Best linear prediction (BLP) and penalized best linear prediction (PBLP) are techniques for combining sources of information to produce task scores, section scores, and composite test scores. The report examines issues to consider in operational implementation of BLP and PBLP in testing programs administered by ETS [Educational Testing Service].

The relevance of the investigated problem is determined by the need to improving the evaluation procedures in education and the student assessment in the age of the context of education widening, new modes of study developing (such as blending learning, e-learning, massive open online courses), immediate feedback necessity, reliable and valid…

This paper describes investigations in visualizing logpaths of students in an online calculus course held at Florida State University in 2014. The clickstreams making up the logpaths can be used to visualize student progress in the information space of a course as a graph. We consider the graded activities as nodes of the graph, while information…

The current study aimed to identify the views of pre-service teachers, who attended a primary school mathematics teaching department but did not take mathematical modeling courses. The mathematical modeling activity used by the pre-service teachers was developed with regards to the modeling activities utilized by Lesh and Doerr (2003) in their…

This study scrutinises approaches and thinking processes displayed by the elementary school students when solving real-world problems. It employed a qualitative inquiry to produce rich and realistic data about the case at hand. The research sample included 116 students. The data were obtained from written exam and semistructured interviews, and…

In this article, the author clarifies the distinction between numeracy and mathematics and the implications of this distinction for teachers of mathematics. In doing so she has, of necessity, focused on one--albeit significant--high stakes assessment genre used on Australian students that purports to measure numeracy. It is essential that teachers…

A class of tests for normality using the ratio of two estimates of the standard deviation is generalized to provide a class of tests for multivariate normality using a characterization of the multivariate normal. The posers of some of the tests are examined numerically and compared with the power of a recent similar test. (Author)

The problem of whether a precise connection exists between the stochastic processes considered in mathematical learning theory and the Guttman simplex is investigated. The approach used is to derive a set of conditions which a probabilistic model must satisfy in order to generate inter-trial correlations with the perfect simplex property.…

The area investigated in the present study is the comparison of the permutation t-test with Student's t-test and the Mann-Whitney U-test. The comparison was made for small samples for three distributions, including a normal distribution, a uniform distribution, and a skewed distribution. The properties of each test compared were the probability of…

The usefulness of the sets of cases developed in a previous technical report are examined as potential tests of leadership. Each set of cases generates, from a single subject, a number of scores which can be logically derived and which have substantial face validity. The intercorrelations among the scores, their split half reliability, and the…

The primary purpose of the present study was to investigate the appropriateness of several tests of significance for use with interrupted time series data. The second purpose was to determine what effect the violation of the assumption of uncorrelated error would have on the three tests of significance. The three tests were the Mood test,…

A two-stage testing procedure, a routing test followed by one of several alternative second-stage tests, is studied in the situation where the purpose is measurement, not classification. Models are developed, examined, and compared with conventional tests and up-and-down procedures. (DG)

Computational formulae for the following three tests of significance, useful in the interrupted time series design, are given: (1) a "t" test (Mood, 1950) for the significance of the first post-change observation from a value predicted by a linear fit of the pre-change observations; (2) an "F" test (Walker and Lev, 1953) of the…

An iterative procedure for adjusting examination marks from papers of varying standards is given. The convergence of the procedure is demonstrated and attention is drawn to an underlying linear model. (MP)