Question

Chapter 13

13.1 Jean tests the effects of four different levels of caffeine (no caffeine, 40mg caffeine, 80mg caffeine, 120mg caffeine) on public speaking ability. One group of participants was tested in all four conditions over the course of four weeks – a different condition each week. What statistical analysis should Jean conduct to determine the effect of caffeine on public speaking?

13.2 How does the formula for the repeated-measures ANOVA differ from the formula for the One-way, independent-measures ANOVA?

13.3 Calculate SS_{between subjects} for the following data set. SHOW WORK

Person   Treatment 1       Treatment 2       Treatment 3

A       8           5           7

B       10           4           5

C       6           4           4

D       8           3           6

E       7           6           5

F       8           4           5

      

13.4 What three hypothesis tests do you have to conduct if you are using a Two-Factor (Factorial) ANOVA to analyze your data? (list/describe each one)

13.5 You can do some basic calculations based on treatment means, to get an idea of what types of effects might be present in a factorial study (even if you can’t say if they are statistically significant). Based on the table of means below, does it look like there could be any main effects or interactions? Specify which ones. SHOW WORK

Factor B
M = 15	M = 30
M = 25	M = 40

Use the following scenario and data to answer questions 13.6 - 13.7

Researchers are interested in how serving temperature and pouring method affect the taste of Champagne (more bubbles = better taste). In this 3x2 factorial design, different glasses of Champagne are poured under different conditions; the summary data for the study appear in the table below. The researchers want to know which method is best.

	Champagne Temperature
	40	46	52
Gentle Pour	T = 70 M = 7 SS = 64	T = 30 M = 3 SS = 54	T = 20 M = 2 SS = 46
Splashing Pour	T = 50 M = 5 SS = 58	T = 10 M = 1 SS = 20	T = 0 M = 0 SS = 0

n = 10

N = 60

∑X² = 1150

*Note, low averages mean few bubbles = Champagne is less tasty

13.6 Work through the steps involved in calculating this Factorial ANOVA for the Champagne study. Fill out the ANOVA table below as you go through the steps. Show work for Full Credit and the chance of Partial Credit.

Source               SS           df       MS       F

Between treatments

   Temperature

   Pour

Temperature X Pour

Within treatments

Total

13.7 What critical F value would you use to evaluate the three hypotheses in the Champagne ANOVA?

Temperature critical F =

Pour critical F =

Temperature X Pour critical F =

Chapter 14

14.1 The figure on the right is a scatterplot showing the relationship between drive ratio and horsepower. Based only on the figure, how would you describe this relationship? (Make sure to address its form, direction, and strength.)

Form –

Direction –

Strength –

14.2 What is the biggest limitation a researcher faces when using a correlational design?

14.3 Give one example of a study that would need to use a correlational design?

End of Lab 10!

Answer 1

13.1

Here public speaking ability is a qualitative variable. And it is observed at four different levels. Therefore the better statistical analysis technique is to determine the effect of caffeine on public speaking by using the Kruskal-Wallis H test

The Kruskal-Wallis H test, sometimes also called the "one-way ANOVA on ranks" is a rank-based nonparametric test that can be used to determine if there are statistically significant differences between two or more groups of an independent variable on a continuous or ordinal dependent variable.

13.2: