Prompt:

A researcher wants to answer 2 research questions related to Americans level of trust

The researcher is using the General Social Survey which has the following questions:

Generally speaking, would you say that people can be trusted or that you can't be too careful in dealing with people? The response options for this variable are (Always trusted, Usually trusted, Usual not trusted, Always not trusted)

This trust variable is coded in the dataset with the name “cantrust”

In addition, in its demographic questions the GSS asks respondents to state their highest education degree achieved. The response options for this variable are: high school or less- college or higher. This educational attainment variable is coded “college” in the dataset.



Research question #1: What percentage of Americans believe strangers can always be trusted?



Create a frequency distribution table for the variable “cantrust”. Make sure you filter out all nonvalid responses (i.e. responses coded “IAP” or “NA” or are “Blank”).



Create and show a (relative) frequency distribution table


Create and show a pie chart with the distribution of responses


State what percentage of respondents say strangers can be “always trusted”?


Calculate and interpret the 95% confidence margin of error for the proportion of Americans that answer strangers can “always be trusted”


Calculate and interpret the 95% confidence interval and make a statement of what proportion of Americans say strangers can “always be trusted”


Explain why we go through the trouble of calculating margin of errors and confidence intervals.