admix (Q62250)

Implements techniques to estimate the unknown quantities related to two-component admixture models, where the two components can belong to any distribution (note that in the case of multinomial mixtures, the two components must belong to the same family). Estimation methods depend on the assumptions made on the unknown component density (see Bordes and Vandekerkhove (2010) <doi:10.3103/S1066530710010023>; Patra and Sen (2016) <doi:10.1111/rssb.12148>); Milhaud, Pommeret, Salhi and Vandekerkhove (2022) <doi:10.1016/j.jspi.2021.05.010>). In practice, one can estimate both the mixture weight and the unknown component density in a wide variety of frameworks. On top of that, hypothesis tests can be performed in one and two-sample contexts to test the unknown component density (see Milhaud, Pommeret, Salhi, Vandekerkhove (2023)). Finally, clustering of unknown mixture components is also feasible in a K-samples setting.