Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Just a note

For sake of clarity, we have only obtained 100 bootstrap estimates, rather than the recommended minimum of 1000 or more. These points are too few to estimate a 95% or 99% interval.

Notice also, because we are assigning them by rank rather than by their location, we do not have to transform our results in order to fit these confidence limits. However, for this example we have chosen a well-behaved unbiased linear estimator, applied to observations from a continuously-distributed population, which had a straightforward rescaling function. Nor have we considered what would happen if our normalising function was applied to the observations rather than the estimates, or how it might affect the error variance.