Selected article for: "sample size and small number"
Author: Camacho, Anton; Ballesteros, Sébastien; Graham, Andrea L.; Carrat, Fabrice; Ratmann, Oliver; Cazelles, Bernard
Title: Explaining rapid reinfections in multiple-wave influenza outbreaks: Tristan da Cunha 1971 epidemic as a case study
  • Document date: 2011_12_22
    • ID: 12y420k8_16
    Snippet: where k is the number of estimated parameters plus initial conditions, T ¼ 59 is the number of observations and l(u ML jH i ) ¼ log L(u ML jH i ) is the maximized log likelihood. This correction accounts for the small sample size relative to the number of parameters (T/k , 10). Finally, we decomposed the maximized log likelihood of each model into conditional log Explaining rapid influenza reinfections A. Camacho et al. 3637 likelihoods log P( .....
    Document: where k is the number of estimated parameters plus initial conditions, T ¼ 59 is the number of observations and l(u ML jH i ) ¼ log L(u ML jH i ) is the maximized log likelihood. This correction accounts for the small sample size relative to the number of parameters (T/k , 10). Finally, we decomposed the maximized log likelihood of each model into conditional log Explaining rapid influenza reinfections A. Camacho et al. 3637 likelihoods log P( y t jy 1:t21 , u ML , H i ) in order to compare the six models at successive observation times t (see electronic supplementary material, text S2, for further details on the inference framework).

    Search related documents:
    Co phrase search for related documents
    • estimate parameter and inference framework: 1
    • estimate parameter and log likelihood: 1, 2, 3
    • estimate parameter and observation time: 1
    • inference framework and log likelihood: 1, 2
    • inference framework and observation time: 1
    • log likelihood and maximized log likelihood: 1, 2
    • log likelihood and model log likelihood: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13
    • log likelihood and observation time: 1, 2, 3, 4