Next Article in Journal
Control Design for Flexible Manipulator Model with Nonlinear Input and State Constraints Based on Symmetric Barrier Lyapunov Function
Previous Article in Journal
Formal Analysis of Rational Exchange Protocols Based on the Improved Buttyan Model
Previous Article in Special Issue
Quasi-Sure Exponential Stability of Stochastic Differential Delay Systems Driven by G-Brownian Motion
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Three-Parameter Record-Based Transmuted Rayleigh Distribution (Order 3): Theory and Real-Data Applications

Department of Computer Science and Engineering, University of Mitrovica “Isa Boletini”, 40000 Mitrovica, Kosovo
Symmetry 2025, 17(7), 1034; https://doi.org/10.3390/sym17071034
Submission received: 13 May 2025 / Revised: 17 June 2025 / Accepted: 24 June 2025 / Published: 1 July 2025
(This article belongs to the Special Issue Symmetric or Asymmetric Distributions and Its Applications)

Abstract

This paper introduces the record-based transmuted Rayleigh distribution of order 3 (rbt-R), a three-parameter extension of the classical Rayleigh model designed to address data characterized by high skewness and heavy tails. While traditional generalizations of the Rayleigh distribution enhance model flexibility, they often lack sufficient adaptability to capture the complexity of empirical distributions encountered in applied statistics. The rbt-R model incorporates two additional shape parameters, a and b, enabling it to represent a wider range of distributional shapes. Parameter estimation for the rbt-R model is performed using the maximum likelihood method. Simulation studies are conducted to evaluate the asymptotic properties of the estimators, including bias and mean squared error. The performance of the rbt-R model is assessed through empirical applications to four datasets: nicotine yields and carbon monoxide emissions from cigarette data, as well as breaking stress measurements from carbon-fiber materials. Model fit is evaluated using standard goodness-of-fit criteria, including AIC, AICc, BIC, and the Kolmogorov–Smirnov statistic. In all cases, the rbt-R model demonstrates a superior fit compared to existing Rayleigh-based models, indicating its effectiveness in modeling highly skewed and heavy-tailed data.

1. Introduction

Standard probability distributions often fail to adequately describe real-world data, particularly when the data exhibit non-standard or complex structural properties. To address this issue, researchers have focused on developing broader families of statistical models that more accurately capture the complexities observed in empirical data. A common and effective approach to achieving greater flexibility involves introducing additional shape parameters into traditional probability distributions.
Shaw and Buckley [1] introduced the Quadratic Rank Transmutation Map (QRTM), a methodology for generating new probability distributions from existing ones through rank-based transformations. This framework has since inspired further generalizations. Merovci, Alizadeh, and Hamedani [2] expanded on this concept by proposing the Exponentiated Transmuted-G family. Subsequently, Moolath and Jayakumar [3] introduced the T-transmuted X family, further enriching this line of research.
Furthermore, Granzotto, Louzada, and Balakrishnan [4] presented a cubic extension of the QRTM, termed the Cubic Rank Transmutation Map (CRTM). More recently, Rahman et al. [5] proposed a modified cubic transmuted-G distribution, adding another layer of adaptability within this class of statistical models.
The Rayleigh distribution is a continuous probability distribution commonly used to model non-negative random variables in probability theory and statistics [6]. It is named after Lord Rayleigh (1842–1919). This distribution often arises when the overall magnitude of a vector is determined by its orthogonal components [6].
The Rayleigh distribution is a special case of the Weibull family and is widely applied in reliability analysis, life-testing, and survival analysis. Specifically, if
X Rayleigh ( σ ) ,
then X is equivalent to a Weibull random variable with shape parameter k = 2 and scale parameter λ = σ , i.e.,
X Weibull ( k = 2 , λ = σ ) .
Moreover, the square of a Rayleigh-distributed variable with parameter σ has the following well-known interpretations:
  • X 2 χ 2 2 , the chi-squared distribution with 2 degrees of freedom;
  • Equivalently, X 2 Exp ( θ ) , the exponential distribution with rate parameter θ = 1 / ( 2 σ 2 ) .
A notable characteristic of the Rayleigh distribution is its increasing hazard function, which makes it especially useful in certain reliability and survival contexts.
The Rayleigh distribution has a rich history, with early foundational contributions by Siddiqui [7,8] and Vickers [9]. Over the years, several authors have proposed generalizations to enhance its flexibility and applicability, including Beckmann [10], Kundu [11], and Voda [12]. More recently, Abd Elfattah et al. [13] explored parameter estimation techniques for the Rayleigh model under various censoring schemes, reflecting continued interest in adapting the model to real-world data scenarios.
However, in many practical situations, the traditional Rayleigh form may not adequately capture emerging data patterns, motivating the development of extended versions. Merovci [14,15] introduced the transmuted Rayleigh and transmuted generalized Rayleigh distributions by applying transmutation techniques to the classical Rayleigh model.
More recently, Mir and Ahmad [16] proposed the MTI Rayleigh distribution, designed to provide improved fit, particularly for datasets such as COVID-19 mortality figures. In a similar vein, Rivera et al. [17] developed the Scale Mixture of Rayleigh (SMR) distribution, which performs well in capturing data with strong skewness and heavy tails.
Definition 1 ([18]). 
A continuous random variable X is said to follow a Rayleigh distribution with scale parameter σ > 0 if its probability density function (PDF) is given by
f ( x ; σ ) = x σ 2 e x 2 / ( 2 σ 2 ) , x 0 ,
and its cumulative distribution function (CDF) is
F ( x ; σ ) = 1 e x 2 / ( 2 σ 2 ) , x 0 .
Here, x denotes the random variable and σ is the scale parameter.
Despite these advancements, the classical Rayleigh distribution remains limited in its ability to accommodate data exhibiting skewness or heavy tails. To address these shortcomings, recent studies have introduced structural extensions aimed at increasing flexibility and improving tail behavior.
One such advancement was proposed by Santoro et al. (2023) [19], who introduced a modified version of the Lomax–Rayleigh distribution using a Slash-type transformation. This modification was designed to increase kurtosis, thereby enhancing the model’s capacity to capture extreme values.
In a different direction, Haj Ahmad et al. (2024) [20] developed a discrete version of the generalized Rayleigh distribution. Utilizing a survival-based discretization approach, their model was tailored for count data—particularly data characterized by overdispersion. They investigated the model’s properties under both classical and Bayesian frameworks and demonstrated its effectiveness through applications to real datasets.
Further extending the Rayleigh family, Dong and Gui (2024) [21] applied the generalized Rayleigh model to stress–strength reliability analysis. Their focus was on estimating the reliability measure P ( Y < X ) , using a sampling technique based on lower record ranked sets. The estimation procedures, developed under both likelihood and Bayesian paradigms, were enhanced with bootstrap confidence intervals, yielding improved precision over traditional sampling methods.
Motivated by these developments, we introduce a new generalization of the Rayleigh distribution: the record-based transmuted Rayleigh distribution of order 3 (rbt-Rayleigh). By incorporating two additional parameters, the proposed model offers increased flexibility while preserving a key reliability feature—the increasing failure rate (IFR)—under specific conditions. We evaluate the model using four distinct datasets and find that it consistently outperforms existing Rayleigh-type models, as assessed by standard criteria such as AIC, BIC, and the Kolmogorov–Smirnov statistic.

2. The Record-Based Transmuted Rayleigh Distribution of Order 3

Balakrishnan and He [22] introduced the record-based transmuted-G (RBT-G) generator of order 3, a flexible framework for constructing new probability models from any given baseline cumulative distribution. This generator includes two additional shape parameters that allow for better control over the distribution’s skewness and tail behavior. The CDF is expressed as
F ( x ) = 1 1 G ( x ) 1 + ( 1 a ) { ln ( 1 G ( x ) ) } + 1 a b 2 { ln ( 1 G ( x ) ) } 2 ,
subject to the constraints 0 a , b 1 and a + b 1 .
The corresponding probability density function (PDF) derived from this generator is given by
f ( x ) = g ( x ) a + b { ln ( 1 G ( x ) ) } + 1 a b 2 { ln ( 1 G ( x ) ) } 2 ,
where g ( x ) denotes the probability density function (PDF) associated with the cumulative distribution function (CDF) G ( x ) .
By taking the Rayleigh distribution as the baseline, we develop a new and flexible model known as the record-based transmuted Rayleigh distribution of order 3 (rbt-Rayleigh). The corresponding PDF and CDF are obtained by substituting the Rayleigh CDF and PDF, given in Equations (1) and (2), into generator Formulas (3) and (4).
f r b t R ( x , σ , a , b ) = x σ 2 exp x 2 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4
F r b t R ( x , σ , a , b ) = 1 exp x 2 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4
0 a , b 1 , a + b 1 .
Remark on the Gamma function. The Gamma function, denoted by Γ ( z ) , is a classical extension of the factorial function to real and complex arguments. For any real number z > 0 , it is defined by the integral
Γ ( z ) = 0 t z 1 e t d t .
One of its key properties is that, for every positive integer n, we have
Γ ( n ) = ( n 1 ) ! ,
and more generally, it satisfies the recurrence relation
Γ ( z + 1 ) = z Γ ( z ) .
We make use of the following well-known integral identity involving the Gamma function:
0 x m e β x n d x = Γ m + 1 n n β m + 1 n ,
where ( β ) > 0 , ( m ) > 1 , and  ( n ) > 0 , as given in Gradshteyn and Ryzhik ([23], Eq. 3.326(2), p. 339).
This identity is used in the proof of Proposition 1 and will also be used in Theorem 1 to derive the moment expressions.
Proposition 1. 
Let f r b t R ( x , σ , a , b ) and F r b t R ( x , σ , a , b ) denote the PDF and CDF of the record-based transmuted Rayleigh distribution of order 3 (rbt-Rayleigh), respectively, as defined in Equations (5) and (6). Then:
1. 
The PDF f r b t R ( x , σ , a , b ) satisfies:
(a) 
f r b t R ( x , σ , a , b ) 0 for all x 0 .
(b) 
0 f r b t R ( x , σ , a , b ) d x = 1 .
2. 
The CDF F r b t R ( x , σ , a , b ) satisfies:
(a) 
It is continuous on [ 0 , ) and right-continuous on [ 0 , ) .
(b) 
It is non-decreasing on [ 0 , ) .
(c) 
It satisfies the limits:
lim x 0 + F r b t R ( x , σ , a , b ) = 0 and lim x F r b t R ( x , σ , a , b ) = 1 .
Proof. 
1a. From the explicit form of the density, we note that it is composed of three factors:
f r b t R ( x , σ , a , b ) = x σ 2 exp x 2 2 σ 2 P ( x ) ,
where
P ( x ) = a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 .
Clearly, x 0 and σ > 0 imply x σ 2 > 0 for x > 0 , and  exp ( x 2 / 2 σ 2 ) > 0 for all x. From the parameter constraints 0 a , b 1 and a + b 1 , it follows that
1 a b 0 .
Thus, P ( x ) 0 for all x 0 , and therefore:
f r b t R ( x , σ , a , b ) 0 for all x 0 .
1b.
0 f r b t R ( x , σ , a , b ) d x = a σ 2 0 x exp x 2 2 σ 2 d x + b 2 σ 4 0 x 3 exp x 2 2 σ 2 d x + 1 a b 8 σ 6 0 x 5 exp x 2 2 σ 2 d x .
By applying the integral identity from Equation (7), we obtain:
0 x exp x 2 2 σ 2 d x = Γ ( 1 ) 2 1 2 σ 2 = σ 2 ,
0 x 3 exp x 2 2 σ 2 d x = Γ ( 2 ) 2 1 2 σ 2 2 = 2 σ 4 ,
0 x 5 exp x 2 2 σ 2 d x = Γ ( 3 ) 2 1 2 σ 2 3 = 8 σ 6 .
Therefore:
0 f r b t R ( x , σ , a , b ) d x = a + b + ( 1 a b ) = 1 .
2a. The function F r b t R ( x , σ , a , b ) is a composition of exponential and polynomial terms, both of which are continuous on [ 0 , ) . Hence, F r b t R ( x , σ , a , b ) is continuous and right-continuous on [ 0 , ) . 2b. To verify monotonicity, we differentiate:
d d x F r b t R ( x ) = f r b t R ( x ) .
From part (1), we know f r b t R ( x ) 0 for all x 0 , so F r b t R ( x ) is non-decreasing on [ 0 , ) .
2c. We now evaluate the limits:
lim x 0 + F r b t R ( x ) = 1 lim x 0 + exp x 2 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4
= 1 1 = 0 .
lim x F r b t R ( x ) = 1 lim x exp x 2 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 .
By Theorem 3.20(d) from Rudin [24], which states that if p > 0 and α R , then
lim n n α ( 1 + p ) n = 0 ,
we conclude:
exp x 2 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 0 as x .
Hence:
lim x F r b t R ( x ) = 1 0 = 1 .
Thus, F r b t R ( x ) satisfies:
F r b t R ( 0 ) = 0 , F r b t R ( ) = 1 , F r b t R ( x ) is non-decreasing and right-continuous .
Therefore, F r b t R ( x ) is a valid cumulative distribution function. Consequently, the record-based transmuted Rayleigh distribution of order 3 satisfies all the necessary conditions to be a valid probability distribution under the given parameter constraints.    □
Figure 1 and Figure 2 illustrate the variability in the shapes of the PDF and CDF for the record-based transmuted Rayleigh distribution of order 3.
The hazard rate function (HRF) of rbt-Rayleigh distribution is given by:
h ( x ; a , b , σ ) = f ( x ) 1 F ( x ) = a x + 1 2 b x 3 σ 2 + 1 8 ( 1 a b ) x 5 σ 4 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4
Since the baseline distribution G ( x ) in our model is the Rayleigh distribution, whose hazard function is strictly increasing (i.e., the Rayleigh distribution is IFR), it is of interest to examine whether this property is preserved under the record-based transmuted transformation of order 3.
This question has been addressed and rigorously proven by Balakrishnan and He (see Section 3.3 in [22]), who showed that the resulting distribution retains the IFR property of the baseline if the transformation parameters satisfy the condition
b a ( 1 a ) .
Hence, in our case, the proposed distribution is IFR whenever this condition holds.

3. Quantile Function

The cumulative distribution function (CDF) of the rbt–Rayleigh distribution is given by
F ( x ; a , b , σ ) = 1 exp x 2 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 .
To compute the quantile function x p , we must solve the nonlinear equation
exp x 2 2 σ 2 1 + ( 1 a ) x 2 2 σ 2 + 1 2 ( 1 a b ) x 2 2 σ 2 2 = 1 p ,
which does not admit a closed-form solution for general values of a, b, and  σ . Therefore, the quantile function is computed numerically.
To address this, we implemented a root-finding algorithm in R that solves the equation above for a given probability level p ( 0 , 1 ) . The corresponding R code is provided below and can be used to generate a full quantile table or compute specific quantiles such as the median or quartiles.

R Code for Computing the Quantile Function of the rbt–Rayleigh Distribution

Listing 1 presents the R code that numerically computes the quantile function of the rbt–Rayleigh distribution by solving the nonlinear equation.
exp x 2 2 σ 2 1 + ( 1 a ) x 2 2 σ 2 + 1 2 ( 1 a b ) x 2 2 σ 2 2 = 1 p .
Listing 1. R code for computing the quantile function of the rbt–Rayleigh distribution.
Symmetry 17 01034 i001
Table 1 reports the quantile values x p of the rbt–Rayleigh distribution for selected probabilities, while Figure 3 illustrates the quantile function x p for p ( 0 , 1 ) , using parameters a = 0.8 , b = 0.15 , and σ = 1 .

4. Moments

Theorem 1. 
If X rbt-R ( a , b , σ ) , then the r th moment of X is given by:
E ( X r ) = 2 r 2 σ r Γ r 2 + 1 a + b 2 ( r + 2 ) + ( 1 a b ) 8 ( r + 2 ) ( r + 4 ) .
Specifically, the mean and variance are obtained as follows:
E ( X ) = σ 2 π 16 ( 15 7 a 3 b ) ,
Var ( X ) = E ( X 2 ) ( E ( X ) ) 2 = 2 σ 2 ( 3 2 a b ) π σ 2 128 ( 15 7 a 3 b ) 2 .
Proof. 
E ( X r ) = 0 x r f ( x ) d x = 0 x r + 1 σ 2 exp x 2 2 σ 2 a + b 2 σ 2 x 2 + ( 1 a b ) 8 σ 4 x 4 d x = a σ 2 0 x r + 1 e x 2 / ( 2 σ 2 ) d x + b 2 σ 4 0 x r + 3 e x 2 / ( 2 σ 2 ) d x + ( 1 a b ) 8 σ 6 0 x r + 5 e x 2 / ( 2 σ 2 ) d x = 2 r 2 σ r a Γ r 2 + 1 + 2 r 2 σ r b r 2 + 1 Γ r 2 + 1 + 2 r 2 σ r 1 a b 2 r 2 + 2 r 2 + 1 Γ r 2 + 1 = 2 r 2 σ r Γ r 2 + 1 a + b 2 ( r + 2 ) + ( 1 a b ) 8 ( r + 2 ) ( r + 4 ) .
The result follows by applying the integral identity given in (7).    □
Throughout the remainder of the manuscript, we denote the r-th raw moment of the distribution by μ r = E ( X r ) . This notation is used for expressing skewness and kurtosis in terms of the central moments.
Theorem 2. 
If X rbt-R ( a , b , σ ) , then the moment generating function of X, denoted by M X ( t ) , is given by:
M X ( t ) = i = 0 t i 2 i / 2 σ i Γ i 2 + 1 i ! a + b 2 ( i + 2 ) + ( 1 a b ) 8 ( i + 2 ) ( i + 4 ) .
Proof. 
By definition,
M X ( t ) = 0 e t x f r b t R ( x ) d x .
Since
e t x = i = 0 t i x i i ! ,
one obtains
M X ( t ) = 0 i = 0 t i x i i ! f r b t R ( x ) d x .
For any finite interval [ 0 , A ] , the function f r b t R ( x ) is continuous on [ 0 , A ] and hence bounded. Therefore, there exists a constant M > 0 such that
f r b t R ( x ) M for all x [ 0 , A ] .
Hence,
t i x i i ! f r b t R ( x ) | t | i A i i ! M .
Since
i = 0 ( | t | A ) i i ! = e | t | A < ,
the series i = 0 t i x i i ! f r b t R ( x ) converges uniformly on [ 0 , A ] by the Weierstrass M-test. Each term is continuous on [ 0 , A ] . By the Uniform Convergence Theorem for the Riemann integral, one obtains
0 A i = 0 t i x i i ! f r b t R ( x ) d x = i = 0 0 A t i x i i ! f r b t R ( x ) d x .
The function f r b t R ( x ) is integrable on [ 0 , ) and tends to zero faster than any polynomial as x . Hence, letting A yields
M X ( t ) = i = 0 t i i ! E ( X i ) .
From the explicit expression of the moments E ( X i ) one obtains
M X ( t ) = i = 0 t i 2 i 2 σ i Γ i 2 + 1 i ! a + b 2 ( i + 2 ) + ( 1 a b ) 8 ( i + 2 ) ( i + 4 ) .
   □
The values presented in Table 2 and Table 3 correspond to the mean and variance of the random variable X rbt-R ( a , b , σ ) computed for selected combinations of the parameters a, b, and  σ .

5. Skewness and Kurtosis

In addition to the first two moments, which characterize the location and dispersion of a distribution, the third and fourth central moments provide insight into its shape. These are commonly summarized by the coefficients of skewness and kurtosis.
The coefficient of skewness measures the asymmetry of the distribution around its mean. A positive skewness indicates a longer right tail, whereas a negative value implies a heavier left tail. For a random variable X, the skewness is defined as:
γ 1 = μ 3 μ 2 3 / 2 = E ( X 3 ) 3 E ( X 2 ) E ( X ) + 2 [ E ( X ) ] 3 E ( X 2 ) [ E ( X ) ] 2 3 / 2 .
The coefficient of kurtosis, on the other hand, quantifies the heaviness of the tails and the sharpness of the peak relative to a normal distribution. It is given by:
γ 2 = μ 4 μ 2 2 = E ( X 4 ) 4 E ( X 3 ) E ( X ) + 6 E ( X 2 ) [ E ( X ) ] 2 3 [ E ( X ) ] 4 E ( X 2 ) [ E ( X ) ] 2 2 .
For the proposed rbt-Rayleigh distribution, explicit expressions for the moments E ( X r ) have been derived in Theorem 1. These can be directly substituted into the formulas above to compute the skewness and kurtosis as functions of the parameters a, b, and  σ .

6. Harmonic Mean

Theorem 3. 
If X rbt-R ( a , b , σ ) , then the harmonic mean of X, defined as H = E 1 / X , is given by:
H = 2 π 16 σ ( 3 + 5 a + 5 b ) .
Proof. 
We compute the expected value of the reciprocal:
H = E 1 X = 0 1 x f ( x ) d x = 0 1 x · x σ 2 exp x 2 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 d x = a σ 2 0 exp x 2 2 σ 2 d x + b 2 σ 4 0 x 2 exp x 2 2 σ 2 d x + 1 a b 8 σ 6 0 x 4 exp x 2 2 σ 2 d x .
Using the Gaussian integrals:
0 exp x 2 2 σ 2 d x = σ 2 π 2 , 0 x 2 exp x 2 2 σ 2 d x = σ 3 2 π 2 , 0 x 4 exp x 2 2 σ 2 d x = 3 σ 5 2 π 2 ,
we conclude that:
H = 2 π 16 σ ( 3 + 5 a + 5 b ) .
   □

7. Mean Deviations

The mean deviation about the mean and the mean deviation about the median are defined by:
δ 1 = 0 | x μ | f ( x ) d x = 2 μ F ( μ ) 2 0 μ x f ( x ) d x ,
δ 2 = 0 | x M | f ( x ) d x = 2 M ( x M ) f ( x ) d x = μ 2 0 M x f ( x ) d x ,
where μ = E ( X ) is the mean, and M denotes the median of the distribution.
Theorem 4. 
For the rbt-R distribution, the mean deviations δ 1 and δ 2 are given by:
δ 1 = 2 μ 1 exp μ 2 2 σ 2 1 + 1 2 ( 1 a ) μ 2 σ 2 + 1 8 ( 1 a b ) μ 4 σ 4 2 μ ( 3 ( 5 a + b 5 ) σ 4 + ( ( 5 a + b 5 ) μ 2 8 a ) σ 2 + μ 4 ( 1 + a + b ) ) exp ( μ 2 2 σ 2 ) 8 σ 2 + 15 σ 3 ( erf ( μ 2 2 σ ) 1 ) π 2 ( ( a + b 5 1 ) σ 2 8 a 15 ) 8 σ 2 ,
and
δ 2 = μ + 15 σ 3 ( erf M 2 2 σ 1 ) π 2 ( ( a + b 5 1 ) σ 2 8 a 15 ) 8 σ 2 2 M ( 3 ( 5 a + b 5 ) σ 4 + ( ( 5 a + b 5 ) M 2 8 a ) σ 2 + M 4 ( 1 + a + b ) ) exp M 2 2 σ 2 8 σ 2 .
Proof. 
0 μ x f ( x ) d x = 0 μ x x σ 2 exp 1 2 x 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 d x = a σ 2 0 x 2 exp 1 2 x 2 σ 2 d x + b 2 σ 2 0 x 4 exp 1 2 x 2 σ 2 d x + ( 1 a b ) 8 σ 4 0 x 6 exp 1 2 x 2 σ 2 d x = a σ 2 σ 3 π 2 erfc μ 2 σ μ σ 2 exp μ 2 2 σ 2 + b 2 σ 2 3 σ 5 π 2 erfc μ 2 σ μ σ 2 exp μ 2 2 σ 2 μ 2 + 3 σ 2 + ( 1 a b ) 8 σ 4 15 σ 7 π 2 erfc μ 2 σ μ σ 2 exp μ 2 2 σ 2 μ 4 + 5 μ 2 σ 2 + 15 σ 4 = 2 μ ( 3 ( 5 a + b 5 ) σ 4 + ( ( 5 a + b 5 ) μ 2 8 a ) σ 2 + μ 4 ( 1 + a + b ) ) exp ( μ 2 2 σ 2 ) 16 σ 2 + 15 σ 3 ( erf ( μ 2 2 σ ) 1 ) π 2 ( ( a + b 5 1 ) σ 2 8 a 15 ) 16 σ 2 .
By substituting into Equations (11) and (12), we obtain the mean deviations. Here, erfc represents the complementary error function.    □

8. Entropy

Entropy measures provide a formal means of quantifying the uncertainty inherent in probability distributions. Among them, Shannon entropy is the most widely used, while the Rényi entropy [25], a parametric generalization, offers a broader framework for analyzing distributional characteristics [26].
Let X be a continuous random variable with probability density function f ( x ) . The Rényi entropy of order α > 0 , α 1 , is defined by
H α ( X ) = 1 1 α log f ( x ) α d x .
Theorem 5. 
Let X rbt-R ( a , b , σ ) . The Rényi entropy of order α for the rbt-R distribution is given by:
H α ( X ) = 1 1 α log ( k = 0 r = 0 α k k r a α k b k r ( 1 a b ) r 2 k + 2 r + 1 σ 2 α + 2 k + 2 r × α 2 σ 2 α + 2 k + 2 r + 1 2 Γ α + 2 k + 2 r + 1 2 ) .
Proof. 
H α ( X ) = 1 1 α log 0 f ( x ) α d x = 1 1 α log 0 x α σ 2 α exp α x 2 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 α d x
Applying the binomial expansion yields
a + b 2 σ 2 x 2 + 1 a b 8 σ 4 x 4 α = k = 0 r = 0 k α k k r a α k b k r ( 1 a b ) r x 2 2 σ 2 k + r .
For any finite interval [ 0 , A ] , the function f r b t R ( x ) α is continuous and hence bounded on [ 0 , A ] . Therefore, there exists a constant M > 0 such that
x α σ 2 α x 2 2 σ 2 k + r exp α x 2 2 σ 2 A α + 2 k + 2 r σ 2 α + 2 k + 2 r 2 k + r M .
Since
k = 0 r = 0 k α k k r a α k b k r ( 1 a b ) r A 2 2 σ 2 k + r
converges absolutely, by the Weierstrass M-test, the double series converges uniformly on [ 0 , A ] . Each term in the sum is continuous on [ 0 , A ] . By the Uniform Convergence Theorem for the Riemann integral, one obtains
0 A k = 0 r = 0 k g k , r ( x ) d x = k = 0 r = 0 k 0 A g k , r ( x ) d x .
The function f r b t R ( x ) tends to zero faster than any polynomial as x . Thus, taking the limit A yields
H α ( X ) = 1 1 α log ( k = 0 r = 0 k α k k r a α k b k r ( 1 a b ) r σ 2 α + 2 k + 2 r 2 k + 2 r × 0 x α + 2 k + 2 r exp α x 2 2 σ 2 d x ) .
Applying the integral identity
0 x ν 1 e μ x 2 d x = 1 2 μ ν / 2 Γ ν 2
gives
0 x α + 2 k + 2 r exp α x 2 2 σ 2 d x = 1 2 α 2 σ 2 α + 2 k + 2 r + 1 2 Γ α + 2 k + 2 r + 1 2 .
Hence,
H α ( X ) = 1 1 α log ( k = 0 r = 0 k α k k r a α k b k r ( 1 a b ) r 2 k + 2 r + 1 σ 2 α + 2 k + 2 r × α 2 σ 2 α + 2 k + 2 r + 1 2 Γ α + 2 k + 2 r + 1 2 ) .
   □

9. Order Statistics

Let X ( 1 ) X ( 2 ) X ( n ) denote the order statistics from an i.i.d. sample X 1 , , X n drawn from a continuous distribution with probability density function (PDF) f X and cumulative distribution function (CDF) F X .
The PDF of the k th order statistic is given by:
f X ( k ) ( x ) = n ! ( k 1 ) ! ( n k ) ! f X ( x ) [ F X ( x ) ] k 1 [ 1 F X ( x ) ] n k , k = 1 , , n .
If X rbt-R ( a , b , σ ) , then
f X ( k ) ( x ) = n ! ( k 1 ) ! ( n k ) ! x σ 2 exp 1 2 x 2 σ 2 × a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 × 1 exp 1 2 x 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 k 1 × exp 1 2 x 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 n k .
When k = 1 , we obtain the PDF of the smallest observation in the sample:
f X ( 1 ) ( x ) = n f X ( x ) [ 1 F X ( x ) ] n 1 .
For the rbt-R distribution, this becomes:
f X ( 1 ) ( x ) = n x σ 2 exp 1 2 x 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 × exp 1 2 x 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 n 1 .
When k = n , we obtain the PDF of the largest observation in the sample:
f X ( n ) ( x ) = n f X ( x ) [ F X ( x ) ] n 1 .
For the rbt-R distribution, this becomes
f X ( n ) ( x ) = n x σ 2 exp 1 2 x 2 σ 2 a + 1 2 b x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 × 1 exp 1 2 x 2 σ 2 1 + 1 2 ( 1 a ) x 2 σ 2 + 1 8 ( 1 a b ) x 4 σ 4 n 1 .

10. Maximum Likelihood Estimation

Let x 1 , x 2 , , x n denote a random sample drawn from the record-based transmuted Rayleigh distribution of order 3, with parameters σ > 0 and a , b [ 0 , 1 ] , subject to the constraint a + b 1 .
The likelihood function corresponding to this sample is given by:
L ( σ , a , b ) = i = 1 n f ( x i ; σ , a , b ) = i = 1 n x i σ 2 exp x i 2 2 σ 2 a + b x i 2 2 σ 2 + ( 1 a b ) x i 4 8 σ 4 .
Taking logarithms, we obtain the log-likelihood function:
( σ , a , b ) = i = 1 n ln ( x i ) 1 2 σ 2 i = 1 n x i 2 2 n ln ( σ ) + i = 1 n ln a + b x i 2 2 σ 2 + ( 1 a b ) x i 4 8 σ 4 .
To estimate ( σ ^ , a ^ , b ^ ) , we differentiate ( σ , a , b ) with respect to each parameter and set the score equations to zero:
σ = 1 σ 3 i = 1 n x i 2 2 n σ + i = 1 n 4 x i 2 ( a x i 2 2 b σ 2 + b x i 2 x i 2 ) σ ( 8 a σ 4 a x i 4 + 4 b σ 2 x i 2 b x i 4 + x i 4 ) = 0 , a = i = 1 n 8 σ 4 x i 4 8 a σ 4 a x i 4 + 4 b σ 2 x i 2 b x i 4 + x i 4 = 0 , b = i = 1 n x i 2 ( 4 σ 2 x i 2 ) 8 a σ 4 a x i 4 + 4 b σ 2 x i 2 b x i 4 + x i 4 = 0 .
In general, this nonlinear system has no closed-form solution, and numerical methods such as the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm or Newton–Raphson are employed to maximize the log-likelihood subject to the parameter constraints.
Under standard regularity conditions, the maximum likelihood estimator is asymptotically normal. Specifically:
n ( θ ^ θ ) D N 3 0 , I 1 ( θ ) ,
where θ = ( σ , a , b ) , and  I ( θ ) is the Fisher information matrix:
I ( θ ) = E θ 2 ( θ ) .
To confirm this result, we verify that the usual regularity conditions are satisfied:
  • Interior Point: The true parameter θ 0 lies in the interior of the space Θ = { ( σ , a , b ) R + × [ 0 , 1 ] 2 : a + b 1 } .
  • Differentiability: The log-likelihood is continuously differentiable on Θ for all x i > 0 .
  • Identifiability: The model is identifiable since each parameter combination yields a distinct density.
  • Fisher Information: The matrix I ( θ ) exists and is positive definite.
  • Finite Expectations: Expectations involving the first and second derivatives are finite due to the exponential tail of the density.
To clarify notation, the gradient θ ( θ ) and the Hessian θ 2 ( θ ) are given by:
θ ( θ ) = σ a b , θ 2 ( θ ) = 2 σ 2 2 σ a 2 σ b 2 a σ 2 a 2 2 a b 2 b σ 2 b a 2 b 2 .
The explicit expressions for the second-order partial derivatives used in this Hessian matrix are provided in Appendix A.
The observed information matrix is:
I ^ i j = 2 θ i θ j θ = θ ^ , i , j { σ , a , b } .
Its inverse gives the estimated variance–covariance matrix:
Var ^ ( θ ^ ) = I ^ 1 .
Approximate ( 1 α ) 100 % confidence intervals are constructed as:
θ ^ j ± z α / 2 [ I ^ 1 ] j j , j { σ , a , b } ,
where z α / 2 is the standard normal quantile.
For reporting purposes:
σ ^ ± z α / 2 [ I ^ 1 ] σ σ , a ^ ± z α / 2 [ I ^ 1 ] a a , b ^ ± z α / 2 [ I ^ 1 ] b b .
This formulation allows practitioners to assess parameter uncertainty and construct valid confidence intervals. Empirical examples using this procedure are provided in the following sections.

11. Application to Real Data

To evaluate the practical performance of the proposed record-based transmuted Rayleigh distribution of order 3 (rbtR), we fitted it to four real-world datasets. For comparison purposes, we also fitted the Rayleigh distribution (R), the transmuted Rayleigh distribution (T-R), the generalized Rayleigh distribution (G-R) as introduced in Surles and Padgett [27], and the transmuted generalized Rayleigh distribution (TGR). Model comparison was conducted using multiple goodness-of-fit criteria, namely the Akaike Information Criterion (AIC), the corrected Akaike Information Criterion (AICc), the Bayesian Information Criterion (BIC), and the Kolmogorov–Smirnov distance (KS). Additionally, overlay plots of the estimated probability density functions and cumulative distribution functions were provided to facilitate a visual assessment of fit quality.

11.1. Dataset 1: Nicotine Yields (FTC, 1994)

Source: Federal Trade Commission (FTC), Cigarette Yields Report, 1994 (EconDataUS).
The first dataset analyzed in this study relates to nicotine yield levels reported in 1994 by the U.S. Federal Trade Commission (FTC) in their widely referenced document titled “Tar, Nicotine, and Carbon Monoxide of the Smoke of 1206 Varieties of Domestic Cigarettes”. This report remains a central source for researchers studying chemical content in cigarettes, and it is freely available online: https://www.ftc.gov/system/files/documents/reports/report-tar-nicotine-carbon-monoxide-smoke-1206-varieties-domestic-cigarettes-year-1994/tarandnico.pdf (accessed on 10 January 2025).
According to the FTC’s documentation, nicotine yields were measured using the Cambridge Filter Method—an approach the agency has endorsed since 1967 to ensure consistency across cigarette brands. The measurements, expressed in milligrams per cigarette, were rounded to the nearest 0.1 mg.
Data were collected from various manufacturers across more than 50 locations in the United States. The report includes results from the five dominant companies at the time: Philip Morris, R. J. Reynolds, Lorillard, Brown & Williamson, and Liggett Group. In the case of lesser-known brands, data were often submitted directly by the manufacturers, following FTC guidelines.
In addition to yield values, the report outlines sample collection protocols and standard smoking conditions, such as the 23 mm smoked butt length, which contribute to the reproducibility of the data. Previous studies by Sloan and Sublett [28] and Schultz and Spears [29] further support the accuracy of the laboratory techniques applied.
This dataset serves as a useful illustration for examining how well the proposed rbt-Rayleigh distribution performs in practice. Descriptive statistics are provided in Table 4, while parameter estimates and model selection criteria—obtained via maximum likelihood estimation—are summarized in Table 5 and Table 6.
A histogram of the observed nicotine yields is presented in Figure 4, while the empirical versus fitted CDFs are displayed in Figure 5. The log-likelihood contour plot, with σ fixed at its MLE, is shown in Figure 6.
The observed Fisher information matrix (i.e., the negative of the Hessian matrix of the log-likelihood evaluated at the MLEs) under the rbt-Rayleigh distribution is estimated as:
I ^ = 18418.040 2081.0342 1303.6585 2081.0342 853.5247 255.8975 1303.6585 255.8975 137.4793 .
The inverse of this matrix, denoted by I ^ 1 , provides the estimated variance–covariance matrix of the maximum likelihood estimators (MLEs):
Var ^ ( θ ^ ) = I ^ 1 = 0.000174 0.000159 0.001949 0.000159 0.002797 0.006720 0.001949 0.006720 0.038266 .
Based on this, the approximate 95% confidence intervals for the parameters σ , a, and b are computed as:
σ [ 0.378 , 0.430 ] , a [ 0.095 , 0.302 ] , b [ 0 , 0.416 ] .

11.2. Dataset 2: Carbon Monoxide Emissions (FTC, 2007)

Source: U.S. Federal Trade Commission (FTC), “Nicotine, Tar, and CO Content of Domestic Cigarettes in 2007—Regular Brands, sorted by nicotine, tar, and CO.” Available at: https://www.econdataus.com/cigrs.html, accessed on 23 June 2025.
This dataset reports carbon monoxide (CO) emissions per cigarette, measured in milligrams, as published by the FTC in 2007. The data were extracted from the publicly available table titled “Regular Brands, sorted by CO”, which presents standardized yield values for a wide range of domestic cigarette brands.
Measurements were obtained using the Cambridge Filter Method, a standardized laboratory technique recommended by the FTC to ensure comparability across brands. CO emission values are rounded to the nearest 0.1 mg and cover major tobacco manufacturers in the U.S. market.
The distribution of CO emissions exhibits moderate right skew due to a small number of high-emission brands. The proposed rbt-Rayleigh model fits the observed data closely, capturing the distributional shape more effectively than alternative models. Among the models evaluated, it achieves the lowest Kolmogorov–Smirnov (KS) distance (0.037), indicating superior goodness-of-fit.
Descriptive statistics for CO emissions are presented in Table 7. Parameter estimates and log-likelihood values for the considered models are reported in Table 8, while goodness-of-fit criteria are summarized in Table 9. A histogram of the observed CO emission values is shown in Figure 7, the empirical versus fitted CDFs are displayed in Figure 8, and the log-likelihood contour plot—with σ fixed at its MLE—is provided in Figure 9.
The estimated variance–covariance matrix of the MLEs under the rbt-R distribution is given by:
H 1 = 0.008926 0.000546 0.006565 0.000546 0.000802 0.001975 0.006565 0.001975 0.010555 .

11.3. Dataset 3: Carbon-Fibre Breaking Stress (50 mm Gauge)

The carbon-fibre breaking stress values analyzed in this study correspond to tensile strength measurements (in GPa) collected from fibres with a gauge length of 50 mm, as reported by Lishamol and Jiju [30]. These measurements were obtained under controlled conditions from production samples, in accordance with standard testing procedures used to ensure that the fibres meet the necessary strength requirements for composite applications.
Of particular interest is the lower tail of the strength distribution—especially the first percentile—as reductions in this region may signal declining fibre quality and compromise the structural integrity of the resulting composite material.
This dataset serves as the third case study in our analysis (see Table 10). Descriptive statistics are visualized in Figure 10, and the empirical versus fitted CDFs are displayed in Figure 11. The proposed three-parameter rbt-Rayleigh distribution demonstrates a superior fit, achieving the lowest AIC, AICc, BIC, and KS values across competing models (Table 11 and Table 12). The corresponding log-likelihood surface (Figure 12) confirms the presence of a unique optimal solution.
The estimated variance–covariance matrix of the MLEs under the rbt-R distribution is given by:
H 1 = 2.4317 × 10 3 1.0494 × 10 3 4.2358 × 10 14 1.0494 × 10 3 3.5987 × 10 3 2.0707 × 10 14 4.2358 × 10 14 2.0707 × 10 14 1.1767 × 10 16 .

11.4. Dataset 4: Carbon-Fibre Breaking Stress (20 mm Gauge)

This dataset consists of tensile strength measurements for carbon fibres tested at a gauge length of 20 mm, as reported by Badar and Priest [31]. The strength values, expressed in gigapascals (GPa), were obtained under controlled laboratory conditions.
Using a shorter gauge length than that in Dataset 3 reduces the likelihood of encountering surface flaws in the tested segment. As a result, the measured strengths in this dataset tend to be slightly higher.
This distinction in testing setup provides a good opportunity to examine how the proposed rbt-Rayleigh distribution performs when the data come from a similar material but under different conditions. The observed breaking stress values for this dataset are presented in Table 13.
A summary of the descriptive statistics is given in Table 14, while parameter estimates and goodness-of-fit results appear in Table 15 and Table 16. Visual diagnostics are shown in Figure 13, Figure 14 and Figure 15. Once again, the rbt-R model provides the best fit, outperforming all four competing distributions across all evaluation metrics (Table 15 and Table 16). This superiority is further supported by graphical diagnostics shown in Figure 13, Figure 14 and Figure 15.
The estimated variance–covariance matrix of the MLEs under the rbt-R distribution is given by:
H 1 = 7.030 × 10 4 6.526 × 10 4 2.321 × 10 14 6.526 × 10 4 4.213 × 10 3 2.478 × 10 14 2.321 × 10 14 2.478 × 10 14 1.177 × 10 16 .

11.5. Summary of Results Across Datasets

The rbt-R distribution provides the best overall fit according to AIC, AICc, BIC, and KS criteria.

12. Random Sampling via Inverse Transform and Newton–Raphson

To investigate the finite-sample properties of the rbt-R maximum likelihood estimators, synthetic data are generated using a combination of the inverse-transform method and Newton–Raphson root-finding. The procedure is as follows:
  • Fix the true parameter vector ( a , b , σ ) , set the sample size n, and choose an initial value x ( 0 ) > 0 (we use the Rayleigh quantile approximation below).
  • For each i = 1 , , n , draw u i U ( 0 , 1 ) .
  • Compute
    x i ( 0 ) = σ 2 ln ( 1 u i ) ,
    which provides a Rayleigh-based initial guess.
  • Solve the equation
    F ( x i ; a , b , σ ) = u i
    iteratively via
    x i ( k + 1 ) = x i ( k ) F ( x i ( k ) ; a , b , σ ) u i f ( x i ( k ) ; a , b , σ ) ,
    where f and F denote the rbt-R density and CDF, respectively. Iteration stops when | x i ( k + 1 ) x i ( k ) | < 10 8 or after 50 steps, whichever occurs first.
  • Upon convergence, set x i = x i ( k + 1 ) . Repeat steps 2–5 for all i = 1 , , n to obtain the simulated sample { x 1 , , x n } .

13. Monte Carlo Experiment

We evaluated the performance of the estimator at the true parameter values ( a , b , σ ) = ( 0.3 , 0.4 , 2 ) , in the sample sizes n { 10 , 20 , 30 , , 500 } .
For each n, we perform S = 1000 independent replications. In each replication:
  • Generate a sample of size n using the inverse-Newton method described above;
  • Obtain the MLEs ( a ^ , b ^ , σ ^ ) via constrained optimization (L–BFGS–B);
  • Store the estimated triplet.
For each parameter θ { a , b , σ } , we compute:
θ ^ ¯ = 1 S s = 1 S θ ^ ( s ) , MSE ( θ ^ ) = 1 S s = 1 S θ ^ ( s ) θ 2 .
The results by sample size are presented in Table A1 and Table A2; both tables are provided in the Appendix B.

14. Conclusions

In this work, we present a new three-parameter extension of the classical Rayleigh distribution by applying the record-based transmuted-G (RBT-G) distribution of order 3, originally introduced by Balakrishnan and He. The resulting model, referred to as the rbt-Rayleigh distribution of order 3, offers increased flexibility to capture skewness and heavy-tailed behavior while retaining analytical tractability. Several analytical properties of the proposed distribution are derived, including the r-th raw and central moments, the harmonic mean, Shannon entropy, the quantile function, and the order statistics. The model parameters are estimated using the maximum likelihood method, implemented via numerical optimization in the R programming environment.
To assess the model’s performance, the rbt-Rayleigh distribution is applied to four empirical datasets: two related to cigarette composition (nicotine content and carbon monoxide emissions), and two concerning carbon-fibre tensile strength. A comparative analysis is conducted using standard goodness-of-fit criteria: Akaike Information Criterion (AIC), corrected Akaike Information Criterion (AICc), Bayesian Information Criterion (BIC), and the Kolmogorov–Smirnov (KS) statistic. In all cases, the rbt-Rayleigh model demonstrates a superior fit relative to the classical Rayleigh, transmuted Rayleigh, generalized Rayleigh, and transmuted generalized Rayleigh distributions.

Funding

This research received no external funding.

Data Availability Statement

Datasets 1 and 2 are publicly available from the EconDataUS repository https://econdataus.com/smoke.html, (accessed 10 May 2025). Datasets 3 and 4 are included within the main text of the paper.

Conflicts of Interest

The author declares no conflicts of interest.

Appendix A. Second-Order Derivatives of the Log-Likelihood

The second-order partial derivatives of the log-likelihood function ( σ , a , b ) are given below:
2 σ 2 = 3 i = 1 n x i 2 σ 4 + 2 n σ 2 5 2 i = 1 n x i 2 A i σ 2 1 a b 8 x i 4 + 1 2 b x i 2 σ 2 + a σ 4 2 ,
where
A i = 1 40 ( 1 a b ) 2 x i 6 + 1 4 b σ 2 ( 1 a b ) x i 4 + σ 4 ( a 2 + a b 1 5 b 2 a ) x i 2 6 5 a b σ 6 .
2 σ a = 8 σ i = 1 n x i 2 8 σ 4 b 4 b x i 2 σ 2 + b x i 4 + 4 x i 2 σ 2 8 a σ 4 a x i 4 + 4 b x i 2 σ 2 b x i 4 + x i 4 2 , 2 σ b = 8 σ i = 1 n x i 2 8 a σ 4 4 a σ 2 x i 2 + a x i 4 x i 4 8 a σ 4 a x i 4 + 4 b x i 2 σ 2 b x i 4 + x i 4 2 , 2 a 2 = i = 1 n ( 8 σ 4 x i 4 ) 2 8 a σ 4 a x i 4 + 4 b x i 2 σ 2 b x i 4 + x i 4 2 , 2 a b = i = 1 n ( 4 σ 2 x i 2 ) ( 8 σ 4 x i 4 ) x i 2 8 a σ 4 a x i 4 + 4 b x i 2 σ 2 b x i 4 + x i 4 2 .

Appendix B. Simulation Study

Table A1. Empirical means of the MLEs for various n.
Table A1. Empirical means of the MLEs for various n.
n a true b true σ true a ^ MLE b ^ MLE σ ^ MLE
100.300.402.000.27760.23151.9304
200.300.402.000.29100.27661.9527
300.300.402.000.30530.29471.9701
400.300.402.000.30520.32381.9809
500.300.402.000.31130.33181.9909
600.300.402.000.31660.32911.9955
700.300.402.000.31580.32831.9948
800.300.402.000.31910.32311.9957
900.300.402.000.31520.33781.9988
1000.300.402.000.31600.34172.0004
1100.300.402.000.31710.34412.0024
1200.300.402.000.31540.34722.0010
1300.300.402.000.31480.35212.0043
1400.300.402.000.31500.35422.0043
1500.300.402.000.31570.35632.0062
1600.300.402.000.31720.35492.0070
1700.300.402.000.31650.35862.0087
1800.300.402.000.31760.35482.0072
1900.300.402.000.31770.35362.0063
2000.300.402.000.31850.35592.0079
2100.300.402.000.31820.35642.0071
2200.300.402.000.31750.35812.0072
2300.300.402.000.31820.35882.0076
2400.300.402.000.31690.36022.0072
2500.300.402.000.31700.36302.0087
2600.300.402.000.31680.36692.0109
2700.300.402.000.31580.37072.0114
2800.300.402.000.31610.36852.0105
2900.300.402.000.31490.36802.0092
3000.300.402.000.31480.37062.0105
3100.300.402.000.31490.37152.0110
3200.300.402.000.31430.37202.0108
3300.300.402.000.31360.37402.0110
3400.300.402.000.31460.37452.0122
3500.300.402.000.31430.37532.0116
3600.300.402.000.31420.37442.0111
3700.300.402.000.31420.37432.0112
3800.300.402.000.31400.37342.0107
3900.300.402.000.31360.37402.0103
4000.300.402.000.31380.37412.0103
4100.300.402.000.31350.37502.0101
4200.300.402.000.31330.37482.0096
4300.300.402.000.31270.37712.0102
4400.300.402.000.31250.38052.0116
4500.300.402.000.31250.38052.0114
4600.300.402.000.31280.38142.0123
4700.300.402.000.31310.38212.0133
4800.300.402.000.31310.38232.0132
4900.300.402.000.31300.38412.0135
5000.300.402.000.31300.38382.0132
Table A2. Empirical MSEs of the MLEs for various n.
Table A2. Empirical MSEs of the MLEs for various n.
n a true b true σ true MSE ( a ^ ) MSE ( b ^ ) MSE ( σ ^ )
100.300.402.000.074780.152150.12203
200.300.402.000.055400.136490.07197
300.300.402.000.048250.127660.05825
400.300.402.000.038070.120220.04425
500.300.402.000.033700.114480.04117
600.300.402.000.029180.110370.03931
700.300.402.000.024880.102900.03669
800.300.402.000.020820.095070.03437
900.300.402.000.017950.093360.03080
1000.300.402.000.016560.090350.02928
1100.300.402.000.016250.088640.02910
1200.300.402.000.014220.084820.02623
1300.300.402.000.013340.084120.02624
1400.300.402.000.011900.080940.02453
1500.300.402.000.011770.078780.02403
1600.300.402.000.010970.077340.02290
1700.300.402.000.010010.073960.02204
1800.300.402.000.009850.071950.02145
1900.300.402.000.009740.070430.02107
2000.300.402.000.009360.069250.02096
2100.300.402.000.009030.066930.02026
2200.300.402.000.008580.064850.01939
2300.300.402.000.008440.063700.01925
2400.300.402.000.008140.062860.01891
2500.300.402.000.007870.062340.01902
2600.300.402.000.007490.061790.01858
2700.300.402.000.007060.060060.01811
2800.300.402.000.006770.058800.01824
2900.300.402.000.006470.057550.01751
3000.300.402.000.006140.057110.01723
3100.300.402.000.005840.056560.01689
3200.300.402.000.005620.056250.01653
3300.300.402.000.005380.055620.01625
3400.300.402.000.005320.055320.01625
3500.300.402.000.005110.054360.01559
3600.300.402.000.005050.053050.01543
3700.300.402.000.005010.051930.01530
3800.300.402.000.004920.050840.01499
3900.300.402.000.004800.050480.01474
4000.300.402.000.004700.049090.01454
4100.300.402.000.004570.048350.01435
4200.300.402.000.004390.048160.01412
4300.300.402.000.004240.048100.01405
4400.300.402.000.004170.047360.01388
4500.300.402.000.004100.047310.01370
4600.300.402.000.004010.047270.01368
4700.300.402.000.003970.046560.01359
4800.300.402.000.003860.045810.01332
4900.300.402.000.003790.045390.01314
5000.300.402.000.003740.044490.01311

References

  1. Shaw, W.T.; Buckley, I.R. The Alchemy of Probability Distributions: Beyond Gram-Charlier and Cornish-Fisher Expansions, and Skew-Normal or Kurtotic-Normal Distributions. UCL Discovery Repository. 2007. Available online: https://library.wolfram.com/infocenter/Articles/6670/alchemy.pdf (accessed on 15 February 2025).
  2. Merovci, F.; Alizadeh, M.; Hamedani, G.G. Another generalized transmuted family of distributions: Properties and applications. Austrian J. Stat. 2016, 45, 71–93. [Google Scholar] [CrossRef]
  3. Moolath, G.B.; Jayakumar, K. T-transmuted X family of distributions. Statistica 2017, 77, 251–276. [Google Scholar]
  4. Granzotto, D.C.T.; Louzada, F.; Balakrishnan, N. Cubic rank transmuted distributions: Inferential issues and applications. J. Stat. Comput. Simul. 2017, 87, 2760–2778. [Google Scholar] [CrossRef]
  5. Rahman, M.M.; Gemeay, A.M.; Khan, M.A.I.; Meraou, M.A.; Bakr, M.E.; Muse, A.H.; Balogun, O.S. A new modified cubic transmuted-G family of distributions: Properties and different methods of estimation with applications to real-life data. AIP Adv. 2023, 13, 095025. [Google Scholar] [CrossRef]
  6. Rayleigh, L. On the stability, or instability, of certain fluid motions. Proc. Lond. Math. Soc. 1880, 9, 57–70. [Google Scholar] [CrossRef]
  7. Siddiqui, M.M. Some problems connected with Rayleigh distributions. J. Res. Natl. Bur. Stand. D 1962, 66, 167. [Google Scholar] [CrossRef]
  8. Siddiqui, M.M. Statistical inference for Rayleigh distributions. J. Res. Natl. Bur. Stand. Sec. D 1964, 68, 1007. [Google Scholar] [CrossRef]
  9. Vickers, J.W. A Parameter Estimation Technique for the Generalized Rayleigh-Rician Distribution and Laha’s Bessel Distribution; PN: Fort Belvoir, VA, USA, 1976. [Google Scholar]
  10. Beckmann, P. Rayleigh distribution and its generalizations. Radio Sci. J. Res. NBS/USNC-URSI 1964, 68, 927–932. [Google Scholar] [CrossRef]
  11. Kundu, D.; Raqab, M.Z. Generalized Rayleigh distribution: Different methods of estimations. Comput. Stat. Data Anal. 2005, 49, 187–200. [Google Scholar] [CrossRef]
  12. Voda, V.G. A new generalization of Rayleigh distribution. Reliab. Theory Appl. 2007, 2, 47–56. [Google Scholar]
  13. Abd Elfattah, A.M.; Hassan, A.S.; Ziedan, D.M. Efficiency of maximum likelihood estimators under different censored sampling schemes for Rayleigh distribution. Interstat 2006, 1, 1–16. [Google Scholar]
  14. Merovci, F. Transmuted Rayleigh distribution. Austrian J. Stat. 2013, 42, 21–31. [Google Scholar] [CrossRef]
  15. Merovci, F. Transmuted generalized Rayleigh distribution. J. Stat. Appl. Probab. 2014, 3, 9. [Google Scholar] [CrossRef]
  16. Mir, A.A.; Ahmad, S.P. A New Extended Rayleigh Distribution with Applications of COVID-19 Data. Austrian J. Stat. 2025, 54, 69–84. [Google Scholar] [CrossRef]
  17. Rivera, P.A.; Barranco-Chamorro, I.; Gallardo, D.I.; Gómez, H.W. Scale Mixture of Rayleigh Distribution. Mathematics 2020, 8, 1842. [Google Scholar] [CrossRef]
  18. Vodă, V.G. Inferential procedures on a generalized Rayleigh variate. I. Apl. Mat. 1976, 21, 395–412. [Google Scholar] [CrossRef]
  19. Santoro, K.I.; Gallardo, D.I.; Venegas, O.; Cortés, I.E.; Gómez, H.W. A Heavy-Tailed Distribution Based on the Lomax–Rayleigh Distribution with Applications to Medical Data. Mathematics 2023, 11, 4626. [Google Scholar] [CrossRef]
  20. Haj Ahmad, H.; Ramadan, D.A.; Almetwally, E.M. Evaluating the discrete generalized Rayleigh distribution: Statistical inferences and applications to real data analysis. Mathematics 2024, 12, 183. [Google Scholar] [CrossRef]
  21. Dong, Y.; Gui, W. Reliability Estimation in Stress Strength for Generalized Rayleigh Distribution Using a Lower Record Ranked Set Sampling Scheme. Mathematics 2024, 12, 1650. [Google Scholar] [CrossRef]
  22. Balakrishnan, N.; He, M. A record-based transmuted family of distributions. In Advances in Statistics-Theory and Applications: Honoring the Contributions of Barry C. Arnold in Statistical Science; Springer: Cham, Switzerland, 2021; pp. 3–24. [Google Scholar]
  23. Gradshteyn, I.S.; Ryzhik, I.M. Table of Integrals, Series, and Products; Academic Press: Cambridge, MA, USA, 2014. [Google Scholar]
  24. Rudin, W. Principles of Mathematical Analysis, 3rd ed.; McGraw-Hill: New York, NY, USA, 1976. [Google Scholar]
  25. Rényi, A. On measures of entropy and information. In Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics; University of California Press: Berkeley, CA, USA, 1961; Volume 4, pp. 547–562. [Google Scholar]
  26. Shannon, C.E. A mathematical theory of communication. Bell Syst. Tech. J. 1948, 27, 379–423. [Google Scholar] [CrossRef]
  27. Surles, J.G.; Padgett, W.J. Inference for reliability and stress strength for a scaled Burr type X distribution. Lifetime Data Anal. 2001, 7, 187–200. [Google Scholar] [CrossRef] [PubMed]
  28. Sloan, C.H.; Sublett, B.J. Determination of methyl nitrite in cigarette smoke. Tob. Sci. 1967, 11, 21–24. [Google Scholar]
  29. Schultz, F.J.; Spears, A.W. Determination of moisture in total particulate matter. Tob. Sci. 1966, 10, 75–76. [Google Scholar]
  30. Lishamol, T.; Jiju, G. A generalized Rayleigh distribution and its application. Biom. Biostat. Int. J. 2019, 8, 139–143. [Google Scholar]
  31. Bader, M.G.; Priest, A.M. Statistical aspects of fibre and bundle strength in hybrid composites. In Progress in Science and Engineering of Composites; The Japan Society for Composite Materials: Tokyo, Japan, 1982; pp. 1129–1136. [Google Scholar]
Figure 1. The PDFs of various rbt-Rayleigh distributions.
Figure 1. The PDFs of various rbt-Rayleigh distributions.
Symmetry 17 01034 g001
Figure 2. The CDFs of various rbt-Rayleigh- distributions.
Figure 2. The CDFs of various rbt-Rayleigh- distributions.
Symmetry 17 01034 g002
Figure 3. The plot of the quantile function x p of the rbt-Rayleigh distribution for p ( 0 , 1 ) , with parameters a = 0.8 , b = 0.15 , and σ = 1 . The function was numerically evaluated using the inverse of the cumulative distribution function and visualized in R.
Figure 3. The plot of the quantile function x p of the rbt-Rayleigh distribution for p ( 0 , 1 ) , with parameters a = 0.8 , b = 0.15 , and σ = 1 . The function was numerically evaluated using the inverse of the cumulative distribution function and visualized in R.
Symmetry 17 01034 g003
Figure 4. Nicotine yields (mg per cigarette).
Figure 4. Nicotine yields (mg per cigarette).
Symmetry 17 01034 g004
Figure 5. Empirical vs. fitted CDF—nicotine yields.
Figure 5. Empirical vs. fitted CDF—nicotine yields.
Symmetry 17 01034 g005
Figure 6. Log-likelihood contour—nicotine yields ( σ fixed at MLE).
Figure 6. Log-likelihood contour—nicotine yields ( σ fixed at MLE).
Symmetry 17 01034 g006
Figure 7. CO emissions (mg per cigarette).
Figure 7. CO emissions (mg per cigarette).
Symmetry 17 01034 g007
Figure 8. Empirical vs. fitted CDF—CO emissions.
Figure 8. Empirical vs. fitted CDF—CO emissions.
Symmetry 17 01034 g008
Figure 9. Log-likelihood contour—CO emissions ( σ fixed at MLE).
Figure 9. Log-likelihood contour—CO emissions ( σ fixed at MLE).
Symmetry 17 01034 g009
Figure 10. Breaking stress (Dataset 3, GPa).
Figure 10. Breaking stress (Dataset 3, GPa).
Symmetry 17 01034 g010
Figure 11. Empirical vs. fitted CDF—breaking stress (Dataset 3).
Figure 11. Empirical vs. fitted CDF—breaking stress (Dataset 3).
Symmetry 17 01034 g011
Figure 12. Log-likelihood contour—breaking stress (Dataset 3) ( σ fixed).
Figure 12. Log-likelihood contour—breaking stress (Dataset 3) ( σ fixed).
Symmetry 17 01034 g012
Figure 13. Breaking stress (Dataset 4, GPa).
Figure 13. Breaking stress (Dataset 4, GPa).
Symmetry 17 01034 g013
Figure 14. Empirical vs. fitted CDF—breaking stress (Dataset 4).
Figure 14. Empirical vs. fitted CDF—breaking stress (Dataset 4).
Symmetry 17 01034 g014
Figure 15. Log-likelihood contour—breaking stress (Dataset 4) ( σ fixed).
Figure 15. Log-likelihood contour—breaking stress (Dataset 4) ( σ fixed).
Symmetry 17 01034 g015
Table 1. Quantile values x p of the rbt-R distribution for selected probabilities p ( 0 , 1 ) . Parameters: a = 0.8 , b = 0.15 , σ = 1 .
Table 1. Quantile values x p of the rbt-R distribution for selected probabilities p ( 0 , 1 ) . Parameters: a = 0.8 , b = 0.15 , σ = 1 .
p x p p x p p x p p x p p x p
0.010.1590.120.5660.230.8090.341.0210.451.225
0.020.2250.130.5900.240.8290.351.0390.461.243
0.030.2760.140.6140.250.8490.361.0580.471.262
0.040.3200.150.6380.260.8690.371.0760.481.281
0.050.3580.160.6610.270.8880.381.0950.491.300
0.060.3930.170.6830.280.9070.391.1130.501.319
0.070.4260.180.7050.290.9260.401.1320.601.516
0.080.4570.190.7260.300.9450.411.1500.701.738
0.090.4860.200.7470.310.9640.421.1690.802.009
0.100.5130.210.7680.320.9830.431.1870.902.401
0.110.5400.220.7890.331.0020.441.2060.993.372
Table 2. Mean values of X for selected combinations of a, b, and  σ .
Table 2. Mean values of X for selected combinations of a, b, and  σ .
ab σ = 1 σ = 1.5 σ = 2 σ = 3 σ = 5 σ = 7 σ = 9
0.0500.9001.8722.8083.7445.6169.36113.10516.849
0.1000.8501.8412.7613.6825.5229.20412.88616.567
0.1500.8001.8092.7143.6195.4289.04712.66616.285
0.2000.7501.7782.6673.5565.3348.89112.44716.003
0.2500.7001.7472.6203.4945.2408.73412.22815.721
0.3000.6501.7152.5733.4315.1468.57712.00815.439
0.3500.6001.6842.5263.3685.0528.42111.78915.157
0.4000.1001.8642.7963.7295.5939.32213.05016.779
0.4500.0801.8192.7283.6385.4579.09412.73216.370
0.5000.0601.7732.6603.5475.3208.86712.41415.961
0.5500.0401.7282.5923.4565.1848.64012.09615.552
0.6000.0201.6832.5243.3655.0488.41311.77815.143
0.6500.0101.6322.4493.2654.8978.16211.42714.692
0.7000.0101.5782.3663.1554.7337.88811.04314.198
0.7500.1001.4802.2212.9614.4417.40210.36313.324
0.8000.0801.4352.1532.8704.3057.17510.04512.915
0.8500.0601.3902.0842.7794.1696.9489.72712.507
0.9000.0401.3442.0162.6884.0336.7219.40912.098
0.9500.0201.2991.9482.5973.8966.4949.09111.689
Table 3. Variance values of X for selected combinations of a, b, and  σ .
Table 3. Variance values of X for selected combinations of a, b, and  σ .
ab σ = 1 σ = 1.5 σ = 2 σ = 3 σ = 5 σ = 7 σ = 9
0.0500.9000.4951.1141.9804.45612.37724.26040.103
0.1000.8500.5111.1512.0464.60312.78625.06041.426
0.1500.8000.5261.1832.1034.73213.14525.76542.591
0.2000.7500.5381.2112.1534.84413.45626.37343.596
0.2500.7000.5491.2352.1954.93813.71726.88544.442
0.3000.6500.5571.2542.2295.01413.92927.30045.129
0.3500.6000.5641.2682.2555.07314.09227.62045.657
0.4000.1000.7241.6302.8976.51918.10935.49458.674
0.4500.0800.7321.6462.9276.58518.29335.85459.268
0.5000.0600.7351.6542.9406.61418.37336.01159.528
0.5500.0400.7341.6512.9366.60618.35035.96659.453
0.6000.0200.7291.6402.9166.56018.22435.71859.044
0.6500.0100.7151.6092.8616.43617.87835.04257.926
0.7000.0100.6911.5552.7656.22017.27933.86655.983
0.7500.1000.6081.3682.4335.47415.20529.80149.263
0.8000.0800.5811.3062.3235.22614.51628.45247.032
0.8500.0600.5491.2352.1964.94113.72426.90044.467
0.9000.0400.5131.1552.0534.61912.83025.14641.568
0.9500.0200.4731.0651.8934.25911.83123.19038.334
Table 4. Descriptive statistics for variable X (N = 346).
Table 4. Descriptive statistics for variable X (N = 346).
StatisticNMeanSDMin Q 1 Median Q 3 Max
X3460.850.330.100.600.901.102.00
Table 5. Parameter estimates and log-likelihood for Rayleigh-type models for Dataset 1.
Table 5. Parameter estimates and log-likelihood for Rayleigh-type models for Dataset 1.
ModelParametersStd. ErrorLogLik
Rayleigh σ = 0.6478 0.0174 136.7884
Transmuted Rayleigh σ = 0.5506 λ = 0.7842 0.0133 0.0700 113.5013
Generalized Rayleigh α = 1.5784 β = 1.2503 0.1185 0.0385 119.6494
Transmuted Generalized Rayleigh α = 1.1731 β = 1.3165 λ = 0.6810 0.1410 0.0394 0.1205 112.6435
Record-Based Transmuted Rayleigh σ = 0.4042 a = 0.1991 b = 0.0334 0.0132 0.0529 0.1956 108.6344
Table 6. Goodness-of-fit measures for Dataset 1.
Table 6. Goodness-of-fit measures for Dataset 1.
ModelKSAICAICcBIC
Rayleigh 0.1867 275.5768 275.5884 279.4232
Transmuted Rayleigh 0.1272 231.0026 231.0376 238.6955
Generalized Rayleigh 0.1382 243.2988 243.3337 250.9916
Transmuted Generalized Rayleigh 0.1189 231.2869 231.3571 242.8263
Record-Based Transmuted Rayleigh 0.0838 223.2689 223.3391 234.8082
Table 7. Descriptive statistics for variable X (N = 816).
Table 7. Descriptive statistics for variable X (N = 816).
StatisticNMeanSDMinQ1MedianQ3Max
X81612.054.0619121521
Table 8. Parameter estimates and log-likelihood for CO emission models.
Table 8. Parameter estimates and log-likelihood for CO emission models.
ModelParametersStd. Error
Rayleigh σ = 8.9938 0.1574 2429.698
Transmuted Rayleigh σ = 7.4408 λ = 0.9536 0.0983 0.0003 2328.177
Generalized Rayleigh α = 2.1584 β = 0.0978 0.1114 0.0018 2330.157
Transmuted Generalized Rayleigh α = 1.6236 β = 0.1022 λ = 0.6556 0.1838 0.0019 0.1238 2316.907
Record-Based Transmuted Rayleigh σ = 5.4697 a = 0.0815 b = 0.1332 0.0945 0.0283 0.1027 2304.837
Table 9. Goodness-of-fit measures for CO emission models.
Table 9. Goodness-of-fit measures for CO emission models.
ModelAICAICcBICKS
Rayleigh4861.3974861.4024866.1010.2154
Transmuted Rayleigh4660.3544660.3694669.7630.1415
Generalized Rayleigh4664.3144664.3284673.7230.1368
Transmuted Generalized Rayleigh4639.8144639.8434653.9270.1223
Record-Based Transmuted Rayleigh4615.6744615.7044629.7870.1087
Table 10. Breaking stress values (in GPa) for Dataset 3.
Table 10. Breaking stress values (in GPa) for Dataset 3.
0.390.851.081.251.471.571.611.611.691.801.84
1.871.892.032.032.052.122.352.412.432.482.50
2.532.552.552.562.592.672.732.742.792.812.82
2.852.872.882.932.952.962.973.093.113.113.15
3.153.193.223.223.273.283.313.313.333.393.39
3.563.603.653.683.703.754.204.384.424.704.90
Table 11. Parameter estimates and log-likelihood for Dataset 3.
Table 11. Parameter estimates and log-likelihood for Dataset 3.
ModelParametersStd. Error
Rayleigh σ = 2.049 0.126 98.208
Transmuted Rayleigh σ = 1.696 λ = 0.959 0.079 0.0003 88.874
Generalized Rayleigh α = 2.348 β = 0.438 0.431 0.028 88.637
Transmuted Generalized Rayleigh α = 1.759 β = 0.461 λ = 0.710 0.495 0.029 0.257 86.920
Record-Based Transmuted Rayleigh σ = 1.217 a = 0.083 b = 4.585 × 10 8 0.002 0.004 1.177 × 10 16 85.490
Table 12. Goodness-of-fit measures for Dataset 3.
Table 12. Goodness-of-fit measures for Dataset 3.
ModelAICAICcBICKS
Rayleigh198.417198.479200.6070.211
Transmuted Rayleigh181.749181.939186.1280.126
Generalized Rayleigh181.274181.464185.6530.105
Transmuted Generalized Rayleigh179.839180.226186.4080.083
Record-Based Transmuted Rayleigh176.979177.366183.5480.070
Table 13. Observed breaking stress values (GPa) for Dataset 4 (carbon fibre, 20 mm gauge length).
Table 13. Observed breaking stress values (GPa) for Dataset 4 (carbon fibre, 20 mm gauge length).
0.3120.3140.4790.5520.7000.8030.8610.8650.9440.958
0.9660.9971.0061.0211.0271.0551.0631.0981.1401.179
1.2241.2401.2531.2701.2721.2741.3011.3011.3591.382
1.3821.4261.4341.4351.4781.4901.5111.5141.5351.554
1.5661.5701.5861.6291.6331.6421.6481.6841.6971.726
1.7701.7731.8001.8091.8181.8211.8481.8801.9542.012
2.0672.0842.0902.0962.1282.2332.4332.5852.585
Table 14. Descriptive statistics for Dataset 4 ( n = 69 ).
Table 14. Descriptive statistics for Dataset 4 ( n = 69 ).
StatisticNMeanSDMin Q 1 Median Q 3 Max
Breaking stress (GPa)691.4510.4950.3121.0981.4781.7732.585
Table 15. Parameter estimates and log-likelihood for Rayleigh-type distributions—Dataset 4.
Table 15. Parameter estimates and log-likelihood for Rayleigh-type distributions—Dataset 4.
ModelParametersStd. Error
Rayleigh σ = 1.083 0.06521 59.4183
Transmuted Rayleigh σ = 0.894 λ = 0.961 0.04055 0.00028 50.9525
Generalized Rayleigh α = 2.174 β = 0.813 0.387 0.0521 50.9049
Transmuted Generalized Rayleigh α = 1.659 β = 0.855 λ = 0.663 0.46035 0.05338 0.27535 49.6063
Record-Based Transmuted Rayleigh σ = 0.649 a = 0.110 b = 2.45 × 10 8 0.02651 0.06490 1.08 × 10 8 48.5363
Table 16. Goodness-of-fit measures for Rayleigh-type distributions—Dataset 4.
Table 16. Goodness-of-fit measures for Rayleigh-type distributions—Dataset 4.
ModelAICAICcBICKS
Rayleigh120.8367120.8964123.07080.185
Transmuted Rayleigh105.9050106.0868110.37320.074
Generalized Rayleigh105.8098105.9916110.27800.061
Transmuted Generalized Rayleigh105.2126105.5818111.91490.039
Record-Based Transmuted Rayleigh103.0726103.4419109.77500.035
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Merovci, F. A Three-Parameter Record-Based Transmuted Rayleigh Distribution (Order 3): Theory and Real-Data Applications. Symmetry 2025, 17, 1034. https://doi.org/10.3390/sym17071034

AMA Style

Merovci F. A Three-Parameter Record-Based Transmuted Rayleigh Distribution (Order 3): Theory and Real-Data Applications. Symmetry. 2025; 17(7):1034. https://doi.org/10.3390/sym17071034

Chicago/Turabian Style

Merovci, Faton. 2025. "A Three-Parameter Record-Based Transmuted Rayleigh Distribution (Order 3): Theory and Real-Data Applications" Symmetry 17, no. 7: 1034. https://doi.org/10.3390/sym17071034

APA Style

Merovci, F. (2025). A Three-Parameter Record-Based Transmuted Rayleigh Distribution (Order 3): Theory and Real-Data Applications. Symmetry, 17(7), 1034. https://doi.org/10.3390/sym17071034

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop