Regression imputation
This approach attempts to fill in the missing data in a column using regression to predict likely values of the missing elements using other columns as predictors. For example, using regression imputation on the drat column would employ a linear regression predicting drat from all the other columns in miss_mtcars. The process would be repeated for all columns containing missing data, until the dataset is complete.
This procedure is intuitively appealing, because it integrates knowledge of the other variables and patterns of the dataset. This creates a set of more informed imputations. As a result, this produces unbiased estimates of the mean and regression coefficients under MCAR and MAR (so long as the relevant variables ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access