Diamonds_Data <- read.csv("D:/Downloads/Diamonds_Data.csv")
View(Diamonds_Data)
attach(Diamonds_Data)
names(Diamonds_Data)
## [1] "Carat" "Cut"
boxplot(Carat ~ Cut)
# Ho - Carat is same for all Cut
aov(Carat ~ Cut)
## Call:
## aov(formula = Carat ~ Cut)
##
## Terms:
## Cut Residuals
## Sum of Squares 1.282353 2.452907
## Deg. of Freedom 3 56
##
## Residual standard error: 0.209289
## Estimated effects may be unbalanced
Anova1 <- aov(Carat ~ Cut)
summary(Anova1)
## Df Sum Sq Mean Sq F value Pr(>F)
## Cut 3 1.282 0.4275 9.759 2.81e-05 ***
## Residuals 56 2.453 0.0438
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
attributes(Anova1)
## $names
## [1] "coefficients" "residuals" "effects" "rank"
## [5] "fitted.values" "assign" "qr" "df.residual"
## [9] "contrasts" "xlevels" "call" "terms"
## [13] "model"
##
## $class
## [1] "aov" "lm"
Anova1$coefficients
## (Intercept) CutGood CutIdeal CutPremium
## 0.6866667 -0.2266667 -0.3233333 -0.3846667
summary(Anova1)
## Df Sum Sq Mean Sq F value Pr(>F)
## Cut 3 1.282 0.4275 9.759 2.81e-05 ***
## Residuals 56 2.453 0.0438
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
TukeyHSD(Anova1)
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Carat ~ Cut)
##
## $Cut
## diff lwr upr p adj
## Good-Fair -0.22666667 -0.4290223 -0.02431100 0.0223331
## Ideal-Fair -0.32333333 -0.5256890 -0.12097767 0.0004937
## Premium-Fair -0.38466667 -0.5870223 -0.18231100 0.0000310
## Ideal-Good -0.09666667 -0.2990223 0.10568900 0.5887892
## Premium-Good -0.15800000 -0.3603557 0.04435567 0.1764082
## Premium-Ideal -0.06133333 -0.2636890 0.14102233 0.8529311
plot(TukeyHSD(Anova1))
plot(TukeyHSD(Anova1), las=1)
kruskal.test(Carat ~ Cut)
##
## Kruskal-Wallis rank sum test
##
## data: Carat by Cut
## Kruskal-Wallis chi-squared = 15.78, df = 3, p-value = 0.001258