D8_1 <- read.table(“C:/Users/keith/Desktop/Data_Table_8.1.txt”,sep = “\t”,fill = TRUE, header=TRUE)
##Still NAs. Scrape all dorsal widths and throw into one vector via concatenate.
Full_Data<-c(D8_1[1:8,1],D8_1[1:10,2],D8_1[1:13,3],D8_1[1:6,4])
HostNum<-c(rep(1,8),rep(2,10),rep(3,13),rep(4,6))
Tick_data<-data.frame(Width=Full_Data,Host=as.factor(HostNum))
res.aov<-aov(Width~Host, data=Tick_data)
summary(res.aov) #1.a Answer
qf(.05, 3, 33, lower.tail=FALSE)
#1.b As our F-Statistic is greater than this critical value of 2.892, we reject the test’s null hypothesis and conclude that there is an association between host and width.
pairwise.t.test(Tick_data$Width,Tick_data$Host)
#1.c Via the pairwise T Test, it appears that Host 1 is statistically different from hosts 2 and 3, and none of the other pairwise relationships differ.
——-
D5a <- D5a <- read.delim(“C:/Users/keith/Desktop/5a_Work_Income_and_economic_activity_aov.txt”)
D5a$Continent <- factor(D5a$Continent)
res.aov2<-aov(GDPpercapita~Continent, data=D5a)
summary(res.aov2)
##2.a As the p-value is less than 0.05, we reject the null hypothesis and conclude that there is a difference in GDP among continents.
pairwise.t.test(D5a$GDPpercapita, D5a$Continent)
##2.b The p-values are less than 0.05 for the following pairs: Africa-America; Africa-Eurasia; Americas-Eurasia; Eurasia-SEAsia. The differences are statistically significant between these pairs of continents.
D5a$Sex<-factor(D5a$Sex)
res.aov3<-aov(EconActivity~Continent+Sex, data=D5a)
summary(res.aov3)
##2.c As the p-value for the sex term is less than 0.05, we reject the null hypothesis. Therefore, holding constant the continent, the effect of sex does have an impact on the Economic Activity in that continent.
Here is the second answer”