A new generator for proposing flexible lifetime distributions and its properties.

In this paper, we develop a generator to propose new continuous lifetime distributions. Thanks to a simple transformation involving one additional parameter, every existing lifetime distribution can be rendered more flexible with our construction. We derive stochastic properties of our models, and explain how to estimate their parameters by means of maximum likelihood for complete and censored data, where we focus, in particular, on Type-II, Type-I and random censoring. A Monte Carlo simulation study reveals that the estimators are consistent. To emphasize the suitability of the proposed generator in practice, the two-parameter Fréchet distribution is taken as baseline distribution. Three real life applications are carried out to check the suitability of our new approach, and it is shown that our extension of the Fréchet distribution outperforms existing extensions available in the literature.

Introduction

The modeling and analysis of lifetime phenomena is an important aspect of statistical work in a wide variety of scientific and technological fields. The field of lifetime data analysis has grown and expanded rapidly with respect to methodology, theory, and fields of application. In the context of modeling the real life phenomena, continuous probability distributions and many generalization or transformation methods have been proposed. These generalizations, obtained either by adding one or more shape parameters or by changing the functional form of the distribution, increase the flexibility of the distributions and model the phenomena more accurately. Extensive developments in software have made it possible to focus less on computational details and hence simplified the methods of estimation.

The following are prominent and highly cited generators or transformations proposed over the past years in the statistical literature for modeling lifetime distributions. [1] transform the survival function by adding an extra shape parameter. The exponentiated family of distributions, which adds a shape parameter as exponent to an existing cumulative distribution function (cdf), is presented by [2]. The beta-generated family by [3] is based on both Beta type-I and Beta type-II distributions, while the Kumaraswamy-generated family by [4] uses the Kumaraswamy distribution instead of the Beta distribution. [5] pioneered a versatile and flexible gamma-G class of distributions based on the Generalized Gamma distribution.

Let F(x; ζ) be the cdf of a given random variable depending on some real-valued parameter(s) ζ. Our approach in this paper consists in enriching this cdf by transforming it into where ξ = (λ, ζ) for some positive real-valued shape parameter λ and the parameter ζ from the baseline distribution. We call this transformation the log-expo transformation (LET). It is aspired from [6] who considered the less versatile transformation While their approach only allows modulating the shape of distributions in a fixed way, ours is more flexible since it contains the extra shape parameter λ to regulate the transformation. To evaluate the suitability of the new proposed transformation, we will take the Fréchet distribution by [7] as example of baseline distribution throughout the rest of this paper.

The remaining paper is organized in the following order. The density function of the proposed method is defined and its basic statistical properties are derived. Next, we discuss, parameter estimation via maximum likelihood for complete and censored data, together with submodel likelihood ratio test. Monte Carlo simulation study to show the consistency of our estimation procedures. The fitting abilities of our new approach is illustrated by means of three real data sets. Finally, we give concluding remarks, and the Appendix collects densities of distributions used in the real data analysis.

The proposed density and its properties

The probability density function (pdf) corresponding to Eq (1) is given by where F(x; ζ) and f(x; ζ) are the arbitrary cdf and pdf of the baseline distribution. The cdf and pdf given in Eqs (1) and (3), respectively, will be more readable for a given expression of F(x; ζ) and f(x; ζ) of any baseline distribution. The flexibility of the proposed family of distributions is increased by adding shape parameter λ. Hereafter, we say that the random variable X having density Eq (3) is a log-expo transformed random variable.

The survival function S(x; ξ) = 1 − G(x; ξ) is of the simple form and the hazard function reads , and the reverse hazard function becomes . The explicit form of the υ quantile of the LET family of distributions is given by the simple expression . Consequently, random number generation from the LET family of distributions turns out to be a straightforward task.

Now, for the sake of illustration, we will briefly present three submodels of the proposed family of distributions, based on the baseline Fréchet, Exponential and Lomax distributions.

LET-Fréchet (LET-F) distribution

Consider the Fréchet distribution with respective cdf and pdf and . The cdf and pdf of the LET-Fréchet distribution then correspond to , λ > 0, α > 0, β > 0, and . Fig 1 illustrates the possible shapes of the pdf and cdf of the LET-F distribution.

Fig 1

Pdf and cdf plots of the LET-F distribution.

Since the LET-F distribution is our red thread example, we also provide some moment expressions. In Table 1, we give the first four moments , n = 1,…,4, the standard deviation (SD), coefficient of skewness (CS) and coefficient of kurtosis (CK) for different combinations of parameters. These values are calculated via Mathematica.

Table 1

Moments of the LET-F model for combinations of parameters.

	λ = 3, α = 6, β = 2	λ = 3, α = 6, β = 1	λ = 3, α = 5, β = 2	λ = 5, α = 6, β = 2	λ = 5, α = 6, β = 3
u1′	1.8825	0.9413	1.8655	1.7847	2.6770
u2′	3.6429	0.9107	3.6324	3.2324	7.2729
u3′	7.3439	0.9180	7.6159	5.9719	20.1550
u4′	15.9440	0.9965	19.3117	11.3993	57.7088
SD	0.0988	0.0247	0.1522	0.0473	0.1065
CS	3.6626	3.6627	4.5784	3.3122	3.3122
CK	43.6080	43.6086	86.1270	47.6170	47.6170

LET-Exponential (LET-E) distribution

Consider the Exponential distribution with respective cdf and pdf F(x; α) = 1 − e− and F(x; α) = αe−. The cdf and pdf of the LET-Exponential distribution then correspond to , λ > 0, α > 0, and Fig 2 illustrates the possible shapes of the pdf and cdf of the LET-E distribution.

Fig 2

Pdf and cdf plots of the LET-E distribution.

LET-Lomax (LET-L) distribution

Consider the Lomax distribution with respective cdf and pdf F(x; α, β) = 1 − (1 + αx)− and f(x; α, β) = αβ(1 + αx)−. The cdf and pdf of the LET-Lomax distribution then correspond to , λ > 0, α > 0, β > 0 and . Fig 3 illustrates the possible shapes of the pdf and cdf of the LET-L distribution.

Fig 3

Pdf and cdf plots of the LET-L distribution.

Lifetime data analysis and parameter estimation

The data encountered in survival analysis and reliability studies are often censored. This is why, besides classical maximum likelihood estimation, we also show how to estimate the parameters of our new family of distributions when the data are censored. More precisely, we consider Type-II, Type-I and random (right) censoring. These censoring schemes have been employed in numerous fields, especially for crash rates on roads which are based on censored data. Such data can be handled by using tobit, multinomial logit, mixed logit, ordered logit probit/logit models. for example, see the articles [8-15]. Finally, we develop likelihood ratio tests for testing the suitability of the baseline distributions against our LET extension.

Maximum likelihood estimation

We derive sample estimates of the unknown parameters of the LET model by using the maximum likelihood estimation technique. Let x1, x2, …, xn be the observations of a random sample of size n from the LET model. The likelihood function is given by and the log-likelihood function by

Differentiating the log-likelihood with respect to λ and ζ and equating to zero, we get the score equations and where and . Solving Eqs (4) and (5) gives the maximum likelihood estimates of the unknown parameters λ and ζ. Typically, this requires numerical optimization techniques such as Newton-Raphson methods as given in [16 and 17].

Parameter estimation under various types of right censoring

Let x1, x2, …, xn be the observations of a random sample of size n from the LET model. In what follows, we explain how to perform maximum likelihood estimation in our LET model for three types of right censoring.

Type-II censoring

In case of Type-II right censoring, t observations out of the n are censored from the right side. The likelihood function then becomes where x( is the order statistic of order i, and the log-likelihood function, expressed in terms of the original baseline distribution, reads

Differentiating this log-likelihood with respect to λ and ζ yields the score equations where , and , and

Expressions (6) and (7) give the maximum likelihood estimates of the unknown parameters λ and ζ for type-II right censored data. It is clear that their solution cannot be obtained analytically, and numerical techniques used in [16 & 17] are required.

Type-I censoring

Suppose that a random sample of n units from G(x; ξ) is processed for a predefined time x and then the process terminate. We observed the lifetime of δ observations before terminating the process and the remaining n − δ observations will be censored. Thus, the lifetimes are observed only if x ≤ x for i = 1, 2, …, n.

Defining and , the likelihood function can be written as and the log-likelihood function is given by

The score equations, and associated maximum likelihood estimates, are obtained along the same lines as in the previous sections. Their solution cannot be obtained analytically, and numerical techniques given in [16 & 17] are required.

Random censoring

Suppose a random sample consists of n observations T1, T2, …, Tn from a continuous failure distribution G(t; ξ) and consider other random censoring variables C1, C2, …, Cn drawn independently from a censoring distribution H(c; ξ). The observations for right censored data are presented as (X, I), i = 1, 2, …, n, where X = Min(T, C), and

The likelihood function for random censored data x1, x2, …, xn can be written as which yields the log-likelihood function

The score equations, and associated maximum likelihood estimates, are obtained along the same lines as in the previous sections. Their solution cannot be obtained analytically, and numerical techniques such as used in [16 & 17] are required.

Submodel testing

Our LET extension paves the way for submodel testing of the baseline distribution by means of likelihood ratio tests. For each parameter ξ, we denote by the unconstrained maximum likelihood estimate and by the maximum likelihood estimate under the restricted submodel. For example, testing for the Fréchet distribution against the LET − F model can be achieved by the test statistic , rejecting H0: λ = 0 at asymptotic level α against H1: λ ≠ 0 whenever T exceeds , the α-upper quantile of the chi-squared distribution with one degree of freedom.

Monte Carlo simulation results of the LET-F model

We perform a Monte Carlo simulation study in order to evaluate the behavior of maximum likelihood estimates of the proposed LET-F distribution for complete and censored data. The data were censored 10% from the right by using the Type-II and Type-I schemes. We calculate means, biases and mean-squared errors (MSEs) of each parameter of the LET-F model for different sample sizes n. To obtain the results, the process is replicated N = 10,000 times for n = 20, 30, 50 and 100 for censored data, and we added the sample sizes 200 and 300 for the complete data. The simulated means, biases and MSEs for complete and censored data are provided in Tables 2 and 3, respectively. We observe that, overall, the estimation procedure works well and that the estimates become better with increasing sample size, as should be the case. It is noteworthy to remark that close-to-zero values of λ are more difficult to estimate, which is probably due to the fact that such small values only slightly trigger our transformation as compared to the baseline model.

Table 2

The simulated means, biases and MSEs of the LET-F model for complete data.

n		α = 5	β = 3	λ = 0.2	α = 7	β = 2	λ = 1
20	Mean	7.4202	7.4202	7.4202	6.1623	2.5125	44.1802
	Bias	2.4202	2.4202	2.4202	-0.8377	0.5125	43.1802
	MSE	5.8575	5.8575	5.8575	0.7018	0.2626	1864.528
30	Mean	6.7879	3.0651	2.9379	6.3019	2.2937	13.1648
	Bias	1.7879	0.0651	2.7379	-0.6981	0.2937	12.1648
	MSE	3.1967	0.0042	7.4960	0.4874	0.0863	147.981
50	Mean	5.9997	3.0253	0.9445	6.2938	2.1755	3.7590
	Bias	0.9997	0.0253	0.7445	-0.7062	0.1755	2.7590
	MSE	0.9994	0.0006	0.5543	0.4987	0.0308	7.6118
100	Mean	5.3205	3.0377	0.5552	6.5032	2.1016	2.1361
	Bias	0.3205	0.0377	0.3552	-0.4968	0.1016	1.1361
	MSE	0.1027	0.0014	0.1261	0.2468	0.0103	1.2907
200	Mean	5.0338	3.0558	0.5266	6.6136	2.0674	1.7273
	Bias	0.0338	0.0558	0.3266	-0.3864	0.0674	0.7273
	MSE	0.0011	0.0031	0.1067	0.1493	0.0045	0.5290
300	Mean	4.9616	3.0579	0.4994	6.7025	2.0501	1.5386
	Bias	-0.0384	0.0579	0.2994	-0.2975	0.0501	0.5386
	MSE	0.0015	0.0033	0.0896	0.0885	0.0025	0.2901

Table 3

The simulated means, biases and MSEs of the LET-F model under Type-II and Type-I censoring schemes.

		Type-II (10%)			Type-I (10%)
n		α = 4	β = 1.5	λ = 0.5	α = 5	β = 3	λ = 0.2
20	Mean	7.1319	1.4222	1.3084	5.1853	3.2814	1.5743
	Bias	3.1319	-0.0778	0.8084	0.1853	0.2814	1.3743
	MSE	9.8089	0.0060	0.6535	0.0344	0.0792	1.8886
30	Mean	6.0671	1.4452	0.4424	5.0811	3.2572	1.4502
	Bias	2.0671	-0.0548	-0.0576	0.0811	0.2572	1.2502
	MSE	4.2729	0.0030	0.0033	0.0066	0.0662	1.5631
50	Mean	5.0600	1.4898	0.4147	4.9503	3.2324	1.2883
	Bias	1.0600	-0.0102	-0.0853	-0.0497	0.2324	1.0883
	MSE	1.1235	0.0001	0.0073	0.0025	0.0540	1.1843
100	Mean	3.9939	1.5588	0.5707	4.8597	3.1896	1.0618
	Bias	-0.0061	0.0588	0.0707	-0.1403	0.1896	0.8618
	MSE	0.0000	0.0035	0.0050	0.0197	0.0359	0.7428

Real data analysis

In this section, the fitting potential of our new procedure is evaluated by means of three real data sets, of which the last one is censored. In each case, we compare our LET-F model with competitors from the literature.

Non-censored data

The first data set shows the failure stresses (in GPa) of 64 bundles of carbon fibres and is also used by [18]. The second data set is presented by [19] and concerns the survival time counted in days of guinea pigs with infected virulent tubercle bacilli.

The proposed LET-F model is compared with the basic Fréchet (F) distribution as well as other extensions of it, such as the logarithmic transformed Fréchet (LTF) of [6], the Exponentiated Fréchet (EF) as initiated by [2], the Marshall-Olkin Fréchet (MOF) of [1], and the Kumaraswamy Fréchet (KF) according to the construction of [4]. We use the Kolmogorov–Smirnov (KS), Cramer–von Mises (W*), Anderson-Darling (A) and Deviance Information Criterion (DIC), goodness-of-fit tests for the comparison. The DIC is a generalized form of AIC and is widely used for model adequacy (see, [20 and 21]). The best model exhibits the smallest value of these statistics. The results are obtained by using R. In the Appendix, we give the respective pdfs of the above mentioned distributions.

In Table 4, we provide the value of the KS test together with the related p-value. As we can see, our LET-F model exhibits twice the lowest KS value and, consequently, largest p-value. For the second data set, the LTF model (2), which we try to improve on in particular, is clearly rejected by the KS test statistic. To further corroborate the strength of our LET-F model, we provide in Table 5 the corresponding values of the W*, the DIC and the A statistics. They also reveal that the LET-F model is very appropriate for these data sets as it outperforms its competitors. For the sake of illustration, the histogram of both data sets and fitted pdfs of all considered models are provided in Fig 4, while Fig 5 exhibits the corresponding PP-Plots. The better fit of the LET-F model for both the data sets included in this study can thus also be recognized visually.

Table 4

KS and P-values of the considered models.

Data	Statistic	LET-F	LTF	EF	MOF	KF	F
1	KS	0.0788	0.0972	0.0816	0.0827	0.0813	0.1006
	P-Value	0.8293	0.5908	0.7953	0.7823	0.7987	0.5471
2	KS	0.1007	0.2101	0.1225	0.1207	0.1031	0.1964
	P-Value	0.4582	0.0035	0.2297	0.2448	0.4283	0.0077

Table 5

Cramer–von Mises (W*), Anderson-Darling (A) and Deviance Information Criterion (DIC) values of the considered models.

Model	Statistics (Data set 1)			Statistics (Data set 2)
	W*	A	DIC	W*	A	DIC
LET-F	0.0449	0.2697	121.9680	0.0936	0.6635	213.4680
LTF	0.1019	0.5681	130.9540	0.5152	3.2925	240.4150
EF	0.0619	0.3310	124.5210	0.1178	0.8483	213.5480
MOF	0.0736	0.3932	129.6140	0.0766	0.5873	223.6090
KF	0.0615	0.3299	122.3000	0.1156	0.8314	214.4140
F	0.1150	0.6420	134.1110	0.5261	3.3486	240.2510

Fig 4

Histogram and estimated pdf of the models for data set 1 (left) and data set 2 (right).

Fig 5

PP-Plots of the LET-F model for data set 1 (left) and data set 2 (right).

Finally, our likelihood ratio test yields a p-value of 0.027 for the first data set and 0.000 for the second data set. Thus, the Fréchet distribution is rejected in favour of the LET-F model for data set 2 at any level, while it is rejected at the classical 5% level for the first data set but no longer at, the 2% level. The maximum likelihood estimates (MLEs), Bayes estimates (BEs), and their corresponding standard errors (SEs) and posterior standard deviations (SDs), respectively, for the parameters of the LET-F and the competitor models are given in Table 6.

Table 6

MLE, its SE and BE with posterior SD of the considered models.

Model	Parameter	Data 1		Data 2
		MLE	BE	MLE	BE
LET-F	λ^	-0.6887 (0.0048)	0.1011 (0.1836)	51.9403 (81.9581)	21.2228 (6.5014)
	α^	9.8006 (1.3536)	5.2812 (0.4522)	0.4453 (0.1776)	0.5755 (0.0657)
	β^	2.2339 (0.0744)	2.7535 (0.0855)	45.9901 (99.4069)	14.3989 (3.6077)
LTF	β^	5.8853 (0.5330)	5.7803 (0.5487)	1.2654 (0.0884)	1.2562 (0.0912)
	λ^	2.6235 (0.0618)	2.6190 (0.0712)	0.8600 (0.0894)	0.8629 (0.0924)
EF	β^	2.4218 (1.6970)	2.1103 (0.3117)	0.6013 (0.0755)	0.6046 (0.0576)
	λ^	4.2205 (2.4978)	4.8781 (0.6147)	8.5769 (3.8476)	9.0086 (2.2129)
	α^	6.6984 (13.027)	6.3642 (3.8191)	12.1029 (5.1417)	12.9036 (3.3128)
MOF	β^	7.8946 (1.1419)	6.8401 (0.2114)	2.5532 (0.1991)	1.8941 (0.15351)
	λ^	2.2055 (0.2335)	2.3815 (1.0483)	0.1762 (0.0285)	0.3085 (0.0769)
	α^	10.2274 (12.2381)	5.4738 (3.5144)	223.4801 (116.671)	18.3103 (4.7330)
KF	α^	9.4893 (20.363)	2.7963 (3.2455)	2.6846 (0.7402)	5.3471 (2.3419)
	θ^	7.0027 (13.815)	5.4046 (2.4840)	12.8647 (4.1109)	8.1203 (2.7692)
	λ^	1.6622 (1.5250)	3.7789 (1.7130)	1.81258 (2.9768)	0.7222 (0.7542)
	β^	2.3784 (1.6768)	2.8077 (0.7167)	0.5830 (0.0568)	0.6691 (0.0882)
F	β^	5.4351 (0.5078)	5.3630 (0.5342)	1.1721 (0.0842)	1.1620 (0.0855)
	λ^	2.7207 (0.0667)	2.7202 (0.0791)	1.0589 (0.1133)	1.0617 (0.1142)

Right-censored data

We now consider a data set presented by [22] and also used by [23]. The data is about the recurrence of leukemia of 46 patients (per year) who received autologous marrow. The full data set is given below where the plus sign indicates that observations are censored:

0.0301, 0.0384, 0.0630, 0.0849, 0.0877, 0.0959, 0.1397, 0.1616, 0.1699, 0.2137, 0.2137, 0.2164, 0.2384, 0.2712, 0.2740, 0.3863, 0.4384, 0.4548, 0.5918, 0.6000, 0.6438, 0.6849, 0.7397, 0.8575, 0.9096, 0.9644, 1.0082, 1.2822, 1.3452, 1.4000, 1.5260, 1.7205+, 1.9890+, 2.2438+, 2.5068+, 2.6466+, 3.0384, 3.1726+, 3.4411, 4.4219+, 4.4356+, 4.5863+, 4.6904+, 4.7808+, 4.9863+, 5.0000+.

This data set is random censored, see [22]. Here we compare our LET-F model with three models proposed recently by [22], namely, the long term Fréchet (LTF), the long term Weibull (LTW) and long term weighted Lindley (LTWL) distributions. The general form of a long term survival function is S*(x) = p + (1 − p) S(x), where S(x) is the survival function of any distribution and p denotes the probability of being cured. The corresponding distributions and pdfs can then be deduced from this mixture survival function.

This time, we use the Akaike information criterion (AIC) and the DIC as model comparison; the smaller its values, the better the fit (of course, the same tests as in the previous section can also be run here). Table 7 contains the maximum likelihood and Bayes estimates of the parameters. For quantification of variability of the estimates, SEs of the MLEs (in parenthesis) and SDs (in parenthesis) of the posterior distributions are reported. The log-likelihood (L) value and AIC of the proposed LET-F model are almost the same as those of the LTF model, and clearly smaller than for the other two models. While considering the DIC value, our proposed LET-F performs better than all other competitive models. Additionally, we present in Fig 6 the empirical survival function adjusted by the Kaplan-Meier estimator (KME) for our LET-F and the other three LT survival distributions.

Table 7

The MLE, its SE and BE with posterior SD for different parameters, together with the log-likelihood (L), Akaike Information Criterion (AIC) and Deviance Information Criterion (DIC).

Distribution	Parameter	MLE	BE	L	AIC	DIC
LET-F	α^	0.4430 (0.314)	0.5156 (0.0714)	-45.52	97.03	94.661
	β^	1.2010 (3.999)	0.6475 (0.3851)
	λ^	1.1990 (4.328)	0.2161 (0.4856)
LTF	α^	0.6570 (0.1410)	0.5958 (0.0792)	-45.33	96.66	94.837
	λ^	0.3140 (0.1240)	0.3612 (0.0993)
	p^	0.1250 (0.1260)	0.0483 (0.0613)
LTW	c^	0.9012 (0.2117)	0.8834 (0.1543)	-46.56	99.12	101.439
	λ^	1.7857 (0.4495)	0.8228 (0.3328)
	P^	0.2721 (0.0676)	0.2357 (0.0863)
LTWL	α^	0.9452 (0.1363)	0.8855 (0.2218)	-46.15	98.3	100.434
	λ^	0.6888 (0.1363)	1.7482 (0.4483)
	P^	0.2689 (0.0683)	0.2614 (0.0669)

Fig 6

Survival functions adjusted by KME for all considered models.

Conclusion

In this paper, we have proposed a new general construction of flexible lifetime distributions by rendering any existing baseline distribution more versatile through a simple transformation. We have discussed properties of the new models and explained how to estimate the parameters for complete and censored data sets. A Monte Carlo and hit-and-run Metropolis-Hasting simulations studies has revealed that the classical and Bayesian estimation procedures work well. On the basis of three distinct real data sets, we could see that the LET-F model, based on the Fréchet distribution as baseline distribution, is a very good competitor to existing distributions, especially to existing generalizations of the Fréchet. These good fitting capacities, combined with the simplicity of our proposal, make a strong case for using our construction in several practical situations.

Probability density functions of the competitors models and data sets.

(DOCX)

Click here for additional data file.

(DOCX)

Click here for additional data file.

11 Feb 2020

PONE-D-20-00826

A new generator for proposing flexible lifetime distributions and its properties

PLOS ONE

Dear Dr. Aslam,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

We would appreciate receiving your revised manuscript by Mar 27 2020 11:59PM. When you are ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.

A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.

An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Feng Chen

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements:

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at http://www.plosone.org/attachments/PLOSOne_formatting_sample_main_body.pdf and http://www.plosone.org/attachments/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please include a separate caption for each figure in your manuscript.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: This paper proposes a new generator for flexible lifetime distributions and discusses its statistical properties. Its performance is demonstrated by a Monte Carlo simulation study and three real-life applications. The paper is generally well structured and easy to access. A limitation is that the comparison between the proposed model and other alternatives only focuses on the goodness-of-fit and the results of AIC suggest that the difference seems to be insignificant. From the perspective of practical application, the model complexity should also be considered. The authors are suggested to conduct the model comparison using Bayesian methods. The deviance information criterion available in Bayesian inference, which is deemed as a generalization of the AIC, provides a combined measure of model fit and complexity. Please refer to some representative works which also model the censored continuous variables as in this paper, including:

A Bayesian spatial random parameters Tobit model for analyzing crash rates on roadway segments. Accident Analysis and Prevention, 2017, 100: 37-43.

A multivariate random parameters Tobit model for analyzing highway crash rate by injury severity. Accident Analysis and Prevention, 2017, 99: 184-191.

Incorporating temporal correlation into a multivariate random parameters Tobit model for modeling crash rate by injury severity. Transportmetrica A: Transport Science, 2018, 14 (3): 177-191.

Jointly modeling area-level crash rates by severity: A Bayesian multivariate random-parameters spatio-temporal Tobit regression. Transportmetrica A: Transport Science, 2019, 15(2): 1867-1884.

Reviewer #2: The topic of this paper is interesting and the methods sound. There are several suggestions to improve this paper.

1. “we will take the Fréchet as example” could be “we will take the Fréchet distribution as example”. And some references are needed.

2. “Typically this requires numerical optimization techniques such as Newton-Raphson.” References are needed for these techniques.

3. This paper lacks of references in the last decade.

4. “The score equations, and associated maximum likelihood estimates, are obtained along the same lines as in the previous sections, hence we leave this to the reader.” This sentence is not suitable. Some reference could be added instead of letting reader guess. For example, the following ones.

[1] Investigation on the Injury Severity of Drivers in Rear-End Collisions Between Cars Using a Random Parameters Bivariate Ordered Probit Model, International Journal of Environmental Research and Public Health, 2019, 16(14) , 2632.

[2] Injury severities of truck drivers in single- and multi-vehicle accidents on rural highway, Accident Analysis and Prevention, 2011, 43(5), 1677-1688.

[3] Analysis of hourly crash likelihood using unbalanced panel data mixed logit model and real-time driving environmental big data. 2018, JOURNAL OF SAFETY RESEARCH. 65: 153-159.

[4] Investigating the Differences of Single- and Multi-vehicle Accident Probability Using Mixed Logit Model, Journal of Advanced Transportation, 2018, UNSP 2702360.

5. For AIC, these references could also be referred to.

6. There are some ◇ in this paper, which might be not correct. For example, Page 10.

7. For censored data, Tobit models are frequently used, which could be referred to the following papers.

[5] Modeling crash rates for a mountainous highway using refined-scale panel data”, Transportation Research Record, 2015, 2515:10-16.

[6] Refined-scale panel data crash rate analysis using random-effects tobit model, Accident Analysis and Prevention, 2014, 73, 323-332.

8. “a p-value of 0.02663451” could be “a p-value of 0.027”.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email us at figures@plos.org. Please note that Supporting Information files do not need this step.

26 Mar 2020

Reviewer #1: This paper proposes a new generator for flexible lifetime distributions and discusses its statistical properties. Its performance is demonstrated by a Monte Carlo simulation study and three real-life applications. The paper is generally well structured and easy to access. A limitation is that the comparison between the proposed model and other alternatives only focuses on the goodness-of-fit and the results of AIC suggest that the difference seems to be insignificant. From the perspective of practical application, the model complexity should also be considered. The authors are suggested to conduct the model comparison using Bayesian methods. The deviance information criterion available in Bayesian inference, which is deemed as a generalization of the AIC, provides a combined measure of model fit and complexity. Please refer to some representative works which also model the censored continuous variables as in this paper, including:

A Bayesian spatial random parameters Tobit model for analyzing crash rates on roadway segments. Accident Analysis and Prevention, 2017, 100: 37-43.

A multivariate random parameters Tobit model for analyzing highway crash rate by injury severity. Accident Analysis and Prevention, 2017, 99: 184-191.

Incorporating temporal correlation into a multivariate random parameters Tobit model for modeling crash rate by injury severity. Transportmetrica A: Transport Science, 2018, 14 (3): 177-191.

Jointly modeling area-level crash rates by severity: A Bayesian multivariate random-parameters spatio-temporal Tobit regression. Transportmetrica A: Transport Science, 2019, 15(2): 1867-1884.

Answer: As per suggestion of the learned reviewer, we have calculated DIC and reported the results along with the results of AIC and other goodness of fit statistics for all three considered data sets. Moreover, Bayes estimates and posterior standard deviations are also reported. Also, some relevant papers reporting DIC as a goodness of fit criterion have been cited at appropriate places.

Reviewer #2: The topic of this paper is interesting and the methods sound. There are several suggestions to improve this paper.

1. “we will take the Fréchet as example” could be “we will take the Fréchet distribution as example”. And some references are needed.

Answer: corrected as suggested. Relevant reference articles have also been mentioned.

2. “Typically this requires numerical optimization techniques such as Newton-Raphson.” References are needed for these techniques.

Answer: References have been included.

3. This paper lacks of references in the last decade.

Answer: Yes! We agree with the referee. Unfortunately, we could not find any major transformer or technique related to this topic. Most of the recent work is based on extensions of previously proposed methods. We have included only major/ well known methods available in the literature. It is to be noted that only those frechet distributions which are generated from well known transformations are considered for comparison purposes using different data sets. As far as censoring schemes are concerned, we have included more recent work.

4. “The score equations, and associated maximum likelihood estimates, are obtained along the same lines as in the previous sections, hence we leave this to the reader.” This sentence is not suitable. Some reference could be added instead of letting reader guess. For example, the following ones.

[1] Investigation on the Injury Severity of Drivers in Rear-End Collisions Between Cars Using a Random Parameters Bivariate Ordered Probit Model, International Journal of Environmental Research and Public Health, 2019, 16(14) , 2632.

[2] Injury severities of truck drivers in single- and multi-vehicle accidents on rural highway, Accident Analysis and Prevention, 2011, 43(5), 1677-1688.

[3] Analysis of hourly crash likelihood using unbalanced panel data mixed logit model and real-time driving environmental big data. 2018, JOURNAL OF SAFETY RESEARCH. 65: 153-159.

[4] Investigating the Differences of Single- and Multi-vehicle Accident Probability Using Mixed Logit Model, Journal of Advanced Transportation, 2018, UNSP 2702360.

Answer: Actually, this line was written for the sake of brevity. Obviously, score equations can be obtained by taking first derivative of log-likelihood function with respect to the parameters and then equating to zero. In earlier draft of the paper, we did not include these simple equations to save the space. To support the brevity, related reference papers have been included now in the revised manuscript.

5. For AIC, these references could also be referred to.

Answer: The mentioned reference papers have been included.

6. There are some ◇ in this paper, which might be not correct. For example, Page 10.

Answer: corrected as mentioned.

7. For censored data, Tobit models are frequently used, which could be referred to the following papers.

[5] Modeling crash rates for a mountainous highway using refined-scale panel data”, Transportation Research Record, 2015, 2515:10-16.

[6] Refined-scale panel data crash rate analysis using random-effects tobit model, Accident Analysis and Prevention, 2014, 73, 323-332.

Answer: Relevant papers discussing tobit models have been cited.

8. “a p-value of 0.02663451” could be “a p-value of 0.027”.

Answer: Changed by rounding all the results on p-values to four decimal places.

Submitted filename: Response to reviewers.docx

Click here for additional data file.

3 Apr 2020

A new generator for proposing flexible lifetime distributions and its properties

PONE-D-20-00826R1

Dear Dr. Aslam,

We are pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it complies with all outstanding technical requirements.

Within one week, you will receive an e-mail containing information on the amendments required prior to publication. When all required modifications have been addressed, you will receive a formal acceptance letter and your manuscript will proceed to our production department and be scheduled for publication.

Shortly after the formal acceptance letter is sent, an invoice for payment will follow. To ensure an efficient production and billing process, please log into Editorial Manager at https://www.editorialmanager.com/pone/, click the "Update My Information" link at the top of the page, and update your user information. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, you must inform our press team as soon as possible and no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

With kind regards,

Feng Chen

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: (No Response)

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: (No Response)

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: (No Response)

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: (No Response)

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: (No Response)

Reviewer #2: (No Response)

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

17 Apr 2020

PONE-D-20-00826R1

A new generator for proposing flexible lifetime distributions and its properties

Dear Dr. Aslam:

I am pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please notify them about your upcoming paper at this point, to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

For any other questions or concerns, please email plosone@plos.org.

Thank you for submitting your work to PLOS ONE.

With kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Feng Chen

Academic Editor

PLOS ONE