14 Exercise 5: Test your knowledge

In this Exercise, we will work with the pmi data set. It’s a data set of a communication science experiment that was conducted by Tal-Or, Cohen, Tsfati, & Gunther in 2010 and comes pre-installed with processR. The data set contains 123 observations of 6 variables. There are three variables of interest to us in this data set:

  1. cond: article about sugar shortage was placed at the front (1) or interior (0) page of a newspaper

  2. pmi: belief that others will be prompted to buy sugar as a result of exposure to the article (scale: 1-7)

  3. reaction: intention to buy sugar (scale: 1-7)

Let’s load processR and save the pmi data to a source object called data:

# installing/loading the package:
if(!require(processR)) {
  install.packages("processR"); 
  require(processR)
} #load / install+load processR

data <- processR::pmi

The theory of presumed media influence suggests that people perceive some effect of a message on others and then react to that perception. Based on this theory, we assume that when the sugar article appears on the front page, the reader will be more likely to believe that others will be prompted to buy sugar. Therefore, the reader will act on this belief and show greater intention to buy sugar themselves (to avoid a personal shortage because others are buying sugar).

Research Question: Is the effect of article placement (front/interior) on the intention to buy sugar mediated by the belief that others will be prompted to buy sugar as a result of exposure to the article? That is, do participants who take part in the front-page experimental condition develop a greater belief that others will be prompted to buy sugar, while this belief increases their own intention to buy sugar?

14.1 Task 1

What variables are X, Y, and M in this scenario? Write it down.

14.2 Task 2

Create three plots:

  1. The effect c of X on Y without controlling for M.

  2. The direct effect a of X on M.

  3. The effect of M on Y without controlling for X.

Evaluate the plots. What do they tell you?

14.3 Task 3

Fit two linear regression models that…

  1. quantify the direct effect a of X on M.

  2. quantify the direct effect c’ of X on Y while controlling for M AND the direct effect b of M on Y while controlling for X.

Evaluate both models. What are the regression equations of these models? And how do you interpret their regression coefficients?

14.4 Task 4

Calculate and interpret the indirect effect ab.

14.5 Task 5

Calculate and interpret the total effect c.

14.6 Task 6

Now run the same analysis, but use processR (i.e., the process function). Only look at this output and write down the coefficients a, b, c’, ab, and c.

14.7 Task 7

Finally, create a diagram that displays the results of your analysis.