2
$\begingroup$

I am working in R and currently working on my thesis where I am analyzing if some factors have impact on purchasing behavior. 15 of the questions in my survey were were Likert Scale (1-5) and I would like to use them as independent variables. Total money spend would be dependent variable and I would also like to use income and gender and some other stuff as independent variable. What statistical analysis would you recommend me to analyze my data? I converted my Likert scale data into factor data with 5 levels and now I am lost. Can I use OLS or would you recommend something else? Any help would be really appreciated

$\endgroup$
2
  • 1
    $\begingroup$ the most rigorous approach would be to use ordinal models (e.g see here) $\endgroup$
    – Ben Bolker
    Commented Nov 19, 2018 at 1:08
  • $\begingroup$ @BenBolker If I was going to use ordinal model I would have to have also cathegorical (factor) as dependent variable or am I mistaken? I would really like to have TotalMoneySpend as dependent variable and see how it changes based on what people chose at the likert scale questions/statements. $\endgroup$
    – Nowada
    Commented Nov 19, 2018 at 16:46

1 Answer 1

2
$\begingroup$

Based on the information you have given I would recommend looking in to PLS (partial least squares) regression. It's a powerful method which will let you mix ordinal and scale variables and it allows for multicollinearity amongst your independent variables, which is often a fact for survey responses.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.