May 1, 2024
Updated June 6, 2025
18 minute read
Missing Data: Understanding and Addressing the Gaps in Your Information
Missing data is a common phenomenon encountered in nearly every field that relies on data for insights and decision-making. At a high level, missing data refers to the absence of values for one or more variables in a dataset. Imagine a survey where some respondents skip certain questions, or a patient record where a particular lab test result was not recorded; these are everyday examples of missing data. The presence of these gaps can significantly complicate data analysis, leading to biased results, reduced statistical power, and ultimately, flawed conclusions if not handled appropriately.
r1zora|
Find a path to becoming a Missing Data. Learn more at:
OpenCourser.com/topic/r1zora/missing
Reading list
We've selected 25 books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
Missing Data.
Provides a comprehensive overview of multiple imputation for nonresponse in surveys, including methods for implementing multiple imputation and assessing the impact of missing data on survey results. It is written by two leading experts in the field and valuable resource for anyone working with missing data in surveys.
Provides a comprehensive overview of statistical methods for missing data, including multiple imputation, maximum likelihood estimation, and Bayesian methods. It valuable resource for anyone working with missing data.
Considered a foundational text in the field, this book provides a comprehensive theoretical framework for understanding and handling missing data. It covers various methods, including maximum likelihood and multiple imputation, and is suitable for those seeking a deep understanding of the statistical principles involved. is often used as a textbook in graduate-level statistics programs and valuable reference for researchers.
Offers a practical and accessible approach to missing data analysis, focusing on applying methods in real-world research. It covers a range of techniques, including multiple imputation and maximum likelihood, with clear explanations and examples. This book is highly recommended for applied researchers and graduate students who need to implement missing data procedures in their work. The second edition includes recent developments and expanded coverage of Bayesian estimation and other timely topics.
Focusing specifically on multiple imputation, this book provides a detailed guide to this powerful technique for handling missing data. The author key developer of the MICE package in R, and the book includes practical guidance and examples using this software. is particularly useful for researchers and practitioners who plan to use multiple imputation in their data analysis. The second edition incorporates recent developments in the field.
Covers up-to-date statistical theories and computational methods for analyzing incomplete data. It delves into topics such as likelihood-based approaches, imputation techniques (including fractional imputation), propensity score methods, and methods for nonignorable missing data. It is aimed at researchers and graduate students in statistics and includes real and simulated data examples.
Specifically addresses missing data issues within the context of clinical trials. It covers the challenges and appropriate methods for handling missing data in this specific domain, which aligns with the healthcare data analysis aspect of the provided course names. It's a valuable resource for researchers and statisticians working in clinical research.
Offers practical methods for analyzing missing data, emphasizing the reasoning behind the techniques. It covers both frequentist and Bayesian perspectives and provides guidance on pragmatic issues such as selecting the number of imputations. This book valuable resource for applied statisticians and researchers looking for practical advice and a bridge between design-based and model-based perspectives.
Provides a detailed account of multiple imputation and its applications. While one review noted potential issues with clarity in an earlier edition, the topic and authors are highly relevant to contemporary missing data practice. It is suitable for researchers and practitioners focusing on applying multiple imputation.
Delves into the theoretical aspects of handling missing data using semiparametric models. It more advanced text, suitable for those with a strong statistical background interested in the theoretical underpinnings of missing data methods. It covers topics like generalized estimating equations and Cox's proportional hazards model in the context of missing data.
Presents a unified, Bayesian approach to the analysis of incomplete multivariate data, covering continuous, categorical, and mixed datasets. It focuses on making missing-data tools accessible and bridges the gap between theory and practice. While published in 1997, it remains a valuable resource for understanding likelihood-based and Bayesian approaches.
This online resource provides a practical introduction to exploring, considering, and dealing with missing values, with a focus on using R. It covers finding, exploring, cleaning, investigating the reasons for missingness, and imputing missing values. It is suitable for those with basic R experience and offers practical guides and exercises.
While not solely focused on missing data, this comprehensive book on Bayesian data analysis includes significant discussion on handling missing data within a Bayesian framework. Given the mention of Bayesian statistics in the course names, this book would be a valuable resource for understanding how Bayesian methods can be applied to missing data problems. It widely recognized text in Bayesian statistics.
Focuses on the analysis of longitudinal data, which often involves missing values. While not exclusively about missing data, it provides essential background and methods for analyzing data collected over time, including techniques for handling incomplete longitudinal data. It is highly relevant for those working with repeated measurements in healthcare or social sciences.
For more information about how these books relate to this course, visit:
OpenCourser.com/topic/r1zora/missing
Save
