Acme Dog Nutrition: Market Segmentation using Wards Clustering and R

Market Survey

You are the marketing manager for Acme Dog Nutrition, an organic, gluten-free food for active dogs.  You believe that not all dog owners are the same. You seek to identify groups among dog owners, with the objective of finding the group(s) who will appreciate the extra care and quality found in every kernel of Acme Dog Nutrition. To that end, you conduct a market survey using a 7-point Likert scale, asking each respondent to state their agreement from 1 (strongly disagree) to 4 (neutral) to 7 (strongly agree). The statements are:

S1: It is important for me to buy dog food that prevents canine cavities

S2: I like dog food that gives my dog a shiny coat

S3: Dog food should strengthen gums

S4: Dog food should make my dog's breath fresher

S5: It is not a priority for me that dog food prevent tooth decay or cavitiies (reverse coded)

S6: When I buy dog food, I look for food that gives my dog shiny teeth

You also collect age and gender data for use in later research. The table below shows the header row on top and 10 of the 45 rows of data under the header. The first six columns show the responses to the market survey for statements S1 – S6. The next three columns show the respondent’s age as an integer, the age category (twenties, thirties, forties, etc.), and gender (male or female).

To identify the groups, you will use the statistical software program known as R to execute the following actions:

Wards: Apply Wards Agglomerative Hierarchical Clustering with Dendograms to identify the number of clusters in the dataset

Interpretation: Interpret the resulting clusters to find actionable patterns or descriptions in the data so you can market to each of the various groups using distinct and effective messaging.

Using Wards, estimate the number of meaningful clusters present in the dataset. Follow the steps listed below to execute the Wards clustering method. Provide screenshots and/or commentary for each step. Refer to the R lecture for detailed instructions.  

a. Download R

b. Launch R

c. Prepare the data file (delete everything except the data and the header, and then save in CSV format)

d. Find out the full filename for the file

e. Read in the data, using the full filename, using the read.csv command in R

f. Confirm that data was properly loaded, using the print(filename) command in R

g. Start executing Ward’s by calculating the distance matrix (dist command)

h. Continue executing Ward’s by calculating the clusters (hclust command)

i. Continue executing Ward’s by plotting the Dendogram (plot command)

j. Interpret the resulting Dendogram. Identify 3 clusters.

k. Determine the membership in each cluster (build matrices for each cluster)

l. Calculate the means for each S variable (S1 – S6). 

m. Identify the dominant S values (S1, S2, S3, S4, S5, or S6) for each cluster

2. Describe the resulting clusters in a meaningful way so you can market to them using distinct messaging for each segment.

a. Cluster 1 interpretation: 

b. Cluster 2 interpretation: 

c. Cluster 3 interpretation: 

3. Compare the clusters you identified with actual segments used by the dog food industry.