Abstract
The main objective of the present paper is to define -gamma and -beta distributions and moments generating function for the said distributions in terms of a new parameter . Also, the authors prove some properties of these newly defined distributions.
1. Basic Definitions
In this section we give some definitions which provide a base for our main results. The definitions (1.1–1.3) are given in [1] while (1.4–1.6) are introduced in [2]. Also, we have taken some statistics related definitions (1.7–1.11) from [3–5].
1.1. Pochhmmer Symbol
The factorial function is denoted and defined by The function defined in relation (1) is also known as Pochhmmer symbol.
1.2. Gamma Function
Let ; the Euler gamma function is defined by and the integral form of gamma function is given by From the relation (3), using integration by parts, we can easily show that The relation between Pochhammer symbol and gamma function is given by
1.3. Beta Function
The beta function of two variables is defined as and, in terms of gamma function, it is written as
1.4. Pochhammer -Symbol
For , the Pochhammer -symbol is denoted and defined by
1.5. -Gamma Function
For and , the -gamma function is defined as and the integral representation of -gamma function is
1.6. -Beta Function
For , the -beta function of two variables is defined by and, in terms of -gamma function, -beta function is defined as
Also, the researchers [6–10] have worked on the generalized -gamma and -beta functions and discussed the following properties: Using the above relations, we see that, for and , the following properties of -beta function are satisfied by authors (see [6, 7, 11]): Note that when , .
For more details about the theory of -special functions like -gamma function, -beta function, -hypergeometric functions, solutions of -hypergeometric differential equations, contegious functions relations, inequalities with applications and integral representations with applications involving -gamma and -beta functions and so forth. (See [12–17].)
1.7. Probability Distribution and Expected Values
In a random experiment with outcomes, suppose a variable assumes the values with corresponding probabilities ; then this collection is called probability distribution and (in case of discrete distributions). Also, if is a continuous probability distribution function defined on an interval , then .
In statistics, there are three types of moments which are (i) moments about any point , (ii) moments about , and (iii) moments about mean position of the given data. Also, expected value of the variate is defined as the first moment of the probability distribution about and the th moment about mean of the probability distribution is defined as where is the mean of the distribution.
Also, shows the expected value of the variate and is defined as the first moment of the probability distribution about ; that is,
1.8. Gamma Distribution
A continuous random variable is said to have a gamma distribution with parameter , if its probability distribution function is defined by and its distribution function is defined by which is also called the incomplete gamma function.
1.9. Moment Generating Function of Gamma Distribution
The moment generating function of is defined by
1.10. Beta Distribution of the First Kind
A continuous random variable is said to have a beta distribution with two parameters and , if its probability distribution function is defined by This distribution is known as a beta distribution of the first kind and a beta variable of the first kind is referred to as . Its distribution function is given by
1.11. Beta Distribution of the Second Kind
A continuous random variable is said to have a beta distribution of the second kind with parameters and , if its probability distribution function is defined by and its probability distribution function is given by
2. Main Results: -Gamma and -Beta Distributions
In this section, we define gamma and beta distributions in terms of a new parameter and discuss some properties of these distributions in terms of .
Definition 1. Let be a continuous random variable; then it is said to have a -gamma distribution with parameters and , if its probability density function is defined by and its distribution function is defined by
Proposition 2. The newly defined distribution satisfies the following properties.(i)The -gamma distribution is the probability distribution that is area under the curve is unity.(ii)The mean of -gamma distribution is equal to a parameter .(iii)The variance of -gamma distribution is equal to the product of two parameters .
Proof of (i). Using the definition of -gamma distribution along with the relation (10), we have
Proof of (ii). As mean of a distribution is the expected value of the variate, so the mean of the -gamma distribution is given by Using the definition of -gamma function and the relation (13), we have
Proof of (iii). As variance of a distribution is equal to , so the variance of -gamma distribution is calculated as Now, we have to find , which is given by Thus we obtain the variance of -gamma distribution as where is the notation of variance present in the literature.
2.1. -Beta Distribution of First Kind
Let be a continuous random variable; then it is said to have a -beta distribution of the first kind with two parameters and , if its probability distribution function is defined by In the above distribution, the beta variable of the first kind is referred to as and its distribution function is given by
Proposition 3. The -beta distribution satisfies the following basic properties.(i)-beta distribution is the probability distribution that is the area of under a curve is unity.(ii)The mean of this distribution is .(iii)The variance of is .
Proof of (i). By using the above definition of -beta distribution, we have By the relation (11), we get
Proof of (ii). The mean of the distribution, , is given by Using the relations (12), (13), and (16), we have
Proof of (iii). The variance of is given by Thus substituting the values of and in (42) along with some algebraic calculations we have the desired result.
2.2. -Beta Distribution of the Second Kind
A continuous random variable is said to have a -beta distribution of the second kind with parameters and , if its probability distribution function is defined by
Note. The -beta distribution of the second kind is denoted by .
Theorem 4. The -beta function of the second kind represents a probability distribution function that is
Proof. We observe that Let , so that ; thus by using the relation (11), the above equation gives
3. Moment Generating Function of -Gamma Distribution
In this section, we derive the moment generating function of continuous random variable of newly defined -gamma distribution in terms of a new parameter , which is illustrated as Let , so that and . Then substituting these values in (48), we obtain Now differentiating times with respect to and putting , we get Thus when , we obtain , when , , and hence = variance of the -gamma distribution proved in Proposition 2.
3.1. Higher Moment in terms of
The th moment in terms of is given by
Theorem 5. The moments of the higher order of -beta distribution of the second kind are given as
Proof. Consider Changing the variables as , above equation becomes Replacing by , we have Now using in the above equation we get the desired result.
4. Conclusion
In this paper the authors conclude that we have the following.(i)If tends to 1, then -gamma distribution and -beta distribution tend to classical gamma and beta distribution.(ii)The authors also conclude that the area of -gamma distribution and -beta distribution for each positive value of is one and their mean is equal to a parameter and , respectively. The variance of -gamma distribution for each positive value of is equal to times of the parameter . In this case if , then it will be equal to variance of gamma distribution. The variance of -beta distribution for each positive value of is also defined.(iii)In this paper the authors introduced moments generating function and higher moments in terms of a new parameter .
Conflict of Interests
The authors declare that there is no conflict of interests regarding the publication of this paper.
Acknowledgment
The authors would like to express profound gratitude to referees for deeper review of this paper and the referee’s useful suggestions that led to an improved presentation of the paper.