Wed 13 Jul, 2022 01:58 am
This is real data file condensed from a study conducted to explore the prevalence and impact of sleep problems on various aspects of people's lives. Staff from a university in Melbourne, Australia were invited to complete a questionnaire containing questions about their sleep behavior (e.g. hours slept per night), sleep problems (e.g. difficulty getting to sleep) and the impact that these problems have on aspects of their lives (work, driving, relationships). The sample consisted of 271 respondents (55% female, 45% male) ranging in age from 18 to 84 years (mean=44yrs).
- What is the main reason for sleep problem
- What are the worse effects of those sleep problems
What is the best way to approach the aforementioned questions?
- For the first one, can a multiple regression be conducted given that the independent variables (potential predictors) have a different scale of measurement?
- For the second one, can a correlation statistical test be conducted to find the effects that correlate highly with the presence of a sleep problem, and if so which test would that be?
First, you need to identify your independent variables. I would think age and gender are key ones, but hopefully there are others on the questionnaire. Then you can look at your regression to see which has the biggest impact. For the second one, what is the definition of "worst"? Small impacts to driving (which could result in deaths) might be worse than medium impacts to work for example. I suppose you could look for metrics with the largest percentage change or largest absolute change. Again, this is open to interpretation. If work problems go from 8 to 12% of people (an increase of 4% points but 50% overall), is that worse or better than relationship problems that go from 1% to 2% of respondents (only 1% point, but doubled in severity)?