Hi all,
I have found an association between social distancing attitudes and the willingness to do social distancing, as studied on a Likert type scale (Never to Always). Now there is also an association between what type of work they have and the same response.
My question is how can I isolate the influence of city from the influence of line of work? Wondering if there is a technique for nominal/ordinal variables similar to adjustment/control variables in regression. I would be interested in anything from AI / statistics, preferrably to be used in R or Excel.
And open for collaborations if anyone wants to co-author or similar
You say you used a Likert type scale, but did this consist of a single-likest scored question, or a set of questions that could be combined?
Your case, as you have described it, is exactly the situation the Cochran-Mantel-Haenszel test is designed for. Many people are familiar with it only in the case where there are many 2×2 tables, but there are generalizations that apply to tables with more than two rows and more than two columns.
Dear Hakan Lane
This article might be helpful, have a look:
https://www.unthsc.edu/newsroom/story/managing-the-emotional-impact-of-isolation-in-remote-work/
Kind Regards
Qamar Ul Islam
Three different questions:
How many contacts? (pure scale)
How willing are you to self-isolate for 7 days? (5 steps, very unwilling to very willing)
How often do you wear face masks? (5 steps, never to always)
Please add more detail on the outcome. Is it a validated scale with multiple items that measure the willingness towards social distancing? If yes, did you perform the background work to know whether to combine the item scores to make a scale score or not? based on that, if you are interested in item-specific adjusted measures of influence, ordinal regression can be done. If you are interested at the scale level, multiple linear regression should suffice.
Search on the Internet either three-way contingency table or two-way contingency table. It gives you the required insight.
Hi
Please read the questions before you write an answer. It is clear from the first post that I already know what contingency tables and chi-squared tests are. Now to those who gave good points, here goes:
I have 2-3 different predictors, both categoric
3 different responses, two on different Likert scales and one numeric . They have completely different dimensions and can not be combined.
My wish is to find a way to quantify which of the categoric has the most influence on the outcome. They are related as well so there is kind of a mutlicollinearity for nominal variables. The Cochran-Mantel-Haenszel looks like the best option
It sounds like you could be analyzing 2-way and 3-way tables with large numbers of cells. What size is your sample?
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Artificial Intelligence