III. MISSING DATA: WHAT TO DO WITH OR WITHOUT THEM

III. MISSING DATA: WHAT TO DO WITH OR WITHOUT THEM Most statistical techniques presented in standard courses on statistical methods in undergraduate and graduate social science programs presume the presence of complete data. In class after class, research scenarios are presented that can be analyzed using t ‐tests of mean differences from independent or dependent samples, z ‐tests or t ‐tests of correlations, analysis of variance using one‐way or multi‐way designs, or other techniques. Because these scenarios are usually idealized examples, the issue of missing data is rarely, if ever, confronted. However, in conducting developmental research, particularly longitudinal investigations, the presence of missing data is the rule, not the exception. Practicing scientists design research studies fully committed to obtaining complete responses by each participant to all questions at each time of measurement, knowing that the likelihood of accomplishing this goal is essentially zero. Because missing data are expected in longitudinal studies, questions naturally arise regarding how to analyze data to arrive at the least biased representation of developmental trends. Research on modern approaches to dealing with missing data began three decades ago, spurred by a framework developed by Rubin (1976) . Then, about two decades ago, several important papers and books were published, including Little and Rubin (1987) http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Monographs of the Society for Research in Child Development Wiley

III. MISSING DATA: WHAT TO DO WITH OR WITHOUT THEM

Loading next page...
 
/lp/wiley/iii-missing-data-what-to-do-with-or-without-them-dwOSktjk5j
Publisher
Wiley
Copyright
Journal Compilation © 2006 The Society for Research in Child Development, Inc.
ISSN
0037-976X
eISSN
1540-5834
DOI
10.1111/j.1540-5834.2006.00404.x
Publisher site
See Article on Publisher Site

Abstract

Most statistical techniques presented in standard courses on statistical methods in undergraduate and graduate social science programs presume the presence of complete data. In class after class, research scenarios are presented that can be analyzed using t ‐tests of mean differences from independent or dependent samples, z ‐tests or t ‐tests of correlations, analysis of variance using one‐way or multi‐way designs, or other techniques. Because these scenarios are usually idealized examples, the issue of missing data is rarely, if ever, confronted. However, in conducting developmental research, particularly longitudinal investigations, the presence of missing data is the rule, not the exception. Practicing scientists design research studies fully committed to obtaining complete responses by each participant to all questions at each time of measurement, knowing that the likelihood of accomplishing this goal is essentially zero. Because missing data are expected in longitudinal studies, questions naturally arise regarding how to analyze data to arrive at the least biased representation of developmental trends. Research on modern approaches to dealing with missing data began three decades ago, spurred by a framework developed by Rubin (1976) . Then, about two decades ago, several important papers and books were published, including Little and Rubin (1987)

Journal

Monographs of the Society for Research in Child DevelopmentWiley

Published: Dec 1, 2006

References

  • Estimating individual developmental functions
    Burchinal, Burchinal; Appelbaum, Appelbaum

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create folders to
organize your research

Export folders, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off