0
$\begingroup$

I am trying determine if there is a significant difference in preference of activities between males and females.I'm using a survey with the following question on 7-point likert scale:

Question 1: I like activity 1. Strongly disagree ---- Strongly agree

Question 2: I like activity 2. Strongly disagree ---- Strongly agree

Question 3: I like activity 3. Strongly disagree ---- Strongly agree

What statisical analysis could I use to determine if there is a significant difference in preference and what activity is most prefered by the sexes?

$\endgroup$
  • $\begingroup$ This is a frequently asked question. Please read the linked thread. If you still have a question after reading that, come back here & edit your Q to state what you've learned & what you still need to know. Then we can provide the information you need rather than just duplicating material elsewhere that didn't help you. $\endgroup$ – gung - Reinstate Monica Dec 10 '14 at 19:11
0
$\begingroup$

When the response options are linked to specific categorical responses, the Likert data are ordinal and should be analyzed with non-parametric statistics because the distances between the response options are not consistent. For example, the distance between strongly agree and agree is not necessarily the same as the distance between agree and neutral. The only exception to this rule is when you aggregate questions. When you combine 2 or more questions into an aggregated score then it is fine to use parametric analyses when comparing scores. However, questions that are aggregated should load onto the same factor in a principal components analysis.

$\endgroup$

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