Question

1. We want to compare whether people give a higher taste rating to Ulker or Eti petit-beurre biscuits. A blind tasting is executed to avoid psychological effects, (i.e., subjects don't know the brand of the biscuits). Describe how to design a study involving independent samples and dependent samples.

1. Design involving independent samples
2. Design involving dependent samples

Answer 1

a. (Using independent samples)

We can carry out the experiment as follows:

-Select 2n individuals and randomly divide them into two groups.

- Give one group Ulker and the another Eti petit-beurre in a blind fashion (i.e. the subjects don't know which biscuit they are testing).

- Record a response on taste-rating from each of the subjects.

-In this manner we have two independent samples. Now carry out an independent sample t-test to validate any research question.

b. (using dependent samples)

- Select n individuals randomly

- Give two biscuits each of them. Ensure the following: i) They don't get to know which biscuit they are tasting. ii) Maintain a wash-out period, i.e. ensure a proper gap between tasting the two biscuits, so that the taste on one doesn't effect the another.

- Record two responses (X,Y) from each individuals

- In this way we have a bivariate sample of length n from each of the individuals, and the observations are dependent as the two responses are coming from one particular individual.

-Now carry out a paired sample t-test to validate any research question.