Here is a sample of my starting dataset. As mentioned in the previous page, there are 983 unique entries comprised of 109 different respondents, each respondent had 9 different tasks where they recorded whether they would buy or not buy based on the type of fish (Tuna, Halibut or Salmon), how the fish was raised: (wild, farm or farm GMO) and the price ($19.99, $13.99, $16.99).
Using salmon as the baseline type of fish and farm raised/genetically modified as the baseline production method, I created a binary logit model inorder to calculate probabilities of buy or no buy with different circumstances. I let price enter the function linearly.
In order to maximize the likelihood of buying, I found that my baseline type, Salmon is the best option to maximize likelihood of purchase and farm raised is the best method to maximize purchase likelihood. Additionally, price has a significant negative correlation with likelihood to buy so the lower price of $13.99 is the best price to maximum purchase probability.
Calculated probability of EACH individual
Here I have computed the derived importance of each attribute. Based on my calculations, I am able to conclude that the METHOD in which fish are obtained is the most important factor to a consumer when deciding to buy or not to buy.
I then calculated the dollar value of the competing criteria in relation to the baseline of Salmon and Farm GMO.
In this last section, I got thrown a curveball with a new marketplace and offerings, shown below.
I used the logit rule to compute the share of respondents predicted to choose each option at the given prices. Then I ran the logit again and compared what happens to the share of Farm Raised Salmon (Product 4) if it becomes Farm Raised and Genetically Modified (still priced at $13.99).
Lastly, I was asked to hold the price of Product 1, Product 2 and Product 4 constant and predict the product shares when the price of Product 3 (the Wild Salmon) varies from $13.99 to $19.99 in increments of $3.00. From there, compute the own and cross price elasticities of the product shares.
From calculating the price elasticities, I observed that Products 1,2,4 and none all had the same elasticity of 52.037 percent. This can be explained by the fact that the only variable changing is the price of product 3. The elasticity of Product 3 is -1.08 which tells us that as the price rises, people demand less of Product 3, Wild Salmon.
​
If you're only looking at product 3, this a sensible pattern of price competition because it shows that as price increases demand decreases. However, overall, this pattern of price and elasticity only showcases product 3 and is not sensible for an overall picture of all the products in the market.