ingots.df: Unreadiness for rolling of metal ingots

In R330: An R package for Stats 330

Description

An experiment testing metal ingots prepared with different soaking times and heats. The number which were not ready were counted

Usage

data(ingots.df)

Format

A data frame which shows a condensed table.

heat

heating times for ingots either 7, 24, 27 or 51

soak

soaking times for ingots either 1.0, 1.7, 2.2, 2.8 or 4.0

notready

the number of ingots not ready for rolling

total

the total number of ingots which were tested under that set of conditions

Source

D.R.Cox. (1970) The Analysis of Binary Data, p. 11

References

D.R.Cox. (1970) The Analysis of Binary Data, Chapman and Hall, London

Examples

data(ingots.df)
ingots.glm<-glm(cbind(notready, total-notready)~heat + 
   soak, weight=total, family = binomial, data = ingots.df)
summary(ingots.glm)

Example output

Loading required package: s20x
Loading required package: leaps
Loading required package: rgl
Loading required package: lattice
Warning messages:
1: In rgl.init(initValue, onlyNULL) : RGL: unable to open X11 display
2: 'rgl_init' failed, running with rgl.useNULL = TRUE 
3: .onUnload failed in unloadNamespace() for 'rgl', details:
  call: fun(...)
  error: object 'rgl_quit' not found 

Call:
glm(formula = cbind(notready, total - notready) ~ heat + soak, 
    family = binomial, data = ingots.df, weights = total)

Deviance Residuals: 
   Min      1Q  Median      3Q     Max  
-6.655  -4.223  -1.135  -0.902   9.757  

Coefficients:
             Estimate Std. Error z value Pr(>|z|)    
(Intercept) -6.315523   0.229739  -27.49  < 2e-16 ***
heat         0.097627   0.005894   16.57  < 2e-16 ***
soak         0.311769   0.063881    4.88 1.06e-06 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 636.20  on 18  degrees of freedom
Residual deviance: 386.64  on 16  degrees of freedom
AIC: 836.85

Number of Fisher Scoring iterations: 5

R330 documentation built on May 2, 2019, 2:12 p.m.