The objectives of this problem set is to orient you to a number of
activities in R and to conduct a thoughtful exercise in
appreciating the importance of data visualization. For each question
enter your code or text response in the code chunk that
completes/answers the activity or question requested. To submit this
homework you will create the document in Rstudio, using the knitr
package (button included in Rstudio) and then submit the document to
your Rpubs account. Once uploaded you
will submit the link to that document on Canvas. Please make sure that
this link is hyper linked and that I can see the visualization and the
code required to create it. Each question is worth 5 points.
anscombe data that is part of the
library(datasets) in R. And assign that data
to a new object called data.#Load the required library
library(datasets)
#Assign 'anscombe' data to a new object and name it 'data'
data = anscombe
#Check the data set
head(data)
## x1 x2 x3 x4 y1 y2 y3 y4
## 1 10 10 10 8 8.04 9.14 7.46 6.58
## 2 8 8 8 8 6.95 8.14 6.77 5.76
## 3 13 13 13 8 7.58 8.74 12.74 7.71
## 4 9 9 9 8 8.81 8.77 7.11 8.84
## 5 11 11 11 8 8.33 9.26 7.81 8.47
## 6 14 14 14 8 9.96 8.10 8.84 7.04
dplyr package!)#Load the required library
library(resample)
## Registered S3 method overwritten by 'resample':
## method from
## print.resample modelr
#Data set summary
summary(data)
## x1 x2 x3 x4 y1
## Min. : 4.0 Min. : 4.0 Min. : 4.0 Min. : 8 Min. : 4.260
## 1st Qu.: 6.5 1st Qu.: 6.5 1st Qu.: 6.5 1st Qu.: 8 1st Qu.: 6.315
## Median : 9.0 Median : 9.0 Median : 9.0 Median : 8 Median : 7.580
## Mean : 9.0 Mean : 9.0 Mean : 9.0 Mean : 9 Mean : 7.501
## 3rd Qu.:11.5 3rd Qu.:11.5 3rd Qu.:11.5 3rd Qu.: 8 3rd Qu.: 8.570
## Max. :14.0 Max. :14.0 Max. :14.0 Max. :19 Max. :10.840
## y2 y3 y4
## Min. :3.100 Min. : 5.39 Min. : 5.250
## 1st Qu.:6.695 1st Qu.: 6.25 1st Qu.: 6.170
## Median :8.140 Median : 7.11 Median : 7.040
## Mean :7.501 Mean : 7.50 Mean : 7.501
## 3rd Qu.:8.950 3rd Qu.: 7.98 3rd Qu.: 8.190
## Max. :9.260 Max. :12.74 Max. :12.500
#Mean calculation
colMeans(data, na.rm = FALSE)
## x1 x2 x3 x4 y1 y2 y3 y4
## 9.000000 9.000000 9.000000 9.000000 7.500909 7.500909 7.500000 7.500909
#Variance calculation
colVars(data, na.rm = FALSE)
## x1 x2 x3 x4 y1 y2 y3 y4
## 11.000000 11.000000 11.000000 11.000000 4.127269 4.127629 4.122620 4.123249
#Correlation b/w each pair
cor(data[ , 1:4], data[ , 5:8])
## y1 y2 y3 y4
## x1 0.8164205 0.8162365 0.8162867 -0.3140467
## x2 0.8164205 0.8162365 0.8162867 -0.3140467
## x3 0.8164205 0.8162365 0.8162867 -0.3140467
## x4 -0.5290927 -0.7184365 -0.3446610 0.8165214
#Load required library
library(ggplot2)
#Create multiple plots in one view
par(mfrow = c(2, 2))
#Pair 1
plot(data$x1, data$y1, main = "Scatterplot for Pair 1", xlab = "x1", ylab = "y1")
#Pair 2
plot(data$x2, data$y2, main = "Scatterplot for Pair 2", xlab = "x2", ylab = "y2")
#Pair 3
plot(data$x3, data$y3, main = "Scatterplot for Pair 3", xlab = "x3", ylab = "y3")
#Pair 4
plot(data$x4, data$y4, main = "Scatterplot for Pair 4", xlab = "x4", ylab = "y4")
#Create multiple plots in one view
par(mfrow = c(2, 2))
#Pair 1
plot(data$x1, data$y1, main = "Scatterplot for Pair 1", xlab = "x1", ylab = "y1", pch = 18, col = "blue")
#Pair 2
plot(data$x2, data$y2, main = "Scatterplot for Pair 2", xlab = "x2", ylab = "y2", pch = 18, col = "blue")
#Pair 3
plot(data$x3, data$y3, main = "Scatterplot for Pair 3", xlab = "x3", ylab = "y3", pch = 18, col = "blue")
#Pair 4
plot(data$x4, data$y4, main = "Scatterplot for Pair 4", xlab = "x4", ylab = "y4", pch = 18, col = "blue")
lm()
function.lm_1 = lm(data$y1~data$x1)
lm_2 = lm(data$y2~data$x2)
lm_3 = lm(data$y3~data$x3)
lm_4 = lm(data$y4~data$x4)
#Create multiple plots in one view
par(mfrow = c(2, 2))
#Pair 1
plot(data$x1, data$y1, main = "Scatterplot for Pair 1", xlab = "x1", ylab = "y1", pch = 18, col = "blue",abline(lm_1, col = "red"))
#Pair 2
plot(data$x2, data$y2, main = "Scatterplot for Pair 2", xlab = "x2", ylab = "y2", pch = 18, col = "blue",abline(lm_2, col = "red"))
#Pair 3
plot(data$x3, data$y3, main = "Scatterplot for Pair 3", xlab = "x3", ylab = "y3", pch = 18, col = "blue",abline(lm_3, col = "red"))
#Pair 4
plot(data$x4, data$y4, main = "Scatterplot for Pair 4", xlab = "x4", ylab = "y4", pch = 18, col = "blue", abline(lm_4, col = "red"))
#Model fit for pair 1
anova(lm_1)
Analysis of Variance Table
Response: data\(y1 Df Sum Sq Mean Sq F
value Pr(>F) data\)x1 1 27.510 27.5100 17.99 0.00217 **
Residuals 9 13.763 1.5292
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05
‘.’ 0.1 ’ ’ 1
#Model fit for pair 2
anova(lm_2)
Analysis of Variance Table
Response: data\(y2 Df Sum Sq Mean Sq F
value Pr(>F) data\)x2 1 27.500 27.5000 17.966 0.002179 **
Residuals 9 13.776 1.5307
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05
‘.’ 0.1 ’ ’ 1
#Model fit for pair 3
anova(lm_3)
Analysis of Variance Table
Response: data\(y3 Df Sum Sq Mean Sq F
value Pr(>F) data\)x3 1 27.470 27.4700 17.972 0.002176 **
Residuals 9 13.756 1.5285
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05
‘.’ 0.1 ’ ’ 1
#Model fit for pair 4
anova(lm_4)
Analysis of Variance Table
Response: data\(y4 Df Sum Sq Mean Sq F
value Pr(>F) data\)x4 1 27.490 27.4900 18.003 0.002165 **
Residuals 9 13.742 1.5269
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05
‘.’ 0.1 ’ ’ 1
#Based on the ANOVA analysis model outcome, we can say that a data set summary statistics could be misleading if the analysis is solely relying on it. The underlying structure of the data set could vary vastly and could be identified by through visual analysis, even though the statistical parameters are same for different data sets. Thus data visualization is an integral part in data analysis, and the visuals could be used to communicate the data. Data visuals could be further used to make informed decisions.