Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I would like to conduct an usability study to assess users' perceived satisfaction with a computer system. I know that there are many well-established questionnaires to carry out this assessment. Now I am wondering how I can determine the sample size to be used in my study.Is there a specific rule?

share|improve this question
This is a topic called power analysis. The sample size needed depends on how tight a confidence interval around the estimate you need. It also depends on the nature of the variable "perceived satisfaction" and its reliability. – Peter Flom Oct 5 '12 at 15:31
This is as big or bigger than what Peter said. He probably just wanted to be brief. It involves survey sampling methods, hypothesis testing. There are many packages that will do it. Some are available in R SAS/STAT has proc power pro glmpower etc. NQueryAdvisor is a nice package also. Search the site and internet to learn more. Then come back with more specific questions and we will be happy to help. – Michael Chernick Oct 5 '12 at 15:36
there isn't a question here yet :) necessary sample size depends on the question. what do you want to get out of this study? – Jonathan Oct 6 '12 at 5:20
Find the test, figure out how they summarize the usability. It can be a score, it can be a percentage, etc. Each of them has its own way of estimating sample size. Then, decide how much uncertainty (the width of the confidence interval) you are willing to tolerate; the higher you can, the smaller the sample size. OR, you can also test your test population's usability against a predetermined value (say, if it's 80 or up, usability is good. Is my population's mean score = 80?) These are probably the items you'll need to bring when consulting other experts. – Penguin_Knight Oct 6 '12 at 14:25
thank you! My idea is to carry out a formative study to discover the problems the users have when they use the system. I am thinking to use the CSUQ questionnaire. – giovanna Oct 8 '12 at 14:00

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.