Enda Kelly <[EMAIL PROTECTED]> wrote: > try and flesh out the problem here. The actual computation I'm > attempting is a genetic linkage disequilibrium (LD) test, with the null > chi-square distribution, and the P-value is thereby obtained. For more > complex cases the alleles at one locus were permuted 1000 times (or > more), and for each permutation S was calculated and the P-value for the > test was the proportion of replicates that produced values of S equal or > greater than the original S. In both cases I bootstrapped the original > data 1000 times to get the CIs.
What kind of bootstrap have you used? And how many genotypes in the observed data? You might remember that bootstraps can be parametric or nonparametric, and that in the latter case, various types of bias correction need to be applied when producing CIs. Also, the variation in P-value for each bootstrap sample reflects both the size of the original sample and the number of permutations used. You might compare your LD P-values to the (Fisher) exact P-values for the genotypic contingency table (if there is HWE and no intergametic association, these shouldn't be too different, and do give a "trustable" upper bound). Of course, you can also compare to results from Arlequin, multiple replicates from SNPhap etc for the same data. -- | David Duffy (MBBS PhD) ,-_|\ | email: [EMAIL PROTECTED] ph: INT+61+7+3362-0217 fax: -0101 / * | Epidemiology Unit, Queensland Institute of Medical Research \_,-._/ | 300 Herston Rd, Brisbane, Queensland 4029, Australia GPG 4D0B994A v . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
