Confidence bands for linear regressions
Author:
- 1 January 1992
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 21 (2) , 333-352
Abstract
A method for obtaining confidence bands for regression functions is given. The algorithm allows for the construction of simultaneous confidence intervals for multiple regression functions containing up to seven parameters. Various types of constraints on predictor variables are allowed as well as different shapes for the confidence bands. Computations, examples and comparisons illuminate the effectiveness and accuracy of the algorithm.Keywords
This publication has 17 references indexed in Scilit:
- Simultaneous Confidence Bounds in Multiple Regression Using Predictor Variable ConstraintsJournal of the American Statistical Association, 1987
- Confidence Bands for Regression FunctionsJournal of the American Statistical Association, 1985
- Comparing Scheffé-Type to Constant-Width Confidence Bounds in RegressionJournal of the American Statistical Association, 1983
- Exact Confidence Bands for Linear Regression over IntervalsJournal of the American Statistical Association, 1983
- Confidence Bands for Linear Regression with Restricted Predictor VariablesJournal of the American Statistical Association, 1980
- Validation of Regression Models: Methods and ExamplesTechnometrics, 1977
- Simultaneous Confidence Bands for Linear Regression ModelsJournal of the American Statistical Association, 1970
- Confidence Bands of Uniform and Proportional Width for Linear ModelsJournal of the American Statistical Association, 1966
- Confidence Bands in Straight Line RegressionJournal of the American Statistical Association, 1964
- Applications of the Theory of Error to the Interpretation of TrendsJournal of the American Statistical Association, 1929