Comparison of Missing Data Treatments in Producing Factor Scores.Report as inadecuate

Comparison of Missing Data Treatments in Producing Factor Scores. - Download this document for free, or read online. Document in PDF available to download.

Because ignoring the missing data in an evaluation may lead to results that are questionable, this study investigated the effects of use of four missing data handling techniques on a survey instrument. A questionnaire containing 35 5-point Likert-style questions was completed by 384 respondents. Of these, 166 (43%) questionnaires contained 1 or more missing responses. The missing data pattern was non-ignorable. Listwise deletion, pairwise deletion, regression, and the expectation maximization (EM) algorithm were used to treat the missing data. Resulting data were then submitted to factor analysis and factor scores obtained. Factor scores for each group defined by missing data method were then contrasted by multivariate analysis of variance. Less than 1% of the variance in scores could be explained by group (F=0.218, df=30,3496, p=1.0). Based on these results, the choice of missing value treatment can be based on the consequences of loss of power by loss of cases or other data handling considerations. (Contains 1 table, 1 figure, and 17 references.) (Author/SLD)

Descriptors: Evaluation Methods, Factor Analysis, Factor Structure, Likert Scales, Multivariate Analysis, Questionnaires, Regression (Statistics), Responses, Surveys

Author: Witta, E. Lea


Related documents