A Comparison of Imputation Methods for Categorical Data
SSRN, ISSN: 1556-5068
2023
- 319Usage
Metric Options: Counts1 Year3 YearSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
Objectives Missing data is commonplace in clinical databases, which are being increasingly used for research. These databases contain mainly categorical variables. The questionable aspect is the best imputation method for categorical data. Materials and methods We utilized data extracted from paper-based maternal health records from Kawempe National Referral Hospital, Uganda. We compared the following imputation methods for categorical data in an empirical analysis: Mode, K-Nearest Neighbors (KNN), Random Forest (RF), Sequential Hot-Deck (SHD), and Multiple Imputation by Chained Equations (MICE). In the first approach to compare the imputation methods, random missing data was injected at varying proportions in the complete dataset (5%-50%). The missing values were imputed by the five imputation methods which were then compared by precision score. In the second approach, the complete dataset was split into training and testing dataset. Random missing data (5%-50%) was then injected into only the training set. Imputation methods were then compared by predictive accuracy of the outcome variable in four classifiers on a single testing set. The consistency of performance of imputation methods was assessed by Kendall’s W test. Results KNN imputation had the highest precision score at levels of missing data (Kendall’s W = 0.853, p = 0.0000842). However, the methods performed differently at all proportions of missing data in the four classifiers. Conclusions KNN imputation is the best method in predicting missing values in categorical variables. There is no universal best imputation method that yields the highest predictive accuracy at all proportions of missing data.
Bibliographic Details
Elsevier BV
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know