EDP 480C – Statistical Analysis for Experimental Data
Homework 1
Grading: This assignment is worth a total of 25 points.
Due date: This is due on Thursday (2/27/25). Work should be submitted on time for full earned
credit. Late work will be accepted for full earned credit if and only if special arrangements are made
with me prior to the due date; otherwise 5% of the total points possible will be deducted for each day
the assignment is late.
In a study of the effect of different messaging in advertising on purchasing, an experimenter recruited
60 college undergraduates and randomly assigned them equally into three different groups. Each
undergraduate student was shown the same picture of an off-brand smartphone and different
messaging with the picture. The dependent variable was the score on the “Attitudes Toward
Purchasing” survey which was administered immediately following the student looking at the
advertisement picture of the smartphone for 30 seconds. Students in group 1 only observed
advertisement of the smartphone (e.g., the look of the phone with optional colors; visuals of photos
taken by the smartphone) with no messaging. In group 2, students observed the same advertisement of
the smartphone in addition to messaging about saving 50% or more when purchasing the smartphone
compared to the iPhone and a link to information discussing more differences between the advertised
smartphone and the iPhone. In group 3, students observed the same advertisement of the smartphone in
addition to messaging about saving 50% or more when purchasing the smartphone compared to the
iPhone and messaging detailing the differences between the advertised smartphone and the iPhone
(e.g., less available apps, less nationwide coverage). These data are in a CSV file entitled,
“[Link].” Below are the data descriptions:
A. advertisement = The type of advertisement each student observed before completing the
survey (1 = control/advertisement visuals only; 2 = advertisement visuals and messaging about
saving 50% or more compared to iPhone with link to information about differences between the
smartphone and the iPhone; 3 = advertisement visuals and messaging about saving 50% or
more compared to iPhone with details about differences between the smartphone and the
iPhone).
B. ATP = Score on the “Attitudes Toward Purchasing” survey (higher scores indicate higher
likelihood of purchasing the smartphone).
Being the brilliant ANOVA student that you are, the experimenter comes to you for help with the
analysis. The experimenter would like to know if the different advertisements (control, link to
differences with iPhone, detailed differences with iPhone) affect their attitudes toward purchasing the
smartphone. In other words, are there significant differences between the three advertisement groups
examined in the study? Assume that outliers, normality, and independence of observations have been
checked and that there are no problems dealing with those issues. To help the experimenter:
1. Write up a summary of the ANOVA results. Use the Eysenck Results Example as a guide and
be sure to include the following information in your results summary:
Purpose of the Study: Indicate the general purpose of the study/experiment and what
statistical procedure was used. (1 point)
1
Assumptions: Indicate whether the homogeneity of variance assumption was violated. If
so, indicate whether the ANOVA is “robust” or indicate what should be done to remedy the
violation (e.g., perform another type of test). (2 points)
ANOVA Results: Indicate whether or not the type of advertisement significantly affected
attitudes toward purchasing and include the statistical proof (e.g., F (2, 27) = 5.4, p < .05).
In addition, include an ANOVA source table and refer to it when describing the overall F
test results (please do not simply copy the table from the R output and paste it into your
document). (6 points)
Strength of the Relationship: Indicate the strength of the relationship between
the independent variable and dependent variable using partial eta squared or R squared and
compare the value to the predetermined threshold value to indicate if a substantial
proportion of the variation in the dependent variable is attributable to the factor. (2 points)
Post Hoc Procedures: Indicate the type of post hoc procedure you used to make
comparisons among groups. Include a table of comparisons that includes the mean
differences, the standard errors, the confidence intervals, and asterisks to signify significant
differences between two groups. Using plain language, indicate which groups significantly
differed from one another and indicate the direction of that difference (which group had
significantly more or less of the dependent variable). NOTE: Be sure to create this table of
comparisons (please do not simply copy the table from the R output and paste it into your
document). (8 points)
Table of Descriptives: When indicating the direction of the differences between groups (as
described above), be sure to refer to and include a table with the mean and standard
deviation for the dependent variable in each group as well as the number of participants
within each group. NOTE: Be sure to create this table of descriptives (please do not
simply copy the table from the R output and paste it into your document). (3 points)
Be sure to upload all the relevant R output in addition to your write up to receive full credit.
(3 points)
If you have any questions, please do not hesitate to contact me or your friendly Teaching Assistant.