Title | | » | Add confidence intervals for slope and intercept in calibration regressions |
Assigned To | | » | Nick Shulman |
Notify | | » | Susan Abbatiello |
Type | | » | Todo |
Area | | » | Skyline |
Priority | | » | 3 |
Milestone | | » | 3.6 |
The slope and y-intercept are shown. That’s awesome. When I was in grad school and had to show my response curves (with regression, slope, y-intercept, etc), I was encouraged to show the confidence interval for both the slope and y-intercept. In this way, if I was plotting the L:H peak area ratio vs the L:H concentration, I “should” get a y=x regression. If it wasn’t m = 1 and b = 0, I could use the confidence intervals (95% or 99%) to see if the actual slope and y-intercept values were within those confidence intervals, and my response was good. Do you think the confidence interval addition would be easy to implement, and/or helpful? I think it would be helpful, but I don’t know if it’s easy and/or if people will think it’s useful.