I have a large dataset of participants with their responses to a psychological test. There are 8 different stimulus presentation durations (16-128ms) with 8 trials at each duration. I have calculated the proportion of trials correct for each presentation duration for each participant, but now I'm not sure how I go about calculating their threshold duration for where their response is above chance. I've tried to follow some tutorials on the internet but I don't know if I'm overthinking what I have to do. I've seen some mention apply a Gaussian distribution, a logistic regression but I'm not sure what it is I need to do.

I am semi-competent in Python if someone could point me in the right direction.

Any help is appreciated.


Edit: Okay turns out I was overthinking it, all I needed to do was interpolate i.e. np.interp(50, x_values, stimulus_durations) ? If I'm missing anything, 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.