Script 2

# Exercise

#.1 Give each 10th element of mis_arith1 NA
mis_arith1 <- arith1
mis_arith1[seq(1,150,10)] <- NA

#.2 Add NA to every 17th variable of mis_educ and mis_educf
mis_educ <- educ
mis_educ[seq(1,150,17)] <- NA
mis_educf <- educf
mis_educf[seq(1,150,17)] <- NA

#.3 Add NA to mis_IQ < 85
mis_IQ <- IQ
mis_IQ <- ifelse(mis_IQ < 85, NA, IQ)

#4. Add NA to mis_arith0 if arith0 > 140
mis_arith0 <- ifelse(mis_arith0>140, NA, mis_arith0)
??ifelse
#5. Make indicators for missing elements
ind_educ <- as.numeric(is.na(mis_educ))
ind_IQ <- as.numeric(is.na(mis_IQ))
ind_arith0 <- as.numeric(is.na(mis_arith0))
ind_arith1 <- as.numeric(is.na(mis_arith1))

#6. Make data frame
misdata <- data.frame(ID, method, methodf, sex, sexf, mis_IQ, mis_arith0, mis_arith1, mis_educ, mis_educf, ind_educ, ind_IQ, ind_arith0, ind_arith1)

#7. Give overviews and compare
summary(misdata)
summary(mydata)

#8. Make complete dataframe without the NAs
compdata <- na.omit(misdata)

#9. Give overview of compdata
View(compdata)

#10. Save data frames
save(misdata, file="misdata.Rdata")
save(compdata, file="compdata.Rdata")

#######
# Assignment
#1. load library
library(foreign)

#2. Read data file
worms <- read.spss("C:/Users/Lenovo/Dropbox/Studie/Masters/Blok 1a/R workshop/Worms.sav", to.dataframe="True")

#3. Inspect file
summary(worms)
edit(worms)
name(worms)
# Field.name, Vegetation and Damp are factor, others are numeric

#4. Plot soil against worm density
plot(worms$Soil.pH, worms$Worm.density)

#5. Add straight lines
abline(mean(worms$Worm.density),0)
abline(lm(worms$Worm.density ~ worms$Soil.pH))

#6. Split area by vegetation
areabyveg <- split(worms$Area, worms$Vegetation, drop = "FALSE", sep=".", lex.order="FALSE"); areabyveg
sapply(areabyveg,length)
sapply(areabyveg,mean)
boxplot(areabyveg, col="lavender", notch = FALSE, varwidth = TRUE)
# I've inserted notch = "FALSE" because TRUE gave an error but I'm not sure what this function does

#7. Tidy up
rm(areabyveg)

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

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...
Meer lezen