NotesFAQContact Us
Collection
Advanced
Search Tips
PDF pending restoration PDF pending restoration
ERIC Number: ED205534
Record Type: RIE
Publication Date: 1981-Apr
Pages: 18
Abstractor: N/A
Reference Count: 0
ISBN: N/A
ISSN: N/A
Specification Bias in Causal Models with Fallible Indicators.
Patteson, Barbara J.; Wolfle, Lee M.
In the bivariate case, measurement error in the independent variable produces an attenuated estimate of the true regression coefficient. In the multivariate case, the bias which results from specifying, incorrectly, a model with no measurement error will produce biased estimates which are predictable in neither their direction nor magnitude. Using data on educational attainment from the National Longitudinal Study of the High School Class of 1972, this paper examines the extent of bias inherent in ordinary least squares regression estimates when the presence of measurement error is ignored. In some cases, the nature of bias can be predicted, but the more usual situation is that measurement error bias is unpredictable. (Author/BW)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: National Center for Education Statistics (DHEW), Washington, DC.
Authoring Institution: Virginia Polytechnic Inst. and State Univ., Blacksburg.
Identifiers: Estimation (Mathematics); National Longitudinal Study High School Class 1972
Note: Paper presented at the Annual Meeting of the American Educational Research Association (65th, Los Angeles, CA, April 13-17, 1981).