Lea Witta - Academia.edu (original) (raw)

Conference Presentations by Lea Witta

Cognition and depression in the elderly have been widely investigated. There has, however, been s... more Cognition and depression in the elderly have been widely investigated. There has, however, been some disagreement concerning these fostered in part by differences in instruments used, in data collection methods, and in analytic methods used. This study used Immediate and Delayed Recall data as well as the CESD Depression data collected by the Health and Retirement Survey housed at the University of Michigan. A latent growth curve model was used to estimate the mean and variability of scores over an eight-year time span. Results indicated there was a statistically non-significant decline in both Immediate Recall, a significant increase in Delayed Recall and negative (sad) CESD scores, and a significant increase in positive (happy) CESD. However, there was substantial variability in the change of scores and most of the starting values.

Papers by Lea Witta

Although reliability and validity are characteristics of test data, social scientists often attri... more Although reliability and validity are characteristics of test data, social scientists often attribute reliability and validity erroneously to the tests themselves. To determine the extent to which this problem exists, 150 reliability and validity studies selected from 3 prominent social science measurement journals over a 3-year period were analyzed for common errors in terminology and categorized according to methodology types used in assessing reliability and validity. Results indicate over 50 percent of the articles contained more than one inappropriate statement concerning reliability or validity. It is suggested that professional journal reviewers and editors could improve research practice by catching and correcting a larger percentage of these errors. In the educational research classroom, it is recommended that teachers emphasize that reliability and validity are properties of data, model correct language about score characteristics while discussing reliability and validity ...

Teachers participating in an educational interactive video program were surveyed each year for fo... more Teachers participating in an educational interactive video program were surveyed each year for four semesters. The survey instrument contained 31 five-point Likert-type questions, with questions concerning specific comparisons between interactive video and traditional teaching methods, and open-ended questions. A total of 74 teachers responded over the four-year time span. Although teachers report that interactive video teaching methods require more preparation and new methods, they also report more comfort with the technology use required for interactive video. More troubling is the decreasing view of interactive video as a good addition to the curriculum. Teachers report that time-on-task and learning are the same in traditional and interactive video classes. They overwhelmingly agreed that they received support from the educational interactive video project director, the remote principal, and other sources. Results are discussed in terms of teaching factors, student factors, stud...

The purpose of this study was to determine if there were differences in evaluation of an educatio... more The purpose of this study was to determine if there were differences in evaluation of an educational interactive video program between high school students and their parents over a 4-year time span. High school students participating in the interactive video program were surveyed during 5 semesters. Survey instruments were also sent to parents via the student. There were 1,024 student respondents and 481 parent respondents. Constructs for each group were determined using exploratory factor analysis. The mean vectors of similar constructs for each status group were contrasted using multivariate analysis of variance (MANCOVA) with semester and site as additional factors. In addition, similar questions for each status group that would not be included in a construct were also contrasted by MANOVA. Because heterogeneity of covariance matrices was not achieved in the initial sample, a stratified random sample of 150 was selected from each site and status group and the analysis repeated. R...

When survey data are statistically analyzed, many times some of the data is missing. If the missi... more When survey data are statistically analyzed, many times some of the data is missing. If the missing values are not correctly handled, results of the analysis may be dubious and publication may jeopardize the credibility of the organization preparing the report. This study examined four of the more commonly used methods of handling missing data. The following techniques were compared: (1) listwise deletion; (2) pairwise deletion; (3) mean substitution; and (4) regression imputation of missing data. Comparisons were made using a sample selected from the General Social Survey--1984 of the National Opinion Research Center. The sample of 829 cases was randomly divided into two sample groups: Sample 1, with 415 cases; and Sample 2, with 414 cases, which was reduced to only non-missing cases at 283. Sample 1 was used to develop regression equations after treatment by each technique. Sample 2 was used to compare the efficiency of these regression equations in predicting the criterion variab...

AUTHOR Witta, E. Lea TITLE High School Student High School Parent: Are There Differences in Perce... more AUTHOR Witta, E. Lea TITLE High School Student High School Parent: Are There Differences in Perceived Strengths and Weaknesses of an Educational Interactive Video Program? PUB DATE 1999-11-00 NOTE 40p.; Paper presented at the Annual Meeting of the American Evaluation Association (Orlando, FL, November 3-6, 1999). For a related document, see TM 030 338. PUB TYPE Reports Research (143) -Speeches/Meeting Papers (150) EDRS PRICE MF01/PCO2 Plus Postage. DESCRIPTORS Analysis of Variance; Distance Education; *High School Students; High Schools; *Interactive Video; *Parent Attitudes; *Parents; Program Evaluation; *Student Attitudes; Surveys

AUTHOR Witta, E. Lea TITLE Does Method of Handling Missing Data Affect Results of a Structural Eq... more AUTHOR Witta, E. Lea TITLE Does Method of Handling Missing Data Affect Results of a Structural Equation Model? PUB DATE 2001-02-00 NOTE 30p.; Paper presented at the Annual Meeting of the Southwest Educational Research Association (New Orleans, LA, February 1-3, 2001). PUB TYPE Reports Research (143) Speeches/Meeting Papers (150) EDRS PRICE MF01/PCO2 Plus Postage. DESCRIPTORS Academic Achievement; *High School Students; High Schools; Regression (Statistics); *Research Methodology; *Statistical Analysis; *Structural Equation Models IDENTIFIERS *Missing Data; National Education Longitudinal Study 1988

This study used log-linear modeling to examine responses of high school students enrolled in an i... more This study used log-linear modeling to examine responses of high school students enrolled in an interactive video program during the 1995, 1996, 1997, and 1998 program years to open-ended questions concerning strengths and weaknesses of the program. Respondents were categorized by home or remote site and by semester. Analyses of the strength responses provided a model with a relationship between strength and site and between strength and semester. The weakness response required a model including the interaction of weakness, site, and semester. Results are discussed.

Cognition in the elderly has been widely investigated, but there has been some disagreement conce... more Cognition in the elderly has been widely investigated, but there has been some disagreement concerning this phenomenon fostered in part by differences in instruments used, in data collection methods, and in analytic methods used. This study used Immediate and Delayed Recall data collected by the Health and Retirement Survey housed at the University of Michigan. After excluding respondents not available for all 5 time periods over the span of 1992 through 2000, there was a final sample of 7,169. A latent growth curve model was used to estimate the mean and variability of scores over a 6-year time span. Results indicate there was a statistically significant decline in both immediate and delayed recall. However, there was substantial variability in both the change of scores and the starting values. (Contains 4 figures and 14 references.) (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the original document. Latent Growth Modeling of Cognition In the Elder...

... ed.). London: Croom Helm. Kenny, RF (2002). The effects of cognitive style and gender on verb... more ... ed.). London: Croom Helm. Kenny, RF (2002). The effects of cognitive style and gender on verbatim and gist memory for rapidly-presented montage video., Univ Microfilms International. ... Journal of Agricultural Education, 42(4), 12-20. Wapner, S., & Demick, J. (Eds.). (1991). ...

An existing large data set, the Health and Retirement Study 2000 (HRS 2000) was used to explore t... more An existing large data set, the Health and Retirement Study 2000 (HRS 2000) was used to explore the relationship between cognition and other factors for individuals aged 65 and older, with a final sample of 1,610 males and 3,549 females. .Using structural equation modeling, the entire model was tested to determine if there were differences in how well the model fit data from both men and women. The influences of direct and indirect contributing factors on cognition were also investigated. Although there were no significant gender differences in the fit of the model for data from this population, future research might study the relationship between cognitive decline and gender within specific age or cultural groups. (Contains 1 table, 3 figures, and 42 references.) (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the on inal document. Social/Biological Factors with Cognition 1 Running Head: Social/Biological Factors with Cognition Structural Equation Mod...

The construct validity and internal consistency (reliability) of the 30-item form of the Leadersh... more The construct validity and internal consistency (reliability) of the 30-item form of the Leadership Behavior Descriptive Questionnaire (E. Fleishman, 1957; A. Halpin and B. Winer, 1957) as presented in a current leadership text was assessed. Classroom teachers and administrators (n.187) completed the instrument. Although reliability was found to be acceptable, neither the two-factor nor the five-factor model was adequate. Although the two-factor model produced adequate estimates of reliability, it should not be used without reverse coding. Reasons for these findings are discussed. An appendix contains two-factor and five-factor rotated convergent matrices. (Contains 5 figures, 3 tables, and 15 references.) (Author/SLD) *

Educational Research Quarterly, Mar 1, 2000

Although the Wechsler Intelligence Scale for Children-Revised (WISC-R) is being rapidly replaced ... more Although the Wechsler Intelligence Scale for Children-Revised (WISC-R) is being rapidly replaced by the third edition of the WISC, questions concerning the construct validity of the WISC-R have.not yet been resolved, including the number of factors it measures and whether the same constructs fit across all age levels. This study sought to determine whether the WISC-R measures the same constructs across age levels, what constructs it does measure, and how many constructs provide the best fitting model. Multi-sample, hierarchical confirmatory factor analyses using the LISREL computer program (version 7.2) were performed on the WISC-R standardization data. This sample consisted of 2,200 subjects, 200 in each of 11 age groups from 6.5 to 16.5 years. The covariance matrices for the 11 age levels were statistically indistinguishable (p>.05). The test did measure the same constructs across ages. The three-factor model provided a statistically better fit than the two-factor model, and a more parsimonious fit than the four-factor model. In addition, the three-factor model produced a consistently good fit as tested by chi-square holding both measurement and error matrices invariant across all 11 age groups. (Contains 3 tables, 4 figures, and 11 references.) (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the original document.

Two types of self-efficacy were investigated in this study: self-efficacy for course content and ... more Two types of self-efficacy were investigated in this study: self-efficacy for course content and self-efficacy for online learning technologies. Specifically, the study examined how these two types of selfefficacy change throughout a semester. Secondly, it examined whether students' self-efficacy is predicative of their satisfaction and course performance. Three hypotheses were tested: (1) self-efficacy for both course content and online learning technologies change across a semester; (2) selfefficacy is predictive of student satisfaction with course; (3) self-efficacy is predictive of course performance. Participants were undergraduate students who enrolled in an online course at the University of Central Florida. In an attempt to longitudinally gauge the student's continuing self-efficacy, a self-efficacy survey for the course content and online learning technologies was administered every three weeks (Four times across a semester). At the end of the semester, students' perceived degree of satisfaction with the online course was measured and students' final course scores were obtained from the instructor. Results indicated that both self-efficacy for course content and self-efficacy for online technologies increased during the semester. In addition, while initial self-efficacy for course content was a significant predicator of students' satisfaction with the course, neither self-efficacy with the course content nor self-efficacy with online technologies was a significant predictor of performance. (Contains 39 references.

Educational Research Quarterly, Mar 1, 2000