The QA program coordinator is trying to determine the best way to invest departm

Question

The QA program coordinator is trying to determine the best way to invest department funds in Facebook Newsfeed advertising.He has data on click-thru rates from the previous round of advertising, broken down by gender and location for several randomly selected dates.He wants to use ANOVA to determine what effect each of those two factors has on the rates.

a) What type of factorial design is this (circle/underline/highlight one)?

i) 2X4

ii) 4X2

iii) 2X4X3

iv) 4X2X3

b) Check whether it is appropriate to use ANOVA to determine whether there is significant difference between the means for gender and location. (Show/explain why it is or isn’t).

c) Complete the ANOVA analysis on whether there is significant difference between the means for gender and location (Do this even if you found it to not be appropriate in step b. You do not need to do any post-hoc/Tukey analysis.)

Gender Male Female Georgia 2.0 2.8 1.2 1.5 2.0 1.1 Location Southeastern US Other US 1.7 2.6 2.2 1.0 1.5 2.2 2.6 2.4 3.0 1.0 0.9 2.5 International 2.6 1.6 1.4 2.1 1.0 2.3

Explanation / Answer

a) the correct answer is a , 2 Independent variables with 2 levels in first and 4 levels in the second variable

b) and c )

we can use anova to analyse the results as we have 1 continous variable and 2 independent variables Gender and location

we will use open source statistical package R to analyse the results. The complete R snippet is as follows

# read the data into R dataframe
data.df<- read.csv("C:\Users\586645\Downloads\Chegg\location.csv",header=TRUE)
str(data.df)

# perform anova analysis
a<- aov(lm(value ~ gender+location,data=data.df))

#summarise the results
summary(a)

############

the results are

> summary(a)
Df Sum Sq Mean Sq F value Pr(>F)
gender 1 0.007 0.0067 0.014 0.907 ## not significant , as the p value is not less than 0.05
location 3 0.660 0.2200 0.460 0.713 ## not significant , as the p value is not less than 0.05
Residuals 19 9.087 0.4782

hence we see that gender and location (main effects) has no significant effect on the click thru rates

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.