Humphreys' comments on double-median splits (TM 504 009) are essentially correct, but are not relevant to the original Kirby and Das article (EJ 182 444). His comments do not weaken our findings. (Author/RD)

This note shows that, under conditions specified by Levin and Subkoviak (TM 503 420), it is not necessary to specify the reliabilities of observed scores when comparing completely randomized designs with randomized block designs. Certain errors in their illustrative example are also discussed. (Author/CTM)

Comments (TM 503 706) on an earlier article (TM 503 420) concerning the comparison of the completely randomized design and the randomized block design are acknowledged and appreciated. In addition, potentially misleading notions arising from these comments are addressed and clarified. (See also TM 503 708). (Author/CTM)

This note continues the discussion of earlier articles (TM 503 420, TM 503 706, and TM 503 707), comparing the completely randomized design with the randomized block design. (CTM)

A survey is an effective way to measure citizen attitudes. Basic steps to follow in sampling public opinion are offered. (Author/MLF)

The relationship between conservatism and openness to experience was examined. One study found that conservatism was significantly related to the scores on the Coan Experience Inventory. The other study demonstrated that high conservative subjects were less willing to volunteer for psychological experiments requiring openness. (Author/MV)

The procedure and sampler described permits detection of less than 50pg of one polychlorinated naphthalene (PCN) isomer. The method uses gas chromatography-mass spectrometry. The PCNs are collected on a glass fiber filter and two polyurethane foam plugs and extracted with toluene at 25 degrees Celsius. (BB)

This paper describes a two-stage sampling design for obtaining probability samples of the elderly and other specialized populations. Results indicate elderly individuals will respond, use of the design does not appear to increase sample bias, and the method is extremely inexpensive. (Author)

Based on data from two experiments, this article attempts to assess degree to which people differ in interpretations of questions referring to library services and the implications for interpreting survey results. Sources of error in questionnaire research--sampling, response (question interpretation, response decision, category choices)--are…

A five-year follow-up study compares the current business school curriculum content in electronic data processing and statistical sampling to the requirements of business. Differences still exist but there is evidence of progress by business schools in meeting the needs of business. (JOW)

Provides an expository presentation of multivariate analysis (MANOVA). Addresses several questions relating to why one should use MANOVA, its structure, how MANOVA test statistics and follow-up tests are obtained and interpreted, presentation of results, and alternatives to MANOVA. Uses an example data set to illustrate these points. (Author/KS)

Describes a study conducted in southeastern Washington to determine public opinion regarding several educational options. Compares study results obtained through structured interviews with adult residents at a randomly selected sample of households with results obtained by mailing questionnaires to all remaining households in the area. (AYC)

Reviews a computer-assisted learning package (available from CONDUIT) which introduces survey and sampling techniques by pretending that the user is a pollster asking one of six questions of a more or less political nature. Documentation and performance are rated fair while ease of use is considered excellent. (JN)

Some sample data used in economic education research may be biased because missing observations may not be random. The authors explain a technique for estimating the relationship between students who fail to take standardized tests (the missing observations) and a core of general variables that might explain this behavior. (Author)

Discusses the concept of reliability in language testing and considers several simple ANOVA (analysis of variance) models which can be used to define and estimate reliability coefficients. Summarizes the main statistical results associated with the commonly used measurements of reliability. Presents results likely to be of use to language testers.…