weeeek 6

There are four different alternative ways of answering our questions in total:

1. Their gender: Female (1), Male (2), Gender Fluid (no numeral code because we did not receive any), Prefer Not To Say (3).

2. Their age: open-ended.

3. One interval scale: 0-1 (1), 2-3 (2), 4-5 (3), 6-7 (4).

4. Second interval scale: Never (1), Very Rarely (2), Rarely (3), Occasionally (4), Frequently (5), Very Frequently (6). 

Since last night, my team and I coded our 31 survey responses. Now we need to do the hard part, figure out which formulas to use and which variables. We have 56% Female, 42% Male, and 2% Prefer Not To Say. The majority of our ages are from 20s to mid 70s. However, now we have an additional 12 (43) responses. Should we go through and add these new responses to our codebook?

My team is taking our response and converting them into numerical values. For those results where the answered 0-1, 2-3, 4-5, 6-7 we put a 1-4 value. Same with those that were never-very frequently, these went from 1-6. Once all of these have numerical values we can get the mean, median, and mode of scores between women and men or even between ages. We have a good clumping of ages with roughly half being within their mid to late 20s and the other half 50+. We can group those two together to see how stress and sleep effects them differently between alcohol usage, perceived anxiety, and restlessness. Not entirely certain which statistical test to run though.