pdk.Math.Probability ($Date: 2002/12/04 10:16:02 $)
index
pdk/Math/Probability.py

Functions related to probability calculations.

FOG 11.1999

 
Functions
            
chisq_quant(n, gamma)
quantiles of the Chi-Square function at gamma with n degrees of freedom. Approximation according to Wilson and Hilferty. Note: not reliable for small n (probably because it depends on the inaccurate gauss_quant_std function ...)
gauss_response(x, opt, tol, ampl=1)
returns the Gaussian response at x. opt is the optimum response (corresponds to mu) tol is the tolearance of the response (corresponds to sigma) ampl is the maximum response
gauss_par_bi_ind(x, y, mu_x, mu_y, sigma_x, sigma_y=None)
computes the density of the bivariate normal distribution at point (x,`y`). x and y are presumed to be independent (i.e., their correlation is 0). See Hartung J(1986): Statistik. Oldenbourg, Muenchen. p. 120.
gauss_response_bi_ind(x, y, opt_x, opt_y, tol_x, tol_y, ampl=1)
returns the value of a bivariate Gaussian response curve at point (x,`y`). x and y are presumed to be independent. opt_* is the x-value of the optimum response (corresponds to mu), tol_* is the tolerance of the response (corresponds to sigma), ampl is the maximum reponse. See Jongman et al.(1987): Data analysis in community and landscape ecology. Pudoc, Wageningen. pp. 40ff.
log_dens_par(mu, sigma)
parametrized lognormal probability density function with mean mu and stddev sigma. Adapted from random.py.
poiss_dens_par(x, param)
value of the parametrized poisson probability density function at x; param must be a 1-Tuple providing the mean.
poiss_distr_par(x, param)
value of the parametrized Poisson probability distribution function in x; param must be a 1-Tuple providing the mean l.
 
Author
            
$Author: gathmann $