Data and Syntax for Investigating Science Education Effect Sizes: Implications for Power Analyses and Programmatic Decisions

Principal Investigator(s):  View help for Principal Investigator(s) Susan M. Kowalski, BSCS Science Learning; Joseph A. Taylor, University of Colorado, Colorado Springs

Version:  View help for Version V1

Version Title:  View help for Version Title Version 1.0

Name File Type Size Last Modified
-Read-Me-Overview-of-Syntax-and-Data-files-associated-with-Taylor-et-al-2018-AERA-Open.docx application/vnd.openxmlformats-officedocument.wordprocessingml.document 22.3 KB 03/23/2019 04:43:AM
data_file_1.sav application/x-spss-sav 38.7 KB 03/22/2019 02:23:PM
data_file_2.sav application/x-spss-sav 21.2 KB 03/14/2019 05:29:AM
data_file_3.dat text/plain 33.9 KB 03/15/2019 08:06:AM
data_file_3.sav application/x-spss-sav 41.5 KB 03/15/2019 11:14:AM
data_file_4_imp1.dat text/plain 30.2 KB 03/15/2019 11:14:AM
data_file_4_imp1.sav application/x-spss-sav 28 KB 03/15/2019 11:15:AM
data_file_4_imp10.dat text/plain 30.2 KB 03/15/2019 11:15:AM
data_file_4_imp10.sav application/x-spss-sav 28 KB 03/15/2019 11:15:AM
data_file_4_imp2.dat text/plain 30.2 KB 03/23/2019 08:08:AM

Project Citation: 

Kowalski, Susan M., and Taylor, Joseph A. Data and Syntax for Investigating Science Education Effect Sizes:  Implications for Power Analyses and Programmatic Decisions. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2019-03-23. https://doi.org/10.3886/E109061V1

Project Description

Summary:  View help for Summary
A priori power analyses allow researchers to estimate the number of participants needed to detect the effects of an intervention. However, power analyses are only as valid as the parameter estimates used. One such parameter, the expected effect size, can vary greatly depending on several study characteristics, including the nature of the intervention, developer of the outcome measure, and age of the participants. Researchers should understand this variation when designing studies. Our meta-analysis examines the relationship between science education intervention effect sizes and a host of study characteristics, allowing primary researchers to access better estimates of effect sizes for a priori power analyses. The results of this meta-analysis also support programmatic decisions by setting realistic expectations about the typical magnitude of impacts for science education interventions.

The primary research question of this meta-analysis is: What is the relationship between the magnitude of the intervention effects and key study characteristics? The study characteristics of interest included the design (randomized studies compared to matched quasi-experimental studies), whether the outcome measure was developed by the study authors, who receives the intervention (e.g., students only, teachers only, both students and teachers), the science discipline targeted by the intervention, the treatment provider’s role (e.g., researcher or teacher), and the grade level of the students.



Funding Sources:  View help for Funding Sources National Science Foundation (1118555)

Scope of Project

Subject Terms:  View help for Subject Terms effect size; meta-analysis; program evaluation; science education; students
Time Period(s):  View help for Time Period(s) 2001 – 2014
Universe:  View help for Universe Manuscripts associated with studies of science education interventions conducted internationally, published in English.

Methodology

Data Source:  View help for Data Source Our data sources were manuscripts from 96 primary studies of science education interventions with primary and secondary students (published and unpublished). A complete description of eligibility criteria for included manuscripts is found in the published paper associated with these data.
Weights:  View help for Weights
We made several adjustments to the data, including Winsorization of sample sizes, Winsorization of effect sizes, grand mean centering, and weighting effect by the inverse variance.
Unit(s) of Observation:  View help for Unit(s) of Observation effect sizes

Related Publications

Download this project

Published Versions

V1 [2019-03-23]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.