The problem with which this study is concerned is articulating all possible CT3 and KR21 reliability measures for every case of a 5x5 binary matrix (32,996,500 possible matrices). The study has three purposes. The first purpose is to calculate CT3 for every matrix and compare the results to the proposed optimum range of .3 to .5. The second purpose is to compare the results from the calculation of KR21 and CT3 reliability measures. The third purpose is to calculate CT3 and KR21 on every strand of a class test whose item set has been reduced using the difficulty strata identified by Order Analysis. The study was conducted by writing a computer program to articulate all possible 5 x 5 matrices. The program also calculated CT3 and KR21 reliability measures for each matrix. The nonparametric technique of Order Analysis was applied to two sections of test items to stratify the items into difficulty levels. The difficulty levels were used to reduce the item set from 22 to 9 items. All possible strands or chains of these items were identified so that both reliability measures (CT3 and KR21) could be calculated. One major finding of this study indicates that .3 to .5 is a desirable range for CT3 (cumulative p=.86 to p=.98) if cumulative frequencies are measured. A second major finding is that the KR21 reliability measure produced an invalid result more than half the time. The last major finding is that CT3, rescaled to range between 0 and 1, supports De Vellis' guidelines for reliability measures. The major conclusion is that CT3 is a better measure of reliability since it considers both inter- and intra-item variances.

Job satisfaction is an important job-related attitude that has been linked to various outcomes for both the organization and its employees. In spite of this, researchers of the construct disagree about how job satisfaction is defined and measured. This study proposes the use of the Facet Satisfaction Scale, a new scale of measurement for job satisfaction that is based on more recent definitions of the construct. Reliability and preliminary predictive validity studies were conducted in order to determine the utility of this scale. Next steps in scale development are discussed.

Multiple-choice questions are acknowledged to be difficult for both English mother-tongue and second-language university students to interpret and answer. In a context in which university tuition policies are demanding explicitly that assessments need to be designed and administered in such a way that no students are disadvantaged by the assessment process, the thesis explores the fairness of multiple-choice questions as a way of testing second-language students in South Africa. It explores the extent to which two multiple-choice Linguistics examinations at Unisa are in fact ‘generally accessible’ to second-language students, focusing on what kinds of multiple-choice questions present particular problems for second-language speakers and what contribution linguistic factors make to these difficulties. Statistical analysis of the examination results of two classes of students writing multiple-choice exams in first-year Linguistics is coupled with a linguistic analysis of the examination papers to establish the readability level of each question and whether the questions adhered to eight item-writing guidelines relating to maximising readability and avoiding negatives, long items, incomplete sentence stems, similar answer choices, grammatically non-parallel answer choices, ‘All-of-the-above’ and ‘None-of-the-above’ items. Correlations are sought between question difficulty and aspects of the language of these questions and an attempt is made to investigate the respective contributions of cognitive difficulty and linguistic difficulty on student performance. To complement the quantitative portion of the study, a think-aloud protocol was conducted with 13 students in an attempt to gain insight into the problems experienced by individual students in reading, understanding and answering multiple-choice questions. The consolidated quantitative and qualitative findings indicate that among the linguistic aspects of questions that contributed to question difficulty for second language speakers was a high density of academic words, long items and negative stems. These sources of difficulty should be addressed as far as possible during item-writing and editorial review of questions.

The problem of this study was to examine the equivalency of two different types of criterion-referenced item-selection techniques on simulated data as item pools varied in degrees of item difficulty. A pretest-posttest design was employed in which pass-fail scores were randomly generated for item pools of twenty-five items. From the item pools, the two techniques determined which items were to be used to make up twelve-item criterion-referenced tests. The twenty-five items also were rank ordered according to the discrimination power of the two techniques.

Students in an inner city junior high school in North Central Texas participated in a study whose purpose was to examine the effect of training in test item construction on their later test performance. The experimental group underwent twelve weeks of instruction using the Test Item Construction Method (TICM). In these sessions students learned to develop test items similar to those on which they were tested annually by the state via the Texas Assessment of Academic Skills (TAAS). The TICM aligned with state mandated test specifications.

Public budgeting has become a central artifact of American government – the principal means for establishing and implementing policy. Modern public budgeting was introduced in the early Twentieth Century as an adaptation of objects of revenue and expenditure budgeting used in commercial businesses. Since then - over a hundred years - a series of budget reform movements have sought to overcome a major drawback to this model: the lack of a direct link between revenues and expenditures and any measure of the quality or quantity of public benefits derived from budget allocations. While a number of major budget reforms have come and gone (or came and stayed), that provided additional information on government activities linked to allocations, little research has been done to assess whether this new information has actually been used in the legislative budget decision making process, and if so, whether it influenced final budget decisions. Framing theory holds that information about a problem presented in different ways will be perceived as a different problem by decision-makers. Using framing theory as a theoretical basis, a laboratory experiment was conducted, where groups using budgets differently framed budget documents deliberated over an identical budget scenario. It was found that the nature of the debate did vary based on type of framed budget, but that the final allocations were not significantly different.This document was prepared using Microsoft WORD 2003

The purpose of this study was to assess the impact of acquiescence on both positively and negatively worded questions, both when unidimensionality was assumed and when it was not. To accomplish this, undergraduate student responses to a previously validated survey of student engagement were used to compare several models of acquiescence, using a priori goodness-offit statistics as evidence for model fit, in order to develop a model that adequately accounted for acquiescence bias. Using a true experimental design, undergraduate students from a variety of classes at a large, urban university were randomly assigned to one of three versions of the same survey of student engagement (all positively worded items, all negatively worded items, an equal balance of both positively and negatively worded items). Structural equation modeling was used to analyze the results. Although the presence of acquiescence was confirmed for both positively and negatively worded items, it was not consistent by content scale or item polarization. This suggests that there may be an interaction between item polarization and content that may cause acquiescence to be present or absent. The scales that did not show acquiescence on the balanced survey portrayed a split factor loading based upon item polarization. Further, the splitting of factor loadings by item polarization was not due to acquiescence, suggesting that something other than acquiescence is causing the loadings to split. Further research is needed to develop models and/or methods to better assess and control for acquiescence. Although demographic groups were compared by gender and race/ethnicity to assess if different groups acquiesced differently, using multi-group confirmatory factor analysis, many of the models did not converge. The findings of this study were limited by the nature of the sample size. Additional research is needed to determine if acquiescence differs by group membership.

Stocker de grandes quantités de données complexifie les interactions avec les systèmes de Business Intelligence (BI). Les systèmes de recommandation semblent un choix logique pour aider les utilisateurs dans leur analyse. Ils extraient des comportements de données historiques et suggèrent des actions personnalisées, potentiellement redondantes, via des scores de similarité. La diversité est essentielle pour améliorer la satisfaction des utilisateurs, d’où l’intérêt particulier accordé aux recommandations complémentaires. Nous avons étudié deux problèmes concrets d’exploration de données en BI et proposons de découvrir et exploiter les intentions utilisateur pour fournir deux recommandeurs de requête. Le premier, un recommandeur collaboratif réactif original basé sur l’intention, recommande des séquences de requêtes à l’utilisateur pour poursuivre son analyse. Le second propose proactivement un ensemble de requêtes pour compléter un rapport BI, en fonction di contexte utilisateur. / The storage of big amounts of data may lead to a series of long questions towards the expected solution which complicates user interactions with Business Intelligence (BI) systems. Recommender systems appear as a natural solution to help the users complete their analysis. They try to discover user behaviors from the past logs and to suggest personalized actions by predicting lists of likeness scores, which may lead to redundant recommendations. Nowadays, diversity is becoming essential to improve users’ satisfaction, thus, a special interest is dedicated to complementary recommendation. We studied two concrete data exploration problems in BI and we propose to discover and leverage the user intents to provide two query recommenders. The first, an original reactive collaborative Intent-based Recommender, recommends sequences of queries for the user to pursue her analysis. The second one proactively proposes a bundle of queries to complete user BI report, based on the user intents.

Information systems (IS) research frequently uses survey data to measure the interplay between technological systems and human beings. Researchers have developed sophisticated procedures to build and validate multi-item scales that measure latent constructs. The vast majority of IS studies uses classical test theory (CTT), but this approach suffers from three major theoretical shortcomings: (1) it assumes a linear relationship between the latent variable and observed scores, which rarely represents the empirical reality of behavioral constructs; (2) the true score can either not be estimated directly or only by making assumptions that are difficult to be met; and (3) parameters such as reliability, discrimination, location, or factor loadings depend on the sample being used. To address these issues, we present item response theory (IRT) as a collection of viable alternatives for measuring continuous latent variables by means of categorical indicators (i.e., measurement variables). IRT offers several advantages: (1) it assumes nonlinear relationships; (2) it allows more appropriate estimation of the true score; (3) it can estimate item parameters independently of the sample being used; (4) it allows the researcher to select items that are in accordance with a desired model; and (5) it applies and generalizes concepts such as reliability and internal consistency, and thus allows researchers to derive more information about the measurement process. We use a CTT approach as well as Rasch models (a special class of IRT models) to demonstrate how a scale for measuring hedonic aspects of websites is developed under both approaches. The results illustrate how IRT can be successfully applied in IS research and provide better scale results than CTT. We conclude by explaining the most appropriate circumstances for applying IRT, as well as the limitations of IRT.

Nesta tese é apresentado o desenvolvimento de um método para elaboração de composições de custo voltado a obras de edificações. Esta abordagem, que considera as composições orçamentárias em forma de redes, foi elaborada a fim de criar uma lógica para a estruturação da massa de informações envolvidas no processo de orçar. Inicialmente foi feita uma revisão bibliográfica e um estudo exploratório que apontaram para tal necessidade. Tendo-se por base trabalhos anteriores de levantamento de produtividade em obra, propôs-se um método para elaboração de composições. Este método foi aplicado levando-se em conta o contexto das obras de um agente da cadeia produtiva da Construção Civil: um órgão financiador de obras (a Caixa Econômica Federal). Tal uso serviu para mostrar a aplicabilidade do método desenvolvido com base bibliográfica, mas também acabou sendo útil para alguns aprimoramentos do mesmo, fazendo uso das discussões entre pesquisadores e pesquisados, chegando-se, então, ao método final apresentado nesta tese. Desta forma, o método de desenvolvimento das redes de composições proposto fornece subsídios para alocação e tratamento das informações sobre custos de obra, resolvendo parte das críticas apontadas pela literatura, propiciando composições mais precisas frente às novas disponibilidades de dados e dando um suporte consistente e adequado às necessidades do gerenciamento dos custos de produção de edificações. / This thesis develops a method that helps experts arrive at unit price items for buildings. It is based on the consideration of a unit price item net as the logical way to deal with the huge amount of information associated to the estimating process. The preliminary bibliography review and an exploratory study showed the accuracy of the authors initial concerns. The method developed was based upon former productivity studies and was applied in the production of unit price items net for Caixa Econômica Federal, a public building construction financial company. Such experience showed not only that the method was feasible but also pointed out some improvements that should be made, leading to the method presented in the thesis. Finally, it can be said the method used to develop unit price item nets can help allocate and deal with information about construction costs; it solved several problems indicated by literature, improving compositions in terms of precision, and of support to cost management in the building construction area.