2. The Statistical Model
Let the lifetimes of components in a CDS follow a baseline Gompertz distribution, whose probability density function (PDF), cumulative density function (CDF), and hazard rate function are defined, respectively, by
and
where
is the scale parameter and
is the shape parameter of the baseline distribution. The Gompertz distribution can reduce to an exponential distribution as
. Many authors, including Read [
28], Makany [
29], Rao and Damaraju [
30], Franses [
31], and Wu and Lee [
32], have studied the statistical methodologies and characterizations of the Gompertz distribution since it was introduced by Gompertz [
33] to characterize the human mortality and establish actuarial tables. Garg, Rao and Redmond [
34] investigated the properties of this distribution. Moreover, he proposed the maximum likelihood estimation method to estimate the distribution parameters of Gompertz. Gordon [
35] established the maximum likelihood procedure for the mixture of two Gompertz distributions. Chen [
36] proposed an exact confidence interval for
and an exact joint confidence region for both parameters by using the properties of the conventional exponential distribution. Wu et al. [
37] proposed un-weighted and weighted least-square estimates for
and
based on first failure-censored samples. Willekens [
38] presented the connections among the Gompertz, Weibull, and other type I extreme value distributions.
Assume that, when the
jth component fails, surviving components in the CDS can equally share the loading. It can be shown that the lifetimes of surviving components still follow a Gompertz distribution, but they have different hazard rates. Following the equal-sharing condition for the surviving components in the CDS, the hazard rate of surviving components is increased. The PDF, CDF, and hazard rate function can be defined by the
,
and
, respectively, for
. It is trivial to show that
for
and
The proportional hazard model assumption that is given in Equation (
4) is equivalent to let
for
. For simplifying the notations, let
,
denote the realizations of the SOS and
. Following the inference procedure of Beutner [
11], the likelihood function that is based on the sample
can be presented by
where
and
for
. Based on Equations (
1), (
Figure 2), and (
5), Balakrishnan, Jiang, Tsai, Lio, and Chen [
24] presented the log-likelihood function by
Use the power-trend hazard rate model of
in Equation (
6). Subsequently,
can be reduced to
, Equation (
6) can be represented as Equation (
7) and the log-likelihood function of can be presented as Equation (
8):
and
where
and
. The MLEs of
and
that are based on SOS samples do not have explicit form and only the MLE of
, given
and
, can be obtained with an explicit form as the following:
It could be difficult to set up the heterogeneity condition in the CSD model to conduct the maximum likelihood estimation procedure. One feasible method is to characterize the heterogeneity among components in the CDS by assuming that the models parameters are random, and then to obtain the BEs of the model parameters for reliability evaluation. Denote the BEs of
,
and
by
,
, and
, respectively. Let the prior distribution of
be defined by
where
and
where
,
,
, and
are hyper-parameters. The Gamma distribution has been widely used as the prior distributions of the parameters of the Gompertz distribution, see, for example, Soliman et al. [
39], Dey et al. [
40], and Chacko and Mohan [
41]. Some of the authors considered using non-informative prior distribution as the prior distributions of the parameters of the Gompertz distribution in order to implement Bayesian estimation, see, for example, Ismail [
42] and Feroze and Aslam [
43]. When the Gamma prior distribution has a large variance, the Gamma prior distribution approaches a non-informative distribution. In this study, we consider using Gamma distribution as the prior distributions of the scale and shape parameters of the Gompertz distribution, respectively. Moreover, a MCMC approach is proposed in order to overcome the computation complexity that is caused by using the Gamma prior distribution.
Using the derivation in
Appendix A, the posterior distribution of
, given the sample
, can be obtained by
where
and
After algebraic computation, we can obtain the conditional posterior distributions of
,
and
by
and
respectively. It can be found that
and
are not conjugate distributions. Hence, it is difficult to update all of the parameters via using the marginal posterior distributions of
and
in order to implement the Gibbs sampling algorithm.
Assume that
and
are the values of
,
and
at the previous state, respectively. Let
be generated from a proposal, say
. Given
and
, it is trivial to show that the ratio of
is simple for computation, due to
only depending on the right hand side of Equation (
18). The Metropolis-Hastings algorithm uses the ratio of
in order to update
. Likewise, assume that
and
are generated from the proposals of
and
, respectively, and the updated value of
is
. Given
and
, we can update
by the ratio of
Let the updated value of
be
. Given
and
, we can update
by the ratio of respectively. The steps to generate the Markov chains of
and
via using the proposed hGSMH-MCMC method are presented in Procedure 1. Please note that the proposed hGSMH-MCMC method is also a Metropolis-Hastings-within Gibbs approach. The proposed hGSMH-MCMC method combines the merits of the Metropolis-Hastings and Gibbs algorithms. Hence, the proposed hGSMH-MCMC method is simple to use as using the typical Metropolis-Hastings algorithm, but it has a higher update rate than the typical Metropolis-Hastings algorithm.
Procedure 1: The proposed hGSMH-MCMC method.
Initial Step: let , and then given the initial estimates are , and .
- Step 1:
if go to Step 4; and go to Step 2 otherwise, where N is a big positive number.
- Step 2:
update , and by , and , respectively, according to Step 2.1 to Step 2.3, as follows:
- Step 2.1:
generate one and generate . If , then , otherwise .
- Step 2.2:
generate one and generate . If , then , otherwise .
- Step 2.3:
generate one and generate . If , then , otherwise .
- Step 3:
obtain the BEs of , and based on the Markov chains of , and , respectively, where the leading chains are used for burn-in.
- Step 4:
stop.
Figure 2 provides the flowchart of Algorithm 1. Based on the primacy of mathematical convenience, we consider the two most commonly used loss functions, the squared loss and absolute loss functions, to obtain the BEs of the CSD parameters in this study. The BEs of
and
based on the squared loss function can be the sample mean of the Markov chains of
,
and
, respectively. The BEs of
,
, and
based on the absolute loss function can be the sample median of the Markov chains of
,
and
, respectively. The performance of the proposed hGSMH-MCMC method will be evaluated through using the Monte Carlo simulations shown in
Section 3.
The confidence interval inference of the baseline survival function,
can provide important information for assessing the reliability of the CDS regarding the probability of a CDS can survive longer than a specific time of
. The Markov chain of
based on the Markov chains of
and
can be obtain and denoted by
, where
for
. The BE of
is denoted by
. Subsequently, the empirical distribution of parameter
can be established based on using
. In this study,
can be
,
,
, or
. The credible interval, as denoted by
, which admits an interpretation of
posterior probability of covering the true
, can be obtained by the following
Procedure 2: find an credible interval of .
Initial Step: let . If , then go to Step 1; and go to Step 5 otherwise, where B is a large positive integer.
- Step 1:
obtain the Markov chains of via using the proposed hGSMH-MCMC method in Procedure 1.
- Step 2:
find the th and (1-)th quantiles, and , from the sorted Markov chains of , where for , , and denotes the largest integer smaller than or equal x.
- Step 3:
let .
- Step 4:
obtained B credible intervals, . The credible interval of parameter can be obtained by .
- Step 5:
stop.
The obtained credible interval can provide information to make statistical inferences for
.
Figure 3 shows the flowchart of Procedure 2.