ERIC Number: ED389727
Record Type: RIE
Publication Date: 1994-Nov
Reference Count: N/A
Are Values Missing Randomly in Survey Research?
Witta, E. Lea
Many missing data studies have simulated data, randomly deleted values, and investigated the method of handling the missing values that would most closely approximate the original data. Regression procedures have emerged as the most recommended methods. If the values are missing randomly, these procedures are effective. If, however, the values are not missing randomly, the use of regression procedures to impute values for missing data is questionable. The purpose of this study was to determine if values were missing randomly in samples selected from the National Education Longitudinal Study of 1988. Four samples were selected: 2 samples of 8 variables, average inter-correlation of 0.2 and 0.4 respectively; and 2 samples of 4 variables, average inter-correlation of 0.2 and 0.4 respectively. All cases containing one or more missing values were selected, and the pattern of missing values for each was determined. Chi square analysis indicated that the missing values are not missing randomly (p<.001). Implications of the use of regression procedures to handle non-randomly missing values are discussed. Appendix A contains four tables of descriptive statistics. (Contains 12 references and 2 tables.) (Author/SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: Missing Data; National Education Longitudinal Study 1988; Random Variables
Note: Paper presented at the Annual Meeting of the Mid-South Educational Research Association (Nashville, TN, November 9-11, 1994).