International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP.

268-279, 2024

Neutrosophic Structure of Sized Biased Exponential Distribution:

Properties and Applications
Mansour F. Yassen1,2
1
Department of Mathematics, College of Science and Humanities, Prince Sattam Bin Abdulaziz University, Al-
Kharj 11942, Saudi Arabia.
2
Department of Mathematics, Faculty of Science, Damietta University, New Damietta 34517 Damietta, Egypt.

Email: [email protected]

Abstract
This study presents a novel distribution derived from the exponential distribution, referred to as the
neutrosophic size-biased exponential distribution (NSBED). Various characteristics of the proposed
model, including moments, skewness, and kurtosis, are investigated. Plots depicting the cumulative
distribution function, density function, and other relevant functions associated with the survival
analysis hazard function under indeterminacy are provided. Parameter estimates for the proposed
model within the neutrosophic framework are computed. To illustrate the statistical applications of
the results in handling imprecise data, a motivation is provided. A simulation analysis is conducted to
validate the theoretical aspects of the proposed NSBED. Results indicate that the new distribution
exhibits right skewness and shares many properties with skewed distributions. Our novel distribution
outperforms the size-biased exponential distribution. Finally, a real application of the proposed model
is provided to illustrate the practical implications.

Keywords: Neutrosophic probability; skewed distribution; neutrosophic measures; estimation

1. Introduction

Researchers explore new distributions of data with statistical methods that are presented in different
ways, as it these types of distributions play a major role in various academic fields. Weighted
distributions find their application when one constructs statistics based on data coming from a
stochastic process which is not evenly recorded; instead, such statistics are based upon weighted
function. Length-biased distribution is found if the weight function gets impacted by the lengths of
the units under consideration [3]. It has been widely reported that many continuous distributions are
size-biased or length- or size-biased subjects for developing singular and desirable properties [4], [5].
In practical scenarios like probability proportional to sizes (PPS) designs, we can see that there are
different chances of selecting distinct samples. Use of method conversed about in reference [6] lead
to noticeable development in dealing with above mentioned problematic issue particularly among size
biased distributions. A lot of study disciplines as econometrics, chemometrics, ecology, agriculture,
linguistics, and medicinal science depend on those distributions. [7]. The length-biased approach was
instrumental around sampling theory and greatly enhanced precision of data analysis in many fields.
Researchers may make more dependable inferences and reach more accurate conclusions by
considering the unequal chance of sample observations, as per this range [8-13].

268
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

To formulate size-biased distributions, let's assume we have a random variable 𝑍 with a probability
density function (PDF) denoted as 𝑓(𝑧, 𝛼), where 𝛼 represents a precise value of the parameter. The
corresponding weighted distribution function, denoted as 𝑔(𝑧, 𝛼), is given by [14]:
𝑤(𝑧)𝑓(𝑧,𝛼)
𝑔(𝑧, 𝛼) = (1)
𝐸(𝑤(𝑧))

Where 𝑤(𝑧) is weight function and the integral in the denominator ensures normalization, making
𝑔(𝑧, 𝛼) a valid probability distribution.

If we assume the weight function 𝑤(𝑧) = 𝑧 𝜗 , the (1) is called size biased distribution of order 𝜗. If
the value of 𝜗 = 1 then it is called length biased distribution, denoted as follow [15]:
𝑧𝑓(𝑧,𝛼)
𝑔(𝑧, 𝛼) = (2)
𝐸(𝑧)

Length-biased models are typically used in numerous domain names such as public health,
dependability design as well as demography to research study populaces with various prices of
advancement. In the world of public health, these circulations play a crucial part in assessing health
issues that advance at differing prices [16-18] Integrity design scientists use the failure times of system
elements to evaluate larger parts that have longer life expectancies. This strategy is vital for
understanding the probability of discovering failings. In demography length-biased circulations are
used to research study human populaces especially in the context of examining fertility plus death.
Scientist can acquire valuable understandings right into populace characteristics as well as projections
by picking people with longer life expectancies or reproductive durations for example [19]
Neutrosophic collections offer a much more comprehensive method in contrast with standard
collection concept when taking care of uncertain, vague, as well as irregular information [20] These
subscription features particularly truth-membership, indeterminacy-membership, plus falsity-
membership supply a clear understanding of the way in which to which a component comes from the
collection is not sure or does not come from the collection. This structure additionally integrates
appropriate data and chance circulations to additional boost its performance in dealing with complex
details [21-24] Neutrosophic stats as well as possibility circulations supply valuable techniques for
examining information or unpredictability that is described by neutrosophic collections [25-27].
Neutrosophic probability distributions calculate likelihood of occurrences or outcomes in uncertainty
situations, focusing on central tendency, dispersion, and other neutrosophic data characteristics [28].
Such an approach is adapted for making decisions, recognizing patterns, and developing artificial
intelligence, especially in situations where normal approaches fail to cope with ambiguity and
vagueness. However, there are few papers on the neutrosophic size-biased exponential distribution
that could be used to analyze imprecise data values meaningfully calling for further study.
The paper’s structure is as follows: Section 2 gives a size-biased form of the exponential distribution.
Section 3: Statistic properties of this modified distribution with simulations in section 4. Besides, in
section 4 information on how to find mode and harmonic mean can be found. Showing real-life
application of NSBED under consideration. Section 5 uses random numbers generation method.
Section 6 demonstrates implementation of the suggested approach in practice. Section 7 finalizes the
research report by giving concluding remarks about it.

2. Proposed Model

In this section, we propose the NSBED distribution. We provide graphical representations of the
proposed model in the form of its probability density function (PDF) and cumulative distribution
function (CDF).
The PDF of the neutrosophic exponential distribution and its CDF function are defined in (3) and (4)
respectively:

𝑓(𝓏) = bN e−bN 𝓏 , 𝓏 > 0, bN > 0 (3)

ℱ(𝓏) = 1 − e−bN 𝓏 , 𝓏 > 0, bN > 0 (4)

The exponential distribution has been widely used in different fields due to its versatility and
practicality, as shown in previous studies [1]. For example, it has been utilized in modeling the
lifetimes of electronic components and radioactive particles, as well as in queuing theory and

269
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

reliability analysis. Additionally, its simple mathematical properties make it a convenient choice for
many statistical analyses.
Using (3) and (4) in (2) provides the density function of the proposed model.

ℊ(𝓏) = b2 N ze−bN 𝓏 , bN > 0, 𝓏 > 0. (5)

The CDF of NSBED has the form

𝒢(𝓏) = 1 − (1 + bN 𝑧)e−bN 𝓏 (6)

Figure 1 shows probability density function (PDF) and figure 2 displays cumulative distribution
function (CDF) of the proposed model. Probability Density Function is an important concept in
probability theory and statistics, it characterizes the distribution of continuous random variables. It
states how probable it is for various outcomes to happen within a given range. In this case, probability
density function (PDF) cannot be negative and its integral over all possible values of variable amounts
to one. Summing up the entire area covered by PDF leaves a total of 1 after integrating the PDF over
all possible values of variable. Alternatively, a CDF integrates the associated PDF to establish
probabilities for random variables less than or equal to a given value. The CDF begins at zero and
goes up to one as the variable approaches’ infinity. In the sphere of probability theory and statistics,
this basic mathematical tool is used to calculate probabilities and make statistical inferences for
random variables. When employed alongside the PDF though, the CDF provides a clear understanding
of the characteristics and distributions of continuous random variables.

Figure 1: Pdf plot of the proposed distribution with different values of neutrosophic parameter

270
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

Figure 2: CDF plot of the proposed distribution with indeterminate parameter values
With neutrosophic probability theory, the range of uncertainty can be well modelled by use of PDF
and CDF when the parameters of uncertainty remain to be indeterminate, as seen in Figure 1 and
Figure 2. The possibilistic solution using the falsehood-membership enables the physical meaning of
uncertainty to be comprehended more perfectly, especially when dealing with the vague and
ambiguous data. The neutrosophic CDF is a mathematical tool for estimating the probability that the
neutrosophic random variable would be no more than or equal to some constant in the light of the
uncertain factors. Neutrosophic probability theory offers the sound and flexible methodology to
process the uncertain data with different fields by putting the uncertain factors into both PDF and
CDF. The survival function denoted briefly by 𝒮(𝓏) is an important piece of any probabilistic model.
The word ‘probability’ refers to the chance that the random variable would be more than or equal to
some value, i.e. the probability that the event would not occur. The survival function in this
mathematical model represents the probability of surviving beyond a specific point in time.
𝒮(𝓏) = 1 − 𝒢(𝓏) = 1 − (1 − 𝑏𝑁 )e−bN𝓏 , 𝓏 > 0 (7)
The survival function is a fundamental concept employed in survival analysis and reliability
engineering to ascertain the chance of an event not occurring within a given timeframe or threshold.
Comprehending this function is crucial for forecasting the timing of occurrences or anticipating
potential breakdowns. Figure 3 depicts the procedure for generating the survival function.

271
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

Figure 3: Survival function of the proposed model

Figure 3 represents a survival function for the proposed model. Neutrosophic theory introduces a new
perspective on survival function, departing from the usual standard of probability theory and statistics.
In this sense, the survival function measures the likelihood or ability of indefinite or uncertain
occurrences or claims to survive beyond a threshold, the inherent uncertainty and indeterminacy that
plays a role in it. In neutrosophic theory, the survival function is of great importance, with it being
possible to study and represent systems and phenomena that surpass conventional probability. It
represents a rigorous way measure uncertain occurrences and claims by considering the notions of
indeterminacy, ambiguity, and missing knowledge. Given the complexity of real-world situations, in
which uncertainty prevails, it was important to have this powerful tool to portray the complexity of
the situations. The hazard function is another linked function of the probability distribution, commonly
employed in reliability theory.
ℊ(𝓏)
𝒽(𝓏) = = 𝑏𝑁 𝓏 (8)
𝒮(𝓏)

The hazard function is a crucial tool in analyzing complex systems prone to failure, enabling
researchers to predict failure patterns, evaluate interventions, and make informed decisions across
fields like epidemiology, medicine, engineering, and finance.
3. Basic Characteristics

This section explores several statistical properties associated with the proposed model. We have
established the basic characteristics of the proposed model in terms of following theorems:

Theorem 1. If 𝓏 ∽ NSBED (bN ) then the 𝓇 𝑡ℎ moment is given by as:

1 𝓇
𝐸(𝒵 𝓇 ) = ( ) Γ(2 + 𝓇) (9)
bN
272
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

Proof. The 𝓇 𝑡ℎ moments of LBPHRD can be attained by

∞
𝐸(𝒵 𝓇 ) = ∫0 𝓏 𝓇 ℊ(𝓏) 𝒹 𝓏,

From (5), then

𝑏𝑁 𝑎 +1
− 𝓏 𝑁
𝓇 ∞ 𝑏 𝓏 𝓇+𝑎𝑁 +1 𝑒 𝑎𝑁 +1
𝐸(𝒵 ) = ∫0 𝑁 1 (10)
a +1 a +1 a +2
( N ) N Γ( N )
bN aN +1

bN
Let 𝓊 = 𝓏 aN +1 , 𝒹𝓊 = bN 𝓏 aN . Upon simplification, (10) leads to
aN +1

1 𝓇
𝐸(𝒵 𝓇 ) = ( ) Γ(2 + 𝓇) (11)
bN

The mean and variance for NSBED can be calculated from (11) as follows.
Theorem 2. Derive mean and variance of the NSBED
Setting 𝓇 = 1, in (11),
1
E(𝒵) = ( ) Γ(2 + 1). (12)
bN

Putting 𝓇 = 2, in (11),
1 2
𝐸(𝒵 2 ) = ( ) Γ(2 + 2) (13)
bN

Therefore, variance of NSBED is

1 2
Var(𝒵) = ( ) [Γ4 − (Γ3)2 ]. (14)
bN

Theorem 3. Derive the shape coefficients of the NSBED

The shape characteristics of the probability distribution, skewness and kurtosis play an important role.
These can be derived from theorem 1, using the following relations.
𝜇3′ −3𝜇1′ 𝜇2′ +2𝜇1′3 𝜇4′ −4𝜇1′ 𝜇3′ +6𝜇1′2 𝜇2′ −3𝜇1′4
𝑆𝑘 = 3⁄ , 𝐾𝑢 = 2 ,
(𝜇2′ −𝜇1′ ) 2 (𝜇2′ −𝜇1′ )

where 𝜇𝓇′ = 𝐸(𝒵 𝓇 ).

Theorem 4. Derive the expression for mode of the proposed distribution.
Taking the logarithm of (5), we have
1
lnℊ(𝓏) = ln(bN ) + ln(𝓏) − bN 𝒵 − ln [ ]. (15)
bN

Differentiate (15) w.r.t. 𝓏 and equating it zero,

𝑑 1
𝑙𝑛ℊ(𝓏) = − 𝑏𝑁 𝓏 = 0, (16)
𝑑𝓏 bN

Therefore
1
𝓏=
bN
Again differentiate (16),
𝑑2 1 1+𝑏𝑁 𝓏
𝑙𝑛ℊ(𝓏) = − − 𝑏𝑁 𝓏 −1 = − ,
𝑑𝓏 2 𝓏2 𝓏2

1
At 𝓏 = ,
bN

273
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

𝑑2 1
𝑙𝑛ℊ(𝓏) = − 2 < 0.
𝑑𝓏 2 𝓏
1
Therefore, the mode is 𝓏 = .
bN

Theorem 5. Derive the expression for percentile of the proposed model.

Using the following relation, 𝑝𝑡ℎ percentile can be obtained.

1 − (1 − bN )e−bN 𝓏 = p. (17)
Substituting from (6) into (17), 𝓏𝑝 satisfies the equation
1 (1−𝑝)
𝓏=− , 𝑝 ∈ [0,1] (18)
bN (1−bN )

Likewise other statistical properties of the proposed model can be derived in neutrosophic framework.
4. Sample Estimation

In this section, the probability density function and its related important statistical properties of the
proposed model are discussed in neutrosophic framework. To derive the MLE of bN for the PDF, we
first need to construct the likelihood function and then maximize it with respect to bN .
The likelihood function 𝐿(bN ) is given by the product of the PDF evaluated at each observed data
point. Let 𝑧1 , 𝑧2 , … 𝑧𝑛 are n independent and identically distributed observations:
𝑛

𝐿(bN ) = ∏ 𝑔(𝑧𝑖 )
𝑖

Taking the logrithem of the likelihood function, we obtain the log likelihood function 𝑙(bN ):

𝑙(bN ) = ∑𝑛𝑖 𝑙𝑛(𝑔(𝑧𝑖 )) (19)

Subtituting the given PDF in (19), we have

𝑙(bN ) = 2𝑛𝑙𝑛(bN ) + ∑𝑛𝑖 𝑙𝑛(𝑧𝑖 ) − bN ∑𝑛𝑖 𝑧𝑖 (20)
To find the MLE of bN we differentiate (2) by bN and equating the expression to zero, we get
2𝑛
bN =
∑𝑛𝑖 𝑧𝑖

where n is the number of observations and 𝑧𝑖 is the time until failure for each transistor. This is
required neutrosophic statistic for the unknown value of bN .
To understand this MLE procedure, let us consider the following example. In the field of reliability
engineering, engineers are studying the time to failure of a specific electronic component that is
assumed to follow NSBED. For example, a manufacturer produces transistors for electronic devices
and engineers are collecting data on the time until failure for a sample of these transistors under
constant stress. This data will help them analyze and predict the reliability of these transistors in real-
world applications. To simplify the process, data was gathered on the time until failure for 10
transistors. The recorded times were imprecisely defined as: 100-120 hours, 150-170 hours, 200-205
hours, 220-230 hours, 250-255 hours, 280-290 hours, 300-315 hours, 320-330 hours, 350-380 hours,
and 380-400 hours. Now, to estimate the parameter 𝑏𝑁 governing the failure rate of these transistors,
they can use Maximum Likelihood Estimation (MLE). The MLE of 𝑏𝑁 provides an estimate of the
rate at which these transistors are failing.
Using the MLE formula given in (20)
10
𝑏𝑁 = = [0.0037, 0.0039]
[2550, 2695]
This implies that, typically, a transistor is anticipated to malfunction around every with failing rate
[0.0037, 0.0039] hours when subjected to the specified stress factors. Such data is essential for
274
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

evaluating reliability, planning maintenance tasks, and enhancing product development tactics. It
enables engineers to make educated choices about designing products, setting usage
recommendations, and providing customer assistance.
5. Quantile Function

The pth quantile of the NSBED can be derived as:

1 1−𝑢
𝑧=− 𝑙𝑛 ( )
𝑏𝑁 1 + 𝜃𝑧
The (a) does not follow the closed form, we can use an iterative method like the inverse transform
sampling to generate the random sample. A code written has been utilized to find the random numbers
of data.
The procedure involves the following steps in the iterative procedure:
1: start with initial guess for z, say 𝑧0
1 1−𝑢
2: Use the (a) to compute a new estimate of z as:𝑧1 = − 𝑙𝑛 ( )
𝑏𝑁 1+𝜃𝑧0

Use 𝑧1 as the new estimate and repeat step 2 until convergence or for a certain number of iterations.
The iterative number eventually converge to a value of z that satisfies the equation. We have simulated
random numbers from the proposed model with bN = [1,4] and 𝜃𝑁 = [0.5, 0.5], results are shown in
Table 1
Table 1: Random number generation from the proposed model

Random Numbers
[1.161, 2.383] [0.710, 3.018]] [0.381,2.893] [0.211, 2.369] [0.904, 1.306]
[0.634, 1.690] [1.332, 8.583] [0.215, 1.563] [0.402, 1.733] [0.262, 1.733]
[0.202, 1.625] [0.636, 2.856] [0.239, 5.710] [0.368, 2.804] [0.125, 1.463]
[0.320, 3.11] [0.822, 1.321] [0.982, 1.799] [0.001,1.723] [1.360, 1.620]

Table 2: Some uncertainty measures of the proposed model

Statistical measures Computed values

Mean [3.099, 31.141]
Variance [0.016, 1.795]
Mode [0.091, 0.947]
Estimated parameter 𝑏𝑁 [1.055, 10.873]

The proposed model incorporates neutrosophic random numbers, a mathematical concept that extends
traditional probabilistic frameworks. These random numbers represent uncertainty in three values:
true, indeterminate, or false, and are useful in fields like artificial intelligence, economics, engineering,
and social sciences. They offer a sophisticated tool for problem-solving under uncertainty and partial
truth. The model's key characteristics can be studied using these random numbers, as shown in Table
2. Table 2 presents the proposed model's characteristics, based on analytical calculations. The variance
ranges from 0.016 to 1.795, indicating significant uncertainty in the data's spread. The mode ranges
from 0.091 to 0.947, indicating uncertainty caused by indeterminate data points. The wide range of
values suggests multiple peaks or unclear data points in the distribution, making it difficult to pinpoint
the most frequent value. The parameter range, which plays a key role in shaping the distribution, falls
between 1.055 and 10.873. The wide range of values indicates a significant level of uncertainty in
275
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

identifying this parameter, impacting statistical measures like mean, variance, and mode. A broad
interval indicates high uncertainty in the data's distribution, affecting subsequent calculations.
6. Application to Real Data

In this section, we have utilized the proposed model on the global see level to analyze the uncertainty
data. The see level is the average height of the entire ocean surface. The global mean sea level rise is
primarily driven by land-based ice sheets and glaciers melting, along with the expansion of saltwater
due to warming temperatures. An important indicator of climate change effects, the global mean sea
level has been steadily increasing for decades. From 1993 onwards, the rate of this rise has doubled
to 0.17 inches (0.44 centimeters) per year from 0.08 inches (0.20 centimeters) per year. Understanding
and predicting future sea level trends is crucial for planners, making this data indispensable. The
global see level data is shown in Figure 4 which is taken from the online source for understanding
purpose [30].

Figure 4: Mean see level change globally [30]

Current measurement technologies have limitations due to the natural variability of oceanic and
atmospheric conditions. Integrating data from tide gauges and satellite altimetry can be complex.
Regional differences and short-term fluctuations can obscure long-term trends, making it challenging
to obtain a consistent global picture. Therefore, while sea level data offers valuable insights, it should
be interpreted cautiously, recognizing the inherent limitations and potential for error in current
measurement techniques. Some see mean see level measurements with uncertainties are shown in
Table 3. Uncertainties in measurements are introduced according to random strategy adopted by [30].

Table 3 Global see level measurements recorded with uncertainty.

See level measurements

[3.38,3.99] [3.33, 3.84] [2.63, 3.74] [4.25, 4.36] [3.32,4.25] [1.08,2.05]
[2.47, 4.10] [3.91, 4.66] [2.62,3.71] [4.13,4.48] [1.77, 3.02] [2.30, 4.07]
[2.54,3.11] [2.72,3.51] [2.46, 3.99 [2.22, 3.55] [4.10, 4.51] [2.78, 3.49]
[1.65, 2.36] [3.06, 4.45] [2.68, 3.75] [2.33, 3.82] [2.53, 3.60] [2.00, 3.49]

Table 3 displays that conventional models for probability distributions cannot be utilized due to
uncertainties present in recorded measurements. We proceed to analyze the data using the proposed
model, and the results are presented in Table 4.

276
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

Table 4: Some uncertainty measures of the proposed model

Statistical measures Computed values

Mean [2.768, 3.750]
Variance [3.831, 7.034]
Mode [1.384,1.875]
Estimated parameter 𝑏𝑁 [0.7224,0.533]

The findings presented in Table 4 offer valuable information regarding the statistical properties of the
data when examined with the suggested model, considering measurement uncertainties. The mean
values calculated fall between 2.768 and 3.750, highlighting the central tendency of the data as per
the proposed model. This range implies that, on average, the dataset values are situated within this
spectrum, showcasing how uncertainty impacts the central location of the data. The range of variance
values, ranging from 3.831 to 7.034, shows how spread out the data is. Larger variance values indicate
more variability in the dataset, likely due to uncertainties in the measurements. The mode values,
ranging from 1.384 to 1.875, highlight the most common data points in the dataset. This interval
signifies the peak regions of the data, showcasing where values occur most frequently amidst
uncertainty. The outcomes demonstrate the success of the suggested model in addressing the inherent
uncertainties within the data, leading to a more thorough statistical analysis compared to traditional
models. The wide range of computed values emphasizes the fluctuation and average tendencies
influenced by the uncertainties within the measurements.
7. Conclusions

This research presents the introduction of the neutrosophic size-biased exponential distribution
(NSBED) as a unique method for managing data with uncertainties. Through the derivation of this
distribution from the exponential distribution, we have analyzed different features of the NSBED such
as moments, skewness, and kurtosis. The study is further enhanced with visual representations of the
cumulative distribution function, density function, and other important functions in relation to survival
analysis under uncertainty. The practical utility of the NSBED in handling imprecise data has been
demonstrated through the computation of parameter estimates within the neutrosophic framework.
Our simulation analysis further confirmed the right-skewed nature and advantageous properties of the
NSBED, highlighting its superiority over the traditional size-biased exponential distribution. An
analysis of uncertainty in global sea level data was performed using the proposed model. The
continuous increase in global mean sea level, primarily caused by ice melting and seawater expansion,
highlights the need for accurate predictions of future trends. Results indicate that the NSBED model
is an effective tool for evaluating uncertain data, providing valuable information for climate
researchers and planners.
Acknowledgment
This study is supported via funding from Prince Sattam bin Abdulaziz University project number
(PSAU/2024/R/1445)
References
[1] H. Y. A. Shihabeldeen and Z. Khan, Neutrosophic Structure of the Log-logistic Model with
Applications to Medical Data, International Journal of Neutrosophic Science, 23(1), 2024.
[2] P. O. Awodutire, Statistical Properties and Applications of the Exponentiated Chen-G Family
of Distributions: Exponential Distribution as a Baseline Distribution, Austrian Journal of
Statistics, 51(2), 2022
[3] M. Abdel-Basset, D. El-Shahat, M. Jameel, and M. Abouhawwash, Exponential distribution
optimizer (EDO): a novel math-inspired algorithm for global optimization and engineering
problems,” Artificial Intelligence Review, 56(9), 2023.
[4] Abhishek Agarwal and Himanshu Pandey, An Inflated Model Based on Sized Biased
Himanshu Distribution and its Applications,Journal of Probability and Statistical Science,
21(1), 2023.

277
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

[5] S. A. Siddiqui, B. Theruvil, S. Jain, S. Divedi, I. Siddiqui, and M. Alam, A mathematical

study of size biased basic distribution of sabir (sbbds), International Journal of Agricultural
and Statistical Sciences,16(2), 2020.
[6] C. Derman, “Review: D. R. Cox, Renewal Theory, The Annals of Mathematical Statistics,
35(1), 1964.
[7] I. Ghosh, Bivariate and Multivariate Weighted Kumaraswamy Distributions: Theory and
Applications, Journal of Statistical Theory and Applications, 18(3), 2019.
[8] Z. Khan, R. B. Razali, H. Daud, N. M. Nor, The largest studentized residual test for bad data
identification in state estimation of a power system, ARPN Journal of Engineering and
applied sciences, 10(21), 2015.
[9] Z. Khan Z, A. Amin, S. A. Khan, M. Gulistan M, Statistical Development of the Neutrosophic
Lognormal Model with Application to Environmental Data, Neutrosophic Sets and Systems,
47, 2021.
[10] A. M. M. Ibrahim and Z. Khan, Neutrosophic Laplace Distribution with Properties and
Applications in Decision Making,” International Journal of Neutrosophic Science, vol. 23(1),
2024.
[11] A. M. Almarashi and M. Aslam, Process Monitoring for Gamma Distributed Product under
Neutrosophic Statistics Using Resampling Scheme, Journal of Mathematics, vol. 2021, pp.
1-12, 2021.
[12] M. Aslam, R. A. R. Bantan, and N. Khan, Design of a control chart for gamma distributed
variables under the indeterminate environment, IEEE Access, 7, 2019.
[13] Z. Khan, M. Gulistan, N. Kausar, and C. Park, “Neutrosophic Rayleigh Model with Some
Basic Characteristics and Engineering Applications,” IEEE Access,9, pp. 71277–71283,
2021.
[14] N. M. Kilany, Weighted Lomax distribution,” Springerplus, 5(1), 2016.
[15] H. Z. Muhammed, A Class of Bivariate Modified Weighted Distributions: Properties and
Applications, Annals of Data Science, 10(4), 2023.
[16] I. Abdullahi and W. Phaphan, “A Generalization of Length-biased Nakagami Distribution,”
Int J Math Comput Sci, 17(1), 2022.
[17] A. I. Al-Omari and A. R. A. Alanzi, Inverse length biased maxwell distribution: Statistical
inference with an application, Computer Systems Science and Engineering, 39(1), 2021.
[18] T. Simmachan and W. Phaphan, Generalization of Two-Sided Length Biased Inverse
Gaussian Distributions and Applications,” Symmetry (Basel), 14(10), 2022.
[19] Y. Atikankul, A. Thongteeraparp, W. Bodhisuwan, and A. Volodin, The Length-Biased
Weighted Lindley Distribution with Applications, Lobachevskii Journal of Mathematics,
41(3), 2020.
[20] S. Broumi and F. Smarandache, Several similarity measures of neutrosophic sets, Infinite
Study, 410(1), 2013.
[21] F. Smarandache, S., Broumi, P. K., Singh, C.F., Liu, V.V., Rao, H.L., Yang, I. Patrascu. and
Elhassouny., Introduction to neutrosophy and neutrosophic environment, In Neutrosophic
Set in Medical Image Analysis, pp. 3–29, 2019.
[22] F. Smarandache. A unifying field in logics: neutrosophic logic. Neutrosophy, neutrosophic
set, neutrosophic probability: neutrosophic logic. Neutrosophy, neutrosophic set,
neutrosophic probability. Infinite Study, 2005.
[23] F. Smarandache. Neutrosophic set-a generalization of the intuitionistic fuzzy set.
International Journal of Pure and Applied Mathematics, 24(3), 287, 2005.

278
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024
International Journal of Neutrosophic Science (IJNS) Vol. 24, No. 03, PP. 268-279, 2024

[24] U. Rivieccio, Neutrosophic logics: Prospects and problems, Fuzzy Sets and Systems, vol.
159, no. 14, pp. 1860–1868, Jul. 2008.
[25] F. Smarandache. Introduction to Neutrosophic Statistics, Sitech & Education Publishing,
Craiova, 2014.
[26] W. Q. Duan, Z. Khan, Z., M. Gulistan, and A. Khurshid. Neutrosophic exponential
distribution: Modeling and applications for complex data analysis, Complexity, 2021, 1-8.
[27] Khan, Z., Gulistan, M., Kadry, S., Chu, Y., & Lane-Krebs, K., On scale parameter monitoring
of the Rayleigh distributed data using a new design, IEEE access, 8, 188390-188400, 2020.
[28] P. Schweizer, Uncertainty: two probabilities for the three states of neutrosophy, International
Journal of Neutrosophic Science, 2(1), 18-26, 2020.
[29] Z. Khan, M. Gulistan, R. Hashim, N. Yaqoob, and W. Chammam, “Design of S-control chart
for neutrosophic data: An application to manufacturing industry,” Journal of Intelligent &
Fuzzy Systems, vol. 38, no. 4, pp. 4743–4751, 2020.
[30] Climate change database {https://climatedata.imf.org}

279
DOI: https://doi.org/10.54216/IJNS.240323
Received: September 15, 2023 Revised: February 05, 2024 Accepted: May 09, 2024