ALL Metrics
-
Views
-
Downloads
Get PDF
Get XML
Cite
Export
Track
Research Article

A better approach to discuss medical science and engineering data with a modified Lehmann Type – II model

[version 1; peer review: 2 approved with reservations]
PUBLISHED 17 Aug 2021
Author details Author details
OPEN PEER REVIEW
REVIEWER STATUS

Abstract

Background: Modeling with the complex random phenomena that are frequently observed in reliability engineering, hydrology, ecology, medical science, and agricultural sciences was once thought to be an enigma. Scientists and practitioners agree that an appropriate but simple model is the best choice for this investigation. To address these issues, scientists have previously discussed a variety of bounded and unbounded, simple to complex lifetime models.
Methods: We discussed a modified Lehmann type II (ML-II) model as a better approach to modeling bathtub-shaped and asymmetric random phenomena. A number of complementary mathematical and reliability measures were developed and discussed. Furthermore, explicit expressions for the moments, quantile function, and order statistics were developed. Then, we discussed the various shapes of the density and reliability functions over various model parameter choices. The maximum likelihood estimation (MLE) method was used to estimate the unknown model parameters, and a simulation study was carried out to evaluate the MLEs' asymptotic behavior.
Results: We demonstrated ML- II's dominance over well-known competitors by modeling anxiety in women and electronic data.

Keywords

Power Function Distribution; Lehmann Type I, II Distribution; Failure Rate Function; Moments; Maximum Likelihood; Order Statistics; Quantile; Rényi Entropy.

Introduction

Over the last two decades, researchers' increasing interest in the development of new models has explored the remarkable characteristics of the baseline model. As a result, new models open new avenues for theoretical and applied researchers to address real-world problems, allowing them to fit asymmetric and complex random phenomena more proficiently and adequately. As a result, several modifications, extensions, and generalizations have been developed and discussed in the literature, with the Lehmann1 type – I (L – I) and Lehmann type – II (L – II) models being among the simplest and most useful. The simple exponentiation of any arbitrary baseline model is given by L – I.

Fxαξ=Gαxξ

where 0<x<1, and α>0 is a shape parameter.

Gupta et al.2 are credited with the use of L–I on exponential distributions. On the other hand, Cordeiro et al.3 established the L–II–G class of distributions and developed a dual transformation of L–I, which is given by

Fxαξ=11Gxξα

where Gxξ is cumulative distribution function (CDF) of the arbitrary baseline model, based on the parametric vector ξ with α>0 as a shape parameter.

The closed-form feature of L–II allows one to derive and study its numerous properties, and in the literature, both approaches (L–I and L–II) have been extensively used in favor of the power function (PF) model, to study the unexplored characteristics of the classical and modified models. Recently, Arshad et al.4,5 developed bathtub-shaped failure rate and PF models followed by L–II and L–I families, respectively, and explored their applications in engineering data. Awodutire et al.6 generalized the half-logistic via L–II class, and Akilandeswari et al.7 proposed the Laplace L–I reliability growth model and discussed its application in the early detection of software failure based on time between failure observations.

The PF is a special case of the beta distribution in distribution theory, and its significance can be evaluated using statistical tests such as the likelihood ratio test. The PF's simplicity and utility has compelled researchers to investigate its further generalizations and applications in various fields of science. For this, we recommend that the reader look at Dallas's illustrious work.8 He discovered an intriguing relationship between PF and Pareto models when the inverse transformation of the Pareto variable explored the PF.8 Meanwhile, Meniconi and Barry9 discovered the PF as a best-fit model on electronic component data. Characterization is based on the independence of record values and order statistics, with lower record values attributed to Chang10 and Tavangar,11 respectively. Cordeiro and Brito12 created the beta version of the PF and discussed its use in petroleum reservoir and milk production data. The PF was characterized by Ahsanullah et al.13 using lower record values. Zaka et al.14 discussed techniques for estimating PF parameters such as least square (LS), relative least square (RLS), and ridge regression (RR). Tahir et al.15 generalized the PF via the Weibull-G class and applied it to bathtub-shaped data. Shahzad et al.16 used the techniques of L-, TL-, LL-, and LH moments to calculate the PF moments. Haq et al.17 generalized the PF via the QRTM-G class and investigated its application in two-lifetime data. Okorie et al.18 generalized the PF via the Marshall-Olkin-G class (Marshall and Olkin19) and investigated its application in data on anxiety in women and evaporation. Usman et al.20 proposed an exponentiated version of transmuted PF and investigated its application in biological and engineering data. Hassan et al.21 generalized the PF by following the odd exponential-G class (Tahir et al.22) and discussed its application in three-lifetime data. Zaka et al.23 developed a new reflected PF and investigated its application in medical sciences data, while Al-Mutairi24 discussed the weighted PF via the QRTM G-class and investigated its application in the engineering sector.

Modified Lehmann type II model

We developed a potentiated lifetime model known as the modified Lehmann type II (ML-II) model. It is constrained by the interval (0, 1). The ML-II is extremely well suited to modeling asymmetric and bathtub-shaped phenomena. By including a scale parameter (α>0), in the baseline model, it begins to outperform its competitors in terms of fit and robustness of the tail weight/skewness of the density function.

The ML-II is said to follow a random variable X if its associated CDF and corresponding probability density function (PDF) are given by

(1)
FMLIIxαβ=11x1+αxβ

and

(2)
fMLIIxαβ=βα+11xβ11+αxβ+1

where 0<x<1, and α>1,β>0 are the scale and shape parameters, respectively. For α = 0, the ML-II reduces to the L–II (baseline model).

Balogun et al.,25,26 has developed the generalized version and G-class of ML-II (Equation (1)), respectively, and explored their applications in multidisciplinary areas of science.

We had the following objectives:

  • (i) to develop a two-parameter model with an approach that had not been studied and discussed in the past;

  • (ii) For the new model to have attractive closed-form features for CDF, PDF, and a likelihood function that is simple to interpret,;

  • (iii) PDF and HRF to hold J, reversed-J, and bathtub shapes;

  • (iv) To provide comparative results and a better fit than competing models.

This article is divided into the following sections:’Linear representation’ presents a mixture representation as well as numerous structural and reliability measures. ‘Estimation’ includes the estimation of model parameters using the maximum likelihood estimation (MLE) method, as well as a simulation study. ‘Application’ discusses real-world applications, and the final section summarizes the conclusion.

Linear representation

The linear representations of CDF and PDF make the calculations much easier than the traditional integral computation for determining the mathematical properties. We consider the binomial expansion for this.

1zβ=i=01iβizi,z<1
FMLIIxαβ=11xβ1+αxβ
FMLIIxαβ=1i=01iβixij=0βjαxj

Hence, the mixture representation of CDF is given as

FMLIIxαβ=i,j=0ϕijxi+j

PDF is given as follows

fMLIIxαβ=β1+αi=01iβ1ixij=0β+1jαxj

or

fMLIIxαβ=β1+αi,j=0ηijxi+j

where ϕij=βiβj1iαj,α>1,β>0,ηij=αj1iβ1iβ+1j,α>1,β>0

Reliability characteristics

The probability model plays an important role in reliability engineering by analyzing and predicting the lifespan of a component. Notable contributions include the survival function S(x), hazard rate function h(x), cumulative hazard rate function hc(x), reverse hazard rate function hr(x), Mills ratio M(x), and odd function O(x)).

The reliability function can be defined as the probability that a component will survive at time x. It is defined analytically as Sx=1Fx. The survival/reliability function of X is denoted by

(3)
SMLIIxαβ=1x1+αxβ

Terms such as “failure rate function”, “hazard rate function”, and “force of mortality” are frequently discussed in the literature. These terms are used to describe the failure rate of a component over a specific time period (say x). It is mathematically defined as hx=fx/Rx.

The failure rate function of X is denoted by

(4)
hMLIIxαβ=βα+11x1+αx

The mechanical components/parts of some systems are frequently assumed to follow the bathtub-shaped failure rate phenomenon. To discuss the significance of the MLII, several well-established and useful reliability measures are available in the literature. One of them is the cumulative hazard rate function, which is defined as hcx=logSx. The cumulative hazard rate function of X is denoted by

hcMLIIxαβ=log1x1+αxβ

The reverse hazard rate function is defined by hrx=fx/Fx. The reverse hazard rate function of X is given by

hrMLIIxαβ=βα+11xβ11+αx1+αxβ1xβ

Mills ratio is defined by Mx=Sx/fx. Mills ratio of X is given by

MMLIIxαβ=1+αx1xββα+11xβ1

The odd function is defined by Ox=Fx/Sx. The odd function of X is given by

OMLIIxαβ=1+αxβ1xβ1xβ

As mentioned above, we can obtain the linear expression for reliability characteristics. In terms of linear expression, the reliability and failure rate functions of X are given by

SMLIIxαβ=i=01iβixij=0βjαxj

and

hMLIIxαβ=β1+αi=01iβ1ixij=0β+1jαxji=01iβixij=0βjαxj

Limiting behavior

Propositions 1 and 2 discuss the limiting behavior of the ML-II's cumulative distribution (CDF), density (PDF), reliability (S(x)), and failure rate (h(x)) functions for x 0 and x 1.

Proposition-1. The limiting behavior of the CDF, PDF, S(x), and h(x) of the ML-II at x 0 is given below.

FMLII0αβ0
fMLII0αββ1+α
SMLII0αβ1
hMLII0αββ1+α

Proposition-2. The limiting behavior of CDF, PDF, S(x), and h(x) of the ML-II at x 1 is given as follows, respectively.

FMLII1αβ=1
fMLII1αβ=0
SMLII1αβ=1
hMLII1αβ=0

Shapes of density and failure rate functions

The possible shapes of the ML-II's density and failure rate functions are sketched over various model parameter choices shown in Figures 1 and 2. Figure 1 depicts the J, reverse-J, and bathtub shapes of the density function, while Figure 2 depicts the U, bathtub, and reverse-J shapes of the failure rate function.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure1.gif

Figure 1. Density function.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure2.gif

Figure 2. Failure rate function.

Quantile, mode, skewness, and kurtosis

The concept of quantile function was introduced by Hyndman and Fan.27 Inverting the CDF yields the pth quantile function of ML-II (Equation (1)). The quantile function is defined as follows: p=Fxp=PXxp,p01. Then, the quantile function of X is given by

(5)
xpMLII=11p1/β1+α1p1/β,α>1,β>0

Put p = 0.25, 0.50, and 0.75 in Equation (3) to get the first quartile, median, and third quartile of X. To generate random numbers in the future, we will assume that the CDF in Equation (1) follows a uniform distribution u = U. (0, 1).

The mode of X is calculated by taking the first derivative of PDF (Equation (2)) and equating it to zero, as shown by

f/MLIIxαβ=βα+11xβ1+αxβ22αx1+αβα+11x2=0

As a result, a simplified form of the mode is given by

ModeMLII=α+1β+112α,α>1,β>0

Measures of skewness and kurtosis based on quartiles and octiles are less sensitive to outliers and work well against models, but they are deficient in moments.

Bowley’s28 measure of skewness
SB=Q34+Q142Q12Q34Q14
Moor’s29 measure of kurtosis
KM=Q38Q18Q58+Q78Q68Q28

According to Figures 3 and 4, the skewness and kurtosis plots of the ML-II may be positively skewed.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure3.gif

Figure 3. Skewness.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure4.gif

Figure 4. Kurtosis.

Moments and associated measures

Moments play a significant role in distribution theory, where they are used to discuss the various characteristics and important features of the probability model.

Theorem 1. Let X ML-II (x;α,β), with α>1,β>0, then the r-th ordinary moment (say μr) of X is given by

μrMLII=Ei=0DiBr+i+1β

where E = β1+α,Di=αiβ1i

Proof: r-th ordinary moment can be written by following Equation (2) as

μrMLII=β1+αo1xr1xβ11+αxβ+1dx
μrMLII=αβγ1+αi=0Dio1xr+i1xβ1dx

As a result, the above integral reduces to the r-th moment, which is given by

(6)
μrMLII=Ei=0DiBr+i+1β

where B(x;α,β) = 0xtα1tβ1dt is the beta function, E = β1+α,Di=αiβ1i and α>1,β>0

The r-th moment is quite helpful in the development of several statistics. For instance, the mean of X can be obtained by setting r =1 in Equation (6) and is given by

μ1MLII'=Ei=0DiB2+i,β

Moment generating function MXt is defined as MXt=r=0trr!μr. It is obtained by following Equation (6) and is given by

MXMLIIt=Er=0trr!i=0DiBr+i+1β

Characteristic function is defined as Xt=r=0itrr!μr. It is obtained by following Equation (6) and is given by

XMLIIt=Er=0itrr!i=0DiBr+i+1β

The factorial generating function of X is defined as Fxt=E1+tx=Eexln1+t=r=0ln1+trr!μr. It is obtained by following Equation (6) and is given by

FxMLIIt=Er=0ln1+trr!i=0DiBr+i+1β

The Fisher index VarXEX may play a supportive role in the discussion of variability in X and it is given by

Fisher indexMLII=Ei=0DiB3+iβEi=0DiB2+iβ2Ei=0DiB2+iβ

For the negative moments of X, substitute r by – w in Equation (6) and it is given by

μwMLII'=Ei=0DiBw+i+1,β

Furthermore, for fractional positive and fractional negative moments of X, substitute r by mn and mn in Equation (6), respectively.

The Mellin transformation is well-known in statistics as a product distribution as well as a quotient for independent random variables. The Mellin transformation is presented by Mxm=Exm1=xm1fxdx. The Mellin transformation of X is given by

MxMLIIm=Ei=0DiBm+iβ.

where B(x;α,β) = 0xtα1tβ1dt is the beta function, E = β1+α,Di=αiβ1i and α>1,β>0.

One may perhaps further determine the well-established statistics such as skewness (τ1=μ32/μ23), and kurtosis (τ2=μ4/μ22), of X by integrating Equation (6). A well-established relationship between the central moments μs and cumulants (Ks) of X may easily be defined by ordinary moments by μs=k=0ssk1kμ1/sμsk/. Hence, the first four cumulants can be calculated by K1=μ1/, K2=μ2/μ1/2, K3=μ3/3μ2/μ1/+2μ1/3, and K4=μ4/4μ3/μ1/3μ2/2+12μ2/μ1/26μ1/4.

Some numerical results of the first four ordinary moments (μ1/,μ2/,μ3/,μ4/), mode (a value that appears frequently in data), ε2 = variance (a measure of dispersion), τ1= skewness (measure of asymmetry), and τ2= kurtosis (a measure to discuss the heaviness of the distribution tails) for some chosen parameters are presented in Table 1 for S-I (α=0.5,β=0.9), S-II (α=0.9,β=1.5), S-III (α=1.2,β=1.9), S-IV (α=3.2,β=0.9), and S-V (α=0.2,β=3.9). Note that the results of moments and variance decrease gradually, while skewness falls between 0 and 1, mode increases, and kurtosis can be negative subject to the model parameter combinations.

Table 1.

Numerical results of moments (μs/), variance (ε2), skewness (τ1), and kurtosis (τ2).

μs/ S-IS-IIS-IIIS-IVS-V
μ1/0.4600.2950.2240.3020.181
μ2/0.2970.1430.0890.1630.056
μ3/0.2210.0860.0460.1100.023
μ4/0.1760.0580.0280.0670.011
Mode1.8502.0832.2411.09112.200
ε20.0290.0440.0250.0670.002
τ10.0100.1000.4920.0281.292
τ20.1190.5980.9810.483−0.076

Incomplete moments

Lower incomplete (LI) and upper incomplete moments are the two types of incomplete moments. LI moments are defined by Φrt=0txrfxdx. The LI moments of X are given as

(7)
ΦrMLIIt=Ei=0DiBtr+i+1β

The residual life function of random variable X, Rt=Xt/X>t, is the likelihood that a component whose life says x, survives in the different time intervals at t0. Analytically, it can be written as follows:

SRtMLIIxαβ=Sx+tSt

Residual life function of X

SRtMLIIxαβ=1x+tβ1+αtβ1+αx+tβ1tβ

with the associated CDF is given as follows

FRtMLIIxαβ=1+αx+tβ1tβ1x+tβ1+αtβ1+αx+tβ1tβ

The mean residual life function of X is given by

ESRMLIIxαβ=1Stμ1/0txfxdxt,t0
ESRMLIIxαβ=1+αtβ1tβEi=0DiB2+iβBt2+iβt

Further, the reverse residual life can be defined as R¯t=tX/Xt

SR¯tMLIIxαβ=FtxFt,t0

Reverse residual life function of X

SR¯tMLIIxαβ=1txβ1+αtβ1+αtxβ1tβ

with the associated CDF is given as follows

FR¯tMLIIxαβ=1+αtxβ1tβ1txβ1+αtβ1+αtxβ1tβ

The mean reversed residual life function/mean waiting time is given by

ESR¯MLIIxαβ=t1Ft0txfxdx,t0
ESR¯MLIIxαβ=t1+αxβ1+αxβ1xβEi=0DiBt2+iβ

where B(x;α,β) = 0xtα1tβ1dt is the beta function, E = β1+α,Di=αiβ1i, and α>1,β>0

Order statistics

Order statistics and its moments play an important role in reliability analysis and life testing of a component in quality control. Let X1, X2, X3 , ..., Xn be a random sample of size n following the ML-II model and {X(1) < X(2) < X(3) < ... < X(n)} be the corresponding order statistics. The random variables X(i) , X(1) , X(n) are the i-th, minimum, and maximum order statistics of X, respectively.

The PDF of the i-th order statistics is given by

fi:nx=1Bini+1!Fxi11Fxnifx,
i = 1,2, 3, … , n.

By incorporating Equations (1) and (2), the PDF of the i-th order statistics is given by

(8)
fi:nMLIIxαβ=βα+1Bini+1!11x1+αxβi11x1+αxβni1xβ11+αxβ+1

Equation (8) can be written as

(9)
fi:nMLIIxαβ=1Bini+1!βα+1i,j=0Gij1iαjxj1x2β+i1

Straightforward computation of Equation (9) leads to the w-th moment order statistics of X and it is given by

(10)
EXw=μwOSMLII/=1Bini+1!βα+1i,j=0Gij1iαjBj+12β+i

where Gij=βiαβ+α+ij,α>1,β>0. Further, the minimum and maximum order statistics of X follow directly from Equation (8) with i = 1 and i = n, respectively.

Stress – strength reliability

Let X1 and X2 represent a component's strength and stress, respectively, following the same univariate distribution. The inadequacy or effectiveness of a component is dependent on whether X2>X1 and X2<X1, respectively. Stress – strength reliability can be written as R=PX2<X1.

Theorem 2. Let X1 ML-II (x;α,β1) and X2 ML-II (x;α,β2) be independent ML-II distributed random variables; then the reliability R is defined as β2β1+β2

Proof: Reliability R is defined as

R=f1xF2xdx

Reliability of X is given by

RMLII=β1α+11xβ111+αxβ1+111x1+αxβ2dx.

Hence the above integral reduces R in terms of β1 and β2, refers to the stress-strength reliability of the ML-II, and it is given by

RMLII=β2β1+β2,β1,β2>0

Entropy

There are a number of schools of thought about defining entropy measures. Entropy can be the quantity of disorderedness, randomness, diversity, or sometimes an uncertainty in a system.

The Rényi30 entropy of X is defined by

IδX=11δlog01fδxdx,δ>0andδ1

First, we simplify fx in terms of fδx by considering Equation (2)

fδMLIIXαβδ=βδα+1δ1Xδβ11+αXδβ+1

by applying the binomial expansion to this equation, we get

fδMLIIXαβδ=βδα+1δi=0δβ+1iαiXi1Xδβ1

and by placing this information in IδX, we get

IδMLIIXαβδ=11δlogβδα+1δ01i=0δβ+1iαixi1xδβ1dx

hence, by integrating the last equation we obtain the reduced form of the Rényi entropy of X and it is given by

(11)
IδMLIIXαβδ=11δlogβδα+1δi=0AiBδβ1+1i+1

where Ai=δβ+1iαi,α>1,β>0.

A generalization of the Boltzmann-Gibbs entropy is the η – entropy, although in physics, it is referred to as the Tsallis entropy. The Tsallis31 entropy/η – entropy is described by

HηX=1η1101fηxdx,η>0andη1.

The Tsallis Entropy of X is given by

HηMLIIXαβη=1η11βηα+1ηi=0CiBηβ1+1i+1

where Ci=ηβ+1iαi,α>1,β>0.

Havrda and Charvat32 introduced ω entropy measure. It is presented by

HωX=12ω1101fωxdx1,ω>0andω1.

The Havrda and Charvat entropy of X is given by

HωMLIIXαβω=12ω11βωα+1ωi=0FiBωβ1+1i+11

where Fi=ωβ+1iαi,α>1,β>0.

Arimoto33 generalized the work of32 by introducing ε entropy measure. It is presented by

HεX=12ε1101f1εxdxε1,ε>0andε1.

The Arimoto entropy of X is given by

HεMLIIXαβε=12ε11β1εα+11ε×i=0GiB1εβ1+1i+1ε1

where Gi=1εβ+1iαi,α>1,β>0.

Boekee and Lubba34 developed the τ entropy measure. It is presented by

HτX=ττ1101fτ1xdx1τ,τ>0andτ1.

Boekee and Lubba entropy of X is given by

HτMLIIXαβτ=ττ11βτ1α+1τ1×i=0IiBτ1β1+1i+11τ

where Ii=τ1β+1iαi,α>1,β>0.

Mathai and Haubold35 generalized the classical Shannon entropy known as ζ entropy. It is presented by

HζX=1ζ101f2ζxdx1,ζ>0andζ1.

The Mathai and Haubold entropy of X is given by

HζMLIIXαβζ=1ζ11β2ζα+12ζi=0JiB2ζβ1+1i+11

where Ji=2ζβ+1iαi,α>1,β>0.

Table 2 presents the flexible behavior of the entropy measures for some chosen model parameters for S-VI (α=1.1,β=2.1), S-VII (α=1.1,β=1.5), and S-VIII (α=2.1,β=3.5).

Table 2.

Numerical results of Rényi, Tsallis, Havrda and Charvat, Arimoto, Boekee and Lubba, and Mathai and Haubold entropy measures.

EntropyInitial valueS-VIS-VIIS-VIIIStatus
Rényiδ=1.1 9.9774.3307.023Decreasing
δ=1.5 2.7211.1811.915
δ=1.7 2.2030.9561.551
δ=1.9 1.9150.8311.348
Tsallisη=1.1 0.7430.3400.548Decreasing
η=1.5 0.3220.1680.267
η=1.7 0.1800.0960.154
η=1.9 0.0570.0310.051
Havrda and Charvatω=1.1 0.0040.0020.004Increasing
ω=1.5 0.1760.0950.162
ω=1.7 0.4330.2320.405
ω=1.9 0.8990.4710.847
Arimotoε=1.1 0.0080.0030.005Increasing
ε=1.5 0.6520.1610.281
ε=1.7 3.3290.4540.824
ε=1.9 177.6091.1042.115
Boekee and Lubbaτ=1.1 0.7560.3440.556Increasing
Decreasing
τ=1.5 0.4660.2330.371
τ=1.7 0.3940.2020.321
τ=1.9 0.3430.1770.282
Mathai and Hauboldζ=1.1 -0.517-0.283−0.455Increasing
Decreasing
ζ=1.5 −0.322−0.167−0.266
ζ=1.7 −0.214−0.106−0.169
ζ=1.9 −0.083−0.037−0.061

Estimation

In this section, we estimate the parameters of the ML-II by following the method of MLE as this method provides the maximum information about the unknown model parameters. Let X1,X2,X3,,Xn be a random sample of size n from the ML-II, then the likelihood function Lϑ=i=1nfxαβ of X is given by

LMLIIϑ=βα+1ni=1n1xiβ11+αxiβ+1

The log-likelihood function LogLϑ=lϑ of X is

(12)
lMLIIϑ=nlogβ+log1+α+β1i=0nlog1xiβ+1i=0nlog1+αxi

Now, we are concerned about obtaining the MLEs of the ML-II. For this, first, we maximize the Equation (12) and second, we calculate the partial derivatives w.r.t., the unknown parameters (α,β) and equate to zero, respectively. The score vector components are given by

Uϑ=l∂ϑ=lαlβT

Partial derivatives w.r.t. α,β are given as follows, respectively

lMLII∂α=n1+αβ+1i=onxi1+αxi
lMLIIβ=nβ+i=0nlog1xii=0nlog1+αxi

The last two non-linear equations do not provide the analytical solution for the MLEs and the optimum value of α, and β. The Newton-Raphson (an appropriate) algorithm plays a supportive role in these kinds of ML estimates. Numerical solutions and estimates of the parameters are calculated using R version 3.6.2 (statistical software).

Simulation

In this sub-section, to observe the asymptotic performance of MLE's φ̂=α̂β̂, we discuss the following algorithm.

Step - 1: A random sample x1, x2, x3 , ..., xn of sizes n = 150, 200, 250, 300, 350, 400, 450, and 500 from Equation (5).

Step - 2: The required results are obtained based on the different combinations of the model parameters placed in S-IX (α = 3.2, β = 2.5), S-X (α = 0.2, β = 0.9), and S-XI (α = 0.2, β = 1.5).

Step - 3: Results of mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) are calculated via nlmib in R. These results are presented in Tables 3 to 8.

Table 3.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (α) for S-IX.

SampleMeanVar.BiasMSECPAW
1503.1262.822−0.0741.6810.9126.383
2003.1572.262−0.0431.5050.9155.527
2503.1631.823−0.0361.3510.9154.931
3003.1421.442−0.0581.2020.9194.469
3503.1551.211−0.0451.1010.9284.137
4003.1551.109−0.0461.0540.9223.867
4503.1550.956−0.0450.9790.9293.942
5003.1740.843−0.0260.9190.9293.463

Table 4.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (β) for S-IX.

SampleMeanVar.BiasMSECPAW
1502.9641.6640.4641.3700.9504.491
2002.8351.0660.3341.0850.9363.397
2502.7590.7430.2590.9000.9422.809
3002.7130.5200.2130.7520.9562.431
3502.6690.3820.1690.6410.9512.148
4002.6520.3190.1520.5850.9501.974
4502.6320.2570.1330.5240.9541.823
5002.6070.2090.1070.4710.9531.693

Table 5.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (α) for S-X.

SampleMeanVar.BiasMSECPAW
1500.2550.0830.0550.2931.0001.432
2000.2470.0690.0480.2670.9981.218
2500.2360.0580.0360.2430.9961.070
3000.2230.0460.0230.2160.9970.962
3500.2180.0400.0180.2010.9960.883
4000.2160.0370.0150.1930.9900.824
4500.2110.s0330.0110.1820.9940.772
5000.2110.0310.0110.1750.9920.730

Table 6.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (β) for S-X.

SampleMeanVar.BiasRMSECPAW
1500.9060.0130.0060.1150.9700.587
2000.9040.0110.0040.1040.9540.499
2500.9060.0090.0060.0950.9570.442
3000.9060.0080.0060.0880.9690.401
3500.9060.0070.0060.0810.9690.369
4000.9050.0060.0050.0780.9680.345
4500.9060.0050.0060.0750.9710.324
5000.90500.0050.0050.0720.9600.306

Table 7.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (α) for S-XI.

SampleMeanVar.BiasMSECPAW
1500.2630.0970.0640.3191.001.633
2000.2540.0820.0540.2910.9981.382
2500.2430.0680.0430.2640.9951.211
3000.2280.0550.0280.2350.9981.087
3500.2220.0470.0220.2190.9960.996
4000.2190.0440.0190.2110.9940.928
4500.2140.0390.0140.1980.9930.869
5000.2130.0360.0130.1910.9880.821

Table 8.

Mean, variance (Var.), bias, mean square error (MSE), coverage probability (CP), and average width (AW) of (β) for S-XI.

SampleMeanVar.BiasMSECPAW
1501.5090.0520.0090.2270.9571.335
2001.5080.0450.0080.2080.9451.125
2501.5110.0370.0110.1940.9540.992
3001.5130.0320.0130.1800.9630.898
3501.5130.0280.0130.1680.9650.824
4001.5120.0260.0130.1630.9600.768
4501.5140.0240.0150.1560.9660.722
5001.5120.0220.0120.1490.9580.680

Step - 4: Each sample is replicated 1000 times.

Step - 5: A gradual decrease with the increase in sample size is observed in mean, biases, MSEs, and Var.

Step - 6: CPs of all the parameters φ=αβ are approximately 0.975, approaching the nominal value, and AW decreases when sample sizes increases.

Furthermore, the frequent use of the measures in the development of average estimate (AE), bias, MSE, CP, AW, are given as follows:

AEφ̂=1Ni=1Nφ̂,Varφ̂=1Ni=1Nφφ¯i2,Biasφ̂=1Ni=1Nφ̂iφ
MSEφ̂=1Ni=1Nφ̂iφ2,CPφ̂=i=1NIφ̂i0.975seφ̂iφ̂i+0.975seφ̂i,and
AWφ̂=1Ni=1Nφ̂i+0.975φ̂i0.975

Application

In this section, we explore the application of ML-II in medical science and engineering data. For this, we consider two lifetime datasets. The first dataset was originally reported by Smithson and Verkuilen.36 They studied a group of 166 healthy women's anxiety performance, i.e., outside of a pathological clinical setting, from Townsville, Queensland, Australia; data points are 0.01, 0.17, 0.01, 0.05, 0.09, 0.41, 0.05, 0.01, 0.13, 0.01, 0.05, 0.17, 0.01, 0.09, 0.01, 0.05, 0.09, 0.09, 0.05, 0.01, 0.01, 0.01, 0.29, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.09, 0.37, 0.05, 0.01, 0.05, 0.29, 0.09, 0.01, 0.25, 0.01, 0.09, 0.01, 0.05, 0.21, 0.01, 0.01, 0.01, 0.13, 0.17, 0.37, 0.01, 0.01, 0.09, 0.57, 0.01, 0.01, 0.13, 0.05, 0.01, 0.01, 0.01, 0.01, 0.09, 0.13, 0.01, 0.01, 0.09, 0.09, 0.37, 0.01, 0.05, 0.01, 0.01, 0.13, 0.01, 0.57, 0.01, 0.01, 0.09, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.05, 0.01, 0.01, 0.01, 0.13, 0.01, 0.25, 0.01, 0.01, 0.09, 0.13, 0.01, 0.01, 0.05, 0.13, 0.01, 0.09, 0.01, 0.05, 0.01, 0.05, 0.01, 0.09, 0.01, 0.37, 0.25, 0.05, 0.05, 0.25, 0.05, 0.05, 0.01, 0.05, 0.01, 0.01, 0.01, 0.17, 0.29, 0.57, 0.01, 0.05, 0.01, 0.09, 0.01, 0.09, 0.49, 0.45, 0.01, 0.01, 0.01, 0.05, 0.01, 0.17, 0.01, 0.13, 0.01, 0.21, 0.13, 0.01, 0.01, 0.17, 0.01, 0.01, 0.21, 0.13, 0.69, 0.25, 0.01, 0.01, 0.09, 0.13, 0.01, 0.05, 0.01, 0.01, 0.29, 0.25, 0.49, 0.01,0.01.

The second dataset was recently reported by Rahman et al.37 They studied the lifetime (in days) of 30 electronic devices and the dataset was as follows: 0.020, 0.029, 0.034, 0.044, 0.057, 0.096, 0.106, 0.139, 0.156, 0.164, 0.167, 0.177, 0.250, 0.326, 0.406, 0.607, 0.650, 0.672, 0.676, 0.736, 0.817, 0.838, 0.910, 0.931, 0.946, 0.953, 0.961, 0.981, 0.982, 0.990.

The ML-II is compared with its competing models (presented in Table 9) based on a series of criteria, namely, -Log-likelihood (-LL), Akaike information criterion (AIC), Bayesian information criterion (BIC), consistent Akaike information criterion (CAIC), and Kolmogorov Smirnov test (K-S) test statistics. Table 10 presents a set of descriptive statistics and Tables 11 and 12 present the parameter estimates and standard errors (in parenthesis) along the goodness-of-fit test. As seen in Tables 11 and 12, the performance of the ML-II abundantly satisfies the criteria of a better fit model. Consequently, we declare that the ML-II is a better fit among all competing models on the anxiety in women data. Moreover, Figures 5 and 6 present the empirically fitted plots comprising PDF (a), CDF (b), Kaplan-Meier Survival (c), Probability-Probability (P-P) (d), Box (e), and total test time (TTT) (f) plots (see Aarset38), which confirm the close fit to the data as well.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure5.gif

Figure 5.

Fitted Probability density function (PDF) (a), Cumulative distribution function (CDF) (b), Kaplan-Meier survival (c), Probability – Probability (PP) (d), Box (e), and Total Test Time (TTT) (f) Plots for women’s anxiety data.

5467fa7b-55de-4662-a9ca-9357bdb503c6_figure6.gif

Figure 6.

Fitted Probability density function (a), Cumulative distribution function (b), Kaplan-Meier survival (c), Probability-Probability (d), Box (e), and Total Test Time (f) Plots for 30 electronic devices data.

Table 9. Competitive models Cumulative distribution functions (cdfs).

Kum = Kumaraswamy distribution ; L–I = Lehmann type I distribution; L–II = Lehmann type II distribution ; T-Kum = transmuted Kumaraswamy distribution ; Mostafa type-II distribution ; T-GPW = transmuted generalized power Weibull distribution; T-Lin = transmuted Lindley distribution.

AbbreviationsModelParameter/variable rangeReference
KumGIxαβ=11xαβα,β>0,
0 < x < 1
Kumaraswamy39
L-IGIIxα=xαα>0,
0 < x < 1
Lehmann1
L-IIGIIIxα=11xαα>0,
0 < x < 1
T-KumGIVxαβε=1+ε11xαβ
ε11xαβ2
α,β>0,
ε1
x > 0
Khan et al.40
MT-IIGVxα=expxαlog21α>0,
0 < x < 1
Muhammad41
T-GPWGVIxαβε=1+ε1e11+xαβ
ε1e11+xαβ2
α,β>0,
ε1,
x > 0
Khan42
T-LinGVIIxα=1+ε11+α+αx1+αeαxε11+α+αx1+αeαx2,α>0
ε1,
x > 0
Khan et al.43

Table 10. Descriptive statistics.

DataMinimum1st
Quart
Mean3rd
Quart
SkewnessKurtosis95% C.I.Maximum
Women’s anxiety0.0100.0100.0910.1302.2127.959(0.071,0.112)0.690
Electronic devices0.0200.1430.4940.8920.0621.312(0.353,0.634)0.990

Table 11. Maximum likelihood estimations with standard errors (in parenthesis) and goodness of fit for the women’s anxiety data.

Model α̂ β̂ ε̂ -LLAICBICHQICK-S
ML-II27.793
(7.857)
0.988
(0.154)
−258.657−513.315−507.091−510.7880.276
T-GPW0.780
(0.046)
5.898
(1.005)
0.453
(0.213)
−250.605−495.210−485.874−491.4200.292
T-Kum0.703
(0.048)
3.805
(0.688)
0.569
(0.178)
−247.915−489.831−480.495−486.0410.290
Kum0.642
(0.045)
4.473
(0.582)
−244.314−484.629−478.405−482.1030.287
T-Lin9.434
(0.960)
0.555
(0.124)
−239.783−475.565−469.341−473.0390.376
L-II9.082
(0.705)
−218.538−435.077−431.965−433.8140.412
L-I0.299
(0.023)
−187.727−373.454−370.342−372.1910.270

Table 12. Maximum likelihood estimations (MLEs) with standard errors (in parenthesis) and goodness of fit for the lifetime (in days) of 30 electronic devices data.

Model α̂ β̂ ε̂ -LLAICBICHQICK-S
ML-II4.852
(3.842)
0.428
(0.115)
−4.401−4.802−2.000−3.9060.128
T-Kum0.609
(0.178)
0.585
(0.174)
0.125
(0.495)
−3.534−1.0693.1340.2760.409
Kum0.587
(0.161)
0.611
(0.134)
−3.502−3.005−0.203−2.1080.385
L-II0.780
(0.142)
−1.00−0.0071.3930.4400.029
L-I0.816
(0.149)
−0.6590.6802.0811.1280.189
MT-II0.700
(0.139)
−1.056−0.1131.2870.3340.253

Conclusion

We developed a potentiated lifetime model that exhibited the bathtub-shaped failure rate and addressed the most efficient and consistent results over complex random phenomena in this article. We called the proposed model a modified Lehmann type II (ML-II) model because it was a modified version of the Lehmann type II model. Several structural and reliability measures were developed and discussed. We used the maximum likelihood estimation method to estimate model parameters, and we also ran a simulation study to investigate the asymptotic performance of the MLEs. Data on anxiety in women from Smithson and Verkuilen36 and data on 30 electronic devices from Rahman et al.,37 were modeled to reveal the dominance ML-II over its competitors. It is hoped that in the future, the ML-II will be regarded as a superior alternative to the baseline model.

Data availability

Figshare: two_dataset.doc, https://doi.org/10.6084/m9.figshare.14903142.45

This project contains the following extended data:

  • Smithson and Verkuilen dataset: anxiety test scores from a group of 166 healthy women

  • Rahman et al., dataset: lifetime (in days) of 30 electronic devices

The authors of this work sought and obtained consent to use the dataset from the respective authors. The dataset from Smithson and Verkuilen37 was originally published on Smithson's website and saved under Example 2.text. Rahman et al.'s dataset is available in their publication.38 The dataset was published in an open repository with the authors' permission.

Grant information

This work was supported by Digiteknologian TKI-ymparisto project A74338 (ERDF, Regional Council of Pohjois-Savo).

Competing interests

No competing interests were disclosed.

Comments on this article Comments (0)

Version 1
VERSION 1 PUBLISHED 17 Aug 2021
Comment
Author details Author details
Competing interests
Grant information
Copyright
Download
 
Export To
metrics
Views Downloads
F1000Research - -
PubMed Central
Data from PMC are received and updated monthly.
- -
Citations
CITE
how to cite this article
Iqbal MZ, Arshad MZ, Özel G and Balogun OS. A better approach to discuss medical science and engineering data with a modified Lehmann Type – II model [version 1; peer review: 2 approved with reservations]. F1000Research 2021, 10:823 (https://doi.org/10.12688/f1000research.54305.1)
NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.
track
receive updates on this article
Track an article to receive email alerts on any updates to this article.

Open Peer Review

Current Reviewer Status: ?
Key to Reviewer Statuses VIEW
ApprovedThe paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approvedFundamental flaws in the paper seriously undermine the findings and conclusions
Version 1
VERSION 1
PUBLISHED 17 Aug 2021
Views
0
Cite
Reviewer Report 10 Sep 2024
Matthew Iwada Ekum, Lagos State University of Science and Technology, Ikorodu, Lagos, Nigeria 
Approved with Reservations
VIEWS 0
Research Paper Review
The authors' work title is appropriate as “A better approach to discuss medical science and engineering data with a modified Lehmann Type – II model”. The work is well organized and follows a logical sequence as ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Ekum MI. Reviewer Report For: A better approach to discuss medical science and engineering data with a modified Lehmann Type – II model [version 1; peer review: 2 approved with reservations]. F1000Research 2021, 10:823 (https://doi.org/10.5256/f1000research.57782.r314601)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
Views
6
Cite
Reviewer Report 17 Jan 2022
Lazhar Benkhelifa, Department of Mathematics and Informatics, Larbi Ben M’Hidi University, Oum El Bouaghi, Algeria 
Approved with Reservations
VIEWS 6
  1. The linear representations of CDF and PDF are based on some infinite sums. The authors need to prove that these sums converge for all or some values of the parameters.
     
  2. In page
... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Benkhelifa L. Reviewer Report For: A better approach to discuss medical science and engineering data with a modified Lehmann Type – II model [version 1; peer review: 2 approved with reservations]. F1000Research 2021, 10:823 (https://doi.org/10.5256/f1000research.57782.r119893)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.

Comments on this article Comments (0)

Version 1
VERSION 1 PUBLISHED 17 Aug 2021
Comment
Alongside their report, reviewers assign a status to the article:
Approved - the paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations - A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approved - fundamental flaws in the paper seriously undermine the findings and conclusions
Sign In
If you've forgotten your password, please enter your email address below and we'll send you instructions on how to reset your password.

The email address should be the one you originally registered with F1000.

Email address not valid, please try again

You registered with F1000 via Google, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Google account password, please click here.

You registered with F1000 via Facebook, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Facebook account password, please click here.

Code not correct, please try again
Email us for further assistance.
Server error, please try again.