% Interpolate tabularized distribution % % Description: % % This function calculates critical values or p-values which cannot % be obtained numerically, and only tabularized version is % available. % % Usage: % % [q] = qtable(p,probs,quants) % % Arguments: % % p: vector of probabilities. % % probs: vector of given probabilities. % % quants: vector of given corresponding quantiles. % % Details: % % This function is mainly internal routine used to obtain Grubbs and Dixon % critical values. It fits linear or cubical regression to closests % values of its argument, then uses obtained function to obtain % quantile by interpolation. But noone disables to call it directly in % any purpose :) % % Value: % % q: A vector of interpolated values % % Note: % % You can simply do 'reverse' interpolation (p-value calculating) by % reversing probabilities and quantiles (2 and 3 argument). % % Author(s): % % Lukasz Komsta, ported from R package 'outliers'. % See R News, 6(2):10-13, May 2006 % % %