'data.frame': 62 obs. of 2 variables:
$ body : num 3.38 0.48 1.35 465 36.33 ...
$ brain: num 44.5 15.5 8.1 423 119.5 ...
str(menarche)
'data.frame': 25 obs. of 3 variables:
$ Age : num 9.21 10.21 10.58 10.83 11.08 ...
$ Total : num 376 200 93 120 90 88 105 111 100 93 ...
$ Menarche: num 0 0 0 2 2 5 10 17 16 29 ...
# Load the MASS packagelibrary(MASS)# Load the mammals datasetdata(mammals)# View the first few rowshead(mammals)
body brain
Arctic fox 3.385 44.5
Owl monkey 0.480 15.5
Mountain beaver 1.350 8.1
Cow 465.000 423.0
Grey wolf 36.330 119.5
Goat 27.660 115.0
# Summary statisticssummary(mammals)
body brain
Min. : 0.005 Min. : 0.14
1st Qu.: 0.600 1st Qu.: 4.25
Median : 3.342 Median : 17.25
Mean : 198.790 Mean : 283.13
3rd Qu.: 48.202 3rd Qu.: 166.00
Max. :6654.000 Max. :5712.00
# Scatter plot of brain vs. body weightplot(mammals$body, mammals$brain,xlab ="Body Weight (kg)",ylab ="Brain Weight (g)",main ="Brain Weight vs. Body Weight")
# Compute the correlation between body and brain weightcor(mammals$body, mammals$brain)
[1] 0.9341638
#the two large numbers on the scatterplot do not seem like outliers because they are close to the best fitted line that has a positive correlationhead(x = mammals, n =20L)
body brain
Arctic fox 3.385 44.50
Owl monkey 0.480 15.50
Mountain beaver 1.350 8.10
Cow 465.000 423.00
Grey wolf 36.330 119.50
Goat 27.660 115.00
Roe deer 14.830 98.20
Guinea pig 1.040 5.50
Verbet 4.190 58.00
Chinchilla 0.425 6.40
Ground squirrel 0.101 4.00
Arctic ground squirrel 0.920 5.70
African giant pouched rat 1.000 6.60
Lesser short-tailed shrew 0.005 0.14
Star-nosed mole 0.060 1.00
Nine-banded armadillo 3.500 10.80
Tree hyrax 2.000 12.30
N.A. opossum 1.700 6.30
Asian elephant 2547.000 4603.00
Big brown bat 0.023 0.30
ggplot(mammals, aes(x ="Body Weight (kg)", y ="Brain Weight (g)")) +geom_point() +geom_smooth(method ="lm", color ="red", se =TRUE) +labs(title ="Brain Weight vs Body Weight", x ="Body Weight (kg)", y ="Brain Weight (g)")
Warning in geom_point(): All aesthetics have length 1, but the data has 62 rows.
ℹ Please consider using `annotate()` or provide this layer with data containing
a single row.
Warning in geom_smooth(method = "lm", color = "red", se = TRUE): All aesthetics have length 1, but the data has 62 rows.
ℹ Please consider using `annotate()` or provide this layer with data containing
a single row.
`geom_smooth()` using formula = 'y ~ x'
# Load the necessary librarieslibrary(MASS) # For the 'mammals' datasetlibrary(ggplot2) # For plottinglibrary(broom) # For tidy model output# Load the datasetdata(mammals)# Perform the linear regressionmodel <-lm(brain ~ body, data = mammals)# Get the coefficientscoefficients <-coef(model)intercept <- coefficients[1]slope <- coefficients[2]# Create a regression equation stringequation <-paste0("y = ", round(intercept, 2), " + ", round(slope, 2), " * x")# Create the scatter plot with regression line and equationplot <-ggplot(mammals, aes(x = body, y = brain)) +geom_point() +# Add pointsgeom_smooth(method ="lm", se =TRUE) +# Add regression line with confidence intervalannotate("text", x =max(mammals$body), y =max(mammals$brain), label = equation, hjust =1, vjust =1, size =5, color ="blue") +labs(title ="Scatter Plot of Brain Weight vs. Body Weight",x ="Body Weight (kg)",y ="Brain Weight (g)") +theme_minimal()# Display the plotprint(plot)
`geom_smooth()` using formula = 'y ~ x'
# Load the menarche datasetdata(menarche)# View the first few rowshead(menarche)
Age Total Menarche
Min. : 9.21 Min. : 88.0 Min. : 0.00
1st Qu.:11.58 1st Qu.: 98.0 1st Qu.: 10.00
Median :13.08 Median : 105.0 Median : 51.00
Mean :13.10 Mean : 156.7 Mean : 92.32
3rd Qu.:14.58 3rd Qu.: 117.0 3rd Qu.: 92.00
Max. :17.58 Max. :1049.0 Max. :1049.00
# Scatter plot of Menarche vs. Ageplot(menarche$Age, menarche$Menarche,xlab ="Age",ylab ="Menarche",main ="Menarche vs. Age")
# Compute the correlation between Age and Menarchecor(menarche$Age, menarche$Menarche)
ggplot(menarche, aes(x ="Age", y ="Menarche")) +geom_point() +geom_smooth(method ="lm", color ="red", se =TRUE) +labs(title ="Menarche vs Age", x ="Age", y ="Menarche")
Warning in geom_point(): All aesthetics have length 1, but the data has 25 rows.
ℹ Please consider using `annotate()` or provide this layer with data containing
a single row.
Warning in geom_smooth(method = "lm", color = "red", se = TRUE): All aesthetics have length 1, but the data has 25 rows.
ℹ Please consider using `annotate()` or provide this layer with data containing
a single row.
`geom_smooth()` using formula = 'y ~ x'
# Load the necessary librarieslibrary(MASS) # For the 'menarche' datasetlibrary(ggplot2) # For plottinglibrary(broom) # For tidy model output# Load the datasetdata(menarche)# Perform the linear regressionmodel <-lm(Menarche ~ Age, data = menarche)# Get the coefficientscoefficients <-coef(model)intercept <- coefficients[1]slope <- coefficients[2]# Create a regression equation stringequation <-paste0("y = ", round(intercept, 2), " + ", round(slope, 2), " * x")# Create the scatter plot with regression line and equationplot <-ggplot(menarche, aes(x = Age, y = Menarche)) +geom_point() +# Add pointsgeom_smooth(method ="lm", se =TRUE) +# Add regression line with confidence intervalannotate("text", x =max(menarche$Age), y =max(menarche$Menarche), label = equation, hjust =1, vjust =1, size =5, color ="blue") +labs(title ="Scatter Plot of Number who have reached menarche vs. Average age of the group",x ="Age",y ="Menarche") +theme_minimal()# Display the plotprint(plot)
