论文信息 - On the Robustness of a Class of Naive Estimators

On the Robustness of a Class of Naive Estimators

A class of naive estimators of correlation was tested for robustness, accuracy, and efficiency against Pearson's r, Tukey's rt , and Spearman's ro . It was found that this class of estimators seems in some respects to be superior being less affected by outliers, reasonably efficient, and frequently more easily calculated. The definition and details of the use of these naive estimators are the subject of this paper.

Howard Wainer | David Thissen | H. Wainer | D. Thissen

[1] R. Hogg. Adaptive Robust Procedures: A Partial Review and Some Suggestions for Future Applications and Theory , 1974 .

[2] R. Strahan,et al. Underestimating Correlation from Scatterplots , 1978 .

[3] Howard Wainer,et al. Estimating Coefficients in Linear Models: It Don't Make No Nevermind , 1976 .

[4] F. Downton,et al. Linear estimates with polynomial coefficients. , 1966, Biometrika.

[5] H. Wainer,et al. When Jackknifing fails (or does it?) , 1975 .

[6] R. Dawes,et al. Linear models in decision making. , 1974 .

[7] E. L. Kelly. Clinical versus statistical prediction: A theoretical analysis and review of the evidence. , 1955 .

[8] R. Hogarth,et al. Unit weighting schemes for decision making , 1975 .

[9] G. C. Tiao,et al. A bayesian approach to some outlier problems. , 1968, Biometrika.

[10] W. Dixon. Simplified Estimation from Censored Normal Samples , 1960 .

[11] H. Wainer,et al. Three steps towards robust regression , 1976 .

[12] S. J. Devlin,et al. Robust estimation and outlier detection with correlation coefficients , 1975 .

[13] A. Tversky,et al. On the psychology of prediction , 1973 .