Thank you all in advance!
I'm writing my Masters Thesis on the importance of Storytelling for sense of place branding strategies and am at the point of analysing my collected date.
I created two questionnaires for an online experiment randomly administered. The questionnaires are identical except for the addition of a storytelling element in combination with the presented products.
I asked the "worker" (I used MTurks) questions pertaining to brand experience, attitude toward the brand and toward the advertisment, knowledge of place and a few demographic questions i.e. age, gender, if they drink beer (product is a craft beer brand)
Brand experience was measured using the Brand Experience Scale developed by Brakus et al. (2009). The 12-item scale includes four dimensions of brand experience: sensory, affective, behavioral and intellectual. Every dimension has 3 items measured on a 7-point Likert Scale (strongly disagree to strongly agree).
Attitude toward the ad was measured using eight 7-point semantic differential scales: good/bad, like/dislike, favorable/unfavorable, enjoyable/unenjoyable, pleasant/unpleasant, appealing/unappealing, interesting/uninteresting, and nice/awful.
Attitude toward the brand was measured using five 7-point semantic differential scales: appealing/unappealing, good/bad, pleasant/unpleasant, favorable/unfavorable and likable/dislikable
My Hypotheses are that BE, Ab und Aad will positively increase with the addition of the storytelling elements.
Does any one have a suggestion how I can analyse my date? I admit I am quite lost. Thanks again.
Dear if check these videos will be better
https://www.youtube.com/watch?v=x684kPgiay0
https://www.youtube.com/watch?v=5BKAcErKVsQ
hi,
compare the means of the variables of interest between the two samples; simple t-test will do, however check for the homogeneity of variance between the samples.
all options are available in SPSS; most probably also in STATA, but unfortunately I am not that handy with stata.
would that help?
cheers, Marija
Hi, Erica,
When developing new scales for use in a study, I think it is always advisable to use exploratory factor analysis to determine the factors actually collected by the scales. Both of your 7-item semantic differential scales may benefit from a quick look at the principle components which is quite easy in SPSS. I would include all 14 items to see if, in fact, there are two separate factors reported - one for brand and one for the ad.
Personally, I would want to confirm the factor structure of the Brakus et al, scale, too, because four factors from 12 items is questionable at best.
Once you have identified the factors collected in your study, you can proceed to group tests, but be careful to use the correct test. T-tests are only appropriate for interval/ratio scales of measurement. If you are unable to create summative factor scores, you may need to use a nonparametric test like Mann Whitney U for your group comparisons.
@Peter A Kindle
I support your answer. Its really helpful in related research.
Use SPSS. Correlation and regression analysis will give you enough statistics to justify your results.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Applied Statistics
- Survey Design
- Questionnaire