For comprehensive review and applications of the mean residual function, we refer, for example, to Guess and Proschan ([1988]), Bairamov et al. ([2002]), Asadi and Bayramoglu ([2005]) and Asadi and Bayramoglu ([2006]).
To produce our final estimates for the mean function and variance we treat each hypothesis as a particle30, and perform a weighted average over.
Therefore, if (phi -1)>delta), we know the mean function (E [e^{L_{theta}(t)} ]) is increasing in θ, and by (7), we know that the mean function (E [U_{theta}(t) ]) is increasing in θ.
Then we use the mean function of the Gaussian process to infer the multiple RSS source locations.
To simplify the algebra, we assume the mean function m(t) = 0 and subtract the mean of y.
To define our GP prior, we choose a zero mean function and the squared exponential function of Equation (8).
In order to introduce the generalized convexity, we first recall the definition of mean function and several classical means.
In all of our simulation experiments we assume a logit link for the mean function.
We model as a GP a distribution over functions with constant mean function and covariance defined by a squared exponential correlation function where H = (h1, …, hM) is a set of correlation lengths for each of the parameters.
In GPR, we assume a GP prior for f(x) with mean function m and covariance function k.
After ovulation, we modeled the log(PdG) with a normal distribution with a quadratic mean function and constant variance.
