Volume 1, Issue 1 (10-2011)
MEJDS (2011) 1: 47 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Kazemi E, Karimlo M, Rahgozar M. A review of missing data. MEJDS 2011; 1 (1) :47-52
URL: http://jdisabilstud.org/article-1-317-en.html
URL: http://jdisabilstud.org/article-1-317-en.html
Abstract: (13557 Views)
In this paper, we are presenting the basic concepts of missing data in a very simple but practical approach.
Missing data are ubiquitous throughout the social, behavioral, and medical sciences. In Statistics, missing data occur when no data value is stored for the variable in the current observation. Missing data reduce the representativeness of the sample and can therefore distort inferences about the population.
Missing data are a common occurrence and can have a significant effect on the conclusions that can be drawn from the data. All the methods of parameters estimation are based on the completion of data set assumption and only in this case the result will be a non- biased one, and with the increase of missing proportion, the rate of biased results increase too.
For decades, researchers have relied on a variety of old techniques that attempt to “fix” the data by discarding incomplete cases or by filling in the missing values. Unfortunately, most of these techniques require a relatively strict assumption about the cause of missing data and are prone to substantial bias.
Missing data are ubiquitous throughout the social, behavioral, and medical sciences. In Statistics, missing data occur when no data value is stored for the variable in the current observation. Missing data reduce the representativeness of the sample and can therefore distort inferences about the population.
Missing data are a common occurrence and can have a significant effect on the conclusions that can be drawn from the data. All the methods of parameters estimation are based on the completion of data set assumption and only in this case the result will be a non- biased one, and with the increase of missing proportion, the rate of biased results increase too.
For decades, researchers have relied on a variety of old techniques that attempt to “fix” the data by discarding incomplete cases or by filling in the missing values. Unfortunately, most of these techniques require a relatively strict assumption about the cause of missing data and are prone to substantial bias.
Keywords: Missing Data, Missing Completely at Random, Missing at Random, Non Ignorable, Missing by Natural Design
Type of Study: Original Research Article |
Subject:
Rehabilitation
References
1. Satten GA, Carroll RJ. Conditional and Unconditional Categorical Regression Models with Missing Covariates. Biometrics 2000;56:384-388. [10.1111/j.0006-341X.2000.00384.x]
2. Fleiss J.L, Levin B, Paik M.C. Statistical Methods for Rates and Proportions. 3rd Edition. New York:John Wiley & Sons 2002. ISBN 0-471-52629-0.
3. Enders CK. Applied Missing Data Analysis. New York and London: Guilford Press 2010. ISBN 978-1-60623-639-0.
4. Hosmer DW, Lemeshow S. Applied Logistic Regression. 2nd Edition. New York: John Wiley & Sons; 2000. ISBN: 0-471-72214-6. [10.1002/0471722146]
5. Chen HY, Little R. A. test of missing completely at random for generalised estimating equations with missing data. Biometrika 1999;86:1-13. [10.1093/biomet/86.1.1]
6. Diggle P.J. Testing for random dropouts in repeated measurement data. Biometrics 1989;45:1255-1258. [10.2307/2531777]
7. Dixon W.J. BMDP statistical software. Los Angeles: University of California Press 1988.
8. Kim K. H, Bentler P. M. Tests of homogeneity of means and covariance matrices for multivariate incomplete data. Psychometrika 2002:67:609-624. [10.1007/BF02295134]
9. Little R. J. A. A test of missing completely at random for multivariate data with missing values. Journal of the American Statistical Association 1988;83:1198-1202. [10.1080/01621459.1988.10478722]
10. Muthén B, Kaplan D, Hollis M. On structural equation modeling with data that are not missing completely at random. Psychometrika 1987;52:431-462. doi: [10.1007/BF02294365]
11. Park T, Lee S-Y. A test of missing completely at random for longitudinal data with missing observations.Statistics in Medicine 1997;16:1859-1871.
https://doi.org/10.1002/(SICI)1097-0258(19970830)16:16<1859::AID-SIM593>3.0.CO;2-3 [DOI:10.1002/(SICI)1097-0258(19970830)16:163.0.CO;2-3]
12. Thoemmes F, Enders C. K. A structural equation model for testing whether data are missing completely at random. Paper presented at the annual meeting of the American Educational Research Association, Chicago, IL 2007 April.
13. SPSS Missing Value Analysis™ 17. SPSS Inc 2007. Printed in the United States of America. http://www.spss.com
14. Longford NT. Missing data and small area estimation. Springer 2005 ISBN-13: 978-185233-760-5.
15. Karimlou M.Jandaghi G.R. Mohammad K.Wolfe R.Azam K. A Comparison of Parameter Estimates in Standard Logistic Regressin Using WinBUGS MCMC and MLE Methods in R for Different Sample Size.Far East J.Theo.stat 2006.
16. Ibrahim J G, Chen MH, Lipsitz SR. Bayesian methods for generalized linear models with covariates missing at random. Canadian Journal of Statistics 2008 DEC 10;2307/3315865.
17. Marwala T. Computational Intelligence for Missing Data Imputation, Estimation, and Management: Knowledge Optimization Techniques. South Africa: University of Witwatersrand IGI Global; 2009 ISBN 978-1-60566-336-4. [DOI:10.4018/978-1-60566-336-4]
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
