I am performing atmospheric correction on a Landsat 8 image using different methods to check which one works best (in order to proceed with further/subsequent analysis). Wondering if it's okay to use as low as 5 observations (pixel points) for regression analysis (to check for agreement between Landsat, dependent variable and MODIS Surface Reflectance, independent variable).

  • 1
    Statistics says 10 in case of one independent variable
    – FelixIP
    Aug 6 '16 at 4:34

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.