Thank you sir for the explanation. I want to calculate the sample size for a cross-sectional survey of unknown prevalence. Can I take p=50% as you suggested? I don't have the prevalence data for the consumption of processed packaged food in the city I am surveying. Or can I take the prevalence data of the country if it is available? please help.
Of course, you can. Also, if unknown you can assume the prevalence to be 50% which will give you the largest sample size as in the graph shown in the video