This study in parametric test theory deals with the statistics of reliability estimation when scores on two parts of a test follow a binormal distribution with equal (case 1) or unequal (case 2) expectations. In each case biased maximum-likelihood estimators of reliability are obtained and converted into unbiased estimators. Sampling distributions…

This booklet is one of a series intended to provide explicit instructions for the collection of oceanographic data and samples at sea. The methods and procedures described have been used by the Scripps Institution of Oceanography and found reliable and up-to-date. Instructions are given for taking air samples on board ship to determine the…

Quality assurance is viewed as a means of maintaining desired performance levels during the operational use of a developed instructional program. Presented here is an analysis of the functions and the basic requirements of a quality assurance system. Procedures for implementing the system are described and discussed. The procedures include…

Included in this report on Arizona Indian demographic data are "an evaluation of several recent studies of Indian populations" and "an extensive analysis of methods for obtaining and maintaining accurate data in the future." Recommended methods by which accurate population data for the smaller reservations should be maintained are included in the…

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)