I want to do comprehensive study of errors in variables and compare the results with regression for selected parameter estimation problems in my domain where it is expected to perform better in terms of accuracy. These problems are of type linear and non linear regression. I want to check if the method under study is an improvement over generalized least squares. I am including multiple factors like accuracy, computational efficiency, robustness, sensitivity in my study under various combinations of stochastic models. What kind of statistical analysis is required for a study to establish superiority of one method over another?

  • $\begingroup$ You need to make your hypothesis clear and quantifiable. Please state the sense in which one algorithm "improves" over another: in terms of computational efficiency? Interpretability? Scope of application? Robustness to outlying data? Bias, accuracy, precision, relative precision, ... ? $\endgroup$ – whuber Feb 8 '20 at 14:44
  • $\begingroup$ @whuber I have added more details. Can you please reopen my question $\endgroup$ – Ankit Sharma Feb 8 '20 at 18:43
  • 1
    $\begingroup$ Thank you. You are posing a great many questions. That doesn't work here: we need each post to articulate one clear, answerable question. Could you think about what you need to know most (or first) and limit your post to asking about that? $\endgroup$ – whuber Feb 8 '20 at 19:22
  • $\begingroup$ @whuber thanks. I have edited the question $\endgroup$ – Ankit Sharma Feb 8 '20 at 19:39

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.