Q
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE)
allx
nox
Q
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
debug(weightedDotPlotGroup)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE)
length(xnum)
table(xnum)
nox
Q
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
debug(weightedDotPlotGroup)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE)
table(xnum)
dim(freq)
nox
graphy[i]
nox
Q
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE)
debug(weightedDotPlotGroup)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE)
summary(freq)
head(freq)
freq=table(y,x)
head(freq)
colSums(freq)
 freq=freq/mean(freq)
mean(freq)
freq=table(y,x)
mean(freq)
warnings()
c
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20)
?plot
?par
?plot
?title
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.axis=.6)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.title=.6)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.title=.26)
?par
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.26)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
n
meany
Q
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
?axis
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
?axis
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,cex.lab=.06)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20)
?axis
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,las=1)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='Genre',ylab='Correct',showmeans=TRUE,scale=20,las=2)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.1),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
?par
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,mai=c(.5,2,0,0))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,mai=c(5,5,,0,0))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,mai=c(5,5,0,0))
?par
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,mai=c(5,0,0,0))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,pin=c(3,3))
plot(1:16)
plot(1:16,mai=c(5,5,0,0))
par(mai=c(5,5,0,0))
plot(1:16)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,pin=c(3,3))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2)
source('~/meetings_workshops/Rmodeling/basicFunctions.r')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.02),xlab='',ylab='Correct',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
??pdf
?pdf
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
fit=lm(PctCorrect~GENRE,data=it)
head(it)
fit=lm(PctCorrect~GENRE..AMG.,data=it)
fit
coef(fit)
predict(fit,data.frame(GENRE..AMG.='Blues'))
predict(fit,data.frame(GENRE..AMG.=I('Blues')))
str(it)
it$genre=as.factor(it$GEN)
head(it)
fit=lm(PctCorrect~genre,data=it)
coef(fit)
predict(fit,data.frame(genre='blues'))
predict(fit,data.frame(genre='Blues'))
predict(fit,data.frame(genre=unique(it$genre)))
predict(fit,data.frame(genre=unique(it$genre)),)
head(study3)
predict(fit,data.frame(genre=unique(it$genre)),interval='prediction')
predict(fit,data.frame(genre=unique(it$genre)),interval='confidence')
pred=predict(fit,data.frame(genre=unique(it$genre)),interval='confidence')
lines(pred$fit)
lines(pred[,'fit'])
pred=data.frame(genre=unique(it$genre))
pred
rownames(pred)=pred[,1]
fill=data.frame(genre=unique(it$genre))
rownames(fill)=fill[,1]
pred=predict(fit,newdata=fill,interval='confidence')
pred
order(rownames(pred))
pred=predict(fit,newdata=fill[ord,],interval='confidence')
ord=order(rownames(pred))
pred
pred[ord,]
pred=pred[ord,]
lines(pred[,'fit'])
lines(pred[,'lwr'])
lines(pred[,'upr'])
fit=lm(PctCorrect~GENRE,data=it)
weightedDotPlot(study3$Tessitura,study3$Authority,ylim=c(1,5.5),xlim=c(1,7.5),scale=2,xlab='Tessitura',ylab='Authority',showmeans=TRUE)
fit=lm(PctCorrect~GENRE,data=it)
weightedDotPlotGroup(x=study3$Gender,y=study3$Authority,ylim=c(0,5.5),xlab='Gender',ylab='Auth',showmeans=TRUE)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,5.5),xlab='Gender',ylab='Auth',showmeans=TRUE)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,7.5),xlab='Gender',ylab='Auth',showmeans=TRUE)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Auth',showmeans=TRUE)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority',showmeans=TRUE)
box()
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority')
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority',scale=2)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority',scale=.2)
weightedDotPlotGroup(x=study3$Authority,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority',scale=.5)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Authority',scale=.2)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1)
box()
graphics.off()
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1)
weightedDotPlotGroup(x=study3$Authority,y=study3$Tessitura,ylim=c(0,8),xlab='Authority',ylab='Tessitura',scale=1)
weightedDotPlotGroup(x=study3$Authority,y=study3$Tessitura,ylim=c(0,8),xlab='Authority',ylab='Tessitura',scale=1,showmeans=TRUE)
weightedDotPlot(x=study3$Authority,y=study3$Tessitura,ylim=c(0,8),xlab='Authority',ylab='Tessitura',scale=1,showmeans=TRUE)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',scale=20,las=2,marg=c(2,1,.5,.5))
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1,showmeans)
weightedDotPlotGroup(x=study3$Gender,y=study3$Tessitura,ylim=c(0,8),xlab='Gender',ylab='Tessitura',scale=1,showmeans=TRUE)
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',scale=20,las=2,marg=c(2,1,.5,.5))
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
head(it)
plot(PctCorrect~seconds,data=it)
weightedDotPlotGroup(x=it$seconds,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Length(sec)',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
weightedDotPlot(x=it$seconds,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Length(sec)',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5))
abline(lm(PctCorrect~seconds,data=it))
summary(lm(PctCorrect~seconds,data=it))
lm(PctCorrect~seconds+GENRE..AMG.)
lm(PctCorrect~seconds+GENRE..AMG.,data=it)
coef(lm(PctCorrect~seconds+GENRE..AMG.,data=it))
data.frame(coef(lm(PctCorrect~seconds+GENRE..AMG.,data=it)))
data.frame(coef(lm(PctCorrect~GENRE..AMG.,data=it)))
head(study3)
plot(AverageHigh~AverageLow,data=MusicTempoData)
abline(lm(AverageHigh~AverageLow,data=MusicTempoData))
summary(lm(AverageHigh~AverageLow,data=MusicTempoData))
fit=summary(lm(AverageHigh~AverageLow,data=MusicTempoData))
names(fit)
options(width=80)
names(fit)
options(width=100)
names(fit)
fit$r.squared
fit$residuals
sd(fit$residuals)
2*sd(fit$residuals)
plot(MusicTempoData$AverageLow,fit$res)
abline(h=0)
abline(h=c(3.4,-3.4))
abline(h=c(6.4,-6.4))
plot(AverageHigh~AverageLow,data=MusicTempoData)
abline(lm(AverageHigh~AverageLow,data=MusicTempoData))

coef(fit)
y = slope * x + intercept
67 * .97 + 20.2
fit$r.squared
sqrt(fit$r.squared)
var(MusicTempoData$AverageHigh)
abline(h=mean(MusicTempoData$AverageHigh))
var(fit$residuals)
fit=(lm(AverageHigh~AverageLow,data=MusicTempoData))
sd(fit$residuals)
fitsumm=summary(lm(AverageHigh~AverageLow,data=MusicTempoData))
names(fit)
names(fitsumm)
fit$fitted.values
names(fit)
points(MusicTempoData$AverageLow,fit$fitted.values,col='red')
?predict
?predict.lm
predict.lm(fit,newdata=data.frame(AverageLow=40))
data.frame(AverageLow=40)
data.frame(AverageLow=35:95)
emptydf=data.frame(AverageLow=35:95)

head(emptydf)
predict.lm(fit,newdata=emptydf)
filleddf=data.frame(emptydf,predict.lm(fit,newdata=emptydf))
filleddf
lines(filleddf[,1],filleddf[,2],lwd=2,col='blue')
predict.lm(fit,newdata=emptydf,interval='confidence')
pred=predict.lm(fit,newdata=emptydf,interval='confidence')
head(pred)
lines(35:95,pred$lwr)
lines(35:95,pred[,'lwr'])
lines(35:95,pred$upr)
lines(35:95,pred[,'lw\\upr'])
lines(35:95,pred[,'lwr'])
lines(35:95,pred[,'upr'])
pred2=predict.lm(fit,newdata=emptydf,interval='prediction')
lines(35:95,pred2[,'upr'],lty='dashed')
lines(35:95,pred2[,'lwr'],lty='dashed')
ls()
ls(fit)
pred2=predict.lm(fit,newdata=emptydf,interval='prediction')
pred=predict.lm(fit,newdata=emptydf,interval='confidence')
weightedDotPlotGroup(x=it$GENRE,y=it$Pct,ylim=c(0,1.03),xlab='',ylab='Fraction Correct',showmeans=TRUE,scale=20,las=2,marg=c(2,1,.5,.5
summary(lm(Tessitura~Authority,data=study3))
head(study3)
(lm(Tessitura~Gender,data=study3))
boxplot(Tessitura~Gender,data=study3)
plot(AverageHigh~AverageLow,data=MusicTempoData)
abline(lm(AverageHigh~AverageLow,data=MusicTempoData))
emptydf=data.frame(AverageLow=35:95)
pred2=predict.lm(fit,newdata=emptydf,interval='prediction')
pred=predict.lm(fit,newdata=emptydf,interval='confidence')
lines(35:95,pred2[,'lwr'],lty='dashed')
lines(35:95,pred2[,c('upr','lwr')],lty='dashed')
lines(35:95,pred2[,'lwr'],lty='dashed')
lines(35:95,pred2[,'upr'],lty='dashed')
lines(35:95,pred[,'lwr'],lty='dashed')
lines(35:95,pred[,'upr'],lty='dashed')
head(study3)
lm(Tessitura~Gender,data=study3)
table(study3$Gender)
table(study3$Gender,exclude=NULL)
plot(Tessitura~Gender,data=study3)
table(study3$Gender,study3$Tessitura,exclude=NULL)
var(study3$Tessitura)
var(study3$Tessitura,na.rm=TRUE)
subset(study3,Gender=='M')
var(subset(study3,Gender=='M')$Tessitura)
var(subset(study3,Gender=='M')$Tessitura,na.rm=TRUE)
var(study3$Tessitura,na.rm=TRUE)
var(subset(study3,Gender=='M')$Tessitura,na.rm=TRUE)
var(subset(study3,Gender=='F')$Tessitura,na.rm=TRUE)
mean(study3$Tessitura,na.rm=TRUE)
abline(h=mean(study3$Tessitura,na.rm=TRUE))
sd(study3$Tessitura,na.rm=TRUE)
lm(Tessitura~Gender,data=study3)
emptydf=data.frame(Gender=c('F','M'))
emptydf
fittess=lm(Tessitura~Gender,data=study3)
emptydf=data.frame(Gender=c('F','M'))
predict.lm(fittess,newdata=emptydf,interval='confidence')
predict.lm(fittess,newdata=emptydf,interval='prediction')
coef(fittess)
summary(fittess)
ls(fittess)
head(study3)
fit=lm(Authority~Tessitura,data=study3)
summary(fit)
plot(Authority~Tessitura,data=study3)
plot(Authority~Tessitura,data=study3,cex=1.5)
abline(fit)
emptydf=data.frame(Tessitura=1:7)
emptydf
emptydf=data.frame(1:7)
emptydf
emptydf=data.frame(Tessitura=1:7)
emptydf
predict.lm(fit,newdata=emptydf)
predict.lm(fit,newdata=emptydf,interval='confidence')
lines(emptydf$Tessitura,pred[,2])
pred=predict.lm(fit,newdata=emptydf,interval='confidence')
pred
lines(emptydf$Tessitura,pred[,2])
lines(emptydf$Tessitura,pred[,3])
for(i in 1:3) lines(emptydf$Tessitura,pred[,2])
for(i in 1:3) lines(emptydf$Tessitura,pred[,i],col='red')
pred=predict.lm(fit,newdata=emptydf,interval='prediction')
for(i in 1:3) lines(emptydf$Tessitura,pred[,i],col='blue')
head(study3)
fit=lm(Authority~Tessitura+Age,data=study3)
summary(fit)
fit=lm(Authority~Tessitura,data=study3)
fit2=lm(Authority~Tessitura+Age,data=study3)
coef(fit)
coef(fit2)
Authority = 2.04 + .048*Age - .118*Tessitura
table(study3$Age)
summary(study3$Age)
plot(Authority~Tessitura,data=study3,cex=1.5)
abline(2.04,-.118)
abline(4.02,-.2)
abline(fit)
.048*33
abline(2.04+1.58,-.118)
abline(2.04+1.58,-.118,col='red')
abline(2.04+.048*65,-.118,col='red')
abline(2.04+.048*0,-.118,col='red')
points(Authority~Tessitura,data=subset(study3,Age<25),pch=16)
points(Authority~Tessitura,data=subset(study3,Age>55),pch=16,col='blue')
points(Authority~Tessitura,data=subset(study3,Age<20),pch=16,col='green')
abline(fit)
summary(fit2)
summary(study3$Age)
fithigh=lm(Authority~Tessitura,data=subset(study3,Age>=42.5))
abline(fithigh,col='blue')
summary(fithigh)
fitlow=lm(Authority~Tessitura,data=subset(study3,Age<=25))
summary(fitlow)
abline(fitlow,col='green')
summary(fit2)
study3457file="~/meetings_workshops/Rmodeling/data/3457.csv"
x=read.delim(study3457file)
head(x)
str(x)
table(x$Meter)
table(x$Participant)
table(x$Pref,exclude=NULL)
table(x$Exp,exclude=NULL)
head(x)
as.numeric('2a')
table(x$Meter)
table(x$Meter,exclude=NULL)
head(x)
lm(Preference~Experience+Meter,data=x)
lm(Preference~Meter,data=x)
fit1=lm(Preference~Meter,data=x)
summary(fit1)$coef
plot(Preference~Meter,data=x)
fit2=lm(Preference~Meter+Experience,data=x)
summary(fit2)$coef
names(fit1)
fitMeter=lm(Preference~Meter+Experience,data=x)
fit1=lm(Preference~Meter,data=x)
warnings()
fit1=lm(Preference~Meter,data=x)
warnings()
emptydf=data.frame(Meter=c('Five','Four','Three','Seven'))
emptydf
predict.lm(fit2,newdata=emptydf)
emptydf=data.frame(Meter=c('Five','Four','Three','Seven'),Experience=c(1,1,1,1)))
emptydf=data.frame(Meter=c('Five','Four','Three','Seven'),Experience=c(1,1,1,1))
emptydf
predict.lm(fit2,newdata=emptydf)
rep(unique(x$Meter),10)
rep(unique(x$Meter),2)
unique(x$Meter)
rep(unique(x$Meter),2)
emptydf=data.frame(Meter=rep(unique(x$Meter),2),Experience=c(1,1,1,1,5,5,5,5))
emptydf
predict.lm(fit2,newdata=emptydf)
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter='Five')
emptydf
predict.lm(fit1,newdata=emptydf)
emptydf=data.frame(Meter=c('Five','Four','Seven'))
emptydf
predict.lm(fit1,newdata=emptydf)
coef(fit1)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
predict.lm(fit1,newdata=emptydf)
rbind(emptydf,predict.lm(fit1,newdata=emptydf))
cbind(emptydf,predict.lm(fit1,newdata=emptydf))
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf))
plot(x$Preference,x$Meter)
plot(x$Meter,x$Preference)
plot(x$Meter,x$Preference,xlab='Meter')
plot(x$Preference,x$Meter)
table(x$Preference,x$Meter)
cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
emptydf
predict.lm(fit1,newdata=emptydf,interval='confidence')
cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
plot(x$Meter,x$Preference,xlab='Meter')
coef(fit1)
mean(subset(x,Meter=='Four)$Preference)
'
'
mean(subset(x,Meter=='Four')$Preference)
mean(subset(x,Meter=='Five')$Preference)
tapply(x$Preference,x$Meter,mean)
tapply(x$Preference,x$Meter,median)
tapply(x$Preference,x$Meter,sd)
cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
emptydf
summary(fit2)
fit2=lm(Preference~Meter+Experience,data=x)
plot(Preference~Meter+Experience,data=x)
boxplot(Preference~Meter+Experience,data=x)
plot(Preference~Meter+Experience,data=x)
table(x$Preference,x$Meter)
table(x$Preference,x$Meter)
plot(Preference~Meter,data=x)
abline(v=1)
abline(v=2)
freq=table(x$Preference,x$Meter)
freq
freq[,1]
points(rep(1,7),1:7,cex=freq[,1])
rep(1,7)
1:7
points(rep(1,7),1:7,cex=freq[,1]/5)
plot(Preference~Meter,data=x)
points(rep(1,7),1:7,cex=freq[,1]/5)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
?arrow
?arrows
arrows(1,4,1,4.29)
?arrows
arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,2],length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,3],length=.1,col='red',lwd=2)
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,2],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,3],length=.1,col='blue',lwd=2)
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
pred
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,1],i,pred[i,4],length=.1,col='blue',lwd=2)
pred[i,1]
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
fit2=lm(Preference~Meter+Experience,data=x)
summary(fit2)
plot(Preference~Meter,data=x)
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
freq=table(x$Preference,x$Meter)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
# arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
# arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
points(1:4,pred[,2],pch=16,col='blue',cex=1.5)
plot(1:7,xlim=c(.5,4.5))
plot(1:7,xlim=c(.5,4.5),col='white')
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
freq=table(x$Preference,x$Meter)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
points(1:4,pred[,2],pch=16,col='blue',cex=1.5)
# arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
# arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
plot(1:7,xlim=c(.5,4.5),col='white',xlab='Meter',ylab='Preference')
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
freq=table(x$Preference,x$Meter)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
points(1:4,pred[,2],pch=16,col='blue',cex=1.5)
# arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
# arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
plot(1:7,xlim=c(.5,4.5),col='white',xlab='Meter',ylab='Preference',axes=FALSE)
axis(1,at=1:4,labels=c('Five','Four','Seven','Three'))
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
freq=table(x$Preference,x$Meter)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
points(1:4,pred[,2],pch=16,col='blue',cex=1.5)
# arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
# arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
plot(1:7,xlim=c(.5,4.5),col='white',xlab='Meter',ylab='Preference',axes=FALSE)
axis(1,at=1:4,labels=c('Five','Four','Seven','Three'))
axis(2)
box()
fit1=lm(Preference~Meter,data=x)
emptydf=data.frame(Meter=c('Five','Four','Seven','Three'))
pred=cbind(emptydf,pred=predict.lm(fit1,newdata=emptydf,interval='confidence'))
freq=table(x$Preference,x$Meter)
for(i in 1:4) points(rep(i,7),1:7,cex=freq[,i]/5)
points(1:4,pred[,2],pch=16,col='blue',cex=1.5)
# arrows(1,4,1,4.29,length=.1,col='red',lwd=2)
# arrows(1,4,1,3.71,length=.1,col='red',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,3],length=.1,col='blue',lwd=2)
for(i in 1:4) arrows(i,pred[i,2],i,pred[i,4],length=.1,col='blue',lwd=2)
savehistory('~/meetings_workshops/Rmodeling/OSU/history/hist9May.txt')