Bootstrap confidence intervals for regression coefficients when the residuals are dependent
- 1 February 1986
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 23 (4) , 317-327
- https://doi.org/10.1080/00949658608810883
Abstract
The bootstrap methodology is used to construct confidence intervals for the regression coefficients in a time series with linear trend. The residuals are assumed to follow an AR(1) or MA(1) process. The behaviour of the confidence level of the intervals are studied by simulation for a variety of parameter values and underlying distributions.Keywords
This publication has 8 references indexed in Scilit:
- Computer-Intensive Methods in StatisticsScientific American, 1983
- A Leisurely Look at the Bootstrap, the Jackknife, and Cross-ValidationThe American Statistician, 1983
- On the construction of confidence limits for the regression coefficient when the residuals are dependentJournal of Statistical Computation and Simulation, 1983
- Bootstrapping Regression ModelsThe Annals of Statistics, 1981
- Robust StatisticsPublished by Wiley ,1981
- Statistical Robustness: One View of Its Use in Applications TodayThe American Statistician, 1979
- Bootstrap Methods: Another Look at the JackknifeThe Annals of Statistics, 1979
- Testing the Mean of a Normal Population Under DependenceThe Annals of Statistics, 1978