diff --git a/Selected-descriptive-and-inferential-statistics-in-r-for-undergraduate-project b/Selected-descriptive-and-inferential-statistics-in-r-for-undergraduate-project new file mode 100644 index 0000000..8cf2c0a --- /dev/null +++ b/Selected-descriptive-and-inferential-statistics-in-r-for-undergraduate-project @@ -0,0 +1,247 @@ +--- +title: "SELECTED DESCRIPTIVE AND INFERENTIAL STATISTICS IN R FOR UNDERGRADUATE PROJECT" +output: + word_document: default + html_document: + df_print: paged +--- +BEING A PRACTICAL AND DEMONSTRATION SESSION HELD ON THURSDAY, 18TH MAY, 2023 AT STATISTICS DEPARTMENT, THE FEDERAL POLYTECHNIC OFFA + +BY +DR. ABDULKABIR MURITALA + + +# Descriptives Statistics simulation +```{r} +x=rnorm(100) +mean(x) +``` + + +```{r} +var(x) +``` + + +```{r} +sd(x) +``` + + +```{r} +median(x) +``` + + +```{r} +summary(x) +``` + + +```{r} +barplot(x) +``` + + +```{r} +hist(x) +``` + + +```{r} +qqnorm(x) +``` + + +```{r} +boxplot(x) +``` + + +```{r} +dotchart(x) +``` + +#Real life data +```{r} +x=c(1,3,5,6,7,8,9,3,2,4) +y=c(2,3,5,6,7,8,4,3,2,1) +z=c(2,3,4,1,2,5,6,7,8,9) +boxplot(x,y,z) +``` + + +```{r} +boxplot(x,y,z,horizontal=T) +``` + + +```{r} +boxplot(x,y,z,horizontal=T,names=c("A","B","C")) +``` + + +```{r} +boxplot(x,y,z,horizontal=T,names=c("A","B","C"),col=c("red","black","blue")) +``` + + +```{r} +par(mfrow=c(2,2)) +barplot(x,y,z) +hist(x) +``` + +#Inferential Statistics +##chi sqaure +```{r} +data <- matrix(c(100, 70, 20, 90, 75, 25), ncol=3, byrow=TRUE) +colnames(data) <- c("Rep","Dem","Ind") +rownames(data) <- c("Male","Female") +data <- as.table(data) +data +``` + + +```{r} +chisq.test(data) +``` + +#one sample t.test +```{r} +daily.sales=c(5260,5470,5640,6180,6390,6515,6805,7515,7515,8230,8770) +``` + + +```{r} +mean(daily.sales) +``` + + +```{r} +sd(daily.sales) +``` + + +```{r} +quantile(daily.sales) +``` + + +```{r} +t.test(daily.sales) +``` + + +```{r} +t.test(daily.sales,mu=7000) +``` + +#Two sample +```{r} +dat=read.csv("hnd.csv") +attach(dat) +t.test(exp~sex,var.equal=T) +``` + +#Paired sample t-test +```{r} +dat=read.csv("hnd2.csv") +t.test(dat$pre,dat$post,paired=T) +``` + +#Regression +```{r} +x1=runif(50,2,3) +x2=rnorm(50,4,1) +y=2*x1+x2 +dat=data.frame(y,x1,x2) +m1=lm(y~x1+x2,dat) +m1 +``` + +```{r} +summary(m1) +``` + + +```{r} +predict(m1) +``` + +```{r} +plot(y,x1) +``` +#Correlation +```{r} +x1=rnorm(100,2,1) +x2=rnorm(100,2,4) +cor(x1,x2) +``` + + +```{r} +cor.test(x1,x2) +``` + + +```{r} +cor.test(x1,x2,method="spearman") +``` + + +```{r} +cor.test(x1,x2,method="kendall") +``` + +#One way ANOVA +```{r} +x1=runif(50,2,3) +y=2*x1+x1 +anova(lm(y~x1)) +``` +#Two way Anova +```{r} +x1=runif(50,2,3) +x2=rnorm(50,4,1) +y=2*x1+x2 +dat=data.frame(y,x1,x2) +anova(lm(y~x1+x2,dat)) +``` + +#Two way Anova with replication +```{r} +x1=runif(50,2,3) +x2=rnorm(50,4,1) +y=2*x1+x2 +dat=data.frame(y,x1,x2) +anova(lm(y~x1*x2,dat)) +``` + + +#Time series +```{r} +Infla=ts(c(13.8,15.7,3.2,5.4,13.2,34.4,23.7,15.6,16.6),start= c(1970,1)) +plot(Infla) +``` + + +```{r} +acf(Infla) +``` + + +```{r} +pacf(Infla) +``` + + +```{r} +library(tseries) +adf.test(Infla) +``` + + +```{r} +adf.test(diff(Infla)) +```