Hi everyone!
I would like to ask some questions for my Phd thesis in cryptocurrencies. In one of the thesis I saw researcher used a questionnaire which several questions and 4 of each questions relate to one variable.
Like in UTAUT2 model; Performance expectancy was measured by 4 questions. Should I just take the average of these four answers to represent the performance expectancy or Should I use some other calculation technique (weighted mean, simply adding them up...etc)? I would really appreciate if someone helps me. Thanks in advance
You should use a Likert scale and analysis. Also, have an option for 'don't know', so that people aren't forced to unwillingly choose an answer or disregard the question, to avoid bias :)
Yes I am using Likert scale but I guess I will use SEM analysis on Amos. Thank you:)
The problem is not the use of different variables. The real issue what you want to determine. If your hypothesis is regarding the relation between the variables, you can use SEM, SPSS (Regression analysis, Correlation). If your hypothesis is related to the differences between the groups you can use SPSS (t-test and ANOVA).
Thank you Muhammad for your answer it really helped a lot for me to understand the relation between variables and how to analyze them.
Kardish Irmak Yolcu, we are one community I am pleased that I have been of any help to you. May Allah Bless You.
- Badges
- Science topic
- Similar topics
- Social Psychology
- Attitude