I gave a recall test to the participants to examine the accuracy of their answers. I have one IV with two levels, present or absent. I have 11 DVs (questions in the exam), 4 of which are continuous (how many letters of the word they got right) and 7 are binary (correct/incorrect answer).

My question is how can I analyze such mixed data to compare the means and see if the two groups (IV abs/IV pres) differ and which one of them outperforms the other?

The exam can be compared to many other tests where there is either right or wrong answer. So, I wonder how the statisticians usually analyze and treat the data from IQ tests, where the data should be binary (correct/incorrect). However, I also have continuous variables where it is not as much about whether the answer is right or wrong as it is about how right it is (let's say by %). You can also think of it as any standardized exam which has multiple choice questions (where the answer is right/wrong) and a section of fill-in questions (points given for how accurate the answer is).

Any help would be highly appreciated. If you need any further information, please let me know :)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.