ERIC Documents Database Citations & Abstracts for the Methodology of Meta Analysis
Instructions for ERIC Documents Access
Search Strategy:
Meta Analysis [ERIC Descriptor, with heavily weighted status]
AND
Research Methodology OR Evaluation Methods OR Methods Research OR Evaluation Research
OR Synthesis [ERIC Descriptors]
AND
Statistical Significance OR Effect Size OR Analysis of Variance OR Generalizability Theory OR Statistical Analysis [ERIC Descriptors]
-----
OR
Gene V Glass [author]
ED403270 TM025465
A Meta-Meta-Analysis: Methodological Aspects of Meta-Analyses in
Educational Achievement.
Sipe, Theresa Ann; Curlette, William L.
Apr 1996
44p.; Paper presented at the Annual Meeting of the American
Educational Research Association (New York, NY, April 8-12, 1996).
Document Type: REVIEW LITERATURE (070); EVALUATIVE REPORT (142);
CONFERENCE PAPER (150)
Selected methodological characteristics of meta-analyses related to
educational achievement are reviewed in an exploration of the
practice of meta-analysis and the characteristics of meta-analyses
related to educational achievement, as well as possible relationships
among background, methodological and substantive characteristics, and
effect sizes. A literature search identified 1,197 documents, of
which 694 were retrieved as pertinent. Using only meta-analyses
published after 1984, 103 published meata-analyses were selected as
having met study criteria. The most frequent type of meta-analysis
was that of treatment effectiveness. Hypothesis and theory testing
did not appear as frequently as descriptive research. Many primary
research articles did not include sample size, precluding the
computation of effect size. Many details of the search procedures in
meta-analyses were not included, and fewer than 40% of the authors
reported some kind of homogeneity of effect size testing. Overall,
results suggest that researchers are not exploiting the full
capabilities of meta-analytic techniques. Appendix A lists meta-
analyses included in the study, and Appendix B lists those
specifically excluded. (Contains 6 tables, 10 figures, and 38
references.) (SLD)
Descriptors: *Academic Achievement; *Effect Size; Elementary
Secondary Education; Higher Education; Hypothesis Testing; Literature
Reviews; *Meta Analysis; *Outcomes of Treatment; *Research
Methodology; Sample Size
Identifiers: *Descriptive Research
EJ520936 TM519322
The Impact of Data-Analysis Methods on Cumulative Research
Knowledge: Statistical Significance Testing, Confidence Intervals,
and Meta-Analysis.
Schmidt, Frank; Hunter, John E.
Evaluation and the Health Professions, v18 n4 p408-27 Dec
1995
Special issue titled "The Meta-Analytic Revolution in Health
Research: Part II."
ISSN: 0163-2787
Available From: UMI
Document Type: EVALUATIVE REPORT (142); JOURNAL ARTICLE (080)
It is argued that point estimates of effect sizes and confidence
intervals around these point estimates are more appropriate
statistics for individual studies than reliance on statistical
significance testing and that meta-analysis is appropriate for
analysis of data from multiple studies. (SLD)
Descriptors: *Effect Size; Estimation (Mathematics); *Knowledge
Level; *Meta Analysis; *Research Methodology; *Statistical
Significance; Test Use
Identifiers: *Confidence Intervals (Statistics)
EJ520935 TM519321
Interpreting and Evaluating Meta-Analysis.
Hall, Judith A.; Rosenthal, Robert
Evaluation and the Health Professions, v18 n4 p393-407 Dec
1995
Special issue titled "The Meta-Analytic Revolution in Health
Research: Part II."
ISSN: 0163-2787
Available From: UMI
Document Type: EVALUATIVE REPORT (142); JOURNAL ARTICLE (080)
Some guidelines are offered for interpreting and evaluating meta-
analytic reviews of research. The choice of unit of analysis, the
issue of fixed versus random effects, the meaning of heterogeneity,
the determination of appropriate contrasts, and the choice of
measures of central tendency are discussed. (SLD)
Descriptors: Comparative Analysis; Effect Size; *Evaluation Methods;
Health; *Medical Care Evaluation; *Meta Analysis; *Research
Methodology; *Synthesis
Identifiers: Heterogeneity of Variance
EJ520933 TM519319
Meta-analysis at 20: Retrospect and Prospect.
Kavale, Kenneth A.
Evaluation and the Health Professions, v18 n4 p349-69 Dec
1995
Special issue titled "The Meta-Analytic Revolution in Health
Research: Part II."
ISSN: 0163-2787
Available From: UMI
Document Type: EVALUATIVE REPORT (142); JOURNAL ARTICLE (080)
Explores the nature of meta-analysis by placing it in the context
of research synthesis. Methods of meta-analysis are described and
compared with other forms of research integration, and findings for
several meta-analyses are provided to show advantages of quantitative
review methods. (SLD)
Descriptors: *Comparative Analysis; Effect Size; Health; *Medical
Care Evaluation; *Meta Analysis; *Research Methodology; Statistical
Data; *Synthesis
EJ498134 RC510475
Going beyond the Literature Review with Meta-Analysis.
McNeil, Keith; Newman, Isadore
Mid-Western Educational Researcher, v8 n1 p23-26 Win
1995
ISSN: 1056-3997
Document Type: RESEARCH REPORT (143); JOURNAL ARTICLE (080)
Presents situations in which researchers can use the general linear
model to uncover reasons for discrepant effect-size results of meta-
analysis of similar studies. Situations include similarly labeled
treatments or participants differing in important ways, treatment
effectiveness varying by subject aptitude or situational variables,
research design strongly influencing outcome, and analysis of several
results from one study. (RAH)
Descriptors: *Effect Size; *Hypothesis Testing; *Meta Analysis;
*Research Methodology; *Research Problems; Statistical Analysis;
Synthesis
Identifiers: *General Linear Model
EJ490157 SP523457
Comparison of the Glass and Hunter-Schmidt Meta-Analytic
Techniques.
Hough, Susan L.; Hall, Bruce W.
Journal of Educational Research, v87 n5 p292-96 May-Jun
1994
ISSN: 0022-0671
Document Type: RESEARCH REPORT (143); JOURNAL ARTICLE (080)
Compares results of Hunter-Schmidt meta-analytic technique with
results of Glass meta-analytic technique on three meta-analytic data
sets chosen from the literature, hypothesizing that the Hunter-
Schmidt mean effect size would be significantly larger than the Glass
mean effect size because of correlation for measurement error.
Results confirmed the hypothesis, but the Glass formulas appear
adequate and are more easily calculated. (SM)
Descriptors: Comparative Analysis; Educational Research; *Effect
Size; *Error of Measurement; *Evaluation Methods; Higher Education;
*Meta Analysis
Identifiers: *Glass Analysis Method; *Hunter Schmidt Meta Analysis
EJ488861 TM518079
A Conservative Inverse Normal Test Procedure for Combining P-Values
in Integrative Research.
Saner, Hilary
Psychometrika, v59 n2 p253-67 Jun 1994
ISSN: 0033-3123
Document Type: RESEARCH REPORT (143); JOURNAL ARTICLE (080)
The use of p-values in combining results of studies often involves
studies that are potentially aberrant. This paper proposes a
combined test that permits trimming some of the extreme p-values.
The trimmed statistic is based on an inverse cumulative normal
transformation of the ordered p-values. (SLD)
Descriptors: *Effect Size; *Meta Analysis; *Research Methodology;
Sample Size; Simulation; Statistical Distributions; *Statistical
Significance; Statistical Studies; *Synthesis
Identifiers: *Integrative Processes; Inverse Normal Test; *P Values
ED372120 TM021963
Philosophical Inquiry into Meta-Analysis.
Grover, Burton L.
Oct 1993
14p.; Paper presented to the Northwest Philosophy of Education
Society (Vancouver, British Columbia, Canada, October 1993).
Document Type: POSITION PAPER (120); EVALUATIVE REPORT (142);
CONFERENCE PAPER (150)
A search of the ERIC database and a review of the literature
suggests that meta-analysis is ignored by philosophers, a situation
that is regrettable but remediable. Meta-analysis is a method by
which one attempts to integrate findings quantitatively from several
research studies related to a common general topic. Philosophers
should certainly pay attention to meta-analysis if their task is to
investigate knowledge claims and assess their significance. Three
areas in particular are fertile ground for philosophers. One is the
importance of the questions considered by meta-analysis. Another is
the matter of generalization to a population. A third area for
philosophers to consider is variation in criterion variables and
parsimony. Many have been excited about the potential of meta-
analysis to make sense of a mass of confusing contradictory studies
and to reach new conclusions where none seemed logically possible.
While results of some meta-analyses encourage this excitement,
disagreements among methodologists can be disconcerting. Better
technical expertise may resolve such problems, but it is also
possible that philosophical consideration will give more direction to
these efforts. (Contains 9 references.) (SLD)
Descriptors: *Effect Size; Hypothesis Testing; Integrated
Activities; Literature Reviews; *Meta Analysis; *Philosophy;
*Research Methodology; *Statistical Analysis
Identifiers: Criterion Variables; *Philosophers
ED358115 TM019881
Trends in Published Meta-Analyses.
Grover, Burton L.
Apr 1993
22p.; Paper presented at the Annual Meeting of the American
Educational Research Association (Atlanta, GA, April 12-16, 1993).
Document Type: REVIEW LITERATURE (070); PROJECT DESCRIPTION (141);
CONFERENCE PAPER (150)
Meta analytic procedures recommended by various authorities were
the subject of a literature review designed not to discuss the
relative merits of contrasting recommendations, but to find what is
actually in the literature. The sample reviewed included 89 articles
published between 1986 and 1992, from 2 journals and 2 information
databases. Meta analyses were coded for a number of variables. Most
reported the databases used to find the studies. The median number
of studies synthesized by the data analysis was 48. About three-
quarters of these reported collecting and aggregating mean
differences. Of the 66 that examined mean differences, 55 calculated
and reported these differences as standardized mean differences.
Fifteen studies reported effect size, eight used the standard normal
deviate, and eight used some other method. A large variety of
statistical methods was reported for the analysis of the relationship
of moderator variables with effect size. Forty-seven studies
reported an overall test of homogeneity of effect sizes. One
implication of the study for researchers is that, given the diversity
of approaches to meta analysis, a good part of the potential audience
may well prefer a meta analytic approach that differs from that
chosen by the researcher. Five tables present information on trends
in meta analysis. An appendix lists studies that appeared in the two
main journals reviewed. (SLD)
Descriptors: Comparative Analysis; Databases; *Effect Size;
Literature Reviews; *Meta Analysis; *Publications; *Research
Methodology; Scholarly Journals; Synthesis; *Trend Analysis
Identifiers: Mean (Statistics)
EJ484369 TM517924
Program Evaluation: A Pluralistic Enterprise.
Sechrest, Lee, Ed.
New Directions for Program Evaluation, n60 p1-101 Win
1993
ISSN: 0164-7989
Document Type: SERIAL (022); EVALUATIVE REPORT (142); JOURNAL
ARTICLE (080)
Two chapters of this issue consider critical multiplism as a
research strategy with links to meta analysis and generalizability
theory. The unifying perspective it can provide for quantitative and
qualitative evaluation is discussed. The third chapter explores meta
analysis as a way to improve causal inferences in nonexperimental
data. (SLD)
Descriptors: Causal Models; *Evaluation Methods; *Generalizability
Theory; Inferences; *Meta Analysis; *Program Evaluation; Qualitative
Research; *Research Methodology; Statistical Analysis
Identifiers: *Critical Multiplism; *Pluralistic Method
EJ458576 TM517006
Meta-Analysis: Literature Synthesis or Effect-Size Surface
Estimation?
Rubin, Donald B.
Journal of Educational Statistics, v17 n4 p363-74 Win
1992
Special issue with title "Meta-Analysis."
ISSN: 0362-9791
Document Type: JOURNAL ARTICLE (080); EVALUATIVE REPORT (142)
In contrast to the average effect sizes of the approach to
metanalysis that can be thought of as literature synthesis, an effect-
size surface is proposed as a function of scientifically relevant
factors, estimated by extrapolating a response surface of observed
effect sizes to a region of ideal studies. (SLD)
Descriptors: *Effect Size; Equations (Mathematics); *Estimation
(Mathematics); *Literature Reviews; *Mathematical Models; *Meta
Analysis; Research Methodology; *Synthesis
Identifiers: *Extrapolation
EJ458572 TM517002
Meta-Analysis.
Hedges, Larry V.
Journal of Educational Statistics, v17 n4 p279-96 Win
1992
Special issue with title "Meta-Analysis."
ISSN: 0362-9791
Document Type: JOURNAL ARTICLE (080); REVIEW LITERATURE (070);
EVALUATIVE REPORT (142)
The use of statistical methods to combine the results of
independent empirical research studies (metanalysis) has a long
history, with work mainly divided into tests of the statistical
significance of combined results and methods for combining estimates
across studies. Methods of metanalysis and their applications are
reviewed. (SLD)
Descriptors: Chi Square; *Educational Research; Effect Size;
*Estimation (Mathematics); Hypothesis Testing; *Mathematical Models;
*Meta Analysis; Research Methodology; *Statistical Data; Statistical
Significance
Identifiers: Empirical Research; Missing Data; Parametric Analysis;
Random Effects
EJ437344 CS742861
Meta-Analysis for Primary and Secondary Data Analysis: The Super-
Experiment Metaphor.
Jackson, Sally
Communication Monographs, v58 n4 p449-62 Dec 1991
ISSN: 0363-7751
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
Considers the relation between meta-analysis statistics and
analysis of variance statistics. Discusses advantages and
disadvantages as a primary data analysis tool. Argues that the two
approaches are partial paraphrases of one another. Advocates an
integrative approach that introduces the best of meta-analytic
thinking into primary analysis without abandoning the characteristic
features of analysis of variance. (SR)
Descriptors: *Analysis of Variance; Higher Education; *Meta
Analysis; *Research; *Research Methodology
ED339743 TM017675
A Comparison of the Glass Meta-Analytic Technique with the Hunter-
Schmidt Meta-Analytic Technique on Three Studies from the Education
Literature.
Hough, Susan L.; Hall, Bruce W.
Nov 1991
25p.; Paper presented at the Annual Meeting of the Florida
Educational Research Association (Clearwater, FL, November 13-16,
1991).
Document Type: RESEARCH REPORT (143); CONFERENCE PAPER (150)
The meta-analytic techniques of G. V. Glass (1976) and J. E. Hunter
and F. L. Schmidt (1977) were compared through their application to
three meta-analytic studies from education literature. The following
hypotheses were explored: (1) the overall mean effect size would be
larger in a Hunter-Schmidt meta-analysis (HSMA) than in a Glass meta-
analysis (GMA) due to correction for measurement error when compared
on the same set of experimental data; (2) the overall mean effect
size calculated using the pooled within-group standard deviation in
HSMA would not differ significantly from that in a GMA that uses the
control group standard deviation; (3) most of the variation between
study effect sizes would be due to sampling error according to
sampling error correction formulas from the HSMA method; and (4) no
moderator variables would be found because most of the variation
between study effect sizes is due to sampling error. A correlated t-
test was used to compare the overall mean effect sizes that were
calculated using GMA and HSMA. Pearson correlations and analyses of
variances were run on the study data. Three meta-analytic studies
were selected and statistical data from each of the individual
studies were collated. Results support Hypotheses 1 and 2, but
reject Hypotheses 3 and 4. It is argued that the HS correction
formulas are technically more accurate, but that the Glass method is
adequate in portraying effect size and more easily calculated. Three
tables present data from the meta-analyses. A 21-item list of
references is included. (SLD)
Descriptors: Comparative Analysis; Educational Research; *Effect
Size; *Error of Measurement; Hypothesis Testing; *Literature Reviews;
*Meta Analysis; *Research Methodology; Sampling
Identifiers: *Gass Analysis Method; *Hunter Schmidt Meta Analysis
EJ412548 TM515213
The Usefulness of the "Fail-Safe" Statistic in Meta-Analysis.
Carson, Kenneth P.; And Others
Educational and Psychological Measurement, v50 n2 p233-43 Sum
1990
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
The utility of the fail-safe "N" statistic was evaluated by
computing it for studies in three organizational research domains in
which discrepant conclusions were reached by initial and subsequent
meta-analyses. Calculation of the fail-safe "N" may have led to more
cautious interpretations. Implications for meta-analyses are
discussed. (SLD)
Descriptors: Comparative Analysis; Effect Size; Evaluation Methods;
Institutional Research; *Mathematical Models; *Meta Analysis;
Organizations (Groups); *Research Methodology
Identifiers: *Fail Safe Strategies
ED322218 TM015467
Conventional and Newer Statistical Methods in Meta-Analysis.
Kulik, James A.; Kulik, Chen-Lin C.
Apr 1990
6p.; Paper presented at the Annual Meeting of the American
Educational Research Association (Boston, MA, April 16-20, 1990).
Document Type: EVALUATIVE REPORT (142); CONFERENCE PAPER (150)
The assumptions and consequences of applying conventional and newer
statistical methods to meta-analytic data sets are reviewed. The
application of the two approaches to a meta-analytic data set
described by L. V. Hedges (1984) illustrates the differences. Hedges
analyzed six studies of the effects of open education on student
cooperation. The conventional way to test the hypothesis that
treatment fidelity significantly influenced results is through a t-
test for independent results. Hedges' more modern approach was to
use a chi-square analog of the analysis of variance (ANOVA), a method
that, in contrast to conventional statistics, found strong support
for the hypothesized effect. Conventional ANOVA and newer techniques
were also applied to a data set in which all studies were of the same
size, with each assumed to have experimental and control groups
containing 25 students each. The cell means and variances for
Hedges' meta-analytic data set were reconstructed to determine the
source of the difference in results between conventional and newer
tests. It is concluded that conventional ANOVA is appropriate for
use with meta-analytic data sets because conventional ANOVA uses the
correct error term for testing the significance of effects of group
factors. Newer meta-analytic methods are not recommended because of
their use of an inappropriate error term. (SLD)
Descriptors: *Analysis of Variance; Chi Square; Comparative
Analysis; *Data Analysis; Hypothesis Testing; *Meta Analysis;
Research Methodology; Statistical Significance
EJ397347 TM514667
Meta-Analysis in Education.
Kulik, James A.; Kulik, Chen-Lin C.
International Journal of Educational Research, v13 n3 p221-340
1989
Document Type: JOURNAL ARTICLE (080); EVALUATIVE REPORT (142);
REVIEW LITERATURE (070)
An overview of meta-analysis in education is provided. Methodology
is discussed and substantive findings from meta-analytic studies are
reviewed for six major areas of educational research: (1)
instructional systems; (2) instructional design; (3) curricular
innovation; (4) teacher education and evaluation; (5) class and
school organization; and (6) equity. (SLD)
Descriptors: Comparative Analysis; *Educational Research;
Evaluation Methods; Literature Reviews; *Meta Analysis; *Research
Methodology; Statistical Analysis
ED309952 SE050788
A Practical Guide to Modern Methods of Meta-Analysis.
Hedges, Larry V.; And Others
National Science Teachers Association, Washington, D.C.
1989
80p.
Sponsoring Agency: National Science Foundation, Washington, D.C.
Available From: National Science Teachers Association, 1742
Connecticut Avenue, NW, Washington, DC 20009 ($9.50; PB-52).
Document Type: INSTRUCTIONAL MATERIAL (051); BOOK (010); RESEARCH
REPORT (143)
Target Audience: Teachers; Researchers; Students; Practitioners
Methods for meta-analysis have evolved dramatically since Gene
Glass first proposed the term in 1976. Since that time statistical
and nonstatistical aspects of methodology for meta-analysis have been
developing at a steady pace. This guide is an attempt to provide a
practical introduction to rigorous procedures in the meta-analysis of
social science research. It approaches the use of modern statistical
methods in meta-analysis from the perspective of a potential user.
The treatment is limited to meta-analysis of studies of between-group
comparisons using the standardized mean difference as an index of
effect magnitude. This guide is organized according to a variant of
Cooper's stages of the research review process: (1) problem
formulation; (2) data collection and data evaluation, data analysis
and interpretation; and (3) presentation of results. Although each
stage is discussed, the greatest emphasis is placed on the stage of
data analysis and interpretation. Examples from a synthesis of
research on the effects of science curricula are used throughout for
illustration. Because this book is intended to be a practical guide,
the references are provided primarily to exemplify issues or
techniques rather than to provide theoretical discussions or
derivations. (CW)
Descriptors: *Comparative Analysis; Effect Size; Higher Education;
*Meta Analysis; *Research Methodology; *Science Education;
*Statistical Analysis; Statistical Data; Statistical Studies;
Synthesis
EJ388296 CG535451
Meta-Analysis: A Statistical Method for Integrating the Results of
Empirical Studies.
Blimling, Gregory S.
Journal of College Student Development, v29 n6 p543-49 Nov
1988
Document Type: JOURNAL ARTICLE (080); GENERAL REPORT (140)
Introduces statistical and procedural methods of meta-analysis, and
explains how to interpret the findings of meta-analytic studies
currently appearing throughout the social science literature.
Includes overview of meta-analysis and discussion of seven steps used
in conducting a meta-analysis. (Author/NB)
Descriptors: *Meta Analysis; *Research Methodology; *Social Science
Research; Statistical Analysis
EJ382869 SE543620
Disturbed by Meta-Analysis?
Wachter, Kenneth W.
Science, v241 n4872 p1407-08 Sep 16 1988
Document Type: JOURNAL ARTICLE (080); PROJECT DESCRIPTION (141)
Defines meta-analysis as statistical procedures for combining
results from previous separate studies. Discusses four charges
promoted by some skeptics as it relates to this statistical procedure.
States that many of the trends making a place for meta-analysis are
disturbing. (RT)
Descriptors: *Comparative Analysis; Effect Size; Higher Education;
*Meta Analysis; *Research Methodology; *Statistical Analysis;
*Statistical Data
ED300411 TM012402
Meta-analysis: A Bibliography of Conceptual Issues and Statistical
Methods.
Preiss, Raymond W.
1988
28p.
Document Type: BIBLIOGRAPHY (131)
Target Audience: Researchers; Teachers; Practitioners
The usefulness of meta-analysis in summarizing domains of primary
research has led to widespread use of the techniques. Often,
however, the researcher will have several options when cumulating
empirical studies and readers will have questions regarding judgment
calls made during a meta-analysis. In these cases, it is helpful to
consult the primary literature on meta-analytic theory and practice.
Reported here are over 160 articles and papers divided into two
bibliographies: (1) conceptual issues; and (2) statistical issues.
The bibliographies are discussed in terms of conducting a meta-
analysis and teaching research methods. Both bibliographies trace
the evolution of meta-analytic procedures in order to highlight the
intellectual dialog surrounding the practice. The bibliography as a
whole may prove valuable to teachers of graduate and undergraduate
research methods courses, and may be used as a teaching tool by
alerting students to the conceptual similarities of diverse
statistical methods. (Author/SLD)
Descriptors: *Educational Research; Higher Education; *Meta
Analysis; *Research Methodology; *Resource Materials; Statistical
Analysis
Identifiers: Conceptual Models
ED297015 TM011982
Meta-analysis: Historical Origins and Contemporary Practice.
Kulik, James A.; Kulik, Chen-Lin C.
Apr 1988
39p.; Paper presented at the Annual Meeting of the American
Educational Research Association (New Orleans, LA, April 5-9, 1988).
Document Type: RESEARCH REPORT (143); CONFERENCE PAPER (150);
REVIEW LITERATURE (070)
The early and recent history of meta-analysis is outlined. After
providing a definition of meta-analysis and listing its major
characteristics, developments in statistics and research are
described that influenced the formulation of modern meta-analytic
methods. Major meta-analytic methods currently in use are described.
Statistical and other research developments contributing to meta-
analysis include the introduction of combined tests, combined
treatment effects, use of percentages as outcome variables, and use
of correlations as outcomes. Meta-analytic approaches reviewed
include Glass' methodology, Hedges' modern statistical methods,
Hunter and Schmidt's validity generalization, and Rosenthal's methods.
Problems affecting meta-analysis include inflated sample sizes, non-
independent measures in statistical analyses, the failure to take
experimental design into account when estimating effect sizes and
sampling errors, and the development of inappropriate statistical
methods for testing the influence of study features on study outcomes.
Four tables and two graphs are included. (TJH)
Descriptors: Generalization; Literature Reviews; *Meta Analysis;
*Research Methodology; *Statistical Analysis
Identifiers: *Historical Background
ED319784 TM015018
Putting the "But" Back in Meta-Analysis: Issues Affecting the
Validity of Quantitative Reviews.
L'Hommedieu, Randi; And Others
Apr 1987
12p.; Paper presented at the Annual Meeting of the American
Educational Research Association (Washington, DC, April 20-24, 1987).
Document Type: EVALUATIVE REPORT (142); CONFERENCE PAPER (150)
Some of the frustrations inherent in trying to incorporate
qualifications of statistical results into meta-analysis are
reviewed, and some solutions are proposed to prevent the loss of
information in meta-analytic reports. The validity of a meta-
analysis depends on several factors, including the: thoroughness of
the literature search; selection of studies for inclusion;
appropriate coding and analysis of studies; and report format
selected. The solution proposed to the problem of methodological
quality is to include all selected studies and report an average
effect size for the aggregate. The report on the meta-analysis then
should be a qualitative, discursive argument rather than a simple
statistic. Proposals for putting the "but" back in meta-analysis
are: (1) assure that it is not a substitute for qualitative review;
(2) offer the reader information necessary to evaluate the validity
of decisions made at the individual level; and (3) assure that
qualifications of studies are not excluded from the analysis. A
thorough quantitative review should include: a discursive review of
each study; a report on how each effect size was calculated; the
location of the summary statistics upon which each effect size was
based; and a discussion of study limitations and the factors that
affect validity of effect size. Suggestions are also given for
appropriate reporting and avoiding publication bias. (SLD)
Descriptors: *Data Analysis; Literature Reviews; *Meta Analysis;
*Research Methodology; Research Problems; Research Reports;
*Statistical Analysis; *Validity
ED262095 TM850578
The Meta-Analytic Debate.
Bangert-Drowns, Robert L.
1985
12p.; Paper presented at the Annual Meeting of the American
Educational Research Association (69th, Chicago, IL, March 31-April
4, 1985).
Document Type: CONFERENCE PAPER (150); EVALUATIVE REPORT (142)
Target Audience: Researchers
Since meta-analysis was described in 1976 (Glass) as the
application of familiar experimental methods to the integration of
available research, at least five coherent approaches to meta-
analysis have appeared in common use. These approaches can be
divided into two broad groups. In the first group (including
procedures by Robert Rosenthal, Larry Hedges, and Frank Schmidt and
John Hunter), meta-analysis is used to approximate data-pooling.
This type of meta-analysis attempts to answer the same questions as
primary research, only larger samples are used by combining
information from many studies. The alternate view (shown in the
procedures of Gene Glass and James Kulik) is that meta-analysis is a
form of literature review. As a literature review, meta-analysis is
not meant to test a hypothesis but to summarize features and outcomes
of a body of research. The differences in approaches to meta-
analysis indicate that the procedure is still in a period of
invention and change. It is important that editors, consumers, and
critics of meta-analysis know about these differences so that they
can make more informed evaluations of meta-analytic findings.
(Author/PN)
Descriptors: Data; Effect Size; Error of Measurement; *Literature
Reviews; *Measurement Techniques; *Meta Analysis; Research Design;
*Research Methodology; Sampling
Identifiers: Glass (GV)
EJ309340 TM510208
Advances in Statistical Methods for Meta-Analysis.
Hedges, Larry V.
New Directions for Program Evaluation, n24 p25-42 Dec
1984
Theme issue with title "Issues in Data Synthesis." Research
supported by the Spencer Foundation.
Document Type: JOURNAL ARTICLE (080); POSITION PAPER (120);
RESEARCH REPORT (143)
The adequacy of traditional effect size measures for research
synthesis is challenged. Analogues to analysis of variance and
multiple regression analysis for effect sizes are presented. The
importance of tests for the consistency of effect sizes in
interpreting results, and problems in obtaining well-specified models
for meta-analysis are discussed. (BS)
Descriptors: Analysis of Variance; *Effect Size; Mathematical
Models; *Meta Analysis; Research Methodology; Research Problems;
*Statistical Analysis
EJ297528 TM508771
Effect Size Estimation in Meta-Analysis.
Holmes, C. Thomas
Journal of Experimental Education, v52 n2 p106-09 Win
1984
Document Type: RESEARCH REPORT (143)
Methods for estimating effect sizes when complete data are not
reported are presented. When not precise, these methods provide a
conservative estimate and, therefore, allow for the inclusion in a
meta-analysis of relevant studies whose data might otherwise be
discarded. (Author/PN)
Descriptors: *Effect Size; *Estimation (Mathematics); *Measurement
Techniques; *Meta Analysis; Research Methodology; *Research Problems;
Statistical Analysis
ED249266 TM840619
Power Differences among Tests of Combined Significance.
Becker, Betsy Jane
Apr 1984
21p.; Paper presented at the Annual Meeting of the American
Educational Research Association (68th, New Orleans, LA, April 23-27,
1984).
Document Type: CONFERENCE PAPER (150); RESEARCH REPORT (143)
Target Audience: Researchers
Power is an indicator of the ability of a statistical analysis to
detect a phenomenon that does in fact exist. The issue of power is
crucial for social science research because sample size, effects, and
relationships studied tend to be small and the power of a study
relates directly to the size of the effect of interest and the sample
size. Quantitative synthesis methods can provide ways to overcome
the problem of low power by combining the results of many studies.
In the study at hand, large-sample (approximate) normal distribution
theory for the non-null density of the individual p value is used to
obtain power functions for significance value summaries. Three p-
value summary methods are examined. Tippett's counting method,
Fisher's inverse chi-square summary, and the logit method. Results
for pairs of studies and for a set of five studies are reported.
They indicate that the choice of a "most-powerful" summary will
depend on the number of studies to be summarized, the sizes of the
effects in the populations studied, and the sizes of the samples
chosen from those populations. (BW)
Descriptors: Effect Size; Hypothesis Testing; *Meta Analysis;
Research Methodology; Sample Size; *Statistical Analysis;
*Statistical Significance
Identifiers: *Power (Statistics)
ED248618 EA017186
Uses and Misuses of Meta-Analysis.
Kulik, James A.
Apr 1984
10p.; Paper presented at the Annual Meeting of the American
Educational Research Association (New Orleans, LA, April 23-27,
1984).
Document Type: POSITION PAPER (120); CONFERENCE PAPER (150)
Target Audience: Researchers
Several developments in the use of the new method of meta-analysis
give cause for optimism. First, different meta-analysts are doing
work in the same areas, leading to increased confidence in meta-
analytic results. Second, meta-analysts are beginning to include raw
data in their reports, which helps readers pinpoint the exact studies
that lead to disagreements in conclusions. Third, reviewers are
comparing results from unrelated meta-analyses, which can lead to a
better understanding of the factors influencing the outcomes of
educational research. Finally, some of the worst abuses that have
taken place in meta-analysis appear to be in the past. (DCS)
Descriptors: *Comparative Analysis; *Meta Analysis; Research;
*Research Methodology; *Statistical Analysis; Statistical Data;
Synthesis
ED248262 TM840565
Developments in Meta-Analysis: A Review of Five Methods.
Bangert-Drowns, Robert L.
Michigan Univ., Ann Arbor. Center for Research on Learning and
Teaching. Jun 1984
69p.
Document Type: REVIEW LITERATURE (070)
Target Audience: Researchers
It is easy to observe that meta-analysis is quickly establishing
itself as useful tool of the social sciences. Perusal of
representative journals confirms that meta-analysis has been applied
in various ways to diverse literatures. It is imperative, therefore,
that reviewers, publishers, consumers, and critics of these reviews
be best informed about the method. It is especially important to
clarify exactly what the term "meta-analysis" refers to. This
article proposes a clarification in two ways. First, meta-analysis
is compared to and distinguished from other methods of research
integration that preceded it. Second, five different types of meta-
analytic method are distinguished by their purposes (for scientific
criticism or for literature review) or by their methods (using
combined probability, using tests of homogeneity, or using estimates
of population variation). (Author/BW)
Descriptors: Estimation (Mathematics); Literature Reviews; *Meta
Analysis; Probability; *Research Methodology; Research Utilization;
Scientific Research; Statistical Analysis
ED243937 TM840250
Diagnostic Techniques in Research Synthesis.
Ludlow, Larry H.
Apr 1984
23p.; Paper presented at the Annual Meeting of the American
Educational Research Association (68th, New Orleans, LA, April 23-27,
1984).
Document Type: CONFERENCE PAPER (150); RESEARCH REPORT (143)
Target Audience: Researchers
One purpose for combining research studies is to estimate a
population treatment effect. The internal validity of a model for
how effect size estimates should be computed and combined will hinge
upon the homogeneity of the effect size variation. Effect size
variation may be assessed in the form of a summary fit statistic, and
a direct consideration of the extent of individual effect variation
from the population estimate. This paper presents some diagnostic
techniques that facilitate the analysis of effect size variation.
Bivariate plots of effect size residuals can aid in detecting sources
of variation inconsistent with the model. Particularly, plotting the
standardized residual of each study against the homogeneity of the
sample if that study were removed is of interest for assessing the
extent of heterogeneity contributed by individual studies. It is
emphasized that the use of diagnostic techniques is useful for
revealing why a lack of fit occurred, and is not advocated for the ad
hoc purpose of finding a best-fitting subset of studies. (BW)
Descriptors: *Data Analysis; *Effect Size; Estimation (Mathematics);
Graphs; *Meta Analysis; Research Methodology
Identifiers: Data Interpretation; *Residuals (Statistics)
EJ292517 TM508577
Theory of Estimation and Testing of Effect Sizes: Use in Meta-
Analysis.
Kraemer, Helena Chmura
Journal of Educational Statistics, v8 n2 p93-101 Sum
1983
Available From: UMI
Document Type: RESEARCH REPORT (143)
Approximations to the distribution of a common form of effect size
are presented. Single sample tests, confidence interval formulation,
tests of homogeneity, and pooling procedures are based on these
approximations. Caveats are presented concerning statistical
procedures as applied to sample effect sizes commonly used in meta-
analysis. (Author)
Descriptors: *Effect Size; *Meta Analysis; *Research Methodology;
Statistical Data; *Statistical Distributions; *Statistical Studies;
Synthesis
ED225049 CG016397
Meta-Analytic Applications in Program Evaluation.
Wolf, Fredric M.
Aug 1982
27p.; Paper presented at the Annual Covention of the American
Psychological Association (90th, Washington, DC, August 23-27, 1982).
Document Type: RESEARCH REPORT (143); CONFERENCE PAPER (150)
In a variety of psychological and educational situations, it is
desirable to be able to make data-based evaluative summary statements
regarding the impact of a given program. Certain procedures
typically used in meta-analytic studies that review and integrate
results from individual studies, such as combined tests and measures
of effect size, are particularly well suited for program evaluation
in certain situations. This paper describes a number of such
situations, briefly reviews the literature on combined tests and
effect size, and provides several illustrative numerical examples of
their application in program evaluation. The three examples
illustrate the practical utility of using combined tests and measures
of effect size in program evaluations in situations where data are
available either cross-sectionally, or on successive occasions, or on
independent components of a larger program. The materials suggest
that measures of effect size are clearly valuable in providing
potential insight into the differential impact of a given program,
information that is more obscured when relying solely on statistical
tests. (Author/JAC)
Descriptors: Case Studies; *Data Analysis; Elementary Secondary
Education; *Evaluation Methods; Higher Education; Literature Reviews;
Pretests Posttests; *Program Effectiveness; *Program Evaluation;
Psychological Evaluation; *Research Methodology; Student Evaluation
Identifiers: *Meta Analysis
EJ269282 TM507246
Fitting Categorical Models to Effect Sizes from a Series of
Experiments.
Hedges, Larry V.
Journal of Educational Statistics, v7 n2 p119-37 Sum
1982
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
A statistical test is described which determines homogeneity of
effect size of an experiment series. An overall fit statistic is
partitioned into between-class fit statistic and within-class fit
statistic. These statistics permit assessment of differences between
effect sizes for different classes and homogeneity of effect size
within classes. (Author/DWH)
Descriptors: *Analysis of Variance; *Data Analysis; *Estimation
(Mathematics); Goodness of Fit; Mathematical Models; Research
Methodology; Statistical Significance; *Statistical Studies
Identifiers: *Effect Size; *Meta Analysis
ED228280 TM830156
Meta-Analysis, Meta-Evaluation and Secondary Analysis.
Martin, Paula H.
Oct 1982
37p.
Document Type: REVIEW LITERATURE (070)
Meta-analysis, meta-evaluation and secondary analysis are methods
of summarizing, examining, evaluating or re-analyzing data in
research and evaluation efforts. Meta-analysis involves the
summarization of research findings to come to some general
conclusions regarding effects or outcomes of a given
treatment/project/program. Glass's approach standardizes various
effect measures and controls for these in analyzing data. Meta-
evaluation is a method of evaluation research examining evaluation
methodologies, procedures, data analysis techniques, interpretation
of results, and the validity and reliability of conclusions.
Secondary analysis, as defined by Glass, is, "the re-analysis of data
for the purpose of answering the original research question with
better statistical techniques or answering new questions with old
data." A review of the literature related to these methodologies
gives examples of actual studies using these techniques. Specifics
on meta-evaluation in federally funded bilingual education programs
illustrate the methodology. As current budgetary cutbacks affect
state and federal programs, meta-analysis and meta-evaluation are
assuming important roles. (CM)
Descriptors: Bilingual Education Programs; *Educational Research;
Elementary Secondary Education; Federal Programs; *Program Evaluation;
*Research Methodology; *Statistical Analysis; *Statistical Data
Identifiers: Elementary Secondary Education Act Title VII; Glass (G
V); *Meta Analysis; *Meta Evaluation; Secondary Analysis
EJ266601 UD509289
Rigor in Data Synthesis: A Case Study of Reliability in Meta-
analysis.
Stock, William A.; And Others
Educational Researcher, v11 n6 p10-14 Jun-Jul 1982
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
Describes a study of reliability among coders of information for
meta-analysis (a quantitative procedure for synthesizing data in
primary research reports) of research on life satisfaction in
American adults. Identifies sources and areas of disagreement among
coders and discusses measures that can be used to enhance intercoder
consistency. (Author/MJL)
Descriptors: *Classification; Correlation; *Data Analysis;
Experimenter Characteristics; *Reliability; *Research Problems;
Researchers; *Synthesis; Validity
Identifiers: Coding; *Meta Analysis
ED227133 TM830125
Statistical Methodology in Meta-Analysis.
Hedges, Larry V.
ERIC Clearinghouse on Tests, Measurement, and Evaluation,
Princeton, N.J. Dec 1982
79p.
Sponsoring Agency: National Inst. of Education (ED), Washington,
DC.
Available From: ERIC/TM, Educational Testing Service, Princeton, NJ
08541 ($7.00).
Document Type: ERIC PRODUCT (071); NON-CLASSROOM MATERIAL (055)
Meta-analysis has become an important supplement to traditional
methods of research reviewing, although many problems must be
addressed by the reviewer who carries out a meta-analysis. These
problems include identifying and obtaining appropriate studies,
extracting estimates of effect size from the studies, coding or
classifying studies, analyzing the data, and reporting the results of
the data analysis. Earlier work by Glass, McGaw, and Smith describes
methods for dealing with these problems: and has generated a great
interest in the development of systematic statistical theory for meta-
analysis. This monograph supplements the existing literature on meta-
analysis by providing a unified treatment of rigorous statistical
methods for meta-analysis. These methods provide a mechanism for
responding to criticisms of meta-analysis, such as that meta-analysis
may lead to oversimplified conclusions or be influenced by design
flaws in the original research studies. Contents include: indices of
effect size, statistical analysis of effect size data, assumptions
and the statistical model, estimations of effect size, an analogue to
the analysis of variance for effect sizes, the effects of measurement
error on effect size, statistical analysis when correlations or
proportions are the index of effect magnitude, and statistical
analysis for correlations as effect magnitude. (Author/PN)
Descriptors: Analysis of Variance; Correlation; Error of
Measurement; *Mathematical Models; *Research Methodology; Research
Problems; *Statistical Analysis; Statistical Studies
Identifiers: *Effect Size; Glass (G V); *Meta Analysis
EJ260365 SE530947
Meta-analysis: An Approach to the Synthesis of Research Results.
Glass, Gene V.
Journal of Research in Science Teaching, v19 n2 p93-112 Feb
1982
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
Discusses three general characteristics and four criticisms of meta-
analysis (statistical analysis of the summary findings of many
research studies). Illustrates application of meta-analysis on
research studies relating to school class size and achievement and
inquiry teaching of biology. (JN)
Descriptors: Academic Achievement; Biology; Class Size; College
Science; Elementary School Science; Elementary Secondary Education;
Higher Education; Inquiry; *Research Methodology; *Science Education;
*Science Instruction; Secondary School Science; *Statistical Analysis
Identifiers: *Meta Analysis; *Science Education Research
EJ256426 EC140469
Meta-Analysis and the Integration of Research in Special Education.
Kavale, Kenneth A.; Glass, Gene V.
Journal of Learning Disabilities, v14 n9 p531-38 Nov
1981
Document Type: JOURNAL ARTICLE (080); REVIEW LITERATURE (070);
POSITION PAPER (120)
Traditional methods of integrating special education research (such
as narrative reviews and box score analyses) are described, and the
procedures involved in meta-analysis, by which findings from previous
studies are systematically synthesized, are detailed. Benefits of
this approach are noted. (CL)
Descriptors: *Disabilities; *Research Methodology; *Statistical
Analysis
Identifiers: *Meta Analysis
ED208024 TM810715
Statistical Aspects of Effect Size Estimation.
Hedges, Larry V.
Apr 1981
40p.; Paper presented at the Annual Meeting of the American
Educational Research Association (65th, Los Angeles, CA, April 13-17,
1981).
Sponsoring Agency: Spencer Foundation, Chicago, Ill.
Document Type: CONFERENCE PAPER (150); RESEARCH REPORT (143)
When the results of a series of independent studies are combined,
it is useful to quantitatively estimate the magnitude of the effects.
Several methods for estimating effect size are compared in this paper.
Glass' estimator and the uniformly minimum variance unbiased
estimator are based on the ratio of the sample mean difference and
the pooled within-group standard deviation. The third estimator is
the maximum likelihood estimator. The fourth estimator is a shrunken
form of the minimum variance unbiased estimator. All four estimators
are shown to be equivalent in large samples, but they differ in
finite samples. Two procedures for testing the fit of the data to
the proposed structural model and for detection of outliers, an
example of the application of the techniques, and a summary of
recommendations on statistical procedures for estimation of effect
size from a series of experiments are presented. (Author/BW)
Descriptors: *Literature Reviews; *Mathematical Models; Maximum
Likelihood Statistics; *Statistical Analysis
Identifiers: *Effect Size; Estimation (Mathematics); *Meta Analysis;
Sample Size
ED208003 TM810675
Integration of Research Studies: Meta-Analysis of Research. Methods
of Integrative Analysis; Final Report.
Glass, Gene V.; And Others
Colorado Univ., Boulder. Lab. of Educational Research.
15 Aug 1980
340p.; Appendix B is removed due to copyright restrictions.
Sponsoring Agency: National Inst. of Education (ED), Washington,
D.C.
Document Type: REVIEW LITERATURE (070); NON-CLASSROOM MATERIAL
Integrative analysis, or what is coming to be known as meta-
analysis, is the integration of the findings of many empirical
research studies of a topic. Meta-analysis differs from traditional
narrative forms of research reviewing in that it is more quantitative
and statistical. Thus, the methods of meta-analysis are merely
statistical methods, suitably adapted in many instances, that are
applicable to the job of integrating findings from many studies. A
meta-analysis involves about a half-dozen steps: (1) defining the
problem, (2) finding the research studies, (3) coding the study
characteristics. The thinking and research reported here is recorded
in roughly the same order. The report encompasses general background
on the approach, and the results of some original research on
approach taken in a meta-analysis, numerous illustrations of the
approach, and the results of some original research on
characteristics, (4) measuring the study findings on a common scale,
and (5) analyzing the aggregation of findings and their relationship
to the characteristics. The thinking can be read in at least three
ways: as a textbook of methods of integrative analysis, as a record
of some new ideas about integrative analysis, or as an apologia for
meta-analysis. (Author/BW)
Descriptors: *Data Analysis; *Literature Reviews; *Research
Methodology; Research Problems; Statistical Analysis
Identifiers: *Meta Analysis
EJ235541 TM505692
Research Integration: The State of the Art.
Walberg, Herbert J., Ed.; Haertel, Edward H., Ed.
Evaluation in Education: International Progress, v4 n1 p1-142
1980
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143);
REVIEW LITERATURE (070)
Forty-five brief papers cover four areas: research integration
methodology; standard curriculum topics in educational research and
evaluation; individual differences and special programs suited to
particular groups of students; and programs of research integration
being conducted by the University of Illinois-Chicago Circle and the
National Institute of Education. (BW)
Descriptors: Curriculum Research; Elementary Secondary Education;
Higher Education; Individual Differences; Policy Formation;
Productivity; *Research Methodology; *Research Problems; State of the
Art Reviews; *Synthesis
Identifiers: *Research Integration
EJ239575 TM505815
Methods for Integrative Reviews.
Jackson, Gregg B.
Review of Educational Research, v50 n3 p438-60 Fall
1980
Document Type: JOURNAL ARTICLE (080); REVIEW LITERATURE (070);
EVALUATIVE REPORT (142)
Methods for reviews of research that focus on inferring
generalizations about substantive issues from a set of studies
directly bearing on those issues are examined. The primary source of
data was a content analysis of two samples of such reviews.
(Author/RL)
Descriptors: *Data Analysis; *Literature Reviews; *Research
Methodology; *Social Science Research
Identifiers: *Integrative Reviews; *Meta Analysis
EJ237866 TM505768
Choice of the Metric for Effect Size in Meta-analysis.
McGaw, Barry; Glass, Gene V.
American Educational Research Journal, v17 n3 p325-37 Fall
1980
Document Type: JOURNAL ARTICLE (080); RESEARCH REPORT (143)
There are difficulties in expressing effect sizes on a common
metric when some studies use transformed scales to express group
differences, or use factorial designs or covariance adjustments to
obtain a reduced error term. A common metric on which effect sizes
may be standardized is described. (Author/RL)
Descriptors: Control Groups; Error of Measurement; *Mathematical
Models; *Research Problems; *Scaling; *Scoring Formulas; Statistical
Bias; Statistical Significance
Identifiers: *Effect Size; *Meta Analysis; Standard Deviation
ED208003 TM810675
Integration of Research Studies: Meta-Analysis of Research. Methods
of Integrative Analysis; Final Report.
Glass, Gene V.; And Others
Colorado Univ., Boulder. Lab. of Educational Research.
15 Aug 1980
340p.; Appendix B is removed due to copyright restrictions.
Sponsoring Agency: National Inst. of Education (ED), Washington,
D.C.
Document Type: REVIEW LITERATURE (070); NON-CLASSROOM MATERIAL
(055)
Integrative analysis, or what is coming to be known as meta-
analysis, is the integration of the findings of many empirical
research studies of a topic. Meta-analysis differs from traditional
narrative forms of research reviewing in that it is more quantitative
and statistical. Thus, the methods of meta-analysis are merely
statistical methods, suitably adapted in many instances, that are
applicable to the job of integrating findings from many studies. A
meta-analysis involves about a half-dozen steps: (1) defining the
problem, (2) finding the research studies, (3) coding the study
characteristics. The thinking and research reported here is recorded
in roughly the same order. The report encompasses general background
on the approach, and the results of some original research on
approach taken in a meta-analysis, numerous illustrations of the
approach, and the results of some original research on
characteristics, (4) measuring the study findings on a common scale,
and (5) analyzing the aggregation of findings and their relationship
to the characteristics. The thinking can be read in at least three
ways: as a textbook of methods of integrative analysis, as a record
of some new ideas about integrative analysis, or as an apologia for
meta-analysis. (Author/BW)
Descriptors: *Data Analysis; *Literature Reviews; *Research
Methodology; Research Problems; Statistical Analysis
Identifiers: *Meta Analysis
EJ207324 TM504364
Meta-Analysis of Research on Class Size and Achievement.
Glass, Gene V.; Smith, Mary Lee
Educational Evaluation and Policy Analysis, v1 n1 p2-16 Jan-Feb
1979
Document Type: JOURNAL ARTICLE (080); REVIEW LITERATURE (070)
The relationship between class size and school achievement is
investigated in this "meta-analysis" of the class size literature.
In addition, some methodological considerations of meta-analysis are
discussed. (JKS)
Descriptors: *Academic Achievement; Classroom Research; *Class Size;
Elementary Secondary Education; *Evaluation; Evaluation Methods;
Literature Reviews
Identifiers: Meta Analysis
EJ149191 UD504875
Primary, Secondary, and Meta-Analysis of Research
Glass, Gene V.
Educational Researcher, 5, 10, 3-8 Nov 1976
Examines data analysis at three levels: analysis of data; secondary
analysis is the re-analysis of data for the purpose of answering the
original research question with better statistical techniques, or
answering new questions with old data; and, meta-analysis refers to
the statistical analysis of many analysis results from individual
studies for the purpose of integrating the findings. (Author/JM)
Descriptors: *Research Methodology; *Data Analysis; *Statistical
Analysis; *Research Utilization; *Educational Research; Research
Problems; Information Utilization; Research Design; Literature
Reviews; Research Reviews (Publications)
Return to the Index of FAQs
|
