What question did this study set out to answer?

Determine conditions causing incorrect slope and intercept calculations in ordinary least-squares regression and evaluate alternative estimation methods under measurement imprecision and outlier contamination.

March 1, 1979Clinical Chemistry

Incorrect least-squares regression coefficients in method-comparison analysis.

View Full Paper

Ask AI

Bookmark

Authors

PCP. Joanne CornbleetStanford University NGNathan GochmanAnaheim University

Discussion

Member takes

Implication

Methodological study demonstrates that Deming regression and residual filtering resolve slope estimation errors, highlighting essential corrections for analytical method comparisons.

Key Points

Determine conditions causing incorrect slope and intercept calculations in ordinary least-squares regression and evaluate alternative estimation methods under measurement imprecision and outlier contamination.
Compared ordinary least-squares estimation against the Deming, Mandel, and Bartlett methods for estimating known regression slopes in the presence of x-variable measurement error.
Evaluated the impact of the ratio of single-measurement standard deviation to sample standard deviation and tested residual threshold criteria for identifying disruptive outliers.
Deming's method was identified as the most effective technique for estimating regression slopes when the independent variable has measurement imprecision.
Least-squares slope estimates incurred significant error when the ratio of the measurement standard deviation of a single x value to the standard deviation of the x-data set exceeded 0.2.
Coefficient errors caused by outliers were eliminated by discarding data points whose vertical distance from the regression line exceeded four times the standard error of the estimate.

Cite This Study

Cornbleet et al. (1979) studied this question.

synapsesocial.com/papers/6a6bc0c479eb7ca1702470d6 https://doi.org/10.1093/clinchem/25.3.432

View Full Paper

Ask AI

Bookmark

Implication

Methodological study demonstrates that Deming regression and residual filtering resolve slope estimation errors, highlighting essential corrections for analytical method comparisons.

Incorrect least-squares regression coefficients in method-comparison analysis.

Discussion

Member takes

Implication

Key Points

Cite This Study

Incorrect least-squares regression coefficients in method-comparison analysis.

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider