Application of Multiple Imputation Method for Missing Data Estimation

Year 2012, Volume: 25 Issue: 4, 869 - 873, 12.10.2012

Gazel Ser

Abstract

The existence of missing observation in the data collected particularly in different fields of study cause researchers to make incorrect decisions at analysis stage and in generalizations of the results. Problems and solutions which are possible to be encountered at the estimation stage of missing observations were emphasized in this study. In estimating the missing observations, missing observations were assumed to be missing at random  and Markov Chain Monte Carlo technique and multiple imputation method were applied.  Consequently, results of the multiple imputation performed after data set was logarithmically transformed produced the closest result to the original data.   

Keywords

Multiple imputation; Missing data; Milk yield

References

• Sartori, N., Salvan, A., Thomaseth, K., “Multiple imputation of missing values in a cancer mortality analysis Computational Statistics & Data Analysis, 49, 937- 953 (2005). exposure dose”, [2] Bal, C., Özdamar, K., “Solving The Missing Value
• Problem By Use Of Simulated Data Sets”,
• Osmangazi Üniversitesi Tıp Fakültesi Dergisi, 26(2):67-76 (2004).
• Hedeker, D., Rose, J.S., “The natural history of smoking: A pattern-mixture
• random-effects regression model”, Multivariate Applications in Substance Use Research, 79-112 (2000).
• Little, R.J.A., Rubin, D.R., “Statistical Analysis with Missing Data”, John Wiley&Sons, New York (2002).
• Ibrahim, J.G., Molenberghs, G., “Missing data methods in longitudinal studies: a review”, Test, 18(1): 1-43 (2009).
• Allison, P.D., “Multiple imputation for missing data: a cautionary tale”, Sociological Methods and Research, 28,301–309 (2000).
• Yozgatlıgil, C., Aslan, S., İyigün, C., Batmaz, İ., Türkeş, M., Tatlı, H., “Comparison of methods to complete the missing data in time series: Turkey on the application of climate data”, Yöneylem Araştırması ve Endüstri Mühendisliği 30. Ulusal Kongresi, 127- 128, 30 June - 2 July, Istanbul (2010).
• Yang, X., Shoptaw, S., “Assessing missing data assumptions in longitudinal studies: an example using a smoking cessation trial”, Drug and Alcohol Dependence, 77, 213-225 (2005).
• Baraldi, A.N., Enders, C.K., “An introduction to modern missing data analyses”, Journal of School Psychology, 48, 5-37 (2010).
• Yang, Y., Kang, J., “Joint analysis of mixed Poisson and continuous longitudinal data with nonignorable missing value”, Computational Statistics and Data Analysis, 54, 193-207 (2010).
• Fitzmaurice, G.M., Laird, N.M., Ware, J.H., “Applied Longitudinal Analysis”, John Wiley & Sons, New York (2004).
• Scheffer, J., “Dealing with missing data”, Res. Lett. Inf. Math. Sci., 3, 153-160 (2002).
• Schaffer, J.L., Olsen, M.K., “Multiple imputation for multivariate missing-data problems: a data analyst’s perspective”, Multivariate Behavioral Research, 33(4): 545-571 (1998).
• SPSS, “IBM SPSS missing values 19” SPSS, Inc., IBM Company (2010).
• Ser, G., “Evaluation of the Multiple Imputation method regarding the quantitative characters with missing observations and covariance structures”, Journal Advances, 10(24): 3269-3273 (2011). and Veterinar y