These data come from an experiment investigation of the heat evolved during the setting and hardening of Portland cements of varied composition and the dependence of this heat on the percentages of four components in the clinkers from which the cement was produced.

datasets

When multicollinearity exists among predictor variables of the linear model, least square estimators does not provide a better solution for estimating parameters. To deal with multicollinearity several estimators are proposed in the literature. Some of these estimators are Ordinary Least Square Estimator (OLSE), Ordinary Ridge Regression Estimator (ORRE), Restricted Least Square Estimator (RLSE), Ordinary Mixed Regression Estimator (OMRE), Liu Estimator (LE), Restricted Liu Estimator (RLE), Stochastic Restricted Liu Estimator (SRLE), Type (1) Liu Estimator (Type-1 LTE), Type (2) Liu Estimator (Type-2 LTE), Type (3) Liu Estimator (Type-3 LTE), Type (1) Adjusted Liu Estimator (Type-1 ALTE), Type (2) Adjusted Liu Estimator (Type-2 ALTE), Type (3) Adjusted Liu Estimator (Type-3 ALTE), Almost Unbiased Ridge Estimator (AURE), Almost Unbiased Liu Estimator (AULE), Stochastic Restricted Ridge Estimator (SRRE) and Restricted Ridge Regression Estimator (RRRE). To select the best estimator in a practical situation the Mean Square Error (MSE) is used. Using this package scalar MSE value of all the above estimators and Prediction Sum of Square (PRESS) values of some of the estimators can be obtained, and the variation of the MSE and PRESS values for the relevant estimators can be shown graphically. 

pcd: Portland Cement Dataset

Description

Usage

Arguments

References

Examples