Chapter#1 : Descriptive Statistics and Graphics
Import your data into R Here, we’ll use the built-in R data set named iris.
# Store the data in the variable my_data
my_data <- iris
Check your data
You can inspect your data using the functions head() and tails(), which will display the first and the last part of the data, respectively.
# Print the first 6 rows
head(my_data, 6)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
Measure of variablity
Measures of variability gives how “spread out” the data are.
Range: minimum & maximum
# Compute the minimum value
min(my_data$Sepal.Length)
## [1] 4.3
# Compute the maximum value
max(my_data$Sepal.Length)
## [1] 7.9
# Range
range(my_data$Sepal.Length)
## [1] 4.3 7.9
Interquartile range
R function:
quantile(my_data$Sepal.Length)
## 0% 25% 50% 75% 100%
## 4.3 5.1 5.8 6.4 7.9
#To compute deciles (0.1, 0.2, 0.3, …., 0.9), use this:
quantile(my_data$Sepal.Length, seq(0, 1, 0.1))
## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 4.30 4.80 5.00 5.27 5.60 5.80 6.10 6.30 6.52 6.90 7.90
#To compute the interquartile range, type this:
IQR(my_data$Sepal.Length)
## [1] 1.3
Variance and standard deviation
# Compute the variance
var(my_data$Sepal.Length)
## [1] 0.6856935
# Compute the standard deviation =
# square root of th variance
sd(my_data$Sepal.Length)
## [1] 0.8280661
Median absolute deviation
# Compute the median
median(my_data$Sepal.Length)
## [1] 5.8
# Compute the median absolute deviation
mad(my_data$Sepal.Length)
## [1] 1.03782
summary() function
summary(my_data$Sepal.Length)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.300 5.100 5.800 5.843 6.400 7.900
summary(my_data, digits = 1)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## Min. :4 Min. :2 Min. :1 Min. :0.1 setosa :50
## 1st Qu.:5 1st Qu.:3 1st Qu.:2 1st Qu.:0.3 versicolor:50
## Median :6 Median :3 Median :4 Median :1.3 virginica :50
## Mean :6 Mean :3 Mean :4 Mean :1.2
## 3rd Qu.:6 3rd Qu.:3 3rd Qu.:5 3rd Qu.:1.8
## Max. :8 Max. :4 Max. :7 Max. :2.5
# Compute the mean of each column
sapply(my_data[, -5], mean)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 5.843333 3.057333 3.758000 1.199333
# Compute quartiles
sapply(my_data[, -5], quantile)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 0% 4.3 2.0 1.00 0.1
## 25% 5.1 2.8 1.60 0.3
## 50% 5.8 3.0 4.35 1.3
## 75% 6.4 3.3 5.10 1.8
## 100% 7.9 4.4 6.90 2.5
Comparing Means in R One-Sample T-test in R
set.seed(1234)
my_data <- data.frame(
name = paste0(rep("M_", 10), 1:10),
weight = round(rnorm(10, 20, 2), 1)
)
head(my_data, 10)
## name weight
## 1 M_1 17.6
## 2 M_2 20.6
## 3 M_3 22.2
## 4 M_4 15.3
## 5 M_5 20.9
## 6 M_6 21.0
## 7 M_7 18.9
## 8 M_8 18.9
## 9 M_9 18.9
## 10 M_10 18.2
# Statistical summaries of weight
summary(my_data$weight)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 15.30 18.38 18.90 19.25 20.82 22.20
Visualize your data using box plots
library(ggpubr)
## Warning: package 'ggpubr' was built under R version 4.3.2
## Loading required package: ggplot2
ggboxplot(my_data$weight,
ylab = "Weight (g)", xlab = FALSE,
ggtheme = theme_minimal())
Preleminary test to check one-sample t-test assumptions
shapiro.test(my_data$weight) # => p-value = 0.6993
##
## Shapiro-Wilk normality test
##
## data: my_data$weight
## W = 0.9526, p-value = 0.6993
# One-sample t-test
res <- t.test(my_data$weight, mu = 25)
# Printing the results
res
##
## One Sample t-test
##
## data: my_data$weight
## t = -9.0783, df = 9, p-value = 7.953e-06
## alternative hypothesis: true mean is not equal to 25
## 95 percent confidence interval:
## 17.8172 20.6828
## sample estimates:
## mean of x
## 19.25
One-Sample Wilcoxon Signed Rank Test in R
# One-sample wilcoxon test
res <- wilcox.test(my_data$weight, mu = 25)
## Warning in wilcox.test.default(my_data$weight, mu = 25): cannot compute exact
## p-value with ties
# Printing the results
res
##
## Wilcoxon signed rank test with continuity correction
##
## data: my_data$weight
## V = 0, p-value = 0.005793
## alternative hypothesis: true location is not equal to 25
# print only the p-value
res$p.value
## [1] 0.005793045
Unpaired Two-Samples T-test in R
# Data in two numeric vectors
women_weight <- c(38.9, 61.2, 73.3, 21.8, 63.4, 64.6, 48.4, 48.8, 48.5)
men_weight <- c(67.8, 60, 63.4, 76, 89.4, 73.3, 67.3, 61.3, 62.4)
# Create a data frame
my_data <- data.frame(
group = rep(c("Woman", "Man"), each = 9),
weight = c(women_weight, men_weight)
)
# Print all data
print(my_data)
## group weight
## 1 Woman 38.9
## 2 Woman 61.2
## 3 Woman 73.3
## 4 Woman 21.8
## 5 Woman 63.4
## 6 Woman 64.6
## 7 Woman 48.4
## 8 Woman 48.8
## 9 Woman 48.5
## 10 Man 67.8
## 11 Man 60.0
## 12 Man 63.4
## 13 Man 76.0
## 14 Man 89.4
## 15 Man 73.3
## 16 Man 67.3
## 17 Man 61.3
## 18 Man 62.4
# Plot weight by group and color by group
library("ggpubr")
ggboxplot(my_data, x = "group", y = "weight",
color = "group", palette = c("#00AFBB", "#E7B800"),
ylab = "Weight", xlab = "Groups")
Preleminary test to check independent t-test assumptions
# Shapiro-Wilk normality test for Men's weights
with(my_data, shapiro.test(weight[group == "Man"]))# p = 0.1
##
## Shapiro-Wilk normality test
##
## data: weight[group == "Man"]
## W = 0.86425, p-value = 0.1066
# Shapiro-Wilk normality test for Women's weights
with(my_data, shapiro.test(weight[group == "Woman"])) # p = 0.6
##
## Shapiro-Wilk normality test
##
## data: weight[group == "Woman"]
## W = 0.94266, p-value = 0.6101
# T_test
res.ftest <- var.test(weight ~ group, data = my_data)
res.ftest
##
## F test to compare two variances
##
## data: weight by group
## F = 0.36134, num df = 8, denom df = 8, p-value = 0.1714
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.08150656 1.60191315
## sample estimates:
## ratio of variances
## 0.3613398
Unpaired Two-Samples Wilcoxon Test in R
res <- wilcox.test(women_weight, men_weight)
## Warning in wilcox.test.default(women_weight, men_weight): cannot compute exact
## p-value with ties
res
##
## Wilcoxon rank sum test with continuity correction
##
## data: women_weight and men_weight
## W = 15, p-value = 0.02712
## alternative hypothesis: true location shift is not equal to 0
Paired Samples T-test in R
#Data in two numeric vectors
# ++++++++++++++++++++++++++
# Weight of the mice before treatment
before <-c(200.1, 190.9, 192.7, 213, 241.4, 196.9, 172.2, 185.5, 205.2, 193.7)
# Weight of the mice after treatment
after <-c(392.9, 393.2, 345.1, 393, 434, 427.9, 422, 383.9, 392.3, 352.2)
# Create a data frame
my_data <- data.frame(
group = rep(c("before", "after"), each = 10),
weight = c(before, after)
)
# Print all data
print(my_data)
## group weight
## 1 before 200.1
## 2 before 190.9
## 3 before 192.7
## 4 before 213.0
## 5 before 241.4
## 6 before 196.9
## 7 before 172.2
## 8 before 185.5
## 9 before 205.2
## 10 before 193.7
## 11 after 392.9
## 12 after 393.2
## 13 after 345.1
## 14 after 393.0
## 15 after 434.0
## 16 after 427.9
## 17 after 422.0
## 18 after 383.9
## 19 after 392.3
## 20 after 352.2
library("dplyr")
## Warning: package 'dplyr' was built under R version 4.3.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
group_by(my_data, group) %>%
summarise(
count = n(),
mean = mean(weight, na.rm = TRUE),
sd = sd(weight, na.rm = TRUE)
)
## # A tibble: 2 × 4
## group count mean sd
## <chr> <int> <dbl> <dbl>
## 1 after 10 394. 29.4
## 2 before 10 199. 18.5
# Compute t-test
res <- t.test(before, after, paired = TRUE)
res
##
## Paired t-test
##
## data: before and after
## t = -20.883, df = 9, p-value = 6.2e-09
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -215.5581 -173.4219
## sample estimates:
## mean difference
## -194.49
Paired Samples Wilcoxon Test in R
# Compute t-test
res <- wilcox.test(weight ~ group, data = my_data, paired = TRUE)
res
##
## Wilcoxon signed rank exact test
##
## data: weight by group
## V = 55, p-value = 0.001953
## alternative hypothesis: true location shift is not equal to 0
# print only the p-value
res$p.value
## [1] 0.001953125
One-Way ANOVA Test in R
my_data <- PlantGrowth
set.seed(1234)
dplyr::sample_n(my_data, 10)
## weight group
## 1 6.15 trt2
## 2 3.83 trt1
## 3 5.29 trt2
## 4 5.12 trt2
## 5 4.50 ctrl
## 6 4.17 trt1
## 7 5.87 trt1
## 8 5.33 ctrl
## 9 5.26 trt2
## 10 4.61 ctrl
my_data$group <- ordered(my_data$group,
levels = c("ctrl", "trt1", "trt2"))
library(dplyr)
group_by(my_data, group) %>%
summarise(
count = n(),
mean = mean(weight, na.rm = TRUE),
sd = sd(weight, na.rm = TRUE)
)
## # A tibble: 3 × 4
## group count mean sd
## <ord> <int> <dbl> <dbl>
## 1 ctrl 10 5.03 0.583
## 2 trt1 10 4.66 0.794
## 3 trt2 10 5.53 0.443
# Compute the analysis of variance
aov(weight ~ group, data = my_data)
## Call:
## aov(formula = weight ~ group, data = my_data)
##
## Terms:
## group Residuals
## Sum of Squares 3.76634 10.49209
## Deg. of Freedom 2 27
##
## Residual standard error: 0.6233746
## Estimated effects are balanced
Two-Way ANOVA Test in R
# Store the data in the variable my_data
my_data <- ToothGrowth
# Show a random sample
set.seed(1234)
dplyr::sample_n(my_data, 10)
## len supp dose
## 1 21.5 VC 2.0
## 2 17.3 VC 1.0
## 3 27.3 OJ 2.0
## 4 18.5 VC 2.0
## 5 8.2 OJ 0.5
## 6 26.4 OJ 1.0
## 7 25.8 OJ 1.0
## 8 5.2 VC 0.5
## 9 6.4 VC 0.5
## 10 9.4 OJ 0.5
# Check the structure
str(my_data)
## 'data.frame': 60 obs. of 3 variables:
## $ len : num 4.2 11.5 7.3 5.8 6.4 10 11.2 11.2 5.2 7 ...
## $ supp: Factor w/ 2 levels "OJ","VC": 2 2 2 2 2 2 2 2 2 2 ...
## $ dose: num 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ...
# Convert dose as a factor and recode the levels
# as "D0.5", "D1", "D2"
my_data$dose <- factor(my_data$dose,
levels = c(0.5, 1, 2),
labels = c("D0.5", "D1", "D2"))
head(my_data)
## len supp dose
## 1 4.2 VC D0.5
## 2 11.5 VC D0.5
## 3 7.3 VC D0.5
## 4 5.8 VC D0.5
## 5 6.4 VC D0.5
## 6 10.0 VC D0.5
table(my_data$supp, my_data$dose)
##
## D0.5 D1 D2
## OJ 10 10 10
## VC 10 10 10
# Box plot with multiple groups
# +++++++++++++++++++++
# Plot tooth length ("len") by groups ("dose")
# Color box plot by a second group: "supp"
library("ggpubr")
ggboxplot(my_data, x = "dose", y = "len", color = "supp",
palette = c("#00AFBB", "#E7B800"))
res.aov2 <- aov(len ~ supp + dose, data = my_data)
summary(res.aov2)
## Df Sum Sq Mean Sq F value Pr(>F)
## supp 1 205.4 205.4 14.02 0.000429 ***
## dose 2 2426.4 1213.2 82.81 < 2e-16 ***
## Residuals 56 820.4 14.7
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Two-way ANOVA with interaction effect
# These two calls are equivalent
res.aov3 <- aov(len ~ supp * dose, data = my_data)
res.aov3 <- aov(len ~ supp + dose + supp:dose, data = my_data)
summary(res.aov3)
## Df Sum Sq Mean Sq F value Pr(>F)
## supp 1 205.4 205.4 15.572 0.000231 ***
## dose 2 2426.4 1213.2 92.000 < 2e-16 ***
## supp:dose 2 108.3 54.2 4.107 0.021860 *
## Residuals 54 712.1 13.2
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Comparing Variances in R F-Test: Compare Two Variances in R
# F-test
res.ftest <- var.test(len ~ supp, data = my_data)
res.ftest
##
## F test to compare two variances
##
## data: len by supp
## F = 0.6386, num df = 29, denom df = 29, p-value = 0.2331
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.3039488 1.3416857
## sample estimates:
## ratio of variances
## 0.6385951
Compare Multiple Sample Variances in R
res <- bartlett.test(weight ~ group, data = PlantGrowth)
res
##
## Bartlett test of homogeneity of variances
##
## data: weight by group
## Bartlett's K-squared = 2.8786, df = 2, p-value = 0.2371
fligner.test(weight ~ group, data = PlantGrowth)
##
## Fligner-Killeen test of homogeneity of variances
##
## data: weight by group
## Fligner-Killeen:med chi-squared = 2.3499, df = 2, p-value = 0.3088
Comparing Proportions in R One-Proportion Z-Test in R
res <- prop.test(x = 95, n = 160, p = 0.5,
correct = FALSE)
# Printing the results
res
##
## 1-sample proportions test without continuity correction
##
## data: 95 out of 160, null probability 0.5
## X-squared = 5.625, df = 1, p-value = 0.01771
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.5163169 0.6667870
## sample estimates:
## p
## 0.59375
Compute two-proportions z-test in R
res <- prop.test(x = c(490, 400), n = c(500, 500))
# Printing the results
res
##
## 2-sample test for equality of proportions with continuity correction
##
## data: c(490, 400) out of c(500, 500)
## X-squared = 80.909, df = 1, p-value < 2.2e-16
## alternative hypothesis: two.sided
## 95 percent confidence interval:
## 0.1408536 0.2191464
## sample estimates:
## prop 1 prop 2
## 0.98 0.80
Multiple REgression:
CGPA <- c(2.8, 2.5, 3.2, 3.5, 3.1, 2.9, 2.6, 2.7, 2.98, 3, 3.1, 3.7, 3.6, 3.56, 3.8, 3.76, 3.2, 2.7, 2.8, 3.2, 3.1, 3, 3.7, 3.2, 3)
AGE <- c(21, 20, 21, 20, 21, 21, 20, 10, 20, 21, 22, 22, 21, 20, 19, 21, 20, 22, 19, 21, 20, 22, 19, 19, 21)
INTER_MARKS <- c(876, 870, 970, 930, 760, 560, 660, 780, 980, 1000, 1020, 995, 1005, 1050, 1075, 2070, 920, 910, 850, 670, 520, 760, 720, 920, 1030)
INCOME <- c(15000, 11000, 10000, 20000, 30000, 35000, 19000, 15000, 17000, 40000, 50000, 30000, 20000, 25000, 20000, 17000, 18000, 16000, 12000, 13000, 35000, 32000, 28000, 25000, 22000)
GPA_1 <- c(2.7, 2.8, 3.5, 3.9, 3.8, 3.2, 3.1, 2.9, 2.8, 2.75, 2.6, 2.5, 2.9, 3, 3.2, 3.6, 3.6, 3.9, 3.7, 3.5, 3.4, 3.3, 3.1, 3.2, 3.3)
#---------------------------------------------------
# Direct method
model <- lm(CGPA ~ AGE + INTER_MARKS + INCOME + GPA_1)
model
##
## Call:
## lm(formula = CGPA ~ AGE + INTER_MARKS + INCOME + GPA_1)
##
## Coefficients:
## (Intercept) AGE INTER_MARKS INCOME GPA_1
## 1.977e+00 4.495e-03 6.544e-04 9.293e-06 8.326e-02
summary(model)
##
## Call:
## lm(formula = CGPA ~ AGE + INTER_MARKS + INCOME + GPA_1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4717 -0.2247 -0.1194 0.2778 0.6480
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.977e+00 8.552e-01 2.312 0.0316 *
## AGE 4.495e-03 3.382e-02 0.133 0.8956
## INTER_MARKS 6.544e-04 2.616e-04 2.502 0.0212 *
## INCOME 9.293e-06 8.294e-06 1.121 0.2757
## GPA_1 8.326e-02 1.906e-01 0.437 0.6669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3541 on 20 degrees of freedom
## Multiple R-squared: 0.2718, Adjusted R-squared: 0.1261
## F-statistic: 1.866 on 4 and 20 DF, p-value: 0.156
confint(model)
## 2.5 % 97.5 %
## (Intercept) 1.931294e-01 3.761014e+00
## AGE -6.604341e-02 7.503437e-02
## INTER_MARKS 1.087427e-04 1.200091e-03
## INCOME -8.006526e-06 2.659343e-05
## GPA_1 -3.143176e-01 4.808336e-01
#---------------------------------------------------
# Matrix approach
# Organize the data into matrices
CGPA <- c(2.8, 2.5, 3.2, 3.5, 3.1, 2.9, 2.6, 2.7, 2.98, 3, 3.1, 3.7, 3.6, 3.56, 3.8, 3.76, 3.2, 2.7, 2.8, 3.2, 3.1, 3, 3.7, 3.2, 3)
AGE <- c(21, 20, 21, 20, 21, 21, 20, 10, 20, 21, 22, 22, 21, 20, 19, 21, 20, 22, 19, 21, 20, 22, 19, 19, 21)
INTER_MARKS <- c(876, 870, 970, 930, 760, 560, 660, 780, 980, 1000, 1020, 995, 1005, 1050, 1075, 2070, 920, 910, 850, 670, 520, 760, 720, 920, 1030)
INCOME <- c(15000, 11000, 10000, 20000, 30000, 35000, 19000, 15000, 17000, 40000, 50000, 30000, 20000, 25000, 20000, 17000, 18000, 16000, 12000, 13000, 35000, 32000, 28000, 25000, 22000)
GPA_1 <- c(2.7, 2.8, 3.5, 3.9, 3.8, 3.2, 3.1, 2.9, 2.8, 2.75, 2.6, 2.5, 2.9, 3, 3.2, 3.6, 3.6, 3.9, 3.7, 3.5, 3.4, 3.3, 3.1, 3.2, 3.3)
# Create a matrix X with independent variables
X <- cbind(AGE, INTER_MARKS, INCOME, GPA_1)
X
## AGE INTER_MARKS INCOME GPA_1
## [1,] 21 876 15000 2.70
## [2,] 20 870 11000 2.80
## [3,] 21 970 10000 3.50
## [4,] 20 930 20000 3.90
## [5,] 21 760 30000 3.80
## [6,] 21 560 35000 3.20
## [7,] 20 660 19000 3.10
## [8,] 10 780 15000 2.90
## [9,] 20 980 17000 2.80
## [10,] 21 1000 40000 2.75
## [11,] 22 1020 50000 2.60
## [12,] 22 995 30000 2.50
## [13,] 21 1005 20000 2.90
## [14,] 20 1050 25000 3.00
## [15,] 19 1075 20000 3.20
## [16,] 21 2070 17000 3.60
## [17,] 20 920 18000 3.60
## [18,] 22 910 16000 3.90
## [19,] 19 850 12000 3.70
## [20,] 21 670 13000 3.50
## [21,] 20 520 35000 3.40
## [22,] 22 760 32000 3.30
## [23,] 19 720 28000 3.10
## [24,] 19 920 25000 3.20
## [25,] 21 1030 22000 3.30
# Create a vector Y with the dependent variable
Y <- CGPA
Y
## [1] 2.80 2.50 3.20 3.50 3.10 2.90 2.60 2.70 2.98 3.00 3.10 3.70 3.60 3.56 3.80
## [16] 3.76 3.20 2.70 2.80 3.20 3.10 3.00 3.70 3.20 3.00
# Calculate X transpose
X_transpose <- t(X)
X_transpose
## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
## AGE 21.0 20.0 21.0 20.0 21.0 21.0 20.0 10.0
## INTER_MARKS 876.0 870.0 970.0 930.0 760.0 560.0 660.0 780.0
## INCOME 15000.0 11000.0 10000.0 20000.0 30000.0 35000.0 19000.0 15000.0
## GPA_1 2.7 2.8 3.5 3.9 3.8 3.2 3.1 2.9
## [,9] [,10] [,11] [,12] [,13] [,14] [,15] [,16]
## AGE 20.0 21.00 22.0 22.0 21.0 20 19.0 21.0
## INTER_MARKS 980.0 1000.00 1020.0 995.0 1005.0 1050 1075.0 2070.0
## INCOME 17000.0 40000.00 50000.0 30000.0 20000.0 25000 20000.0 17000.0
## GPA_1 2.8 2.75 2.6 2.5 2.9 3 3.2 3.6
## [,17] [,18] [,19] [,20] [,21] [,22] [,23] [,24]
## AGE 20.0 22.0 19.0 21.0 20.0 22.0 19.0 19.0
## INTER_MARKS 920.0 910.0 850.0 670.0 520.0 760.0 720.0 920.0
## INCOME 18000.0 16000.0 12000.0 13000.0 35000.0 32000.0 28000.0 25000.0
## GPA_1 3.6 3.9 3.7 3.5 3.4 3.3 3.1 3.2
## [,25]
## AGE 21.0
## INTER_MARKS 1030.0
## INCOME 22000.0
## GPA_1 3.3
# Calculate X transpose times X
X_transpose_X <- X_transpose %*% X
X_transpose_X
## AGE INTER_MARKS INCOME GPA_1
## AGE 10249.00 462966.0 1.1723e+07 1616.6500
## INTER_MARKS 462966.00 22928751.0 5.1657e+08 73603.2000
## INCOME 11723000.00 516570000.0 1.5595e+10 1814600.0000
## GPA_1 1616.65 73603.2 1.8146e+06 261.6125
# Calculate the inverse of X transpose times X
X_transpose_X_inv <- solve(X_transpose_X)
X_transpose_X_inv
## AGE INTER_MARKS INCOME GPA_1
## AGE 6.682802e-03 -2.150337e-05 -1.088708e-06 -2.769541e-02
## INTER_MARKS -2.150337e-05 5.219324e-07 2.593845e-09 -3.195286e-05
## INCOME -1.088708e-06 2.593845e-09 5.115760e-10 2.449571e-06
## GPA_1 -2.769541e-02 -3.195286e-05 2.449571e-06 1.669669e-01
# Calculate X transpose times Y
X_transpose_Y <- X_transpose %*% Y
X_transpose_Y
## [,1]
## AGE 1587.06
## INTER_MARKS 73291.90
## INCOME 1823580.00
## GPA_1 252.74
# Calculate the coefficients beta
beta <- X_transpose_X_inv %*% X_transpose_Y
# Display the coefficients
print(beta)
## [,1]
## AGE 4.490083e-02
## INTER_MARKS 7.806016e-04
## INCOME 1.426753e-05
## GPA_1 3.700375e-01
Chi_squared_test: Test of independence:
observed_values<-matrix(c(24,11,32,10,83,62,121,26,17,28,34,44),nrow = 4)
observed_values
## [,1] [,2] [,3]
## [1,] 24 83 17
## [2,] 11 62 28
## [3,] 32 121 34
## [4,] 10 26 44
row.names(observed_values)<-c('Music','Craftswork','Reading','Drams')
colnames(observed_values)<-c('Maths','Chemistry','Physics')
contigency_table<-observed_values
contigency_table
## Maths Chemistry Physics
## Music 24 83 17
## Craftswork 11 62 28
## Reading 32 121 34
## Drams 10 26 44
#Hypothesis Formulation:
#Ho: Degrees and Hobbies are Independent
#H1: Degrees and Hobbies are associated
#Level_of_significance:
alpha<-0.05
#Test_Statistics:
row_Total<-rowSums(observed_values)
row_Total
## Music Craftswork Reading Drams
## 124 101 187 80
column_Total<-colSums(observed_values)
column_Total
## Maths Chemistry Physics
## 77 292 123
Total_values<-sum(observed_values)
expected_values <-outer(row_Total,column_Total,'*') /Total_values
expected_values
## Maths Chemistry Physics
## Music 19.40650 73.59350 31.00
## Craftswork 15.80691 59.94309 25.25
## Reading 29.26626 110.98374 46.75
## Drams 12.52033 47.47967 20.00
chi_square_test<-sum(((observed_values-expected_values)^2)/expected_values)
chi_square_test
## [1] 54.10532
#Critical_Region
#reject Ho if X_cal >=X(alpha,df)
df<-(nrow(contigency_table)-1)*(ncol(contigency_table)-1)
df
## [1] 6
qchisq(1-0.05,df)
## [1] 12.59159
#Reject Ho
#By using function
result<-chisq.test(contigency_table)
if (result$p.value<alpha)
{
cat("Reject Ho")
}else
{cat("Do not Reject Ho")}
## Reject Ho
#Result:
#Reject Ho as p-value is less than alpha