Skip to main content

PS2010 Workshop Code Book

14 Workshop 17: Multiple Regression with Continuous Variables

14.1 Exercise One

Packages and Import Data

# Before doing any analyses, you need to get everything set up and ready...

# Set the working directory -WD- so R knows where the data lives. Do this by going Session > Set working directory > Choose directory

# You can check the working directory...

getwd()

#Before doing anything, need to make sure the right packages are installed and open. We will use all of these......

install.packages(tidyverse)
install.packages(correlation)
install.packages(gridExtra)

library(tidyverse)
library(correlation)
library(gridExtra)

# Once you have done this, you should see them ticked in the "Packages" list - you can also manually tick the boxes.
# If you need to install any of these, the code is install.packages("name of package")
# Make sure you can then see it in the "Packages" list, and call it using library("name of package") or just tick it in the "Packages" list

# Now get R to open our dataset

mydata <- read_csv("WS_data_R_optimism.csv")

14.2 Exercise Two

Prepare Data

# To check the data have opened ok, you can view the data...

view(mydata)

# You can also check the number of participants (obs) and the number of variables in the "Environment" tab.

# Next, we need to tell R which variables are continuous (as.numeric) and which are categorical (as.factor).

# You can check the names of the variables with this...

names(mydata)

mydata$p_num <- as.numeric(mydata$p_num)
mydata$optimism <- as.numeric(mydata$optimism)
mydata$positive_SC <- as.numeric(mydata$positive_SC)
mydata$negative_SC <- as.numeric(mydata$negative_SC)
mydata$age_years <- as.numeric(mydata$age_years)
mydata$extra_curr <- as.factor(mydata$extra_curr)
mydata$reading_age <- as.numeric(mydata$reading_age)

# Before getting into correlations, we might want a summary of our variables. For the continuous variables, we get descriptives. For the categorical/binary variables, we get frequencies.

summary(mydata)

# We should run the zero order correlations for all continuous variables, the outcome variable and the predictors.

mydata %>%
  dplyr::select(optimism, positive_SC, negative_SC, age_years) %>%
  correlation(p_adjust = "none")

# In addition to giving you the r and p values, it gives the N, so check that this is correct. To write up the correlation, remember that df = N-2.

14.3 Exercise Three

Run, Interpret, and Graph the Regression

# Now, let's run a multiple regression.
# We have SWL as the outcome variable that we want to predict
# Then the three wellbeing measures and the number of negative life experiences giving us four continuous predictor variable.

model <- lm(optimism ~ positive_SC + negative_SC + age_years, data = mydata)
summary(model)

# We then want to create scatterplots to graphically represent any significant predictors (so three)

# Optimism and positive self compassion

plot1 <- ggplot(mydata, aes(x = positive_SC, y = optimism)) +
  geom_point() +
  geom_smooth(method = "lm",
              se = FALSE) +
  theme_classic()

# Optimism and negative self compassion

plot2 <- ggplot(mydata, aes(x = negative_SC, y = optimism)) +
  geom_point() +
  geom_smooth(method = "lm",
              se = FALSE) +
  theme_classic()

# Optimism and age in years

plot3 <- ggplot(mydata, aes(x = age_years, y = optimism)) +
  geom_point() +
  geom_smooth(method = "lm",
              se = FALSE) +
  theme_classic()

# To see what the plots look like, we need to arrange them in the "Plot" window. Make sure "gridextra" is ticked in the "Packages" window

grid.arrange(plot1, plot2, plot3, ncol = 3)

# ncol = 3 tells R to put two next to each other, nrow = 1 tells R to put one above the other

14.4 Exercise Four

Hierarchical Regression

# Now, let's move on to hierarchical regression - exactly what we just did, but adding years of education as a control variable.

# First, let's see if the control variable is significant by building model 1. Make sure it is called "model 1" and you need to run the summary to see the output.

model1 <- lm(optimism ~ reading_age, data = mydata)
summary(model1)

# Next, build our final model that has all the variables (control and predictor variables). This is "model 2", and again, use the summary to see the output.

model2 <- lm(optimism ~ reading_age + positive_SC + negative_SC + age_years, data = mydata)
summary(model2)

# Finally, we want to see if adding the predictor variables is significantly "better" than the control variable alone, this has two parts.

# First - how much does the variance explained (adjusted R sq) increase?

r2_control <- summary(model1)$adj.r.squared  # Adj Rsq of control model
r2_full <- summary(model2)$adj.r.squared     # Adj Rsq of full model

r2_change <- r2_full - r2_control  

print(r2_change)  # Print the Adj Rsq change

# Does the model significantly improve?

anova(model1,model2)

# We then want to create scatterplots to graphically represent any significant predictors (so two)

# Optimism and positive self compassion

plot1 <- ggplot(mydata, aes(x = positive_SC, y = optimism)) +
  geom_point() +
  geom_smooth(method = "lm",
              se = FALSE) +
  theme_classic()

# Optimism and negative self compassion

plot2 <- ggplot(mydata, aes(x = negative_SC, y = optimism)) +
  geom_point() +
  geom_smooth(method = "lm",
              se = FALSE) +
  theme_classic()

# To see what the plots look like, we need to arrange them in the "Plot" window. Make sure "gridextra" is ticked in the "Packages" window

grid.arrange(plot1, plot2, nrow = 1, ncol = 2)

Well Done. You have reached the end of the workshop