# Alternative approach if dependent variable violates regression linearity

I am working on a research project to identify the impact of dominant personalities, and sexual esteem on sadistic behavior. I am also completely new to statistical analysis.

Both of my independent and dependent variables have been measured using standard questionnaires used in the field of research. The independent variables are measured using a 5 point and 4 point Likert scale. The dependent variable is measured using a questionnaire with mainly yes/no items scored with 1/0 respectively. Each item is assigned a numerical value and the responses are summed to get the scores for each scale.

I have collected approximately 200 responses and have measured my independent and dependent variables based on the scoring systems. I also know there is a huge debate about whether or not to use Likert scale data as interval or continuous; but many similar studies have followed this approach and I have decided to do the same.

The Cronbach's alpha for the scales are consistent with the original studies and is well over 0.70.

My problem right now is my dependent variable violates linearity with the independent variable so a regression analysis is not possible (see graph below). Spearman's rank correlation coefficient does not show any sort of relationship between my dependent variable and independent variables. The correlation coefficients are really low.

I have thought converting my summed independent variable metric back to a single ordinal value (Agree, Slightly Agree, Slightly Disagree, Disagree) to run some nonparametric tests against the DV. Would this make sense?

• You can (and should) look at graphs of the data to try to find problems. But it could be that your theory is just not supported by the data. Apr 16, 2020 at 11:34
• I have added a bit more information regarding the problem and updated the question to be more specific. It could very well be an issue with data. Just want to make sure I exhaust all my options before accepting defeat i guess. Apr 16, 2020 at 11:59