#### Likelihood Ratio Test Statistic [Equation of the Week]

From Protassov et al. (2002, ApJ, 571, 545), here is a formal expression for the Likelihood Ratio Test Statistic,

T_{LRT}= -2 ln R(D,Θ_{0},Θ)

R(D,Θ_{0},Θ) = [ sup_{θεΘ}_{0}p(D|Θ_{0}) ] / [ sup_{θεΘ}p(D|Θ) ]

where D are an independent data sample, Θ are model parameters {θ_{i}, i=1,..M,M+1,..N}, and Θ_{0} form a subset of the model where θ_{i} = θ_{i}^{0}, i=1..M are held fixed at their nominal values. That is, Θ represents the full model and Θ_{0} represents the simpler model, which is a subset of Θ. R(D,Θ_{0},Θ) is the ratio of the maximal (technically, supremal) likelihoods of the simpler model to that of the full model.

Continue reading ‘Likelihood Ratio Test Statistic [Equation of the Week]’ »