Statistical Testing in Treatment by Replication Designs: Three Options Reconsidered.

Jackson, Sally; And Others

Notes FAQ Contact Us

Back to results

Peer reviewed

ERIC Number: EJ448419

Record Type: CIJE

Publication Date: 1992

Pages: N/A

Abstractor: N/A

ISBN: N/A

ISSN: ISSN-0146-3373

EISSN: N/A

Statistical Testing in Treatment by Replication Designs: Three Options Reconsidered.

Jackson, Sally; And Others

Communication Quarterly, v40 n3 p211-27 Sum 1992

Examines mathematical relationships among three methods for statistical analysis of treatment by replication experiments involving message variables: ignoring them in the statistical analysis; treating them as levels of a fixed effect; or treating them as levels of a random effect. Finds the third method is the only one offering a reasonable test of the treatment main effect. (SR)

Descriptors: Communication Research, Higher Education, Research Design, Research Methodology, Statistical Analysis

Publication Type: Journal Articles; Reports - Research

Education Level: N/A

Audience: N/A

Language: English

Sponsor: N/A

Authoring Institution: N/A

Grant or Contract Numbers: N/A