See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/269178432
Kim JK and Shao J, Statistical methods for handling incomplete data
Article in Statistical Methods in Medical Research · December 2014
DOI: 10.1177/0962280214562507 · Source: PubMed
CITATIONS READS
0 596
1 author:
Claire Keeble
University of Leeds
55 PUBLICATIONS 976 CITATIONS
SEE PROFILE
All content following this page was uploaded by Claire Keeble on 07 January 2016.
The user has requested enhancement of the downloaded file.
Statistical Methods in Medical Research
http://smm.sagepub.com/
Kim JK and Shao J, Statistical methods for handling incomplete data
Claire Keeble
Stat Methods Med Res published online 2 December 2014
DOI: 10.1177/0962280214562507
The online version of this article can be found at:
http://smm.sagepub.com/content/early/2014/12/01/0962280214562507
Published by:
http://www.sagepublications.com
Additional services and information for Statistical Methods in Medical Research can be found at:
Email Alerts: http://smm.sagepub.com/cgi/alerts
Subscriptions: http://smm.sagepub.com/subscriptions
Reprints: http://www.sagepub.com/journalsReprints.nav
Permissions: http://www.sagepub.com/journalsPermissions.nav
>> OnlineFirst Version of Record - Dec 2, 2014
What is This?
Downloaded from smm.sagepub.com at University of Leeds on December 3, 2014
XML Template (2014) [26.11.2014–9:38am] [1–1]
//blrnas3.glyph.com/cenpro/ApplicationFiles/Journals/SAGE/3B2/SMMJ/Vol00000/140127/APPFile/SG-SMMJ140127.3d (SMM) [PREPRINTER
stage]
Statistical Methods in Medical Research
0(0) 1
Book Review ! The Author(s) 2014
Reprints and permissions:
sagepub.co.uk/journalsPermissions.nav
DOI: 10.1177/0962280214562507
smm.sagepub.com
Kim JK and Shao J, Statistical methods for handling incomplete data. CRC Press: Boca Raton, 2014; 223 pp. £57.99
Hardback, ISBN 978-1439849637
Claire Keeble, Division of Epidemiology & Biostatistics, University of Leeds, UK
Missing or incomplete data occur in a wide range of subject areas, often through an absence of data
entry or when participation or consent is required. Approaches for dealing with this lack of data
have been developed in various fields under different names, such as solutions for non-participation
or survey non-response. Recent developments in theoretical discoveries and advances in software
have resulted in an uncatalogued collection of statistical approaches.
This book aims to summarise the current methods for analysing incomplete data, incorporating
these recent developments. It focuses on the frequentist framework, through explanations and
examples, to guide those with background knowledge of statistical theory and linear modelling
through missing data techniques.
The book assumes a familiarity with the notion of missing data, so provides a concise rather than
a detailed introduction to the subject matter. The next eight self-contained chapters have a logical
ordering, covering various important aspects associated with incomplete data, first more traditional,
then more recent, with the latter providing the main substance of the book. A rigorous investigation
of theories and computational approaches is followed by recent work in the field. The book can be
read from cover to cover, giving a firm grounding on which a new reader can later build, or for those
more conversant and seeking to update their knowledge, just relevant chapters can be read. Each
chapter begins with an informative introduction, explaining any new concepts or notation.
Definitions, lemmas, examples and exercises partition the sections into workable pieces while
using the concise format found in many mathematical books. The writing style is clear and
succinct, helpfully guiding the reader through the different analysis techniques. Theories are
explained using both text and notation, with emphasis on the latter, allowing for different
learning styles. A substantial bibliography directs further reading and investigation. Pages and
formulae are well displayed, but increased page margins and a table of notation for reference
would be welcomed.
The authors’ aims of writing a book which guides readers through the statistical methods for
handling incomplete data are achieved. The authors appropriately describe the book as written for
those in their second year of a PhD course in statistics, since a solid background in mathematics is
essential. Provided the reader has this prerequisite, this book is a key educational tool, for a
graduate course or for the self-taught student and especially for a newcomer to incomplete data.
Libraries may be interested due to the thoroughness of the book; it is certainly a comprehensive
summary of the solutions for missing data, from those well-established to those recently developed,
for readers who appreciate mathematically intensive learning.
Downloaded from smm.sagepub.com at University of Leeds on December 3, 2014
View publication stats
