Abstract
Consider the correlation between two random variables (X, Y), both not directly observed. One only observes over(X, ̃) = φ{symbol}1 (U) X + φ{symbol}2 (U) and over(Y, ̃) = ψ1 (U) Y + ψ2 (U), where all four functions {φ{symbol}l ({dot operator}), ψl ({dot operator}), l = 1, 2} are unknown/unspecified smooth functions of an observable covariate U. We consider consistent estimation of the correlation between the unobserved variables X and Y, adjusted for the above general dual additive and multiplicative effects of U, based on the observed data (over(X, ̃), over(Y, ̃), U).
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1684-1689 |
| Number of pages | 6 |
| Journal | Statistics and Probability Letters |
| Volume | 79 |
| Issue number | 15 |
| DOIs | |
| State | Published - Aug 1 2009 |
ASJC Scopus subject areas
- Statistics, Probability and Uncertainty
- Statistics and Probability
Fingerprint Dive into the research topics of 'A consistent local linear estimator of the covariate adjusted correlation coefficient'. Together they form a unique fingerprint.
Cite this
Nguyen, D. V., & Şentürk, D. (2009). A consistent local linear estimator of the covariate adjusted correlation coefficient. Statistics and Probability Letters, 79(15), 1684-1689. https://doi.org/10.1016/j.spl.2009.04.021