Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Publication
- Publication Type
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Adaptive Estimation, Douglas G. Steigerwald
Adaptive Estimation, Douglas G. Steigerwald
Douglas G. Steigerwald
No abstract provided.
Locally Efficient Estimation Of Regression Parameters Using Current Status Data, Chris Andrews, Mark J. Van Der Laan, James M. Robins
Locally Efficient Estimation Of Regression Parameters Using Current Status Data, Chris Andrews, Mark J. Van Der Laan, James M. Robins
U.C. Berkeley Division of Biostatistics Working Paper Series
In biostatistics applications interest often focuses on the estimation of the distribution of a time-variable T. If one only observes whether or not T exceeds an observed monitoring time C, then the data structure is called current status data, also known as interval censored data, case I. We consider this data structure extended to allow the presence of both time-independent covariates and time-dependent covariate processes that are observed until the monitoring time. We assume that the monitoring process satisfies coarsening at random.
Our goal is to estimate the regression parameter beta of the regression model T = Z*beta+epsilon where the …
Adaptive Estimation In Timeseries Regression Models, Douglas Steigerwald
Adaptive Estimation In Timeseries Regression Models, Douglas Steigerwald
Douglas G. Steigerwald
I develop adaptive estimators for linear regression with serially correlated errors. The efficiency results hold even when the serial correlation structure is unknown. Simulations indicate that efficiency gains can be substantial with samples of only 50 observations. We apply the method to a study of forward exchange rates.
On The Finite Sample Behavior Of Adaptive Estimators, Douglas Steigerwald
On The Finite Sample Behavior Of Adaptive Estimators, Douglas Steigerwald
Douglas G. Steigerwald
With only 50 observations, the adaptive estimator produces confidence intervals that are 20 to 50 percent shorter than those produced by GLS procedures. The key feature is that the underlying error density is symmetric. Under asymmetry the interval length is shortened by a smaller amount.