Multivariate Imputation By Chained Equations (MICE) algorithm for missing values | Machine Learning

In this tutorial, we'll look at Multivariate Imputation By Chained Equations (MICE) algorithm, a technique by which we can effortlessly impute missing values in a dataset by looking at data from other columns and trying to estimate the best prediction for each missing value.

We'll look at the different types of missing data, viz. Missing Completely at Random (MCAR), Missing at Random (MAR) and Missing Not at Random (MNAR).

Machine Learning models can't inherently work with missing data, and hence it becomes imperative to learn how to properly decide between different kinds of imputation techniques to achieve the best possible model for our use case.

#mice #algorithm #python

Table of contents:

0:00 Intro
0:30 MCAR/ MAR/ MNAR
3:02 Problem statement
4:30 Univariate vs Multivariate imputation techniques
7:21 (finally) The MICE algorithm

I've uploaded all the relevant code and datasets used here (and all other tutorials for that matter) on my github page which is accessible here:

Link:

https://github.com/rachittoshniwal/machineLearning

Some useful resources that might be helpful for further reading:

https://cran.r-project.org/web/packages/mice/mice.pdf

https://stefvanbuuren.name/fimd/sec-MCAR.html

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3074241/

https://towardsdatascience.com/all-about-missing-data-handling-b94b8b5d2184

https://towardsdatascience.com/how-to-handle-missing-data-8646b18db0d4

https://towardsdatascience.com/uncovering-missing-not-at-random-data-8d2cd3eda31a

If you like my content, please do not forget to upvote this video and subscribe to my channel.

If you have any qualms regarding any of the content here, please feel free to comment below and I'll be happy to assist you in whatever capacity possible.

Thank you!

Видео Multivariate Imputation By Chained Equations (MICE) algorithm for missing values | Machine Learning канала Rachit Toshniwal