Missing values

From Wikipedia, the free encyclopedia

In statistics, missing values are a common occurrence. Several statistical methods have been developed to deal with this problem. Missing values mean that no data value is stored for the variable in the current observation. Modern statistical packages have made dealing with missing values much easier. Often these use a maximum likelihood estimation for summary statistics, confidence intervals, etc.

[edit] Techniques of dealing with missing values

• Imputation (statistics)
• EM imputation, i.e.expectation-maximization imputation: see Expectation-maximization algorithm)
• full information maximum likelihood estimation
• indicator variable
• Listwise deletion/casewise deletion
• Pairwise deletion
• Mean substitution
• Mplus
• MCAR (missing completely at random)
• Censoring (statistics)

[edit] Further reading

• Little, R. J. A. & Rubin, D. B.. Statistical Analysis with Missing Data. John Wiley and Sons, New York, 2002.
• Acock, A. C, Working With Missing Values, JOURNAL OF MARRIAGE AND FAMILY, 2005, VOL 67; NUMBER 4, pages 1012-1028
• Jan Van den Broeck, Solveig Argeseanu Cunningham, Roger Eeckels, and Kobus Herbst, Data Cleaning: Detecting, Diagnosing, and Editing Data Abnormalities, PLoS Med. 2005 October; 2(10): e267. [1]

[edit] References

• Missing values
• Missing values
• Missing values
• Missing Values, Identifying Missing Values, and Dealing with Missing Values