"gZ`dZddlZddlmZddlmZddlmZGddeZ Gd d e Z y) a This script contains empirical likelihood ANOVA. Currently the script only contains one feature that allows the user to compare means of multiple groups. General References ------------------ Owen, A. B. (2001). Empirical Likelihood. Chapman and Hall. N) _OptFuncts)optimize)chi2ceZdZdZdZy) _ANOVAOptzX Class containing functions that are optimized over when conducting ANOVA. c|j}|j}|j}tj||f}d}t t |D]$}|t ||z}|||z ||||f<|}&|} tj| jdd| jdz z} |jtj|| | } dtj| | jz} d|z dz| z |_ tjtj||jz} d| zS)a7 Optimizes the likelihood under the null hypothesis that all groups have mean mu. Parameters ---------- mu : float The common mean. Returns ------- llr : float -2 times the llr ratio, which is the test statistic. rg?)nobsendog num_groupsnpzerosrangelenonesshape _modif_newtondotT new_weightssumlog)selfmur r r endog_asarrayobs_numarr_num new_obs_numest_vectwtseta_stardenomllrs X/var/www/dash_apps/app1/venv/lib/python3.12/site-packages/statsmodels/emplike/elanova.py_opt_common_muz_ANOVAOpt._opt_common_mus.yy __ $ !34 SZ( "G!Cg$77K;@><M';.7 8!G  " !gghnnQ'(B(..2C,DE%%bhhz&:HcJRVVHhjj119r>E1ffRVVD4#3#3345CxN)__name__ __module__ __qualname____doc__r&r'r%rrs  r'rceZdZdZdZddZy)ANOVAz A class for ANOVA and comparing means. Parameters ---------- endog : list of arrays endog should be a list containing 1 dimensional arrays. Each array is the data collected from a certain group. c||_t|j|_d|_|jD]}|jt|z|_!y)Nr)r rr r )rr is r%__init__zANOVA.__init__FsF djj/  +A CF*DI +r'Nc|N|j|}dtj||jdz z }|r||||jfS|||fSt j |j|dd}|d}ttj|d}dtj||jdz z }|r||||jfS|||fS)a( Returns -2 log likelihood, the pvalue and the maximum likelihood estimate for a common mean. Parameters ---------- mu : float If a mu is specified, ANOVA is conducted with mu as the common mean. Otherwise, the common mean is the maximum empirical likelihood estimate of the common mean. Default is None. mu_start : float Starting value for commean mean if specific mu is not specified. Default = 0. return_weights : bool if TRUE, returns the weights on observations that maximize the likelihood. Default is FALSE. Returns ------- res: tuple The log-likelihood, p-value and estimate for the common mean. rF) full_outputdispr) r&rcdfr rr fmin_powellfloatrsqueeze)rrmu_startreturn_weightsr$pvalres mu_commons r% compute_ANOVAzANOVA.compute_ANOVAMs8 >%%b)CtxxT__q%899DD"d&6&666D"}$&&t':':H345BCa&CbjjQ01ItxxT__q%899DD)T-=-===D)++r')Nrr)r(r)r*r+r1r>r,r'r%r.r.:s +,,r'r.) r+numpyr descriptiverscipyr scipy.statsrrr.r,r'r%rCs1 #% %P?,I?,r'