R : Copyright 2003, The R Development Core Team
Version 1.7.1  (2003-06-16)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type `license()' or `licence()' for distribution details.

R is a collaborative project with many contributors.
Type `contributors()' for more information.

Type `demo()' for some demos, `help()' for on-line help, or
`help.start()' for a HTML browser interface to help.
Type `q()' to quit R.

> pr<-read.table("prostate.data")
> dim(pr)
[1] 97 10
> pr[1:4,]
      lcavol  lweight age      lbph svi       lcp gleason pgg45       lpsa
1 -0.5798185 2.769459  50 -1.386294   0 -1.386294       6     0 -0.4307829
2 -0.9942523 3.319626  58 -1.386294   0 -1.386294       6     0 -0.1625189
3 -0.5108256 2.691243  74 -1.386294   0 -1.386294       7    20 -0.1625189
4 -1.2039728 3.282789  58 -1.386294   0 -1.386294       6     0 -0.1625189
  train
1  TRUE
2  TRUE
3  TRUE
4  TRUE
> is.factor(pr$gleason)
[1] FALSE
> prostate.frame<-data.frame(pr)
> attach(prostate.frame)
> rm(pr)
> pairs(prostate.frame)
> std<-function(x){(x-mean(x))/sqrt(var(x))}
> lcavol.z<-std(lcavol)
> lweight.z <- std(lweight)
> age.z <-std(age)
> lbph.z <- std(lbph)
> svi.z <- std(svi)
> lcp.z <- std(lcp)
> gleason.z <- std(gleason)
> pgg45.z <- std(pgg45)
> prostate.z.frame<-cbind(lpsa,lcavol.z,lweight.z,age.z,lbph.z,svi.z,lcp.z,gleason.z,pgg45.z,train)
> dim(prostate.z.frame)
[1] 97 10
> is.data.frame(prostate.z.frame)
[1] FALSE
> prostate.z.frame<-data.frame(prostate.z.frame)
> pr.z.train<-subset(prostate.z.frame,train=="1",select=c(lpsa,lcavol.z,lweight.z,age.z,lbph.z,svi.z,lcp.z,gleason.z,pgg45.z))
> dim(pr.z.train)
[1] 67  9
> is.data.frame(pr.z.train)
[1] TRUE
> dim(pr.z.train)
[1] 67  9
> lm(lpsa~lcavol.z+lweight.z+age.z+lbph.z+svi.z+lcp.z+gleason.z+pgg45.z,data=pr.z.train)

Call:
lm(formula = lpsa ~ lcavol.z + lweight.z + age.z + lbph.z + svi.z +     lcp.z + gleason.z + pgg45.z, data = pr.z.train)

Coefficients:
(Intercept)     lcavol.z    lweight.z        age.z       lbph.z        svi.z  
    2.47951      0.67953      0.30494     -0.14146      0.21015      0.30520  
      lcp.z    gleason.z      pgg45.z  
   -0.28849     -0.02131      0.26696  

> pr.z.lm<-.Last.value
> summary(pr.z.lm)

Call:
lm(formula = lpsa ~ lcavol.z + lweight.z + age.z + lbph.z + svi.z + 
    lcp.z + gleason.z + pgg45.z, data = pr.z.train)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.64870 -0.34147 -0.05424  0.44941  1.48675 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  2.47951    0.08963  27.665  < 2e-16 ***
lcavol.z     0.67953    0.12663   5.366 1.47e-06 ***
lweight.z    0.30494    0.11086   2.751  0.00792 ** 
age.z       -0.14146    0.10134  -1.396  0.16806    
lbph.z       0.21015    0.10222   2.056  0.04431 *  
svi.z        0.30520    0.12360   2.469  0.01651 *  
lcp.z       -0.28849    0.15453  -1.867  0.06697 .  
gleason.z   -0.02131    0.14525  -0.147  0.88389    
pgg45.z      0.26696    0.15361   1.738  0.08755 .  
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1 

Residual standard error: 0.7123 on 58 degrees of freedom
Multiple R-Squared: 0.6944,	Adjusted R-squared: 0.6522 
F-statistic: 16.47 on 8 and 58 DF,  p-value: 2.042e-12 

> mean(pr.z.train$lpsa)
[1] 2.452345
> mean(prostate.frame$lpsa)
[1] 2.478387
> pr.z.test = subset(prostate.z.frame,train=="0",select=c(lpsa,lcavol.z,lweight.z,age.z,lbph.z,svi.z,lcp.z,gleason.z,pgg45.z))
> dim(pr.z.test)
[1] 30  9
> is.data.frame(pr.z.test)
[1] TRUE
> x=cbind(pr.z.test$lcavol.z,pr.z.test$lweight.z,pr.z.test$age.z,pr.z.test$lbph.z,pr.z.test$svi.z,pr.z.test$lcp.z,pr.z.test$gleason.z,pr.z.test$pgg45.z)
> dim(x)
[1] 30  8
> test.fitted = x %*% coef(pr.z.lm)
Error in x %*% coef(pr.z.lm) : non-conformable arguments
> coef(pr.z.lm)
(Intercept)    lcavol.z   lweight.z       age.z      lbph.z       svi.z 
 2.47951205  0.67952814  0.30494116 -0.14146483  0.21014656  0.30520060 
      lcp.z   gleason.z     pgg45.z 
-0.28849277 -0.02130504  0.26695576 
> x=cbind(rep(1,30),x)
> dim(x)
[1] 30  9
> test.fitted = x %*% coef(pr.z.lm)
> sum((lpsa-test.fitted)^2)
[1] 17.58988
> .Last.value/30
[1] 0.5863292
> sum((lpsa-2.47951205)^2)/30
[1] 1.052896 
> test.x=x
> rm(x)
> save.image(jan16)
> q()