Scribd
Upload
3K views6 pages

Coursera R Lab - Correlation and Regression Answers

This document provides answers and explanations for an online Coursera lab on correlation and regression. It includes R code to create scatterplots and contingency tables, calculate Pearson's correlation and regression coefficients, plot regression lines, and interpret correlation versus causation. The key steps covered are plotting relationships between variables, calculating correlation, finding the regression equation that best fits the data, and determining how much variation in the dependent variable can be explained by changes in the independent variable.

Uploaded by

Furkan Memmedov
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3K views6 pages

Coursera R Lab - Correlation and Regression Answers

This document provides answers and explanations for an online Coursera lab on correlation and regression. It includes R code to create scatterplots and contingency tables, calculate Pearson's correlation and regression coefficients, plot regression lines, and interpret correlation versus causation. The key steps covered are plotting relationships between variables, calculating correlation, finding the regression equation that best fits the data, and determining how much variation in the dependent variable can be explained by changes in the independent variable.

Uploaded by

Furkan Memmedov
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Coursera R lab - Correlation and Regression Answers

Here are the answers of the R lab - Correlation and Regression of second
week basic statistics coursera's online course you simply copy the r code from
there and paste it and get 100 % results.
Scatterplots
# Plot height and weight of the "women" dataset. Make the title "Heights and
Weights"
plot(women$weight, women$height, main = "Heights and Weights")
Making a Contingency Table
# Make a contingency table of tobacco consumption and education
table(smoking$tobacco, smoking$student)
Calculating Percentage From Your Contingency Table
# What percentage of high school students smoke 0-9g of tobacco?
38.6
# Of the students who smoke the most, what percentage are in university?
57.7
Interpreting Your Scatterplot
This is the graph you created of heighs and weights. Based on your graph,
what can you say about the relationship between height and weight?
Possible Answers

It is linear and positive


Pearson's R I
Pearson's r is a measure of how strongly the variables are correlated with
each other. Look at the graph on the right. Which of the following Pearson's r
values are likely to belong to this graph?
1.0
Pearson's R II
35xp
Which of the following Pearson's r values are likely to belong to this graph?
0.418
Pearson's R III
Which of the following Pearson's r values are likely to belong to this graph?
-0.77
Pearson's R IV
Which of the following Pearson's r values are likely to belong to this graph?
-0.26
Calculating Correlation Using R
# Calculate the correlation between var1 and var2
cor(var1,var2)
Finding The Line
# predicted values of y according to line 1
y1 <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
sum(y-y1)
# predicted values of y according to line 2
y2 <- c(2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
sum(y-y2)
# actual values of y
y <- c(3, 2, 1, 4, 5, 10, 8, 7, 6, 9)
 
# calculate the squared error of line 1
sum((y-y1)^2)
 
# calculate the squared error of line 2
sum((y-y2)^2)
Interpreting The Line
# How prosocial would we predict someone to be when they recieve 6 units of
money?
6
# How prosical was the person who recieved 6 units of money in our study?
10
The Regression Equation
26.1
Describing The Line
The equation for the blue line in the graph is Y = 1 + 0.7818(X). What is the
equation for the red line?
Y = 4 + 0.7818(x)
Finding The Regression Coefficients in R
# Our data
money <- c(1,2,3,4,5,6,7,8,9,10)
prosocial <- c(3, 2, 1, 4, 5, 10, 8, 7, 6,9)
# Find the regression coefficients
lm(prosocial~money)
Using lm() To Add A Regression Line To Your Plot
# Your plot
plot(money, prosocial, xlab = "Money", ylab = "Prosocial Behavior")
# Store your regression coefficients in a variable called "line"
line <- lm(prosocial ~ money)
# Use "line" to tell abline() to make a line on your graph
abline(line)
Adding A Line
# Your plot
plot(money, prosocial, xlab = "Money", ylab = "Prosocial Behavior")
# Your regression line
line <- lm(prosocial ~ money)
abline(line)
# Add a line that shows the mean of the dependent variable
abline(mean(prosocial), 0)
R Squared I
# Calculate the R squared of prosocial and money
cor(prosocial,money)^2
R Squared II
In addition to being the reduction in residual error from using the regression
line over the mean line, and, of course the pearson correlation coefficient
squared, how else can we describe the R squared?
The variation in the dependent variable explained by the independent variable
Correlation and Causation
You measured how much money people have and their education level in a
town. The graph on the right shows the results. We cannot say that more
educaion causes more money, we say it isrelated to more money. Which of
the following is not a reason why education is only related to money?
There could be a third unmeasured variable that influences only money
 
Putting It Together: Regression
# your data
money <- c(4, 3, 2, 2, 8, 1, 1, 2, 3, 4, 5, 6, 7, 9, 9, 8, 12)
education <- c(3, 4, 6, 9, 3, 3, 1, 2, 1, 4, 5, 7, 10, 8, 7, 6, 9)
 
# calculate the correlation between X and Y
cor(money, education)
 
# save regression coefficients as object "line"
line <- lm(money ~ education)
 
# print the regression coefficients
line
 
# plot Y and X
plot(education, money, main = "My Scatterplot")
 
# add the regression line
abline(line)
Putting It Together: Contingency Tables
# percentage of people with high money that are university educated
83.3
# percentage of people with low money that are high schol educated
72.7
# what kind of education is linked to more money?
"university"

You might also like