Script 1

#1. Set random seed to a fixed number
set.seed(631)

#2. Create IDs
ID <- c(1:150)

#3. Random assignment of instruction method
method <- rbinom(150,1,0.5)
methodf <- factor(method,labels=c("A", "B"))

#4. Sex of the child
sex <-rbinom(150,1,0.4)
sexf <-factor(sex,labels=c("girl", "boy"))

#5. Take random sample
library(MASS)
mu <- c(100,130)
sigma <- matrix(c(64,40,40,100),2,2)
X <- mvrnorm(150,mu,sigma)
X <- round(X,digits=0)
colnames(X) <- c("IQ","arith0")
IQ <- cbind(X[,1])
arith0 <- cbind(X[,2])
arith0 <- round(arith0)

#6. Generate normally distributed variables
e1 <- rnorm(150,0,3)
e2 <- rnorm(150,0,3)
e3 <- rnorm(150,0,3)

#7. Compute the arithmetic score after one year
arith1 = round(0.8*method + 0.3*(arith0 + e1) + 1.5*(IQ + e2) + 0.6*sex + e3, 0)

#8. Parental education
Xeduc <- rmultinom(150, 1, c(0.3, 0.5, 0.2))
Xeduct <-t(Xeduc)
v<-c(0,1,2)
educ <- Xeduct %*% v
educf <- factor(educ,labels=c("low","middle","high"))

#9. Store variables in dataframe
mydata <- data.frame(ID, method, methodf, sex, sexf, IQ, arith0, arith1, educ, educf); mydata

#10. Save data
save(mydata, file="mydata.Rdata")

Reacties

Een reactie posten

Populaire posts van deze blog

Script 3

#Exercise load("misdata.Rdata") names(misdata) misdata$educ <- NULL; misdata$educ misdata2 <- misdata[,-c(2:4,7,8)] names(misdata2) save(misdata2, file="misdata2.Rdata") table(misdata$mydata.sex) #Exercise 3.1 #1. table(misdata$mis_educf) # missing values are not counted #2. Create table of gender x educf table(misdata$mydata.sexf, misdata$mis_educf) table(misdata$mydata.sexf, misdata$mydata.methodf) #3. proportions instead of frequencies prop.table(table(misdata$mydata.sexf, misdata$mis_educf),1) prop.table(table(misdata$mydata.sexf, misdata$mis_educf),2) prop.table(table(misdata$mydata.sexf, misdata$mis_educf)) #if a number is given behind a comma, the values will be a proportion of that number #if no number is given, the values will be a proportion of the sum of all values in the table #4. bonus prop table prop.table(table(misdata$mydata.sexf, misdata$mis_educf, exclude=NULL)) #the NAs are treated as a different category alltogeth...
Meer lezen

Script 5

#Exercise 5.1 #1 define improve improve <- (misdata$mis_arith1 - misdata$mis_arith0) misdata$improve <- improve #2. scatterplot plot(improve ~ misdata$mis_IQ) # relationship is linear, higher IQ score predicts larger improvement #3. ??lm #4. model1 <- lm(improve ~ misdata$mis_IQ); model1 #5.ask summary summary(model1) # IQ is a significant predictor of improvement on arithmetic test score #6. ??abline abline(model1) #7. model2 <- lm(improve~misdata$mis_IQ, na.action=na.exclude) ??na.exclude summary(model2) #there is no difference in the two models, hence na.exclude is the default #8. fittie <- fitted(model1); fittie fittie2<- fitted(model2); fittie2 resid <- resid(model1); resid resid2<-resid(model2); resid2 #model 1 does not include NAs anymore, they were deleted. model 2 does include NAs #so the function na.exclude just excludes the NAs from analysis but leaves them in #9. qqnorm(resid); qqline(resid) # residuals seem light taile...
Meer lezen