Problem Statement: Learning-teaching activities bring along the need to determine whether they achieve their goals. Thus, multiple choice tests addressing the same set of questions to all are frequently used. However, this traditional assessment and evaluation form contrasts with modern education, where individual learning characteristics are…

This study investigated how best to study a matrix. Fifty-three participants studied a matrix topically (1 column at a time), categorically (1 row at a time), or in a unified way (all at once). Results revealed that categorical and unified study produced higher: (a) performance on relationship and fact tests, (b) study material satisfaction, and…

This investigation had two major purposes. The first was to explore the use of an inferential technique called Tukey's Jackknife in establishing a confidence interval about cooefficient alpha reliability. The second purpose was to study the robustness of the Feldt and the jackknife procedures when the data fails to satisfy usual normality…

Standard errors of pooled mean estimate in multiple matrix sampling were compared for two procedures. The data were from tests involving items with and without replacement. The two procedures involve the formulations of Madow and Lord, and Novick; the former permits sampling of item, with or without replacement, whereas the latter is to be used…

Investigated empirically through post mortem item-examinee sampling were the relative merits of two alternative procedures for allocating items to subtests in multiple matrix sampling and the feasibility of using the jackknife in approximating standard errors of estimate. The results indicate clearly that a partially balanced incomplete block…

Six in-general samples have been generated to fit different developments of the SVIB, Twenty experimental homogeneous scales were used to measure the similarities and differences among the six in-general samples. Generally, all samples were strikingly similar with the greatest differences appearing between male and female in-general samples.…

A rederivation of Lord's formula for estimating variance in multiple matrix sampling is presented as well as the ways Cronbach's coefficient alpha and the Spearman-Brown prophecy formula are related in this context. (Author/JKS)

Authors present a formula for use when restrictions result from complex or unmeasured variables. (Authors/MB)

Assesses conditional states of item mastery found among items from different item domains and the effectiveness of various procedures for identifying such conditional relations. Item domains considered were from the curriculum area of multiplication of whole numbers, and were defined by a domain referenced testing system. (Author/RC)

A method based on the Poisson approximation to the binomial distribution and on the relation between the Chi-Squared distribution and the Poisson distribution is suggested for selected use in determining the number of items and passing scores in mastery Lests. (Author/RL)

It is sometimes desirable to obtain an estimated total-test score for an individual who was administered only a subset of the items in a total test. The present study compared six methods, two of which utilize the content structure of items, to estimate total-test scores using 450 students in grades 3-5 and 60 items of the ll0-item Stanford Mental…

This research examined 2 elements of multiple-choice test construction, balancing the key and optimal number of options. In Experiment 1 the 3 conditions included a balanced key, overrepresentation of a and b responses, and overrepresentation of c and d responses. The results showed that error-patterns were independent of the key, reflecting…

This study involving 352 students was designed to verify empirically the a priori use of multiple matrix sampling procedures in an elementary school using a nationally normed, commercizlly published achievement test. The study focused on effect of changes in item context, effect of previous exposure to items, and relative effectiveness of multiple…

Binomial models for domain-referenced testing are compared, emphasizing the assumptions underlying the beta-binomial model. Advantages and disadvantages are discussed. A proposed item sampling model is presented which takes the effect of guessing into account. (Author/CM)