I need to evaluate a test (posterior predictive value) but the test results can change based on certain other independent factors. Let's say my test measures a biochemical value but depending on what room temperature the test is performed the value changes. How can I model this fact in my calculations without running a bunch of tests in different temperatures or something similar?

  • 2
    $\begingroup$ Any model for the way the test depends on temperature that doesn't use results from the test run at different temperatures would appear to be pure guesswork. $\endgroup$ – onestop Sep 23 '11 at 12:25
  • $\begingroup$ What is the test, and why do you want to model the effects of these "other independent factors"? $\endgroup$ – Thomas Levine Sep 27 '11 at 18:53

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.