Data Cleaning and Summary

We started out with 330 responses to our survey; 62 were removed by the screening and consent questions. Of those left, only 251 respondents answered all the choice questions. However, 37 chose the same response for every question, and so were discarded. We further took into consideration how long respondents spent on the entire survey, eventually removing the bottom 5th percentile of responses, those who spent less than 2.9 minutes on the survey. In the same vein we checked how long respondents spent on each individual choice question, setting a minimum of 3 seconds to read the three alternatives and weigh them against each other. Ultimately, we ended up with 201 responses to analyze.

The demographics information we collected in those responses is summarized as follows.

More women than men took our survey, with 53.7%. In total there were 2 who chose not to report their gender and 5 who reported their gender as “Other”.

We can see in the chart that the age distribution skews younger. In fact 49.8% were born before 1990. Only 3 people chose not to state their age.

The above table shows all the races that were reported by respondents. Of these, 13 respondents reported multiple races.

Collection of states of residence ended up being nigh meaningless, with state population and respondent concentration following similar trends.

As we can see in education, there is a huge concentration of respondents with Bachelor’s degrees. Bachelor’s degrees accounted for 98 and 48.8% of respondents. Combined with graduate degrees, completed college educations accounted for 63.7% of all respondents.

From graph, income looks to be mostly normally distributed around about $60,000 a year.

We can see a majority of respondents live in 1- or 2-person households. (A total of 67.6% in fact.) Answers ranged from 1-person housedholds up to 8-person households. There were also 25 respondents who chose not to report the number of adults in their household. The response for minors was even worse, with 158 not providing any response, not even a zero, making us unable to use that data in any meaningful way.

Because we were recording the times as respondents went through the survey, we were able to make a guess at whether respondents took the time to actually watch the educational video or not. The video was 80 seconds long, and the timespan covered the following page where Omao was introduced; we therefore decided on 2 minutes as being the minimum amount of time to spend on those pages if the video was watched. As you can see here, the split is fairly even. By this metric, 56.7% of respondents watched the video.

Modeling

After data cleaning, we apply the estimate multinomial logit (MNL) models by the logitr, which is a library package in R that help us to create the model and conduct further analysis.

First, we have to create some dummy coded variables for categorical variables for the attributes of material and setOptions. Due to plastic disposable cutlery being the most numerous product on the market, we decided to set Plastic as the baseline of the material attribute. As for the setOption, we selected simplest set type as the baseline, which is the package that only includes a fork.

Model Equation \[u_j = \beta_1 x_j^{price} + \beta_2 x_j^{quantity} + \beta_3 \delta_j^{Bamboo} + \beta_4 \delta_j^{Eco} + \beta_5 \delta_j^{setFK}+\beta_6 \delta_j^{setFKS} + \varepsilon_j\]

If the product is plastic, the Bamboo and Eco dummy variables will be zero; likewise, if the set type of product is fork only, setFK and setFKS will be zero.

To build the model correctly, we would need to divide the price with the default quantity, which is 50.

The following is the summary of the multinomial logit (MNL) models.

#> =================================================
#> Call:
#> logitr(data = data, outcome = "choice", obsID = "obsID", pars = c("set_price", 
#>     "quantity", "material_Bamboo", "material_Eco", "setOptions_fk", 
#>     "setOptions_fks"))
#> 
#> Frequencies of alternatives:
#>       1       2       3 
#> 0.37313 0.51244 0.11443 
#> 
#> Exit Status: 3, Optimization stopped because ftol_rel or ftol_abs was reached.
#>                                 
#> Model Type:    Multinomial Logit
#> Model Space:          Preference
#> Model Run:                1 of 1
#> Iterations:                   13
#> Elapsed Time:        0h:0m:0.05s
#> Algorithm:        NLOPT_LD_LBFGS
#> Weights Used?:             FALSE
#> Robust?                    FALSE
#> 
#> Model Coefficients: 
#>                    Estimate  Std. Error z-value  Pr(>|z|)    
#> set_price       -6.26461527  0.50041805 -12.519 < 2.2e-16 ***
#> quantity        -0.00770772  0.00059816 -12.886 < 2.2e-16 ***
#> material_Bamboo  1.58033458  0.09752304  16.205 < 2.2e-16 ***
#> material_Eco     2.07456124  0.09869923  21.019 < 2.2e-16 ***
#> setOptions_fk    1.10057164  0.10063229  10.937 < 2.2e-16 ***
#> setOptions_fks   1.72934820  0.10270681  16.838 < 2.2e-16 ***
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>                                      
#> Log-Likelihood:         -1250.1664989
#> Null Log-Likelihood:    -1766.5685602
#> AIC:                     2512.3329978
#> BIC:                     2544.6295000
#> McFadden R2:                0.2923193
#> Adj McFadden R2:            0.2889229
#> Number of Observations:  1608.0000000

We need to focus on the model’s coefficients.

From the result, we could see that the coefficients of price are negative which means people prefer the cheaper product. The effect on quantity in the package is really small.

For the material attribute, we could see that material_Bamboo and material_Eco are all positive, which means people prefer material of disposable cutlery in bamboo and Eco-friendly materiel over plastic, especially for the Eco-friendly one.

For the setOptions attribute, we could see that people all slightly prefer the set types that include fork&knife and fork&knife&spoon more than the package only include a fork.

Other Approach

We also run the model that set price and quantity as the categorical variables. From this model, we could slightly tell the difference effect of quantity; however, for the feature of the dataset and further analysis, we believe that the variables price and quantity should be numerical data.

Utility

Let’s see the apply our default setting of the product to the utility to review each attribute and review the model more clearly. We can clearly see that the influence of quantity is the smallest and you can headly tell by the visulization result.

We also run the model that sets price and quantity as the categorical variables. From this model, we could slightly tell the difference among different quantities; however, for the feature of the dataset and further analysis, we believe that the variables price and quantity should be numerical data.

Willingness to Pay

Using the data that we collected from our survey, we computed consumers’ Willingness to Pay for the attributes Quantity, Set Option, and Material using the model data.

From our computations it is evident that the WTP for quantity is the lowest with a value of $-0.0012306. This value being near 0 indicates that quantity as an attribute did not have much impact on consumers’ willingness to pay. It did however seem to have a negative correlation, indicating that large quantities are not seen as desirable. On the other hand, material has a strong effect on willingness to pay. With plastic as the base model in our computations, consumers were willing to pay $0.1758702 extra for Bamboo. Eco-friendly material is even more desirable, with a WTP of $0.2760958. This proves that consumers value sustainability in their cutlery more than price. The set options FK and FKS (with F set as base) have willingness to pay values of $0.2525033 and $0.3313158. The difference implies that consumers were willing to pay more for a set consisting of a fork, knife & spoon as opposed to fork & knife or fork only.

The below plot of all the computed willingness to pay along with their 95% confidence intervals, helps visualize the results better.

Market Shares

To understand the market share that Omao could achieve based on our model, we ran a market simulation to predict probable market shares of different products. The competing products that we used to identify the market shares are given below.

By the running this single market alternative, we found that Eco-friendly material takes the highest market share of all the materials with 66%. Bamboo captures a market share of 32%, while plastic captures the least with 2%.

This indicates that the Eco-friendly option has a stronger stand in the market compared to bamboo and plastic alternatives.

To confirm the market shares, we ran a simulation using multiple alternatives. On comparing our baseline parameters with multiple market data, we noticed a repeated pattern of Eco-friendly material capturing the highest market share and plastic capturing the lowest.

On running this simulation, the Eco-Friendly material captured a market share of 72%, 50%, 5%, while bamboo held market shares of 23.8%, 18.4%, 68.3%. In both the single and multi model simulations, plastic mostly held the lowest market share of 4.3%, 31.5%, 26.8%

From our analysis, it is understood that the material used for the cutlery influences the market shares more than the set options and quantity.

Sensitivity Analysis

To identify the impact of the price of the cutlery on the market shares, we ran a simulation using prices from our baseline model. For this computation we changed the price per set of the Eco-Friendly option to identify the change in market shares (the set price was also presented to our survey takers).

From our analysis, a downward trajectory is evident with the market shares gradually falling when the price per set increases. Market share drops from 91% at a price of $0.20 per set to 2% at a price of $1.20. This could be a result of people valuing the eco-friendly material more than its price.

The error terms at our price of $0.80 per set indicate that the market could be as high as 26% or as low as 15%.

This also means that Eco-friendly cutlery prices could be increased, based on the target market share. The optimal price point to maintain at least a 50% market share would be between $0.50 to $0.60 per set.

Sensitivity of Revenue to Price

Our sensitivity analysis indicates that revenue of the market is reasonably sensitive to changes in price. The curve shows that as price increases, revenue increases. But this is only true when price increases from $0.20 to $0.80. The mean revenue drops from $3.1 Million for a price of $0.50 per set to a mean revenue of $2.80 Million for a set price of $0.60. This shows that by increasing the set price from $0.50 to $0.60 per set, there is a possible revenue drop of $0.3 Million. Therefore, based on our analysis the ideal price to maximize revenue should be between $0.50 to $0.60.

With the survey data that we collected, for our baseline cutlery market data, a revenue of $3.02 Million to $1.6 Million is achievable.

Disposable Cutlery Study Survey

Welcome to our survey!

We are engineering graduate students from George Washington University conducting market research on people’s preferences when it comes to using individually wrapped disposable cutlery on a day-to-day basis. We would love to hear about what you value the most when you purchase disposable cutlery for your personal use. The results of this survey will give us insights into what product attributes to prioritize when designing a new, eco-friendly disposable cutlery.

We realize how precious your time is, so this survey will take you no more than 10 minutes to complete.

Talk to us if you have any questions, concerns, complaints, or think you have been harmed. You can contact us via email at omaoanalytics@gmail.com

To ensure anonymity, your signature is not required. Your willingness to participate in this research study is implied if you proceed.

We really appreciate your input and your time!

Screenout Questions

Thank you for your interest in this survey.

Before we bog you down with learning more about this study, let’s see if this survey is for you!

Are you currently living in the United States?

• Yes, I am currently living in the U.S.
• No, I am currently living outside the U.S.

How often do you use disposable cutlery?

• Never
• Less than once a month
• About once a month
• About 2 or 3 times a month
• bout once a week
• 2-5 times a week
• Every day

Consent form

This survey is conducted by students from the George Washington University in Washington, D.C.

We will not be collecting any sensitive personal information such as your name or address. Your participation and your specific answers will be completely anonymous.

Your participation is voluntary and you may exit the survey at any time as you wish.

If you would like to participate, please answer the following questions:

I am age 18 or older

• Yes
• No

I have read and understand the above information:

• Yes
• No

Background

Why not plastic?

Here is why…

The following short video will explain a little more about the plastic materials situation.

(Heads up! We will be asking one question from this video)

According to the video, what percentage of plastics are not recycled?

• 95%
• 10%
• 91%
• 50%

Introduction

What is Omao?

Omao is a company that discovered a biodegradable material that can be used in place of disposable plastics. Omao’s biodegradable material decomposes in about 90 days upon disposal!

Why Omao?

Most of the so-called ‘green’ straws are made of PLA (Polylactic acid, or ’corn-plastic). PLA straws only break down in a strictly controlled composting environment. Indeed, PLA straws could take anywhere from 100 to 1,000 years to decompose in a landfill, just as bad as traditional petroleum-based plastic straws.

Omao solves this problem with its groundbreaking material- PHA (Polyhydroxyalkanoates), an advanced, bio-plastic that will naturally breakdown to carbondioxide and water. PHA is a naturally-occurring material derived from vegetable oil. ^Source

Product Attributes Introduction

This survey is designed to gather information about 4 different product attributes and how they matter to consumers.

Attribute 3: Material

Disposable cutlery can come in several different materials. For the purposes of this survey we will be presenting General plastic, Biodegradable plastic, and Bamboo. In our choice questions cutlery images with a green leaf mark denote bio-degradable plastic, wood color denotes bamboo, and plain white denotes general plastic.

From left to right: General plastic. Biodegradable plastic. Bamboo.

Attribute 4: Set Content

This attribute presents the choice of utensils in one package at time of purchase. The images below explain our set options:

From left to right: A package includes a fork only. A package includes a fork and a knife. A package includes a fork, a knife and a spoon.

All of the above information is summarized in the table below.

Let’s Practice!

Let’s do a quick practice question. Look at the three options below, and choose which option you would prefer to buy.

For example, if these were the only products available, which would you choose?

Option 1

Material: Plastic

Price: $20 ($0.40 each)

Quantity: 50 sets per box.

Set Content: A package includes a fork and a knife.

Option 2

Material: Bamboo

Price: $20 ($0.40 each)

Quantity: 50 sets per box.

Set Content: A package includes a fork and a knife.

Option 3

Material: Eco

Price: $20 ($0.40 each)

Quantity: 50 sets per box.

Set Content: A package includes a fork, a knife and a spoon.

Great Work!

Now let’s begin the choice tasks from the next page. You will be asked 8 questions in total similar to the practice question. (Only one question reproduced here)

Nice Job!

You have completed the main survey part!

Now, we’d like to ask you for some basic demographic information. As a reminder, your answers will be completely anonymous and we will not be collecting any personal information such as your name or address.

Almost Done!

Your answers are appreciated, as we will be incorporating them into the analysis.

1. In what year were you born?

• (Drop down menu including Prefer not to say and years 1920 - 2003)

2. What is your current gender identity?

• Man
• Woman
• Genderqueer/Gender non-conforming/Other
• Prefer not to say

3. I identify my race as (select all that apply):

• Asian
• African American or Black
• White (Not of Hispanic or Latino origin)
• Hispanic or Latino
• American Indian or Alaska Native
• Native Hawaiian or Pacific Islander
• Prefer not to say
• Different identity (please state):

4. What state or region are you currently living in:

• (Drop down menu including all states selections)

5. What is the highest degree or level of school you have completed? If currently enrolled, please use the highest degree received.

• Less than a high school diploma
• High school degree or equivalent (e.g. GED)
• Some college or university, no college degree
• Trade/technical/vocational training, no degree awarded
• Associate’s degree (e.g. AA, AS)
• Bachelor’s degree (e.g. BA, BS)
• Graduate or Professional Degree (e.g. PhD, MD, JD, MS)
• Prefer not to say

6. What is your annual household income (from all sources) before taxes and other deductions from pay?

• Less than $10,000
• $10,000 - $14,999
• $15,000 - $24,999
• $25,000 - $34,999
• $35,000 - $49,999
• $50,000 - $74,999
• $75,000 - $99,999
• $100,000 - $149,999
• $150,000 - $199,999
• $200,000 or more
• Prefer not to say

7. How many adults (over 18) live in your household? (Optional Question)

• (Rolling number selection)

8. How many minors (under 18) live in your household?(Optional Question)

• (Rolling number selection)

9. How often did you use disposable cutlery before the COVID-19 pandemic?

• Never
• About 2 or 3 times a month
• About once a week
• About 2-5 times a week
• Everyday

10. How often do you use disposable cutlery since the COVID-19 pandemic?

• Never
• About 2 or 3 times a month
• About once a week
• About 2-5 times a week
• Everyday

11. What platform(s) do you frequently use to get your disposable cutlery? (Optional Question)

• Online website
• Physical Box Stores, e.g. Walmart, Dollar Store, Target
• Physical Supermarkets or Groceries
• With delivery orders or takeout

Congratulations! You have reached the end of this survey.

Please indicate below with any thoughts and feedback about our survey. (optional) Your feedback will help us make future improvements :)

Finish