NotesFAQContact Us
Search Tips
ERIC Number: ED038656
Record Type: RIE
Publication Date: 1970
Pages: 38
Abstractor: N/A
Reference Count: 0
The Future of Sociological Research: Measurement Errors and Their Implications.
Blalock, H. M.
The report deals with the relationship between measurement and data analysis procedures in sociological research. The author finds that too many measured variables exist in both theory and measurement assumptions. Since these procedures are interrelated, improvements in either or both areas are necessary. Presented are three sections: (1) specific complications and distortions which may be produced by random and nonrandom measurement errors; (2) statistical approaches designed to eliminate or estimate the effects of measurement errors; and (3) exploration of some practical implications for the profession. The first section includes discussions on multicollinearity, choosing among alternative causal models, and nonlinearity and nonadditivity. The second section deals with various approaches of estimating random and nonrandom errors. The third section concludes that although much remains to be accomplished research sociologists should not be immobilized because of well-recognized but unmet assumptions. (Author/MC)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: North Carolina Univ., Chapel Hill.