Linear regression assumptions violated

I have an independent variable hours/day sitting and a dependent variable test scores, I think all of the assumptions of linear regression are violated, as in the pictures that I added

So I did one way anova instead and I grouped the independent variable into two catagories (6-11 hours, and 12-17 hours). And I used Mann Whitney test instead of t test following the chart that I attached from this site: https://www.spss-tutorials.com/spss-independent-samples-t-test/ I added the results of Mann Whitney test I also added the questionnaire that I used for the two dependent variables.

I'm not sure if this is the correct method because many authors say that grouping continuous independent variables is not a good method, which method should I use?

I have 6 more independent variables and I used one-way anova or t test or kruskal wallis test and Mann Whitney test separately according to violation of the assumptions.

Are these methods that I conducted correct? Sample size is 100 Thank you

• Can you tell us more about the data? You've recorded how long individuals sit in hours, and they have these test scores. Are the test scores on a 1-5 scale or something? How is that test score measured? Mar 22, 2022 at 18:27
• @DemetriPananos thank you for your response, my research is about carpal tunnel syndrome I want to determine the associated factors with carpal tunnel syndrome in college students, I have collected data from 100 students. Yes the test scores are scaled from 1-5 for each question. I have two dependent variables symptom severity scale and functional status scale. For Symptoms severity scale I took the total score, the same for functional status scale. I added the questionnaire which I used for the two dependent variables symptom severity scale and functional status scale. Mar 22, 2022 at 18:36
• ANOVA is linear regression, so cannot be a solution for violating assumptions of linear regression.
– Tim
Mar 22, 2022 at 19:13
• @Stats34 If your outcome is an ordinal outcome then you need to perform ordinal regression. Mar 22, 2022 at 21:33
• The variable you actually analyzed, though, is not continuous: when you grouped the outcome, you reduced it to (at best) an ordinal variable.
– whuber
Mar 22, 2022 at 22:55