Two researchers conduct a survey to estimate a population's take on various issues. Each question provides a statement presenting a position on the issue, and the respondent must answer among the following choices:

A. Very strongly agree

B. Strongly agree

C. Somewhat agree

D. Somewhat disagree

E. Strongly disagree

F. Very Strongly disagree

a) The answer scale used presents a major issue in terms of measurement. What is this issue? Briefly describe the problem (max 3 lines).

For the rest of the questions below, you can assume that the problem identified in a) has been fixed.

b) To do their estimations for population parameters, the researchers aim to build confidence intervals for each question in the survey. In order to obtain a satisfactory level of confidence, the researchers aim to have answers from 2,000 respondents selected randomly from the adult population.

After initially selecting 3,000 people (randomly), they obtain 2,850 answers, as the rest of selected respondents decide not to participate. This response rate is extremely high by most standards, so the researchers decide that selection bias is a negligible problem and no special consideration will be given to it. Do you agree? Why?

c) Given that the results will be used to inform the design of an important policy, the researchers worry about ending up with confidence intervals that do not contain the true parameter for each question (i.e., the value of the average answer to each question for the entire population). If they want their intervals to keep the same width as with their original results, what should they do? Be specific and state why.