Search

We investigate the performance of three statistics, R [subscript 1], R [subscript 2] (Glas in "Psychometrika" 53:525-546, 1988), and M [subscript 2] (Maydeu-Olivares & Joe in "J. Am. Stat. Assoc." 100:1009-1020, 2005, "Psychometrika" 71:713-732, 2006) to assess the overall fit of a one-parameter logistic model (1PL) estimated by (marginal) maximum likelihood (ML). R [subscript 1] and R [subscript 2] were specifically designed to target specific assumptions of Rasch models, whereas M [subscript 2] is a general purpose test statistic. We report asymptotic power rates under some interesting violations of model assumptions (different item discrimination, presence of guessing, and multidimensionality) as well as empirical rejection rates for correctly specified models and some misspecified models. All three statistics were found to be more powerful than Pearson's X [superscript 2] against two- and three-parameter logistic alternatives (2PL and 3PL), and against multidimensional 1PL models. The results suggest that there is no clear advantage in using goodness-of-fit statistics specifically designed for Rasch-type models to test these models when marginal ML estimation is used.

Data analysis plays an important role in people's lives. Citizens need to be able to conduct critical analyses of statistical information in the work place, in their personal lives, and when portrayed by the media. However, becoming a conscientious consumer of statistics is a gradual process. The experiences that students have with data in the middle grades can potentially lay the foundation for developing statistical reasoning. Statistical thinking requires students to engage in both mathematical and nonmathematical thinking. This article contains innovative tasks that have been used to help students construct a robust, "mathematical" understanding of the mean as a mathematical point of balance and to describe students' responses to such tasks as they constructed this understanding. (Contains 6 figures.)

This article examines the stance options used by writers responding to a data description task in the discipline of Statistics. Based on a small learner corpus, it uses inductive qualitative content analysis to explore both the content propositions that students included in their writing, and the ways in which they expressed evaluative stance vis-a-vis such propositions. In the light of an interview with a specialist informant, the article discusses the appropriacy of the content choices and stance options taken by students. It then discusses the potential exploitation of the learner corpus for pedagogic purposes. (Contains 3 tables and 2 figures.)

The purpose of this study was to investigate whether differences in social support, submissive behaviors, and loneliness existed among Turkish university students who had had premarital sexual intercourse and those who had not. Using self-reported questionnaires, students who had experienced sexual intercourse were contrasted with those who had not. Data were gathered on 420 university students in Ankara, Turkey. MANOVA statistics were used in the data analysis. Results indicated that more than 75% of the total respondents reported that they had never had sexual intercourse; the frequency of sexual intercourse was higher among males than females. It was found that students who had had sexual intercourse reported less perceived support from family. The two groups were not significantly different, however, in perceived support from friends, submissive behaviors and loneliness. Possible interpretations of these data and implications for future study are suggested.

This paper argues for a renewed focus on statistical reasoning in the beginning school years, with opportunities for children to engage in data modelling. Results are reported from the first year of a 3-year longitudinal study in which three classes of first-grade children (6-year-olds) and their teachers engaged in data modelling activities. The theme of "Looking after our Environment," part of the children's science curriculum, provided the task context. The goals for the two activities addressed here included engaging children in core components of data modelling, namely, selecting attributes, structuring and representing data, identifying variation in data, and making predictions from given data. Results include the various ways in which children represented and re-represented collected data, including attribute selection, and the metarepresentational competence they displayed in doing so. The "data lenses" through which the children dealt with informal inference (variation and prediction) are also reported.

Measures of human efficiency under increases in mental workload or attentional limitations are vital in studying human perception, cognition, and action. Assays of efficiency as workload changes have typically been confined to either reaction times (RTs) or accuracy alone. Within the realm of RTs, a nonparametric measure called the "workload capacity coefficient" has been employed in many studies (Townsend & Nozawa, 1995). However, the contribution of correct versus incorrect responses has been unavailable in that context. A nonparametric statistic that is capable of simultaneously taking into account accuracy as well as RTs would be highly useful. This theoretical study develops such a tool for two important decisional stopping rules. Preliminary data from a simple visual identification study illustrate one potential application. (Contains 4 footnotes, 1 table, and 3 figures.)

Background: Previous work suggests that the expectation of failure is related to higher test anxiety and achievement goals grounded in a fear of failure. Aim: To test the hypothesis, based on the work of Elliot and Pekrun (2007), that the relationship between perceived competence and test anxiety is mediated by achievement goal orientations. Sample: Self-report data were collected from 275 students in post-compulsory education following courses in A Level Psychology. Results: Competence beliefs were inversely related to the worry and tension components of test anxiety, both directly and indirectly through a performance-avoidance goal orientation. A mastery-avoidance goal orientation offered an indirect route from competence beliefs to worry only. Conclusion: These findings provide partial support for Elliot and Pekrun's (2007) model. Although significant mediating effects were found for mastery-avoidance and performance-avoidance goals, they were small and there may be other mechanisms to account for the relations between competence beliefs and test anxiety.

The skill-development model contends that achievements have an effect on academic self-confidences, while the self-enhancement model contends that self-confidences have an effect on achievements. Differential psychological processes underlying the 2 models across the domains of mathematics and science were posited and examined with structural equation modeling using the data of grade 8 students from the Trends in International Mathematics and Science Study across 28 countries (N = 144,069), which generated 2 major findings. In statistical terms, (1) there were "negative" cross-domain paths leading from achievements to self-confidences, controlling for the positive matching domain paths, as predicted by the skill-development model across domains; (2) there were "positive" cross-domain paths leading from self-confidences to achievements, controlling for the positive matching domain paths, as predicted by the self-enhancement model across domains. There were, however, qualitative variations in the degrees of support for the 2 models across countries.

As middle school mathematics becomes more abstract, it is imperative for teachers to introduce concepts in ways that are interesting and meaningful to students. Since her students struggled at times to stay engaged in mathematics and seemed to have difficulty developing conceptual understanding, the author looked for ways to create learning contexts that would be noteworthy and relevant. Working with data seemed to lend itself readily to contexts that were appealing to students. To give her students additional experience with measures of central tendency and data collection, she developed an activity that involved making and flying paper airplanes. This lesson, which ultimately focused on measures of central tendency, also addressed measurement, scatter plots, and the four main forces of flight. (Contains 5 figures.)

Locating a target in a visual search task is facilitated when the target location is repeated on successive trials. Global statistical properties also influence visual search, but have often been confounded with local regularities (i.e., target location repetition). In two experiments, target locations were not repeated for four successive trials, but with a target location bias (i.e., the target appeared on one half of the display twice as often as the other). Participants quickly learned to make more first saccades to the side more likely to contain the target. With item-by-item search first saccades to the target were at chance. With a distributed search strategy first saccades to a target located on the biased side increased above chance. The results confirm that visual search behavior is sensitive to simple global statistics in the absence of trial-to-trial target location repetitions. (Contains 2 figures, 1 table and 3 footnotes.)

Statistics and probability have become an integral part of mathematics education. Therefore it is important to understand whether curricular materials adequately represent statistical ideas. The "Guidelines for Assessment and Instruction in Statistics Education" (GAISE) report (Franklin, Kader, Mewborn, Moreno, Peck, Perry, & Scheaffer, 2007), endorsed by the American Statistical Association, provides a two-dimensional (process and level) framework for statistical learning. This paper examines whether the statistics content contained in the NSF funded elementary curricula "Investigations in Number, Data, and Space, Math Trailblazers," and "Everyday Mathematics" aligns with the GAISE recommendations. Results indicate that there are differences in the approaches used as well as the GAISE components emphasized among the curricula. In light of the fact that the new Common Core State Standards have placed little emphasis in statistics in the elementary grades, it is important to ensure that the minimal amount of statistics that is presented aligns well with the recommendations put forth by the statistics community. The results in this paper provide insight as to the type of statistical preparation students receive when using the NSF funded elementary curricula. As the Common Core places great emphasis on statistics in the middle grades, these results can be used to inform whether students will be prepared for the middle school Common Core goals. (Contains 3 tables and 1 footnote.)

This study examines associations between binge drinking and other substance use and perpetration of violence against self and others. Data were pooled from the 2003, 2005, and 2007 Youth Risk Behavior Surveys, yielding a sample of 43,172 U.S. high school students. A typology was constructed to reflect four categories of behaviors: other-directed violence only, self-directed violence only, combined other- and self-directed violence, and no violence. Results from multinomial logistic regressions show that the frequency of binge drinking and other substance use were significant risk factors for each of the violence categories relative to no violence. However, the strengths of these associations varied across the violence categories. (Contains 2 tables.)

This article compares the definition of "box plot" as used in the "Australian Curriculum: Mathematics" with other definitions used in the education community; describes the difficulties students experience when dealing with box plots; and discusses the elaboration that is necessary to enable teachers to develop the knowledge necessary to use them effectively. The box plot is 40 years old. Like many 40-year-olds the box plot has changed its shape and varied its personal descriptors over the years. Its power to inform exploratory data analysis has gained it a place in statistics curricula at various levels in many countries. The "Australian Curriculum: Mathematics" has placed it at Year 10 in the Statistics and Probability strand of the learning area. As the curriculum document is sparse in its description and elaboration of the term, three issues relating to the needs of the teachers required to implement the curriculum are discussed in this article: (1) there is not one universally accepted definition of a box plot and teachers need to be aware that they and their students may encounter contradictions in different contexts where different conventions apply; (2) teachers need to be aware of the difficulties their students encounter in understanding box plots; and, (3) there is minimal advice in the curriculum elaborations about how the box plot can be used effectively in a statistical investigation. (Contains 12 figures, 1 table and 1 footnote.)

We are delighted to reflect on the 10 papers highlighted in this important special issue of "Early Childhood Research Quarterly" devoted to recent secondary data analyses of the FACES and EHSREP datasets. First, we provide some background on Head Start research and give an overview of the large-scale Head Start and Early Head Start datasets that are available for researchers to analyze. Then, we comment on the papers in this special issue from a methodological and statistical standpoint. Finally, we reflect on themes that stood out across the various papers. Throughout, we make recommendations for future large-scale data collection efforts and future research on Head Start and Early Head Start programs.

Data from a cough challenge study are displayed with dot charts to demonstrate the importance of graphs in understanding data, principles of graph construction and visual perception. The data are available for use in the classroom.

Since it was first published 30 years ago, the seminal paper of Chi "et al." on expert and novice categorization of introductory problems led to a plethora of follow-up studies within and outside of the area of physics [Cogn. Sci. 5 121 (1981)]. These studies frequently encompass "card-sorting" exercises whereby the participants group problems. While this technique certainly allows insights into problem solving approaches, simple descriptive statistics more often than not fail to find significant differences between experts and novices. In moving beyond descriptive statistics, we describe a novel microscopic approach that takes into account the individual identity of the cards and uses graph theory and models to visualize, analyze, and interpret problem categorization experiments. We apply these methods to an introductory physics (mechanics) problem categorization experiment, and find that most of the variation in sorting outcome is not due to the sorter being an expert versus a novice, but rather due to an independent characteristic that we named "stacker" versus "spreader." The fact that the expert-novice distinction only accounts for a smaller amount of the variation may explain the frequent null results when conducting these experiments. (Contains 12 figures and 2 tables.)

Practical project work based on eBay selling prices is described. It is suitable for secondary school students of a wide range of statistical expertise and it may be used to introduce a statistical package. (Contains 4 figures and 5 tables.)

In this article a continuous-time stochastic model (the Ornstein-Uhlenbeck process) is presented to model the perpetually altering states of the core affect, which is a 2-dimensional concept underlying all our affective experiences. The process model that we propose can account for the temporal changes in core affect on the latent level. The key parameters of the model are the average position (also called home base), the variances and covariances of the process, and the regulatory mechanisms that keep the process in the vicinity of the average position. To account for individual differences, the model is extended hierarchically. A particularly novel contribution is that in principle all parameters of the stochastic process (not only the mean but also its variance and the regulatory parameters) are allowed to differ between individuals. In this way, the aim is to understand the affective dynamics of single individuals and at the same time investigate how these individuals differ from one another. The final model is a continuous-time state-space model for repeated measurement data taken at possibly irregular time points. Both time-invariant and time-varying covariates can be included to investigate sources of individual differences. As an illustration, the model is applied to a diary study measuring core affect repeatedly for several individuals (thereby generating intensive longitudinal data). (Contains 3 tables, 10 footnotes and 11 figures.)

Advances in statistics provide new methods for analyzing practice data. These advances include person-centered methods (PCMs) that identify subgroups of research participants with similar characteristics. PCMs derive from a frame of reference that is similar to the risk factor perspective in practice. In practice, the delivery of services is often contingent on identifying at-risk populations and then providing interventions to groups based on shared risk profiles. PCMs use this perspective. Moreover, PCMs provide a means for identifying high-risk groups with a precision rarely afforded by routine variable-centered methods. This article describes a latent profile transition analysis (LPTA), one of several PCMs. To demonstrate LPTA, we estimate risk profiles and treatment effects using data from a cohort study of a school-based social skills training program. We define four steps in PCMs analysis, describe key statistical tests, and conclude with a discussion of the strengths and limitations of PCMs for practice research. (Contains 4 tables and 2 figures.)

Introductory business statistics students often receive little guidance on how to apply the methods they learn to further business objectives they may one day face. And those students may fail to see the continuity among the topics taught in an introductory course if they learn those methods outside a context that provides a unifying framework. The DCOVA problem-solving framework that presents discrete steps to define, collect, organize, visualize, and analyze data addresses these concerns while helping to enhance the perceived value of taking statistics courses.

This article presents an interview with David Rindskopf, a Distinguished Professor of Educational Psychology and Psychology at the City University of New York Graduate Center, where he has taught since 1979. His research and teaching are in the area of applied statistics, measurement, and research design. He is a fellow of the American Statistical Association (ASA) and the American Educational Research Association (AERA), and has served as the president of the New York Chapter of the ASA. He has also served as president of the Society of Multivariate Experimental Psychology and as associate editor of the society's journal, "Multivariate Behavioral Research." Professor Rindskopf just completed a term as editor of the "Journal of Educational and Behavioral Statistics," jointly published by ASA and AERA. His research mostly involves creative applications of statistical techniques to applied problems. One such current application is the use of multilevel models to analyze data from single case designs, which he is pursuing with Professor William Shadish of University of California, Merced, and Professor Larry Hedges of Northwestern University, for which they have a grant from the Institute of Educational Sciences in the U.S. Department of Education. In this interview, Professor Rindskopf discusses his interest in statistics, his current projects, and his legacy.

Background: In program evaluation interventions are usually examined for global effects but not always for differential effects. The reasoning behind the focus on global effects is that most of the concepts applied in data analyses, and most of the hypotheses being assessed, are variable-oriented. Consequently, existing differential effects will not be detected through global analyses based on a variable-oriented perspective. Accordingly, the intervention under evaluation will be wrongly considered to be ineffective. Purpose: This contribution, therefore, argues for the application of person-oriented analyses in addition to the common variable-oriented approach in order to identify the differential effects of an intervention during evaluation. Setting: Both approaches will be applied in the evaluation of a showcase program conducted in real life setting. The results of the two perspectives will be compared. Intervention: An internet supported program for the promotion of self-regulated learning in an academic context called Vienna E-Lecturing (VEL). Research Design: The evaluation of the VEL was conducted with a treatment-control-design. Data was collected at the beginning as well as at the end of the intervention. Data Collection and Analysis: Data regarding motivation as well as factual knowledge was collected. All motivational variables were assessed using previously published scales consisting of 3-4 items. Factual knowledge in statistics and methodology was tested regarding the aspects of reproduction, comprehension and the production of methodological content. Findings: The application of a variable-oriented perspective showed small effects with low practical relevance. Through the application of a person-oriented approach, and taking into account the theoretical framework of the intervention, three students groups which differed systematically in their learning motivation could be identified. For two of these groups the intervention was very successful. The discussion provides recommendations on how person-oriented approaches can be used systematically in program evaluation. (Contains 6 tables.)

The purpose of the study reported herein was to identify the important aspects of statistical knowledge that students in the middle school grades in United States are expected to learn as well as what the teachers are expected to teach. A systematic study of 49 states standards and one set of national standards was used to identify these important aspects, and to measure the degree of emphasis or importance suggested for the content. Results show that state and national standards differ greatly in their expectations of what topics in data analysis and statistics students and teachers should master. There is also a large variation in the degree of emphasis given to the content. The majority of the standards analyzed suggest giving greater emphasis to the selection and proper use of graphical data representation and measures of center. (Contains 2 tables and 2 figures.)

Two basic data sources required for research studies have been secondary and primary. Secondary data collection helps the researcher to provide relevant background to the study and are, in most cases, available for retrieval from recorded sources. Primary data collection requires the researcher to venture into the field where the study is to take place; armed with the relevant instruments--questionnaire, interview schedules or arranged meetings with the selected population--to solicit the necessary information. Data collected assist the researcher to answer the research questions and address the research problem. The collection, treatment, analysis and interpretation of both secondary and primary data combine to make the researcher produce a report. This paper proposes to present a systematic methodological application where data collected for a research study can be conveniently treated, analysed and interpreted. Attempt to present the collected primary data in both quantitative and qualitative spheres will be made so that researchers who use either method or both are able to apply them confidently. (Contains 3 figures.)

As anyone who has taught or taken a statistics course knows, statistical calculations can be tedious and error-prone, with the details of a calculation sometimes distracting students from understanding the larger concepts. Traditional statistics courses typically use scientific calculators, which can relieve some of the tedium and errors but provide little record for the student to study and/or submit. Mastering the calculator also involves a steep learning curve, especially for more complex statistical calculations. "Excel," on the other hand, provides an excellent visual learning tool for statistics classes, from the introductory level focusing on descriptive statistics and graphs to the advanced statistics courses involving hypothesis testing, ANOVA, and multiple linear regression. This is especially the case for online statistics courses, since both student and instructor are already communicating solely via computer and most students have "Excel" software on their machines. From there it's just a matter of the student learning how to use "Excel" for statistical calculations, analyses, and graphs. In this article, the author discusses a tutorial methodology which relies on static tutorials presented directly in "Excel," using graphs, instructional textboxes, arrows, numbered steps, formulas tied to cell references, screen shots of function dialog boxes, and Data Analysis Tools, with each tutorial tied directly to examples in the textbook. Thus, the student is able to see and compare both the textbook's approach and the "Excel" approach to solving the same problem, reinforcing the learning of both concepts and methodology. (Contains 8 figures.)

This study tests a process model of learning in which trainer and trainee traits are simultaneously considered as endogenous variables of learning outcomes. The article builds on a social view of training and similarity-attraction paradigms. In this context, the authors hypothesize that trainer-trainee similarity in personality (agreeableness) engenders social reactions that influence how much trainees learn. To test the study hypotheses, undergraduate students (N = 194) participated in a training program during an academic semester. Results from structural-equation modeling indicate that similarity in personality acted on trainees' emotional states, which, in turn, accounted for trainees' posttraining declarative knowledge. With the use of hierarchical regression procedures, results indicated that personality similarity explained incremental variance of posttraining declarative knowledge beyond modal learning correlates (e.g., cognitive abilities, conscientiousness). The results provide evidence of a social view of training in which combined attributes of dyads (trainer-trainee) account for learning results that the extant literature primarily relates to individual-level variables (e.g., cognitive abilities). The discussion section addresses theoretical implications of the findings, with special emphasis on compositional approaches of personality. From an applied perspective, the authors discuss why corporate trainers should consider the role of their personality in training, and they also make suggestions for weighting the effect of personality similarity when evaluating training results. In this study, the authors center their attention on the trainer-trainee (T-T) dyad. Specifically, they explore how social reactions emerging from T-T's contacts impact trainees' learning processes. The notion that training is a social event suggests that interpersonal reactions (e.g., affiliation, rejection) may be operating in training. However, little is known about how trainees socially respond to trainers and, ultimately, how these responses may influence learning. The authors rely on similarity-attraction theory to hypothesize social reactions in training. Because individuals prefer to relate socially with those they perceive as similar, T-T's similarity (or lack thereof) can modify trainees' states in training, potentially altering learning outcomes. This article describes a process model that depicts the hypothetical paths connecting T-T's similarity to learning outcomes. The authors review interpersonal attraction theory with the goal of laying the theoretical foundations for the hypothesized model. (Contains 1 figure and 2 tables.)

This paper discusses the use of interactive graphics to teach multivariate data analysis to Psychology students. Three techniques are explored through separate activities: parallel coordinates/boxplots; principal components/exploratory factor analysis; and cluster analysis. With interactive graphics, students may perform important parts of the analysis "by hand," using techniques such as pointing at, selecting and changing the colors of the points/observations. Our experience demonstrates that this approach is very useful when teaching an intermediate/advanced course on multivariate data analysis to students of Psychology, who tend to have low to moderate proficiency in Mathematics. (Contains 6 figures.)

This study evaluated whether pubertal development and gender role orientation (i.e., masculinity and femininity) can partially explain sex variations in youth anxiety symptoms among clinic-referred anxious youth (N = 175; ages 9-13 years; 74% Hispanic; 48% female). Using youth and parent ratings of youth anxiety symptoms, structural equation modeling results indicated that youth who reported being more advanced in their pubertal development reported high levels of femininity and anxiety symptoms. Youth who reported high levels of masculinity had low levels of anxiety symptoms as reported by both youths and parents. The estimated effects of pubertal development, femininity, and masculinity on youth and parent ratings of youth anxiety symptoms were not significantly moderated by biological sex. Pubertal development and gender role orientation appear to be important in explaining levels of youth anxiety symptoms among clinic-referred anxious youth. (Contains 2 tables and 2 figures.)

Our research addresses the role that context expertise plays when students compare data. We report findings from a study conducted in 3 countries: Australia, United States, and Thailand. In each country, six middle school students analyzed authentic data relating to selected students' areas of interest. We examined the data analysis processes and discussion among students as each country cohort worked in two groups of three, where only one group included a student with particular expertise with the data context. We found that students used context knowledge to (a) bring new insight or additional information to the task, (b) explain the data, (c) provide justification or qualification for claims, (d) identify useful data for the task at hand, and (e) state facts that may enhance the picture of the data but are irrelevant to the process of analyzing the data. Implications for practice are discussed. (Contains 1 table, 1 figure and 2 footnotes.)

Context is identified as an important factor when considering the learning of informal statistical inferential reasoning, but research in this area is very limited. This small exploratory study in one grade 10 (14 year olds) classroom seeks to learn more about the role context plays in learners' inferential reasoning, where both teacher and students are positioned as learners. Two frameworks for context are used to analyze the classroom dialogue: The data-context used in statistical enquiry and in the formation of statistical concepts and the learning-experience-contexts such as prior statistical knowledge, which can affect the learning process. The analysis tracks the learning of informal inferential reasoning before, during, and after the introduction of sampling variability concepts. Data-context was found to assist learners in finding meaning from observed patterns, but could divert their attention during the construction of concepts and when attempting to apply newly-learned theory. Learning-experience-contexts played a significant role in mediating learners' development of informal inferential reasoning. Implications for developing concepts for informal inferential reasoning and for research are discussed. (Contains 2 tables and 3 figures.)

A broad-based survey using the Delphi method was conducted to garner current information from private sector stakeholders and build consensus opinions supporting key ideas for enhancing plant breeder education and training. This study asked respondents to suggest and rate topics and content they deemed most important to plant breeding graduate programs and curricula related to the areas of knowledge, experiences, skills, and specialties. Examination of private stakeholder recommendations for integration into a student's education and preparation for jobs outside academia was then performed. Knowledge of traditional plant breeding, genetics, statistics, and experimental design, along with emerging topics including database management and ethics, were rated very important. Experiences rated as very important included designing an experiment, as well as field and laboratory data analysis. Stakeholders suggested that experiences focusing on communication, teamwork, and management are key aspects of training. Scientific skills suggested by stakeholders aligned quite well with important knowledge and experience categories and also included skills a student can acquire through a variety of experiences focused on judgment and ideas, time and efficiency in completing tasks, and decision making abilities. The information detailed in this study will be useful to all educators seeking content ideas from private sector stakeholders for curriculum programs. It will also be a valuable tool for new graduate students seeking to understand the knowledge and skill sets that are recommended for a plant breeder prior to seeking a job in the private sector. (Contains 4 tables and 3 figures.)

Clickers were used for real-time data collection in two introductory biology laboratory courses so that students could perform statistical analysis on large data sets. Student attitudes toward this use of clickers were surveyed and students were administered a pre- and posttest on statistical content. Capture of large data sets allowed instructors to align statistical analysis content with the laboratory exercises, and students reported that use of clickers for data collection helped them to perform data analysis, understand the role of statistics, and understand the need for larger data sets. (Contains 6 figures.)

Two methods of data analysis are compared: spreadsheet software and a statistics software suite. Their use is compared analysing data collected in three selected experiments taken from an introductory physics laboratory, which include a linear dependence, a nonlinear dependence and a histogram. The merits of each method are compared. (Contains 7 figures.)

The purpose of this study was to assess some of the effects of a nontraditional, experimental learning approach designed to improve rapid acquisition and long-term retention of quantitative communication skills (QCS) such as descriptive and inferential statistics, hypothesis formulation, experimental design, data characteristics, and data analysis. The authors found that (1) the experimental learning approach used in this study resulted in significant improvement in QCS by the end of the semester, (2) there was no significant difference in the QCS backgrounds between students enrolled in the major's biology course and those enrolled in the nonmajors biology course, (3) there was significant retention of QCS beyond the major's biology experience, and (4) there was no significant change in QCS beyond the major's biology experience as a result of other experiences currently in place in the core and upper-division courses that were a part of this study. The results of this study have encouraged the biology faculty to begin the redesign of their curriculum to accommodate a greater use of QCS, including strong intervention of QCS in laboratory sections of all freshman and sophomore courses as well as in most upper-division courses. (Contains 2 tables.)

How can statistics clearly be mathematical and yet distinct from mathematics? The answer lies in the reality that statistics is both an art and a science, and both aspects are important for teaching and learning statistics. Statistics is a mathematical science in that it applies mathematical theories and techniques. Mathematics provides the theoretical means for justifying statistical methods as well as the procedural tools for implementing them. Methods for collecting, analyzing, and interpreting data combine to form the science of statistics. In this article, the author describes artistic and scientific facets of statistics and uses a task to illustrate how teachers can encourage students to incorporate elements of both art and science in their reasoning. (Contains 4 figures.)

Contemporary argument increasingly relies on quantitative information and reasoning, yet our profession neglects to view these means of persuasion as central to rhetorical arts. Such omission ironically serves to privilege quantitative arguments as above "mere rhetoric." Changes are needed to our textbooks, writing assignments, and instructor development programs to broaden how both we and our students perceive rhetoric. (Contains 1 figure, 1 table and 7 notes.)

The use of The Three Stooges' films as a source of data in an introductory statistics class is described. The Stooges' films are separated into three populations. Using these populations, students may conduct hypothesis tests with data they collect.

This article looks at a process of integrating real-life data investigation in a course on descriptive statistics. Referring to constructivist perspectives, this article suggests a look at the potential of inculcating alternative teaching methods that encourage students to take a more active role in their own learning and participate in the process of assessing what they have learned. The article illustrates how this teaching method enabled students to realize that imparting meaning to sets of data is a complex activity which involves conceptual flexibility, integration of all the procedures that one has learned, and creative reasoning.

Introduction: This research seeks to determine the influence exercised by a set of presage and process variables (students' pre-existing opinion towards statistics, their dedication to mastery of statistics content, assessment of the teaching materials, and the teacher's effort in the teaching of statistics) in students' resolution of activities and acquisition of competencies relating to quantitative data analysis (product variable). Method: We developed a correlational-predictive study with a sample of undergraduate students in Pedagogy from the University of Granada (N = 70). These students responded to a test with five problem situations, resolving the situations after having first rated the influence of the five predictive variables in their resolution process. Results: The results obtained from analyzing a linear multiple regression indicate that the teacher's effort and students' attitude towards statistics (in this order) play an essential role in performance achieved in the resolution of statistics problems and in mastering competencies of quantitative data analysis. Discussion or Conclusion: The model inferred from this study, in this particular case, gives less importance to the role of student effort or of supplementary instructional materials made available to students in their performance in statistics. (Contains 12 tables and 3 figures.)

The technical complexities and sheer size of international large-scale assessment (LSA) databases often cause hesitation on the part of the applied researcher interested in analyzing them. Further, inappropriate choice or application of statistical methods is a common problem in applied research using these databases. This article serves as a primer for researchers on the issues and methods necessary for obtaining unbiased results from LSA data. The authors outline the issues surrounding the analysis and reporting of LSA data, with a particular focus on three prominent international surveys. In addition, they make recommendations targeted at applied researchers regarding best analysis and reporting practices when using these databases. (Contains 5 tables and 3 notes.)

The amount, complexity and provenance of data have dramatically increased in the past five years. Visualization of observed and simulated data is a critical component of any social, environmental, biomedical or scientific quest. Dynamic, exploratory and interactive visualization of multivariate data, without preprocessing by dimensionality reduction, remains a nearly insurmountable challenge. The Statistics Online Computational Resource (www.SOCR.ucla.edu) provides portable online aids for probability and statistics education, technology-based instruction and statistical computing. We have developed a new Java-based infrastructure, SOCR "Motion Charts," for discovery-based exploratory analysis of multivariate data. This interactive data visualization tool enables the visualization of high-dimensional longitudinal data. SOCR "Motion Charts" allows mapping of ordinal, nominal and quantitative variables onto time, 2D axes, size, colors, glyphs and appearance characteristics, which facilitates the interactive display of multidimensional data. We validated this new visualization paradigm using several publicly available multivariate datasets including Ice-Thickness, Housing Prices, Consumer Price Index, and California Ozone Data. SOCR "Motion Charts" is designed using object-oriented programming, implemented as a Java Web-applet and is available to the entire community on the web at www.socr.ucla.edu/SOCR_MotionCharts. It can be used as an instructional tool for rendering and interrogating high-dimensional data in the classroom, as well as a research tool for exploratory data analysis. (Contains 8 figures and 6 tables.)