scores with state…

Results from bootstrap samples of 50, 100, and 200 indicate that 3 imputation procedures for missing data produce biased estimates of R2 and both standardized regression weights used. Two deletion procedures (listwise and pairwise) provided accurate parameter estimates with up to 30% of data missing. (SLD)

The regression coefficients and the associated standard errors in hierarchical regression, when a theoretical basis for the analysis exists, are determined for four regression models. Each reflects different controlling or partialling of the variates. An illustration is presented using data from the Berkeley Growth Study. (SLD)

A model for the age standardization of test scores is presented, which is fitted to the percentile points of the raw score distribution and assumes a linear trend of each percentile with age. The model's applications in standardizing tests and diagnostic plots produced by a computer program--STANEW--are described. (SLD)

A general model for two-level multivariate data, with responses possibly missing at random, is described. The model combines regressions on fixed explanatory variables with structured residual covariance matrices. The likelihood function is reduced to a form enabling computational methods for estimating the model to be devised. (Author)

Empirically estimates a multiple-product total-cost function and output relationship for United States comprehensive universities. Statistical results for 158 private and 171 public universities find economies of both scale and scope in higher education. Product-specific economies of scope do not exist for all output levels and activities. (28…