Metaanalysis
From PsychWiki  A Collaborative Psychology Wiki
(Difference between revisions)
Line 1:  Line 1:  
Have you ever wanted to learn about metaanalysis or conduct a metaanalysis but didn't know where to start? This webpage is devoted to providing  Have you ever wanted to learn about metaanalysis or conduct a metaanalysis but didn't know where to start? This webpage is devoted to providing  
+  
+  
+  
+  
+  
+  
+  
+  
+  
==Where should I start?==  ==Where should I start?==  
  <TABLE BORDER=  +  <TABLE BORDER="10" bordercolor="#0000CD" cellspacing="0" cellpadding="5"> 
<TR>  <TR>  
  <TD valign=top width=  +  <TD valign=top width=360> 
  If you want to learn '''what is a metaanalysis  +  If you want to learn '''what is a metaanalysis...''' 
<ol>  <ol>  
<li>For the <u>basics</u>, see below where we lay out:</li>  <li>For the <u>basics</u>, see below where we lay out:</li>  
Line 21:  Line 30:  
</ol>  </ol>  
</TD>  </TD>  
  <TD valign=top width=  +  <TD valign=top width=360> 
  If you want to learn '''how to start conducting a meta  +  If you want to learn '''how to start conducting a meta...''' 
<ol>  <ol>  
<li>For the <u>basics</u>, see below were we lay out:</li>  <li>For the <u>basics</u>, see below were we lay out:</li> 
Revision as of 02:23, 18 July 2006
Have you ever wanted to learn about metaanalysis or conduct a metaanalysis but didn't know where to start? This webpage is devoted to providing
Where should I start?
If you want to learn what is a metaanalysis...

If you want to learn how to start conducting a meta...

What is a metaanalysis?
Definition
Three Basic Questions
 A metaanalysis answers three general questions:
 Central tendency – The central purpose of a metaanalysis is to test the relationship between two variables such that X causes Y. Central tendency refers to identifying whether X affects Y via statistically summarizing signficance levels, effect sizes, and/or confidence intervals. You are trying to answer whether X affects Y, is the effect significant, and how strong is that effect?
 Variability – There is always going to be some degree of variation between the outcomes of the individual studies that compose the metaanalysis. The question is whether the degree of variablity is signficantly different than what we would expect by chance alone. If so, then its called heterogeneity.
 Prediction – If there is heterogeneity (variability), then we look for moderating variables that explain the variability. In other words, does the effect of X on Y differ with moderator variables?
Five Basic Steps
 There are generally five separate steps in conducting a metaanalysis:
 Define your hypothesis
 Locate the Literature
 Identify and input data
 Cacluate Effect Sizes
 Analyze Variables
How do I conduct a metaanalysis?
First, choose what statistical approach suits your needs
 There are generally three different statistical approaches to conduct a metaanalysis so first you need to choose which approach best fits your needs. For an excellent detailed comparison of these three approaches, see (Johnson, Mullen, & Salas, 1995) (Comparison of Three Major MetaAnalytic Approaches. Journal of Applied Psychology, 80, 94106). Some basic information from that article is posted below to get you started:
 Hedges & Olkin Approach – see (Hedges, 1981); (Hedges, 1982); (Hedges & Olkin, 1985)
 Rosenthal & Rubin Approach – see (Rosenthal, 1991); (Rosenthal & Rubin, 1978); (Rosenthal & Rubin, 1988)
 Hunter, Schmidt, & Jackson  see (Hunter, Schmidt, & Jackson, 1982); (Hunter & Schmidt, 1990)
Second, choose which effect size to calculate?
Third, choose your statistical software
If you want to follow the Hedges & Olkin approach...
If you want to follow the Rosenthal & Rubin approach...
If you want to follow the Hunter, Schmidt, & Jackson approach...
Just as an individual study collects data from many individuals (data points) that is statistically summarized to answer the question of interest, a metaanlay
 What is the good number of studies to have bare minimum for a metaanalysis? A metaanalysis with 10 studies have been published before but is not recommended.
 In a metaanalysis, don’t have raters code conditions for which no effect sizes can be calculated.
 In a metaanalysis, have judge rate each variable across studies, one moderator at a time, instead of rating all variables in a single study before moving on to next study.
 With metaanalysis coding with a high number of studies to code, such as 75+, can have some coders rate the entire set, but can also have some coders (undergrads) code only a subset as long there is overlap, so that more than 1 judge is rating each study.
► Back to Research Tools mainpage