Hi Reserchers,
I am doing a computer science dissertation on the topic '' Automate text tool to analysis reflective writing''.
The hypothesis set is ‘To what extent is the model valid for assessed reflective writing?’ I just want from the questionnaire( closed ended questions and one open question) to validate the proposed model.
I have used the used the 5 point likert scale for analysing the data, option given strongly agree, agree, neutral, disagree, strongly disagree. The sample size is 10 participants. I have chosen my participate based on their experience, career and knowledge of the reflective writing.
1) Which statistical analysis tool shall I use to analyse 10 sample size to validate the model? Please show me step by step on how to analyse the data?
2) What would be the associated hypothesis?
3) Can I use Content Validity Index with 10 sample size participants on the questionnaires using 5 point likert scale?
4) this step on my research Is it qualitative method or quantitative method?why?
If you have any suggestion on my hypothesis, the sample size and the tool I need to analyse?
Thank you in advance !
Dear Huda,
n=10 is not enough to run EFA, which is what you would do when developing a new questionnaire. You might find it more fruitful to select a suitable technique for you open-end questions. Hence, you would take a qualitative approach to design your measurement instrument.
If you increase your sample size to n=50 at the very least, it will allows you to use other quantitative approaches (e.g. EFA) other than descriptives statistics.
Kind regards
Marcel
Dear Huda,
I think the only possible quantitative analysis you might want to consider is a 2 by 2 contingency table which compares two responses to an individual question for two groups. This would lead to a Fisher's exact test.
Otherwise I would recommend an informal interpretation of your descriptive statistics which you can try to compare with your qualitative responses.
Thank you Marcel Grieger , I cant increase my sample what can I do in this case ? Is there any statistical analysis tool for such sample size?
Dear Peter,
I dont understand ”2 by 2 contingency table which compares two responses to an individual question for two groups.”!!
my sample 10 participants and the questionnaie consists into 4 parts each part has 2 to 4 questions overall 16 questions.
Dear Juda,
I would follow Peter's advice. Quantitatively, there is not much you can do. Have you talked this over with your professor?
Kind regards
Marcel
Dear Huda,
You cannot analyse more questions than you have respondents in your sample. You cannot run a scale reliability analysis with a sample size less than about 30. If your participants are not split into groups you will need to compare one question against another. I am not clear as to what your research question is.
Dear Huda,
I think you want to collect perceived opinion of 10 experts regarding performance of your model to answer your research question as I can understand from your hypothesis as you mentioned. But, perceived opinion of only 10 respondent is not at all enough to statistically satisfy your hypothesis and more over, there will be a question on research design. I think you should try out your model on at least 30 potent respondents and then judge their performances on the model on some preconceived parameters. Judgement can also be done in Likert scale on odd numbered continuum. Then you can try out EFA or other quantitative analyses to satisfy your hypothesis.
To answer your second question, an example of a 2 by 2 contingency table would be male v female on one dimension and two groups of Likert responses on the other (e.g. strongly disagree to neutral, and agree to strongly agree). Your sample of 10 would then be split into one of these 4 cells. Fisher's exact test would then analyse whether there was an association between gender and the two groups of Likert responses.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size