The BLT of the random vector created using the BLTPM operator is
Setting we obtain the marginal LT of Y which is given by
. One can recognize that this is a LT of a negative binomial distribution and for this distribtion, the corresponding probability
generating function (PGF) , see Klugman et al.  (p. 83) for the PGF of a negative binomial distribution.
The marginal is the LT of a continuous random variable.
In this example we shall obtain a bivariate negative binomial distribution using
the BLTPM operator. Let , and
, and . Apply the BLTPM operator this gives a
joint distribution for with BLT given by
This is a BLT of a bivariate negative binomial distribution which is also ID. In the literature, this distribution has been constructed using various methods and by many authors, see Mardia  (p. 84). We can see that the BLTPM operator is very useful for constructing bivariate distribution with the property being ID. This property is useful in finance and actuarial sciences as the corresponding bivariate process is a bivariate Lévy process with stationary and independent increments. This property often leads to nice results in risk theory and pricing formulas in finance. Simulation of sample paths from these processes are also simplified using this property.
We briefly mention on how to simulate from bivariate distribution with a specified created by the BLTPM operator. The procedures are similar to the procedures described in section 5 and given by Marshall and Olkin  (p. 840) but the inverse transform method might not be necessary explicitly.
For the inverse transform method, see Ross  (pp. 69-70).
The main steps are:
1) Generate an observation for the mixing random variable α from the distribution H which has LT
2) Use the observed value α, generate an observation from a distribution with LT . Often from the expression of , we have a procedure to simulate from this distribution and the inverse method might not be needed explicitly at this step.
3) Use the same observed value α, simulate another observation which is independent of obtained from 2) from a distribution with LT .
The pair of observations obtained will follow a bivariate distribution with BLT as specified by .
3.3. LT Copulas
Observe that the BLTPM operator given by expression (2) is similar to the BDSPM operator given by expression 2.2 in Marshall and Olkin  (p834) where a class of distribution or survival copulas can be obtained, it is considered below. Without loss of generality we consider distribution copulas which are related to the BDSPM operator. By using the specified marginal distributions and , a new bivariate distribution can be constructed with these two specified marginals which is given by
is a univariate LT and its inverse given by .
If we let which is a LT of a gamma distribution, its inverse is given by , then we will have the classical distribution or survival
distribution Clayton copula as shown in example 4.2 given by Marshall and Olkin  (p. 837). For other copulas of the form given by expression (4), see Shih and Louis  .
For new bivariate distribution constructed using the BLTPM, we restrict the attention to nonegative distributions. Note that if the marginal distributions are specified respectively using LTs and given by and and subject to the two functions and are proper LT, a BLT of a new distribution with marginal LTs given respectively by and can also be obtained as
which is similar to the procedure as given by expression (4) using distribution or survival functions. This also means that some of the distribution or survival copulas of the class given by expression (4) can also be used as LT copulas. But the drawback of this approach using LT copula here is even by specifying the marginals and being LT of ID distributions, constructed using expression (5) might not necessary be a BLT of a bivariate ID distribution.
It is also more difficult to simulate from a BLT obtained using the LT copula as given by expression (5). Despite the algorithm used to generate a pair of observations from a specified BLT procedure is already given as above but when apply the procedures here we encounter the difficulty on how to simulate from distributions with LTs given by and as we might not be able to recognize these distributions.The inverse transform method can be applied by using the approximate quantile function based on moment generating functions and to obtain a simulated sample with some accuracy. The approximate quantile functions based on moment generating functions can be obtained explicitly using the saddle point technique and it is given by Arevelillo  . If these univariate MGFs do not exist, these LTs can be converted to characteristic functions and the numerical methods based on the inverse method and the approximate quantile functions as described by Glasserman and Liu  (pp. 1613-1615) can also be used to generate a pair of observations with some degree of accuracies.
There is a vast literature on survival or distribution copula, we just mention a few here. For a good general review on distribution or survival copula models with emphasis on goodness-of-fit test statistics, see Genest et al.  and for a good review of inference methods based on survival copulas used in actuarial science, see Klugman et al.  (pp. 187-213), Frees and Valdez  .
As mentioned earlier, asymptotic theory for Maximum entropy empirical likelihood (MEEL) and empirical likelihood (EL) for models where we have a sample of multivariate observations independent and identically distributed (iid) as which follows a d-variate multivariate distribution are well established but assuming a set of moment conditions or constraints has been chosen, see Qin and Lawless  , Schennach  , Owen  , Mittelhammer et al.  ; also see discussions in section 3.2 by Luong  (pp. 471-472).
For applications, the question on how to choose moment conditions or equivalently bases so that MEEL methods have high efficiencies is a relevant one and we would like to address mainly this issue here for models with closed form BLTs or BMGFs as introduced in previous sections. The moment conditions are viewed as constraints and can be identifed with elements of a chosen basis used to project the true score functions as in the univariate case, see Luong  (pp. 461-467). Beside estimation, empirical likelihood type methods also give a chi-square test statistics for model testing which is useful for practical applications. We shall emphasize moment conditions and focus on how to choose constraints for models with closed form BLTs or BMGFs in the next section as asymptotic theory is similar to the univariate case and already discussed in section 3.2 as given by Luong  .
4. MEEL Methods
Let be sample of bivariate observations and they are independent and identically distributed as which follows a bivariate distribution , has no closed from but its BLT or BMGF has a closed form expression and given respectively by or .The true vector of parameters is denoted by .The parameter space Ω is assumed to be compact.
Suppose that we can identify k constraints of the form where these functions are unbiased estimating functions with the property , these functions also form a basis used to project the true score functions and MEEL estimators can be viewed as equivalent to quasilikelihood estimators based on the projected score functions, see Luong  (pp. 466-468). Therefore, the constraints are linked to a basis and the ability to obtain projected score functions close to the true score functions for some restricted but useful parameter space will make MEEL estimators have high efficiencies in practice.
4.1. Choice of Bases
In this section, we shall recommend a base when using a model BLT to extract moment conditions which can be used as a guideline for forming other bases if needed for applying bivariate MEEL methods.
We shall define the first five gi’s as follows which make use of the first two moments of X, i.e.,
The variances of y and z are given respectively by and , the covariance between y and z is denoted by . Subsequently we will pick the gi’s directly using the model BLT . We shall choose first four points of the BLT , which belong to a circle of radius in the nonnegative quadrant and centered at the origin, i.e., let
which lead to define
We might want to add another 4 points on the part of the circle of radius of the nonnegative quadrant and centered at the origin by letting
which leads to define
If needed, pick another 4 points on the circle of radius radius of the nonnegative quadrant centered at the origin by letting
which leads to define
With all these gi’s, the basis can be formed and given by
Therefore, if the number of parameters m in the model, , bivariate MEEL methods can be used for estimation and model testing using this basis to generate constraints. Note that the choice of do not put restrictions on the parameter space as the model BLT is well defined on the nonnegative quadrant for all values of the vector . This might not be the case with the use of the BMGF where the domain of s might depend on . We have to be ensured that if restrictions are imposed, the restricted parameter space is all we need for applications. The choice of points are based on the intuitve ground that the BLT contains more information at points near the origin and obviously there is some arbitrairiness on the choice of points or equivalently moment conditions for using MEEL methods.
If we use moment conditions based on the BMGF such as estimation for the jump-diffusion model as given by example 2, in general we might want to keep the first five ’s as given by expression (6) for BLT and add 12 additional gi’s with chosen points on the circle of radius centered at the origin without restricting on the first quadrant and define
which leads to define
Consequently, the base
which makes use of the model BMGF can be used for generating constraints.
Note that the BMGF for the jump-diffusion model as given by example 2 is well defined for all points . Note that with a basis of elements, it will allow the number of parameters .It appears that such a base gives a good balance between efficiency and numerically tractability for the MEEL methods and can be used as a guideline to form other bases if necessary in practice.
4.2. Estimation and Model Testing
Asymptotic properties for Multivariate MEEL methods and for EL methods for models with independent and identically distributed of vector of observations are well established, see Qin and Lawless, Mittelhammer et al.  (p. 323), Schennach  . Now if we use the constraints as defined using a basis , MEEL estimators are obtained as the vector which maximizes the entropy or minimizes
The λj's depend on and are only implicitly defined using expression (11).
Using standard regularity conditions as indicated in the references just listed, also see section 3.2 given by Luong  (pp. 471-472), we then have consistency and asymptotic normality for the MEEL estimators given by , i.e., , is the vector of the true parameters,
An estimator for is given below,
. If we let , we have another consistent
estimator for . The asymptotic results are very similar to the ones for the univariate case as given by Luong  but for completeness they are reproduced to make the paper easier to follow.
For model testing, it is viewed as testing the validity of the moment conditions, i.e., tesing the null hypothesis just as in the univariate case, the expectations are under the true parametric model.
The following test statistics given below is a chi-square test statistics which has an asymptotic chi-square distribution with degree of freedom, i.e.,
This test might be useful for testing bivariate normality in empirical finance and it is based on the MEEL estimators and since the basis used spans the true score functions of the bivariate normal model which makes as efficient as the maximum likelihood estimator , as the projected score functions are identical to the score functions. Furthermore, the asymptotic chi-square distributions are practical for the use of these test statistics and we do not need intensive simulations to implement model testing procedures as in other methods. Also, MEEL methods can be applied for model with a singular part in the domain provided that the model BLT has a closed form expression.
4.3. Numerical Implementations
As for the univariare case, a penalty approach can be used which means that we can perform unconstrained minimization using the following objective function with respect to and ,
The penalty constant K is a large positive value, direct search agorithms which are derivative free are recommended and these direct search algorithms are also more stable.
It is important to note that only a local minimizer is found each time using these algorithms, some strategies are needed to identify the global minimizer. Often, we might need a starting vector being close to the vector of the estimators to initialize the algorithm, this is important when working with real data and bivariate models might have many parameters. We might want to adopt the following strategy to look for a good starting vector. Using the two submodels based on the two marginal distributions of the model separately we can fit using univariate MEEL methods using and as described in Luong  to obtain respectively the vector which estimates the vector of parameters of the first marginal model and similarly obtain which estimates the vector of parameters of the second marginal model.The vector of parameters of the bivariate model is and can be partitioned into three components,i.e.,
. Now if we apply MEEL methods with the bivariate model but fixing
and only estimate , the vector which estimates is denoted by . We can construct the following starting vector
, and fit the bivariate model using penalty method by minimizing jointly with respect to the vector and the vector the objective function as given by expression (14).
5. A Simulation Study
In this section we perform a limited simulation study for model given by example 1. We compare the performance of the Method of moment(MM) estimators with the MEEL estimators using the following basis with elements which is formed using the first 9 elements of the basis given by expression (7) as the model only has five parameters given by the vector
and these parameters will be introduced below. Using the model in example
density function and specifying another exponential distribution for V with density function . The random
vector follows a bivariate Poisson distribution with parameters and these parameters all all positive. We have n independent and identically distributed observations
. They have the same distributions as and using the model as specified, the following first two moments of X can be obtained, they are also given by Partrat  (p. 221),
where and denote respectively the mean, the variance and covariance of the expression inside the parenthesis. Now if we replace , , , and by their sample counterparts which are given by and in expression (15) and by solving the system of equation,it will give us the MM estimators given by the vector with
The model BLT is
see Partrat  (p. 221) and example 1 in section (2). For efficiency, observe that the quasi-score functions of the MM estimators belong to the linear space spanned by and based on asymptotic theory MEEL estimators will be more efficient than MM estimators for large samples already as belong the basis used for MEEL methods, see Luong  for quasi-score functions related to MEEL estimation. Another advantage of the MEEEL methods over methods of moments (MM) is that a chi-square statistics with four degree of freedom is available for model testing as the methods provide a unified approach to estimation and model testing.
with its components given by with and the equalities hold in distribution. The vector will follow a bivariate Poisson distribution with parameters , , , see Johnson et al.  (pp. 124-126) for this representation. To simulate an observation we can use the random sum representations of and and therefore it suffices to simulate from exponential distributions and perform the appropriate summations.
We use M = 100 samples and each of the sample is of size . For the range of parameters we fix and let varies from 1, 2, …, 10. For the parameters of the bivariate Poisson distribution we fix , and let . Similarly, we fix and let varies from 1, 2, …, 10 and we fix , and let .
The mean square errors (MSE) are estimated using simulated samples. The mean square error of an estimator for is defined as
. We use the following criterion for comparison between the efficiencies of MEEL estimators versus MM estimators
The results are displayed in Table 1 where we observe that overall the MEEL estimators are two to four time more efficient than MM estimators with the ARE estimated using simulated samples. We also observe that each individual estimate MSE is smaller for MEEL estimators than their counterpart for MM estimators. Furthermore, we also have a chi-square goodness-of-fit statistics for model selection for a model without closed form density function. This model testing statistics can be useful for applications in general. Despite the study is limited as
Table 1. Overall relative efficiency of MEEL estimators versus MM estimators.
we do not have large computing resources but it does confirm the asymptotic results on efficiencies of MEEL estimators. More works need to be done for assessing the efficiencies of MEEL methods by using various parametric models especially in finite samples.
MEEL estimators using the proposed moment conditions or bases appear to have the potential of higher efficiencies than MM estimators in general. The methods also provide chi-square goodness-of-fit test statistics for model testing. These features make the methods useful for inferences for bivariate distributions with closed form BLTs or BMGFs without closed form for the bivariate density functions. For these distributions, the implementation of likelihood methods might be difficult.
The helpful and constructive comments of a referee which lead to an improvement of the presentation of the paper and support form the editorial staffs of Open Journal of Statistics to process the paper are all gratefully acknowledged.