FitDefSc: An Effective Design Based Model Fitting Method for Definitive...

In daewr: Design and Analysis of Experiments with R

Description

This function performs fits a model to a Definitive Screeing Design by first restricting main effects to the smallest main effects and those significant at at least the .20 level in a main effects model. Next forward stepwise selection is used to enter 2 factor interactions and quadratic effects.

Usage

FitDefSc(y,design,alpha=.05)

Arguments

y	input - this is a vector containing a single numeric column of response data.
design	input - this is a data frame containing the numeric columns of the candidate independent variables created by the DefScreen function with only numerical factors i.e. c=0. The factor names or colnames(design) should always be of length 1 (for example letters of the alphabet "A", "B", etc.)
alpha	input - alpha to enter in the forward stepwise regression with second order candidates should be between 0.05 and 0.20

Author(s)

John Lawson

Examples

design<-DefScreen(m=5,c=0,randomize=FALSE)
Smeso<-c(241,295,260,338,320,265,275,248,66,383,313)
FitDefSc(Smeso,design,alpha=.12)

Example output

Registered S3 method overwritten by 'DoE.base':
  method           from       
  factorize.factor conf.design

Call:
lm(formula = y ~ (.), data = ndesign)

Residuals:
      1       2       3       4       5       6       7       8       9      10 
-13.348 -14.470  -5.452  -3.882  10.255  10.927   7.645   5.627  -3.206  -3.430 
     11 
  9.333 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  303.667      8.447  35.951 3.57e-06 ***
B            -81.652      5.695 -14.338 0.000137 ***
D            -30.945      5.918  -5.229 0.006389 ** 
B:D          -27.045      6.238  -4.335 0.012298 *  
I(B^2)       -48.803     10.027  -4.867 0.008236 ** 
A            -46.015      5.695  -8.080 0.001275 ** 
E            -23.145      5.918  -3.911 0.017381 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 14.63 on 4 degrees of freedom
Multiple R-squared:  0.9869,	Adjusted R-squared:  0.9672 
F-statistic: 50.22 on 6 and 4 DF,  p-value: 0.001012

daewr documentation built on March 13, 2021, 3:01 a.m.