I have 30 participants reading 5 lists of words containing vowels to discover the most difficult vowel for them. Which statistical test should I use? T-test or ANOVA?
Could you tell me how many independent and dependent variables you have got?
Thank you Patchanok for responding to my question. It is a comparative study that does not involve treatment (independent variable) and results (dependent variable). However, I think the type of vowel here is the independent variable and participants' reading is the dependent.
Yes. As Amir said, t-test will be used when you have two groups of participants to compare, and ANOVA is when you have more than two. But if you have one group, how will you use them? Maybe you can go back to your research question and see what you want to investigate. Then decide what the independent and dependent variables.
Thank you Amir and Patchanok. As a matter of fact, I am trying to find which English long vowel is the most difficult for Arab students learning EFL/ESL. I am going to compare their pronunciation of the five long vowels in English using a scale of measurement of four categories 'accurate', 'close' and 'inaccurate'. Then I will compare the results. I am thinking of using paired sample t-test, but with five categories, it might be inappropriate unless I do it with every two categories. I hope you got the picture clear.
Exactly. Consider it a hypothesis-generating study, and show that you have a trend towards a particular ordering of the vowels in order of difficulty. If you then proceed with a larger study, consider using STATA's ologit command.
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis