rm(list=ls())
cat("\014")
dat4 = read.csv("D:/Users/cse/Downloads/dat4.csv")
attach(dat4)
head(dat4)
## ID Company Concentration
## 1 1 A 101.09
## 2 2 A 99.95
## 3 3 A 101.37
## 4 4 A 102.94
## 5 5 A 99.78
## 6 6 A 99.78
str(dat4)
## 'data.frame': 100 obs. of 3 variables:
## $ ID : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Company : chr "A" "A" "A" "A" ...
## $ Concentration: num 101.1 100 101.4 102.9 99.8 ...
Company=as.factor(Company)
Concentration = as.factor(Concentration)
sd(dat4$Concentration)
## [1] 1.797305
summary(dat4)
## ID Company Concentration
## Min. : 1.00 Length:100 Min. : 96.02
## 1st Qu.: 25.75 Class :character 1st Qu.: 98.89
## Median : 50.50 Mode :character Median : 99.98
## Mean : 50.50 Mean :100.02
## 3rd Qu.: 75.25 3rd Qu.:101.17
## Max. :100.00 Max. :103.97
max = 103.97
min = 96.02
max - min
## [1] 7.95
Q1 = 98.89
Q3 = 101.17
Q3 - Q1
## [1] 2.28
hist(dat4$Concentration, main = "Distribution of Tablet Concentrations", xlab = "Concentration (mg)", breaks = 10 )
?hist
## starting httpd help server ... done
my_boxplot <- boxplot(Concentration ~ Company,
data = dat4, main = "Tablet Concentrations by Company",
xlab = "Company",
ylab = "Concentration (mg)")
outlier_values <- my_boxplot$out
print(outlier_values)
## [1] 103.53 96.02 97.22
t.test(dat4$Concentration, mu = 100)
##
## One Sample t-test
##
## data: dat4$Concentration
## t = 0.099037, df = 99, p-value = 0.9213
## alternative hypothesis: true mean is not equal to 100
## 95 percent confidence interval:
## 99.66118 100.37442
## sample estimates:
## mean of x
## 100.0178
t.test(Concentration ~ Company, data = subset(dat4, Company %in% c("A", "B")))
##
## Welch Two Sample t-test
##
## data: Concentration by Company
## t = 1.9312, df = 64.692, p-value = 0.05784
## alternative hypothesis: true difference in means between group A and group B is not equal to 0
## 95 percent confidence interval:
## -0.02577558 1.53172923
## sample estimates:
## mean in group A mean in group B
## 99.91176 99.15879
# Perform ANOVA
anova_model <- aov(Concentration ~ Company, data = dat4)
# Display ANOVA table
summary(anova_model)
## Df Sum Sq Mean Sq F value Pr(>F)
## Company 2 55.67 27.836 10.22 9.36e-05 ***
## Residuals 97 264.13 2.723
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
remove