I have a questionnaire that includes 15 likert scale questions (regarding the attitude of respondents to celebrities) and 1 question asking the gender of respondents.
One of my research questions is how men and female differ in their attitude toward celebrities.
Is that one question regarding gender is enough for this?
And then how can I please figure out the relation between gender and attitude during my data analysis? Does it include complicated statistics tests, or is it easy and simple to figure out this?
Thanks.
It can be as simple or complex as you wish to make it. The simplest approach would be to analyze the results descriptively making two profiles of the 15 questions, one for males and one for females. By displaying the profiles on the same graph, it would be rather easy to compare them logically.
An inferential approach would be to conduction a multivariate t-test comparing the males and females over the 15 Likert scales. The best way to accomplish this would be to run a discriminant analysis of the two profiles. A by-product of this would be a multivariate t-test and it would give you the opportunity to identify what questions contribute the most to the difference.
I agree with James here. You can exhibit your descriptive part with a graph or chart to show how males and females differ in terms of attitude.
To find associations between the two, first determine which is your dependent variable (I believe it's the score of your attitude derived from the Likert scale). When your dependent variable is continuous (a score of attitude) and your independent variable is a category of two levels (like male and female), you may conduct Independent t-test. It will derive the mean with a reference category, as such you may interpret either males or females have better attitude or vice versa in comparison to another, and subsequently to see if this analysis is statistically significant or not.
Good luck!
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS