Comparing more than two means: two factor ANOVA with independent samples; the important role of interaction - Improving the User Experience through Practical Data Analytics - page 189

Table 8.1 Means and Sample Size for the Different Age Groups

Age Bracket 1 Age Bracket 2 Age Bracket 3 Age Bracket 4 Age Bracket 5

18-25
Gen Z

26-35
Gen Y

36-45
Gen X

46-55
Younger
boomers

56-66
Older boomers

Mean = 2.25
n = 28

4.38
26

4.50
26

3.04
23

2.74
23

Agreement with Statement: This page makes Mademoiselle seem sophisticated.
1 = Strongly disagree, 5 = Strongly agree.

Which is great news for Mademoiselle La La, since their greatest sales come from
the 26-45 age bracket. In general, the customers who are buying the most are the
ones who think the new home page is most sophisticated.
After some initial skepticism, Bittle was happy with the results and stated that
it “looks like we're right where we need to be with that home page design.” You
provided Bittle with a summary of the results, which she took to Mademoiselle La
La Founder Mary Flynn Myers.
The morning after you delivered the results to Bittle, you step into the elevator
and run smack dab into Bittle. This time, she's clutching an iced pumpkin macchiato
in one hand and her iPhone in the other, still managing to text!
“Good morning!” she says, as her thumb continues to pound the phone. “Mary liked
your research results regarding age differences, but she has another request.” She
leans in and whispers: “I think it's silly, but you have to appease your boss, ya know.”
“Of course,” you reply good-naturedly.
“She wants to have the data sliced by gender too. She thinks there's a funda-
mental difference between how different age brackets of men and women perceive
sophistication, and she wants to verify.”
“Ah, potential interaction effects; interesting,” you respond.
“Interwhat?” she says before she takes a large gulp of her macchiato .
“I can look at the individual effect of age, the individual effect of gender, plus the
simultaneous effect of both.”
“Good. I'm sure it's a colossal waste of time,” she says, stepping off on her loor.
“I mean, seriously, over 75 percent of our clients are females. What's the point? But
she's the boss. Can I have results by end of day?”
“You got it!”
Getting back to your desk, you open up your spreadsheet, but this time you dis-
play gender information. See Table 8.2 , which includes not only the responder's age ,
but also his/her gender .
We will later analyze the data in Table 8.2 .