Performance of Ridge Regression Approach in Linear Measurement Error Models with Replicated Data
Abstract
It is well known that bias in parameter estimates arises
when there are measurement errors in the covariates of regression mod-
els. One solution for decreasing such biases is the use of prior informa-
tion concerning the measurement error, which is often called replication
data. In this paper, we present a ridge estimator in replicated measure-
ment error (RMER) to overcome the multicollinearity problem in such
models. The performance of RMER against some other estimators is
investigated. Large sample properties of our estimator are derived and
compared with other estimators using a simulation study as well as a
real data set.
when there are measurement errors in the covariates of regression mod-
els. One solution for decreasing such biases is the use of prior informa-
tion concerning the measurement error, which is often called replication
data. In this paper, we present a ridge estimator in replicated measure-
ment error (RMER) to overcome the multicollinearity problem in such
models. The performance of RMER against some other estimators is
investigated. Large sample properties of our estimator are derived and
compared with other estimators using a simulation study as well as a
real data set.
Keywords
Measurement error model, Ridge regression, Multicollinearity, Corrected log-likelihood
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.