INDIVIDUAL ASSIGNMENT:
This is an individual assignment, but you can discuss questions and help with tips on the class Slack channel (do not share completely worked solutions on the Slack channel... this assignment helps people 'practice' for parts of the upcoming quiz, so don't undermine the learning by sharing complete answers!).
--ASSIGNMENT PART 1: Optimal Sample Size --
ASSIGNMENT OVERVIEW: In this part of the exercise, you will utilize your knowledge about the optimal sample size formulas to determine the optimal sample size for a variety of marketing research scenarios.
An important thing to keep in mind is that simply using the sample size equations is quite easy (simple multiplication & division). This assignment isn't really about simply using the equations; rather, this assignment is about you applying the principles and approaches we discussed in the videos in order to correctly specify the values we plug into the equations. That's the "tricky" (and much more relevant and important!) part of sample size calculation.
For each of the scenarios presented to you in this assignment, you will need to: (1) Determine the right formula to use (2) Determine the most appropriate settings for each variable in the sample size equation (3) Report the optimal sample size required
Submission Template: When submitting your assignment, use the template provided here. The only thing you need to change is replacing the bracketed areas [ ] with your answers.
------------------------------------------------------------------------------------
SCENARIO 1: I want to estimate the average score U.S. consumers 18+ in age have on a ‘GMO or NO?’ quiz. Possible score on this quiz is from 0 to 30. I want my level of confidence to match typical marketing research practice. I want my margin of error to be within +/- 3 points. 1. Sample Size Formula to Use: [ answer here ] 2. Confidence Interval set to [ answer here ] because [explain why it is the right choice for this scenario] . 3. Margin of Error set to [ answer here ]because [explain why it is the right choice for this scenario] . 4. Variance set to [ answer here ] because [explain why it is the right choice for this scenario] . 5. Optimal Sample Size for my study = [insert number here] SCENARIO 2:
I designed a survey asking customers about their level of satisfaction with a local grocery delivery service. There were three different satisfactions questions (satisfaction with: (1) delivery time, (2) ease of ordering, and (3) courtesy of delivery agent). Each question was measured using a standard 7-point satisfaction scale.
For each of the three satisfaction questions, I want to estimate the % of people who score in the 2-Box score on a 7-point satisfaction scale.
My population is anyone who is my current customer, meaning they bought in the last 6 months. I want my confidence to be 99%. I would like my error to be +/- 5 percentage points. 1. Sample Size Formula to Use: [ answer here ] 2. Confidence Interval set to [ answer here ] because [explain why it is the right choice for this scenario] . 3. Margin of Error set to [ answer here ]because [explain why it is the right choice for this scenario] . 4. Variance set to [ answer here ] because [explain why it is the right choice for this scenario] . 5. Optimal Sample Size for my study = [insert number here] SCENARIO 3: Last year, I conducted a survey study of my customers. Results showed average customer satisfaction was 7.9 out of 10, and the standard deviation of customer satisfaction was 0.87. I am replicating that exact same study again this year. I want a confidence interval of 95%, and a margin of error of 0.10. 1. Sample Size Formula to Use: [ answer here ] 2. Confidence Interval set to [ answer here ] because [explain why it is the right choice for this scenario] . 3. Margin of Error set to [ answer here ]because [explain why it is the right choice for this scenario] . 4. Variance set to [ answer here ] because [explain why it is the right choice for this scenario] . 5. Optimal Sample Size for my study = [insert number here]
-- PART 2: Total Sampling Elements --
In this next portion of the assignment, you will use the Total Sampling Elements formula to help you determine the number of sampling elements you need for a particular research study. Recall that the TSE formula is: 
Valid Sample Size = this is the total number of valid, complete responses you desire to analyze BCI = % of people in sample estimated to have bad contact information, meaning you never reach them NR = % of people who you have correct information for, but you simply never make contact with after multiple attempts REF = % of people who you do contact, but simply refuse to participate in your study NQ = % of people willing to participate but cannot because they don't actually qualify for the study INC = % of people who qualify and start the the study, but fail to complete important sections of the study meaning their response is essentially an incomplete
-------------------------------------------------------------------------------------------------
SCENARIO 4:
I need a final, complete sample of 1,067 respondents for my survey. My client has provided me with a list of 200,000 e-mail addresses from their customer database to draw my sample. The client warned me that about 5% of the e-mail addresses are likely invalid.
Based on my own internal benchmarks, I expect about 85% of the e-mail invitations to simply go unread. However, because there is a $10 gift card incentive for a short survey, I expect only about 10% of people who see the survey invite to refuse the opportunity.
However, only 35% of the people who try to take the survey will actually qualify (customers only qualify if they have ever returned one of the company's products). Assuming people do qualify for the study, I estimate only 5% of them won't finish the survey (it only takes about 2-3 minutes to complete).
1. Total Sampling Elements = [answer here ]
SCENARIO 5:
I need a final, complete sample of 200 respondents for my survey. My client provided me with 100,000 telephone numbers of their current customers to use as my sampling frame. Previous validation efforts have confirmed that we can expect 95% of the phone numbers to be correct and active lines.
I am using a market research company that specializes in live telephone polling to collect the data. They have informed me that we can expect about 25% of people will at least answer the phone call. Among those people who pick up, 10% will agree to participate in the study.
Fortunately, the only criteria for qualification is that the person is a "current customer" of the company, so anyone who is willing to take the study also qualifies for the study. The telephone polling company told me that I can expect about 50% of the people who start the phone survey will complete the phone survey. *hint: carefully read how the information is presented in this scenario. Think carefully how this applies to using the TSE formula!
1. Total Sampling Elements = [answer here ]
Previous
Next