Address correspondence to Honghu Liu, Ph.D., Department of Medicine, Division of General Internal Medicine and Health Services Research, University of California, Los Angeles, 911 Broxton Avenue, Los Angeles, CA 90024. Dr. Liu, Ron D. Hays, Ph.D., Wen-Pin Chen, M.S., Diana Tisnado, Ph.D., Carol M. Mangione, M.D., M.P.H. and Katherine L. Kahn, M.D., are with the Department of Medicine, Division of General Internal Medicine and Health Services Research, University of California, Los Angeles, CA. Ron D. Hays, Ph.D., John L. Adams, Ph.D., Carol M. Mangione, M.D., M.P.H., Cheryl L. Damberg, Ph.D., Katherine L. Kahn, M.D., are with the RAND Corporation, Santa Monica, CA. Cheryl L. Damberg, Ph.D., is with the PBGH, San Francisco, CA.
Imputation of SF-12 Health Scores for Respondents with Partially Missing Data
Article first published online: 24 MAY 2005
Health Services Research
Volume 40, Issue 3, pages 905–922, June 2005
How to Cite
Liu, H., Hays, R. D., Adams, J. L., Chen, W.-P., Tisnado, D., Mangione, C. M., Damberg, C. L. and Kahn, K. L. (2005), Imputation of SF-12 Health Scores for Respondents with Partially Missing Data. Health Services Research, 40: 905–922. doi: 10.1111/j.1475-6773.2005.00391.x
- Issue published online: 24 MAY 2005
- Article first published online: 24 MAY 2005
- Health related quality of life;
- SF-12 health survey;
Objective. To create an efficient imputation algorithm for imputing the SF-12 physical component summary (PCS) and mental component summary (MCS) scores when patients have one to eleven SF-12 items missing.
Study Setting. Primary data collection was performed between 1996 and 1998.
Study Design. Multi-pattern regression was conducted to impute the scores using only available SF-12 items (simple model), and then supplemented by demographics, smoking status and comorbidity (enhanced model) to increase the accuracy. A cut point of missing SF-12 items was determined for using the simple or the enhanced model. The algorithm was validated through simulation.
Data Collection. Thirty-thousand-three-hundred and eight patients from 63 physician groups were surveyed for a quality of care study in 1996, which collected the SF-12 and other information. The patients were classified as “chronic” patients if they reported that they had diabetes, heart disease, asthma/chronic obstructive pulmonary disease, or low back pain. A follow-up survey was conducted in 1998.
Principal Findings. Thirty-one percent of the patients missed at least one SF-12 item. Means of variance of prediction and standard errors of the mean imputed scores increased with the number of missing SF-12 items. Correlations between the observed and the imputed scores derived from the enhanced models were consistently higher than those derived from the simple model and the increments were significant for patients with ≥6 missing SF-12 items (p<.03).
Conclusion. Missing SF-12 items are prevalent and lead to reduced analytical power. Regression-based multi-pattern imputation using the available SF-12 items is efficient and can produce good estimates of the scores. The enhancement from the additional patient information can significantly improve the accuracy of the imputed scores for patients with ≥6 items missing, leading to estimated scores that are as accurate as that of patients with <6 missing items.