Incorporating Uncertainty Into Parallel Analysis for Choosing the Number of Factors via Bayesian Methods

A number of psychometricians have suggested that parallel analysis (PA) tends to yield more accurate results in determining the number of factors in comparison with other statistical methods. Nevertheless, all too often PA can suggest an incorrect number of factors, particularly in statistically unfavorable conditions (e.g., small sample sizes and low factor loadings). Because of this, researchers have recommended using multiple methods to make judgments about the number of factors to extract. Implicit in this recommendation is that, when the number of factors is chosen based on PA, uncertainty nevertheless exists. We propose a Bayesian parallel analysis (B-PA) method to incorporate the uncertainty with decisions about the number of factors. B-PA yields a probability distribution for the various possible numbers of factors. We implement and compare B-PA with a frequentist approach, revised parallel analysis (R-PA), in the contexts of real and simulated data. Results show that B-PA provides relevant information regarding the uncertainty in determining the number of factors, particularly under conditions with small sample sizes, low factor loadings, and less distinguishable factors. Even if the indicated number of factors with the highest probability is incorrect, B-PA can show a sizable probability of retaining the correct number of factors. Interestingly, when the mode of the distribution of the probabilities associated with different numbers of factors was treated as the number of factors to retain, B-PA was somewhat more accurate than R-PA in a majority of the conditions.     

Gender and IT in the Household: Evolving Patterns of Internet Use in the United States

Information technology (IT)—computers and related technologies—is the latest technology to enter the household. Like other technologies, gender is a major factor in its adoption and use as well as its perceived usefulness. Unlike prior household technologies, the computer's entry into the household has followed a different pattern. Early statistics revealed a vast gender divide, with men using computers and related technologies much more in the household. More recent statistics show a narrowing of the divide, perhaps even a reversal, particularly in the United States, with women outnumbering men in the access to and use of the Internet. In this article, the role of gender and its relationship with Internet use in the home are reviewed. In addition to overall adoption and access, the review focuses on specific Internet applications and examines the factors that contribute to gender differences in adoption and use of computers and Internet applications in the home.     

Data‐Driven Improvement in Prekindergarten Classrooms: Report From a Partnership in an Urban District

In 2014–2015 and 2015–2016, a metropolitan school system in the southern United States embarked on a unique mission to improve the quality of its public prekindergarten programs through a partnership with a group of developmental researchers in an iterative, data‐based venture. Data on 407 children in Year 1 and 433 in Year 2 (who were enrolled in 26 classrooms and extensively observed) are presented from the first 2 years of the ongoing partnership. All children were 4 years of age. Variability in classroom practices, measured empirically, and variability in child outcomes provided the means to examine the relations between children's gains in academic and social‐emotional areas and major areas of classroom practices. Lessons learned, the eight identified significant practices, implications, and next steps in the partnership are addressed.     

Faculty ratings as a measure of departmental and administrator quality

This study examined the usefulness of faculty ratings as a measure of departmental quality. Two hundred and thirty-three faculty members from six departments responded to two questionnaires relating to the department—the Department Evaluation Survey (DES)—and to the department head—the Administrator Evaluation Survey (AES). A factor analysis of the DES revealed three underlying dimensions: Satisfaction with the Department's Academic Environment, Satisfaction with the Department's Governance and Operating Procedures, and Satisfaction with Student Quality. The factor analysis of the AES identified only one underlying dimension. Both the DES and AES were found to be highly reliable and effective in discriminating among departments. Very high positive correlations were also found between selacted DES and AES items suggesting that the performance of the head plays a very important role in faculty perceptions of the departments, and vice versa. Faculty ratings would appear to be a useful initial criterion in evaluating a department or head.     

Letting girls speak out about science

The purpose of this study was to try to determine what influences girls to choose science. Forty girls were interviewed in Grades 2, 5, 8, 11 using a semistructured protocol. The interview focused on feelings about science, science careers, peer and parental support, and how science is taught. To determine whether their responses were based on gender, each girl was asked to respond to questions as if she were a boy. The girls were highly self-confident and positive about science. All of the girls took a strong equity position and asserted that women can and should do science. The girls liked learning science in an interactive social context rather than participating in activities that isolated them such as independent reading, writing, or note taking. Those who chose science careers were drawn to them because of strong affective experiences with a loved one and a desire to help. The interviews were analyzed through the framework of women's affective and psychological needs.     

The effects of various mastery criteria on student performance and attitude in a mastery-oriented course

The purpose of this study was to determine the effects of various mastery criteria on student performance and attitude in a course in which mastery learning strategies were employed. Undergraduates in an introductory course in educational psychology were randomly assigned to one of three treatments—one in which mastery criteria gradually increased from 70% to 90%, a second in which mastery criteria gradually decreased from 90% to 70%, or a third in which mastery criteria remained constant at 80%. Results indicated that although the high mastery criterion (90%) had a positive effect on some aspects of quiz performance, it did not have an effect on final examination performance. Results also indicated that students preferred that mastery criteria remain constant during a semester. These findings, when examined in light of previous research, call into question some prior notions regarding the levels at which mastery criteria should be set.