Outlier Identification Strategy

Plot jackknife residuals r(, ) vs. x,- values (all the r,- corresponding to x,-values, except for the present r(, ) value). 

Once any extreme r(, ) values are noted, do not merely remove the corresponding x,- values from the data pool, but find out under what cmiditions they were collected, who collected them, where they were collected, and how they were input into the computer data record. 

The jackknife procedure reflects an expectation si iV(0, (r ), which is the basis for the Student s f-distribution at a/2 and n k 2 degrees of freedom. The jackknife residual, however, must be adjusted, because there are, in fact, n tests performed, one for each observation. If n = 20, a = 0.05, and a two-tail test is conducted, then the adjustment factor is 

---