Question

Let’s say that someone collects data on the kind of soda people prefer. We’ll call the different soda flavors A, B, C, and D. They find that 15% of people preferred A, 20% of people preferred B, 30% of people preferred C, and 35% of people preferred D.

1. tell what kind of data this is (numerical or categorical),

2. what the population and sample are,

3. how the data is being summarized,

4. how you think the data might have been collected, and what this data might be used to infer.

Answer 1

1. This is numerical data since there is clearly quantitative information given when percentage of people favoring a specific soda flavor is talked about.

2. Population : Set of all the people in that geographic region ; Sample : A finite size subset of people taken out from the full population.

3. Data is being summarized in terms of the proportion of people favoring a particular soda flavor.

4. Data might have been collected through a survey done across various regions where the entire population of interest is living. This data might be used to infer the actual fraction of people in the overall population who prefer a specific soda flavor and as a result, one can infer the most popular soda flavor among the people in the population.