1
Week 5 Research Project Exercise: Analysis.
Your name
Institutional affiliation
Course
Date
2
H1a: People are more likely to buy cupcakes when they’re on sale.
It is reasonable to assume that people may be more inclined to purchase cupcakes when
they are on sale, as a sale may make the product more appealing due to the perceived value or
cost savings. To test this hypothesis, data would need to be collected on cupcake sales during
both sale and non-sale periods, and then analyzed to determine whether there is a significant
difference in sales during these periods.
Experiment: To test the hypothesis that people are more likely to buy cupcakes when
they are on sale, a randomized controlled trial (RCT) can be conducted. A sample of cupcake
consumers from a population will be selected and randomly assigned into two groups: a
treatment group and a control group. The treatment group will be offered cupcakes on sale,
while the control group will be offered the same cupcakes at regular prices. The cupcakes in both
groups should be of the same quality and quantity and should be sold in the same location.
Records of how many cupcakes are sold in each group during a specified time period will be
kept. A Comparison of the % of shoppers who buy cupcakes when they’re on sale vs. when
they’re not on sale will be made. An analysis of the data to see if there is a significant difference
in the number of cupcakes sold in the treatment group compared to the control group will be
conducted.
Comparison. The main focus of this hypothesis test is Frequency. Chi-square test can be
used to analyze the data collected from the experiment designed to test the hypothesis that people
are more likely to buy cupcakes when they are on sale. The Chi-square test is used to determine
if there is a significant association or relationship between two categorical variables. In this case,
the categorical variables are "cupcakes purchased" (either on sale or at regular price) and "group"
(treatment or control). The observed number of cupcakes purchased in each group can be
3
recorded and compared to the expected number of cupcakes purchased in each group assuming
that there is no significant difference between the groups. The Chi-square test can then be
performed on these observed and expected values to determine whether the difference in cupcake
sales between the treatment and control groups is statistically significant.
H1b: The lower the price, the more cupcakes people buy.
The hypothesis that the lower the price, the more cupcakes people buy is a reasonable
assumption. Price is one of the key factors that influences consumer behavior, and it is expected
that people will buy more cupcakes when they are cheaper. To test this hypothesis, data should
be collected on cupcake sales at different price points, and then analyzed to determine if there is
a correlation between price and the number of cupcakes purchased.
Experiment. A sample of cupcake consumers from a population will be selected and
offered cupcakes at different price points. For example, cupcakes can be offered at $1.00, $1.50,
$2.00, and $2.50. Records of how many cupcakes are sold at each price point during a specified
time period (such as a week or a month) will be made. The data will then be subjected to analysis
to see if there is a significant correlation between the price of cupcakes and the number of
cupcakes sold.
Comparison. The objective of this hypothesis is to compare the means. This can be done
using statistical tests such as ANOVA. ANOVA (Analysis of Variance) can be used to test the
hypothesis that the lower the price, the more cupcakes people buy. ANOVA is a statistical test
that compares the means of three or more groups to determine if there is a significant difference
between them (Kao, 2008). After calculating the mean number of cupcakes sold at each pricing
point, ANOVA to compare the means of the different price points. If there is a significant
4
difference between the means, it suggests that price is a significant factor in determining the
number of cupcakes sold. However, if there is no significant difference between the means, it
may suggest that price is not a significant factor in determining the number of cupcakes sold, or
that other factors are more influential.
H1c: The lower the price, the more people buy, but only in the morning.
This hypothesis suggests that the effect of price on cupcake sales may be dependent on
the time of day.
Experiment. A sample of cupcake consumers from a population will be selected and
randomly assigned to different price points. For example, cupcakes can be offered at $1.00,
$1.50, $2.00, and $2.50. They will be offered cupcakes at different price points during two
different time periods: morning (e.g. 8am-12pm) and afternoon (e.g. 1pm-5pm). A record of how
many cupcakes are sold at each price point during each time period will be kept. The data will be
subjected to analysis to determine if there is a significant correlation between the price of
cupcakes and the number of cupcakes sold in the morning and afternoon time periods separately.
Comparison. The focus of this hypothesis is on the mean. Two-way ANOVA (Analysis
of Variance) can be used. A two-way ANOVA allows for the analysis of two independent
variables (in this case, price and time period) and their interaction on the dependent variable (in
this case, the number of cupcakes sold) (Sturm-Beiss, 2005). The advantage of using a two-way
ANOVA is that it allows for the evaluation of whether the effects of price and time period on
cupcake sales are independent of each other or if there is an interaction effect between the two
variables. An interaction effect will suggest that the effect of price on cupcake sales depends on
the time period, and vice versa.
5
References.
Kao, L. S., & Green, C. E. (2008). Analysis of variance: is there a difference in means and what
does it mean?. Journal of Surgical Research, 144(1), 158-170.
Sturm-Beiss, R. (2005). A visualization tool for one-and two-way analysis of variance. Journal
of Statistics Education, 13(1).