Estimation method of mixture distribution and modeling of COVID-19 pandemic

Tabassum Naz Sindhu; Zawar Hussain; Naif Alotaibi; Taseer Muhammad; Tabassum Naz Sindhu; Zawar Hussain; Naif Alotaibi; Taseer Muhammad

doi:10.3934/math.2022554

AIMS Mathematics

2022, Volume 7, Issue 6: 9926-9956. doi: 10.3934/math.2022554

Previous Article Next Article

Research article Special Issues

Estimation method of mixture distribution and modeling of COVID-19 pandemic

1.
Department of Statistics, Quaid-i-Azam University 45320, Islamabad 44000, Pakistan
2.
Department of Social & Allied Sciences, Cholistan University of Veterinary & Animal Sciences, Bahawalpur 63100, Pakistan
3.
Department of Mathematics and Statistics, Imam Mohammad Ibn Saud Islamic University, Kingdom of Saudi Arabia
4.
Department of Mathematics, College of Sciences, King Khalid University, Abha 61413, Saudi Arabia

Received: 21 August 2021 Revised: 18 December 2021 Accepted: 17 January 2022 Published: 21 March 2022
MSC : 62E10, 62E15, 62F10

The mathematical characteristics of the mixture of Lindley model with 2-component (2-CMLM) are discussed. In this paper, we investigate both the practical and theoretical aspects of the 2-CMLM. We investigate several statistical features of the mixed model like probability generating function, cumulants, characteristic function, factorial moment generating function, mean time to failure, Mills Ratio, mean residual life. The density, hazard rate functions, mean, coefficient of variation, skewness, and kurtosis are all shown graphically. Furthermore, we use appropriate approaches such as maximum likelihood, least square and weighted least square methods to estimate the pertinent parameters of the mixture model. We use a simulation study to assess the performance of suggested methods. Eventually, modelling COVID-19 patient data demonstrates the effectiveness and utility of the 2-CMLM. The proposed model outperformed the two component mixture of exponential model as well as two component mixture of Weibull model in practical applications, indicating that it is a good candidate distribution for modelling COVID-19 and other related data sets.

Keywords:

Citation: Tabassum Naz Sindhu, Zawar Hussain, Naif Alotaibi, Taseer Muhammad. Estimation method of mixture distribution and modeling of COVID-19 pandemic[J]. AIMS Mathematics, 2022, 7(6): 9926-9956. doi: 10.3934/math.2022554

Related Papers:

[1]	Xin Zhao, Xin Liu, Jian Li . Convergence analysis and error estimate of finite element method of a nonlinear fluid-structure interaction problem. AIMS Mathematics, 2020, 5(5): 5240-5260. doi: 10.3934/math.2020337
[2]	Yuwen He, Jun Li, Lingsheng Meng . Three effective preconditioners for double saddle point problem. AIMS Mathematics, 2021, 6(7): 6933-6947. doi: 10.3934/math.2021406
[3]	Jin-Song Xiong . Generalized accelerated AOR splitting iterative method for generalized saddle point problems. AIMS Mathematics, 2022, 7(5): 7625-7641. doi: 10.3934/math.2022428
[4]	Zhuo-Hong Huang . A generalized Shift-HSS splitting method for nonsingular saddle point problems. AIMS Mathematics, 2022, 7(7): 13508-13536. doi: 10.3934/math.2022747
[5]	Yasir Nadeem Anjam . Singularities and regularity of stationary Stokes and Navier-Stokes equations on polygonal domains and their treatments. AIMS Mathematics, 2020, 5(1): 440-466. doi: 10.3934/math.2020030
[6]	Luigi Accardi, El Gheted Soueidi, Abdessatar Souissi, Mohamed Rhaima, Farrukh Mukhamedov, Farzona Mukhamedova . Structure of backward quantum Markov chains. AIMS Mathematics, 2024, 9(10): 28044-28057. doi: 10.3934/math.20241360
[7]	Danxia Wang, Ni Miao, Jing Liu . A second-order numerical scheme for the Ericksen-Leslie equation. AIMS Mathematics, 2022, 7(9): 15834-15853. doi: 10.3934/math.2022867
[8]	Tiantian Zhang, Wenwen Xu, Xindong Li, Yan Wang . Multipoint flux mixed finite element method for parabolic optimal control problems. AIMS Mathematics, 2022, 7(9): 17461-17474. doi: 10.3934/math.2022962
[9]	Salman Zeb, Muhammad Yousaf, Aziz Khan, Bahaaeldin Abdalla, Thabet Abdeljawad . Updating $QR$ factorization technique for solution of saddle point problems. AIMS Mathematics, 2023, 8(1): 1672-1681. doi: 10.3934/math.2023085
[10]	Shu-Xin Miao, Jing Zhang . On Uzawa-SSI method for non-Hermitian saddle point problems. AIMS Mathematics, 2020, 5(6): 7301-7315. doi: 10.3934/math.2020467

Abstract

1. Introduction

It is known to us all that tumor growth has attracted considerable attention over the past few decades. In order to study the importance of tumor growth and better understand the disease itself, it is critical to find a model that may help to treat the tumor. For this purpose, some basic relations between mathematical modeling and tumor model have been presented in ^[1]. With the diffusion process about cell and nutrient proliferation as a basis, many mathematical models ^{[2,3,4,5,6,7,8]} have been used to discuss these growth phenomena, such as the fractional mathematical model of tumor invasion and metastasis ^[2], tumor spheroid models ^[3,4], the androgen-deprivation prostate cancer treatment model ^[5], the foundations of cancer modeling ^[6] and hepatitis C evolution models ^[7,8].

In this paper, we will discuss the following reaction-diffusion model for cancer invasion ^[9,10]:

$\begin{eqnarray} &&{} u_t = u(1-u)-auw, \\ && v_t = d[(1-u)v_x]_x+bv(1-v), \\ &&{} w_{t} = w_{xx}+c(v-w), \end{eqnarray}$

(1.1)

where $u(x, t), v(x, t)$ and $w(x, t)$ stand for dimensionless and rescaled versions of healthy tissue, tumor tissue and excess $H^+$ ions, respectively. The subscripts represent the partial derivatives relative to the corresponding variables. $a, b, c$ and $d$ are all constant functions. $a$ indicates the destructive effect of $H^+$ ions on the healthy tissue, $b$ is the productivity of neoplastic tissue which pumps $H^+$ ions at a rate $c$ and $d$ is displayed in the form $d = D_2/D_3$ where $D_2$ and $D_3$ are the diffusion coefficients of malignant tissue and $H^+$ ions, respectively. The phenomenon in many instances of tumor propagation of an interstitial gap has been discussed in ^[9]. Some wave propagation dynamics were considered in ^[11].

As everyone knows, the Lie group method plays an important role in studying the exact significant solutions of nonlinear partial differential equations ^{[12,13,14,15]}. The main aims of the symmetry method are to construct invariance conditions and obtain reductions to differential equations ^[16,17,18]. Once the reduced equations are given, a large number of corresponding exact solutions can be obtained. Utilizing Lie group analysis, we are going to get some fascinating special solutions of Eq (1.1) and identify the analysis stability behaviors of the model.

The remainder of the paper is arranged as follows. Symmetries of the acid-mediated cancer invasion model are analyzed in Section 2; Section 3 considers the symmetry reductions through the use of similar variables; in Section 4, some new explicit solutions are provided with help of the power-series method, and the convergence of the solutions of the power-series is presented; also, we will investigate the properties of different solutions via imaging analysis; the last section summarizes the results of the study.

2. Lie point symmetry

In this paper, we demonstrate the Lie symmetry technique for Eq (1.1). First of all, let us think about a vector field of infinitesimal transformations of Eq (1.1) with the form

$\begin{eqnarray} &&X = \xi\partial_x+\tau\partial_t+\phi\partial_u+\varphi\partial_v+\eta\partial_w, \end{eqnarray}$

(2.1)

where $\xi, \tau, \phi, \varphi$ and $\eta$ are functions of $x, t, u, v, w$ respectively and are called infinitesimals of the symmetry group.

Based on the transformation (2.1), applying the invariance conditions to Eq (1.1), we get ^[16,19]

$\begin{eqnarray} &&{} \mbox{pr}^{(1)}X(u_t-u(1-u)+auw) = 0, \\ &&{} \mbox{pr}^{(2)}X(v_t-d((1-u)v_x)_x-bv(1-v)) = 0, \\ &&{} \mbox{pr}^{(2)}X(w_{t}-w_{xx}-c(v-w)) = 0, \end{eqnarray}$

where $\mbox{pr}^{(i)}X, \; i = 1, 2$ is the $i$ th-order prolongation of $X$ ^[16,19]. For Eq (1.1),

$\begin{eqnarray} \label{prol} &&{} \mbox{pr}^{(1)}X = X+\phi_t^{(1)}\frac{\partial}{\partial {u_t}}, \\ &&{}\mbox{pr}^{(2)}X = X+\phi_x^{(1)}\frac{\partial}{\partial {u_x}}+\varphi_x^{(1)}\frac{\partial}{\partial {v_x}}+\varphi_t^{(1)}\frac{\partial}{\partial {v_t}}+\eta_t^{(1)}\frac{\partial}{\partial {w_t}}+\varphi_{xx}^{(2)}\frac{\partial}{\partial {v_{xx}}}+\eta_{xx}^{(2)}\frac{\partial}{\partial {w_{xx}}}, \end{eqnarray}$

where

$\begin{eqnarray*} &&{\nonumber} \phi_x^{(1)} = D_x\phi-u_x D_x\xi-u_t D_x\tau, \\ &&{\nonumber} \phi_t^{(1)} = D_t\phi-u_x D_t\xi-u_t D_t\tau, \\ &&{\nonumber} \varphi_x^{(1)} = D_x\varphi-v_x D_x\xi-v_t D_x\tau, \\ &&{\nonumber} \varphi_t^{(1)} = D_t\varphi-v_x D_t\xi-v_t D_t\tau, \\ &&{\nonumber} \eta_t^{(1)} = D_t\eta-w_x D_t\xi-w_t D_t\tau, \\ &&{\nonumber} \varphi_{xx}^{(2)} = D_x^2(\varphi-\xi v_x-\tau v_t)+\xi v_{xxx}+\tau v_{xxt}, \\ &&{\nonumber} \eta_{xx}^{(2)} = D_x^2(\eta-\xi w_x-\tau w_t)+\xi w_{xxx}+\tau w_{xxt}, \end{eqnarray*}$

and $D_x$ and $D_t$ represent the total differential operators; for example,

$\begin{eqnarray} &&{} D_t = \frac{\partial}{\partial t}+u_t\frac{\partial}{\partial u}+v_t\frac{\partial}{\partial v}+w_t\frac{\partial}{\partial w}+u_{tx}\frac{\partial}{\partial u_x}+v_{tx}\frac{\partial}{\partial v_x}+u_{tt}\frac{\partial}{\partial u_t}+w_{tt}\frac{\partial}{\partial w_t}+\cdots. \end{eqnarray}$

Next, we get an overdetermined system of equations for $\xi, \tau, \phi, \varphi$ and $\eta$

$\begin{eqnarray} &&{}\xi_x = \xi_t = \xi_u = \xi_v = \xi_w = 0, \\ &&{}\tau_x = \tau_t = \tau_u = \tau_v = \tau_w = 0, \\ &&{}\phi = \varphi = \eta = 0. \end{eqnarray}$

Solving the above equations, one gets

$\begin{eqnarray} &&{} \xi = c_1, \; \tau = c_2, \; \phi = \varphi = \eta = 0, \end{eqnarray}$

where $c_1$ and $c_2$ are arbitrary constants. Therefore, Lie algebra $L_2$ of the transformations of Eq (1.1) is spanned by the following vector fields

$\begin{eqnarray} \label{reduceoper} &&{} X_1 = \partial_x, \; X_2 = \partial_t. \end{eqnarray}$

To obtain the symmetry groups, we solve the initial problems of the following ordinary differential equations

$\begin{eqnarray} &&{}\frac{d\tilde{x}}{d\epsilon} = \xi(\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w}), \; \tilde{x}|_{\epsilon = 0} = x, \\ &&{}\frac{d\tilde{t}}{d\epsilon} = \tau(\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w}), \; \tilde{t}|_{\epsilon = 0} = t, \\ &&{}\frac{d\tilde{u}}{d\epsilon} = \phi(\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w}), \; \tilde{u}|_{\epsilon = 0} = u, \\ &&{}\frac{d\tilde{v}}{d\epsilon} = \varphi(\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w}), \; \tilde{v}|_{\epsilon = 0} = v, \\ &&{}\frac{d\tilde{w}}{d\epsilon} = \eta(\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w}), \; \tilde{w}|_{\epsilon = 0} = w; \end{eqnarray}$

then we get the one-parameter symmetry groups $G_i:(x, t, u, v, w)\rightarrow (\tilde{x}, \tilde{t}, \tilde{u}, \tilde{v}, \tilde{w})$ of the infinitesimal generators $X_i(i = 1, 2)$ as follows:

$\begin{eqnarray} &&{} G_1:\; (x, t, u, v, w)\rightarrow (x+\epsilon, t, u, v, w), \\ &&{} G_2:\; (x, t, u, v, w)\rightarrow (x, t+\epsilon, u, v, w). \end{eqnarray}$

Based on the above discussion, we obtain the following theorem.

Theorem 2.1. If $u = f(x, t), \; v = g(x, t)$ and $w = h(x, t),$ constitute a solution of Eq (1.1), then by applying the above-mentioned groups $G_i(i = 1, 2)$ , the corresponding new solutions $u_i, \; v_i, \; w_i\; (i = 1, 2)$ can be presented respectively as follows:

$\begin{eqnarray} &&{} u_1 = f(x-\epsilon, t), \; v_1 = g(x-\epsilon, t), \; w_1 = h(x-\epsilon, t), \\ &&{} u_2 = f(x, t-\epsilon), \; v_2 = g(x, t-\epsilon), \; w_2 = h(x, t-\epsilon). \end{eqnarray}$

3. Similarity reductions

In this section, we are going to cope with the similarity reductions of Eq (1.1).

Case 3.1. For the generator $X_1+X_2$ , the invariants are $z = x-t, \; u = f(z), \; v = g(z)$ and $w = h(z)$ , Eq (1.1) becomes

$\begin{eqnarray} &&{} -f' = f-f^2-afh, \\ && -g' = d(-f'g'+g''-fg'')+bg-bg^2, \\ &&{} -h' = h''+c(g-h), \end{eqnarray}$

(3.1)

where $f' = \frac{df}{dz}, \; g' = \frac{dg}{dz}$ and $h' = \frac{dh}{dz}$ .

Case 3.2. For the generator $X_1$ , the invariants are $z = t, \; u = f(z), \; v = g(z)$ and $w = h(z)$ , Eq (1.1) can be reduced to

$\begin{eqnarray} &&{} f' = f-f^2-afh, \\ && g' = bg-bg^2, \\ &&{} h' = c(g-h), \end{eqnarray}$

(3.2)

where $f' = \frac{df}{dz}, \; g' = \frac{dg}{dz}$ and $h' = \frac{dh}{dz}$ . The invariant solution of Eq (1.1) is as follows: $u(x, t) = f(t), \; v(x, t) = g(t), \; w(x, t) = h(t)$ . Obviously, in this case, the variable $x$ has no effect on the solution of Eq (1.1).

Case 3.3. For the generator $X_2$ , analogously, we have $z = x, \; u = f(z), \; v = g(z)$ and $w = h(z)$ . The reduction of Eq (1.1) is

$\begin{eqnarray} &&{} f-f^2-afh = 0, \\ && d(-f'g'+g''-fg'')+bg-bg^2 = 0, \\ &&{} h''+c(g-h) = 0, \end{eqnarray}$

(3.3)

where $f' = \frac{df}{dz}, \; g' = \frac{dg}{dz}$ and $h' = \frac{dh}{dz}$ . The invariant solution of Eq (1.1) is as follows: $u(x, t) = f(x), \; v(x, t) = g(x), \; w(x, t) = h(x)$ . In this case, the variable $t$ has no effect on the solution of Eq (1.1).

4. Power-series solutions

Next, by way of the power-series method which is a very useful technique for treating partial differential equations ^[20], we will discuss cases 3.1–3.3.

4.1. Power-series solutions of Eq (3.1)

For Case $3.1$ , we assume that the power-series solution to Eq (3.1) is as follows

$\begin{eqnarray} && f(z) = \sum\limits_{n = 0}^\infty p_nz^n, \; g(z) = \sum\limits_{n = 0}^\infty q_nz^n, \; h(z) = \sum\limits_{n = 0}^\infty l_nz^n, \end{eqnarray}$

(4.1)

where the coefficients $p_n, \; q_n$ and $l_n$ are constants to be resolved.

Putting Eq (4.1) into Eq (3.1), we obtain

$\begin{eqnarray} && {}-\sum\limits_{n = 0}^\infty(n+1)p_{n+1}z^{n} = \sum\limits_{n = 0}^\infty p_{n}z^{n}-\sum\limits_{n = 0}^\infty\sum\limits_{k = 0}^n p_kp_{n-k}z^n-a\sum\limits_{n = 0}^\infty\sum\limits_{k = 0}^np_kl_{n-k}z^n, \\&&{}-\sum\limits_{n = 0}^\infty(n+1)q_{n+1}z^{n} = d[-\sum\limits_{n = 0}^\infty\sum\limits_{k = 0}^n(k+1)(n-k+1)p_{k+1}q_{n-k+1}z^n\\&&{}+\sum\limits_{n = 0}^\infty(n+1)(n+2)q_{n+2}z^n-\sum\limits_{n = 0}^\infty\sum\limits_{k = 0}^n(n-k+1)(n-k+2)p_kq_{n-k+2}z^n]\\&&+b\sum\limits_{n = 0}^\infty q_nz^{n}-b\sum\limits_{n = 0}^\infty\sum\limits_{k = 0}^nq_kq_{n-k}z^n, \\&&{} -\sum\limits_{n = 0}^\infty(n+1)l_{n+1}z^{n} = \sum\limits_{n = 0}^\infty (n+1)(n+2)l_{n+2}z^{n}+c(\sum\limits_{n = 0}^\infty q_nz^n-\sum\limits_{n = 0}^\infty l_nz^n). \end{eqnarray}$

(4.2)

Comparing the coefficients for Eq (4.2), we get

$\begin{eqnarray} &&{} p_1 = p_0(-1+p_0+al_0), \\&& q_2 = \frac{bq_0(q_0-1)+q_1(dp_1-1)}{2d(1-p_0)}, \\&&{} l_2 = \frac{1}{2}[c(l_0-q_0)-l_1]. \end{eqnarray}$

(4.3)

Generally, for $n\geq 1$ , we have

$\begin{eqnarray} && {} p_{n+1} = -\frac{1}{n+1}[p_n-\sum\limits_{k = 0}^np_k(p_{n-k}+al_{n-k})], \\&& {} q_{n+2} = \frac{1}{(n+1)(n+2)d(1-p_0)}\{(dp_1-1)(n+1)q_{n+1}-bq_n+b\sum\limits_{k = 0}^nq_kq_{n-k}\\&& \; \; \; \; \; \; \; \; \; \; +\sum\limits_{k = 1}^nd(n-k+1)[(k+1)p_{k+1}q_{n-k+1}+(n-k+2)p_kq_{n-k+2}]\}, \\&& {} l_{n+2} = \frac{1}{(n+1)(n+2)}[c(l_n-q_n)-(n+1)l_{n+1}]. \end{eqnarray}$

(4.4)

Given Eq (4.4), the coefficients $p_i(i\geq2), q_j$ and $l_j(j\geq3)$ of (4.1) can be obtained, i.e.,

$\begin{eqnarray} &&{} p_2 = -\frac{1}{2}[p_1-2p_0p_1-a(p_0l_1+p_1l_0)], \\ &&{} q_3 = \frac{1}{6d(1-p_0)}(4dp_1q_2+2bq_0q_1+2dp_2q_1-2q_2-bq_1), \\ &&{} l_3 = \frac{1}{6}[c(l_1-q_1)-2l_2]. \end{eqnarray}$

Therefore, for the arbitrary constants $p_0\neq1, q_0, l_0, q_1$ and $l_1$ , the other terms of the sequences $\{p_n, q_n, l_n\}_{n = 0}^\infty$ , according to Eqs (4.3) and (4.4), can be determined. This implies that there is a power-series solution, i.e., Eq (4.1) which has coefficients that are composed of Eqs (4.3) and (4.4).

Furthermore, for Eq (3.1), we confirm the convergence of Eq (4.1). In fact, from Eq (4.4), we get

$\begin{eqnarray} && {} |p_{n+1}|\leq M[|p_{n}|+\sum\limits_{k = 0}^n|p_k|(|p_{n-k}|+|l_{n-k}|)], \\&& {} |q_{n+2}|\leq N[|q_{n+1}|+|q_n|+\sum\limits_{k = 0}^n|q_k||q_{n-k}|+\sum\limits_{k = 1}^n(|p_{k+1}||q_{n-k+1}|+|p_k||q_{n-k+2}|)], \\&& {} |l_{n+2}|\leq L(|l_{n}|+|q_n|+|l_{n+1}|), \end{eqnarray}$

where $M = \mbox{max}\{1, a\}, \; N = \mbox{max}\{|\frac{dp_1-1}{d(1-p_0)}|, |\frac{b}{d(1-p_0)}|, |\frac{1}{1-p_0}|\}$ and $L = \mbox{max}\{1, c\}$ .

Next, we construct three power-series $R = R(z) = \sum_{n = 0}^\infty r_nz^n,$ $S = S(z) = \sum_{n = 0}^\infty s_nz^n$ and $T = T(z) = \sum_{n = 0}^\infty t_nz^n$ by using

$\begin{eqnarray} &&{} r_i = |p_i|, \; i = 0, 1, \\&&{} s_j = |q_j|, \; t_j = |l_j|, \; i = 0, 1, 2, \end{eqnarray}$

and

$\begin{eqnarray} && {} r_{n+1} = M[r_{n}+\sum\limits_{k = 0}^nr_k(r_{n-k}+t_{n-k})], \\&& {} s_{n+2} = N[s_{n+1}+s_n+\sum\limits_{k = 0}^ns_ks_{n-k}+\sum\limits_{k = 1}^n(r_{k+1}s_{n-k+1}+r_ks_{n-k+2})], \\&& {} t_{n+2} = L(t_{n}+s_n+t_{n+1}), \end{eqnarray}$

where $n = 1, 2, \cdots.$ It is easily seen that

$\begin{eqnarray} &&{} |p_n|{\leq}r_n, \; |q_n|{\leq}s_n, \; |l_n|{\leq}t_n, \; \; \; n = 0, 1, 2, \cdots. \end{eqnarray}$

Therefore, $R = R(z) = \sum_{n = 0}^\infty r_nz^n,$ $S = S(z) = \sum_{n = 0}^\infty s_nz^n$ and $T = T(z) = \sum_{n = 0}^\infty t_nz^n$ are majorant series of Eq (4.1) respectively. Next, we prove that $R = R(z), \; S = S(z)$ and $T = T(z)$ have a positive radius of convergence.

$\begin{array}{l} {} R(z) = r_0+r_1z+\sum\limits_{n = 1}^\infty r_{n+1}z^{n+1} = r_0+r_1z+M[\sum\limits_{n = 1}^\infty r_nz^{n+1} +\sum\limits_{n = 1}^\infty\sum\limits_{k = 0}^nr_k(r_{n-k}+t_{n-k})z^{n+1}] \\ \; \; \; \; \; \; = r_0+r_1z+M[(R-r_0)+(R^2-r_0^2)+r_0(T-t_0)+T(R-r_0)]z, \\ S(z) = s_0+s_1z+s_2z^2+\sum\limits_{n = 1}^\infty s_{n+2}z^{n+2} = s_0+s_1z+s_2z^2+N[\sum\limits_{n = 1}^\infty s_{n+1}z^{n+2}+\sum\limits_{n = 1}^\infty s_nz^{n+2}\\ \; \; \; \; \; \; \; \; \; \; +\sum\limits_{n = 1}^\infty\sum\limits_{k = 0}^ns_ks_{n-k}z^{n+2}+\sum\limits_{n = 1}^\infty\sum\limits_{k = 1}^nr_{k+1}s_{n-k+1}z^{n+2}+\sum\limits_{n = 1}^\infty\sum\limits_{k = 1}^nr_ks_{n-k+2}z^{n+2}] \\ \; \; \; \; \; \; = s_0+s_1z+s_2z^2+N[z(S-s_0-s_1z)+z^2(S-s_0)+z^2(S^2-s_0^2) \\ \; \; \; \; \; \; \; \; \; +(S-s_0)(R-r_0-r_1z)+(R-r_0)(S-s_0-s_1z)], \end{array}$

and

$\begin{eqnarray} &&{} T(z) = t_0+t_1z+t_2z^2+\sum\limits_{n = 1}^\infty t_{n+2}z^{n+2}\\&& \; \; \; \; \; \; = t_0+t_1z+t_2z^2+L[\sum\limits_{n = 1}^\infty t_nz^{n+2}+\sum\limits_{n = 1}^\infty s_nz^{n+2} +\sum\limits_{n = 1}^\infty t_{n+1}z^{n+2}] \\ &&\; \; \; \; \; \; = t_0+t_1z+t_2z^2+L[z^2(T-t_0)+z^2(S-s_0)+z(T-t_0-t_1z)]. \end{eqnarray}$

Then, we discuss the implicit functional system with the independent variable $z$ :

$\begin{eqnarray} &&{} F_1(z, R, S, T) = R-r_0-r_1z-M[(R-r_0)+(R^2-r_0^2)+r_0(T-t_0)+T(R-r_0)]z, \\&&{} F_2(z, R, S, T) = S-s_0-s_1z-s_2z^2-N[z(S-s_0-s_1z)+z^2(S-s_0)+z^2(S^2-s_0^2)\\&& \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; \; +(S-s_0)(R-r_0-r_1z)+(R-r_0)(S-s_0-s_1z)], \\&&{} F_3(z, R, S, T) = T-t_0-t_1z-t_2z^2-L[z^2(T-t_0)+z^2(S-s_0)+z(T-t_0-t_1z)]. \end{eqnarray}$

Based on the implicit function theorem ^[21], because $F_1, F_2$ and $F_3$ are analytic in the neighborhood of $(0, r_0, s_0, t_0)$ and $F_1(0, r_0, s_0, t_0) = F_2(0, r_0, s_0, t_0) = F_3(0, r_0, s_0, t_0) = 0$ , and given the Jacobian determinant

$\begin{eqnarray} &&{} \frac{\partial(F_1, F_2, F_3)}{\partial(R, S, T)}\mid_{(0, r_0, s_0, t_0)} = 1\neq0, \end{eqnarray}$

we reach that $R = R(z), \; S = S(z)$ and $T = T(z)$ are analytic in a neighborhood of the point $(0, r_0, s_0, t_0)$ and have a positive radius. This shows that Eq (4.1) converges in a neighborhood of the point $(0, r_0, s_0, t_0)$ . The proof is completed.

Thus the power-series solution given by Eq (4.1) for Eq (3.1) is analytic and can be described as

$\begin{eqnarray} &&{} f(z) = p_0+p_1z+\sum\limits_{n = 1}^\infty p_{n+1}z^{n+1}\\&&{} \; \; \; \; \; \; = p_0+p_0(-1+p_0+al_0)z-\sum\limits_{n = 1}^\infty\frac{1}{n+1}[p_n-\sum\limits_{k = 0}^np_k(p_{n-k}+al_{n-k})]z^{n+1}, \\&&{} g(z) = q_0+q_1z+q_2z^2+\sum\limits_{n = 1}^\infty q_{n+2}z^{n+2}\\&&{} \; \; \; \; \; \; = q_0+q_1z+\frac{bq_0(q_0-1)+q_1(dp_1-1)}{2d(1-p_0)}z^2\\&&{} \; \; \; \; \; \; \; \; \; \; +\sum\limits_{n = 1}^\infty\frac{1}{(n+1)(n+2)d(1-p_0)}\{(dp_1-1)(n+1)q_{n+1}-bq_n+b\sum\limits_{k = 0}^nq_kq_{n-k}\\&&{} \; \; \; \; \; \; \; \; \; \; +\sum\limits_{k = 1}^nd(n-k+1)[(k+1)p_{k+1}q_{n-k+1}+(n-k+2)p_kq_{n-k+2}]\}z^{n+2}, \\&&{} h(z) = l_0+l_1z+l_2z^2+\sum\limits_{n = 1}^\infty l_{n+2}z^{n+2}\\&&{} \; \; \; \; \; \; = l_0+l_1z+\frac{1}{2}[c(l_0-q_0)-l_1]z^2+\sum\limits_{n = 1}^\infty\frac{1}{(n+1)(n+2)}[c(l_n-q_n)-(n+1)l_{n+1}]z^{n+2}. \end{eqnarray}$

Moreover, the power-series solution of Eq (1.1) is

$\begin{eqnarray} &&{} u(x, t) = p_0+p_1(x-t)+\sum\limits_{n = 1}^\infty p_{n+1}(x-t)^{n+1}\\&&{} \; \; \; \; \; \; = p_0+p_0(-1+p_0+al_0)(x-t)-\sum\limits_{n = 1}^\infty\frac{1}{n+1}[p_n-\sum\limits_{k = 0}^np_k(p_{n-k}+al_{n-k})](x-t)^{n+1}, \\&&{} v(x, t) = q_0+q_1(x-t)+q_2(x-t)^2+\sum\limits_{n = 1}^\infty q_{n+2}(x-t)^{n+2}\\&&{} \; \; \; \; \; \; = q_0+q_1(x-t)+\frac{bq_0(q_0-1)+q_1(dp_1-1)}{2d(1-p_0)}(x-t)^2\\&&{} \; \; \; \; \; \; \; \; \; \; +\sum\limits_{n = 1}^\infty\frac{1}{(n+1)(n+2)d(1-p_0)}\{(dp_1-1)(n+1)q_{n+1}-bq_n+b\sum\limits_{k = 0}^nq_kq_{n-k}\\&& \; \; \; \; \; \; \; \; \; \; +\sum\limits_{k = 1}^nd(n-k+1)[(k+1)p_{k+1}q_{n-k+1}+(n-k+2)p_kq_{n-k+2}]\}(x-t)^{n+2}, \\&&{} w(x, t) = l_0+l_1(x-t)+l_2(x-t)^2+\sum\limits_{n = 1}^\infty l_{n+2}(x-t)^{n+2}\\&&{} \; \; \; \; \; \; \; \; \; = l_0+l_1(x-t)+\frac{1}{2}[c(l_0-q_0)-l_1](x-t)^2 \\&&{} \; \; \; \; \; \; \; \; \; \; \; \; \; +\sum\limits_{n = 1}^\infty\frac{1}{(n+1)(n+2)}[c(l_n-q_n)-(n+1)l_{n+1}](x-t)^{n+2}, \end{eqnarray}$

(4.5)

where $p_0\neq1, q_0, l_0, q_1$ and $l_1$ are arbitrary constants; the other terms $p_n, q_n$ and $l_n\; (n\geq2)$ can be provided according to Eqs (4.3) and (4.4).

4.2. Numerical simulation of power-series solutions of Eq (3.1)

We take the first six terms of Eq (4.5) as approximate to $u, v$ and $w$ for $a = 1.5, \; b = 1, \; c = 2, \; d = 4\times10^{-10}, \; p_0 = 0.5, \; q_0 = 3, \; l_0 = 5, \; q_1 = 4$ and $l_1 = 6$ . Then the approximation is depicted in Figure 1.

Figure 1. Power series-solution of Eq (4.5).

DownLoad: Full-Size Img PowerPoint

shows that the values of $u, v$ and $w$ tend to be stable when $x\in(0, 1)$ and $t\in(0, 1)$ . However, when $x\rightarrow0$ and $t\rightarrow1$ or $x\rightarrow1$ and $t\rightarrow0$ , $u$ and $w$ change suddenly in one direction and $v$ changes sharply in the other direction. The rate of change of $v$ is faster than that of $u$ , and that of $w$ is between them. This shows that healthy tissue may be destroyed before malignant cells arrive. Tumor progression is mediated by the acidification of surrounding tissues. Due to anaerobic glycolysis and metabolism, tumor cells produce excessive $H^+$ ions. This leads to local acidification, which then destroys the surrounding healthy tissue and promotes tumor invasion.

4.3. Power-series solutions of Eq (3.2)

For Case $3.2$ , similarly, we can also obtain the following power-series solution to Eq (1.1):

$\begin{eqnarray} &&{} u(x, t) = p_0+\sum\limits_{n = 0}^\infty p_{n+1}t^{n+1} = p_0+\sum\limits_{n = 0}^\infty\frac{1}{n+1}[p_n-\sum\limits_{k = 0}^np_k(p_{n-k}+al_{n-k})]t^{n+1}, \\&& v(x, t) = q_0+\sum\limits_{n = 0}^\infty q_{n+1}t^{n+1} = q_0+\sum\limits_{n = 0}^\infty\frac{b}{n+1}(q_n-\sum\limits_{k = 0}^nq_kq_{n-k})t^{n+1}, \\&&{} w(x, t) = l_0+\sum\limits_{n = 0}^\infty l_{n+1}t^{n+1} = l_0+\sum\limits_{n = 0}^\infty\frac{c}{n+1}(q_n-l_n)t^{n+1}, \end{eqnarray}$

(4.6)

where $p_0, q_0$ and $l_0$ are arbitrary constants.

4.4. Numerical simulation of Power-series solutions of Eq (3.2)

We get the first six terms of the power-series solutions of (4.6) as approximate to $u, v$ and $w$ for $a = 1.5, \; b = 1, \; c = 2, \; d = 4\times10^{-10}, \; p_0 = 0.5, \; q_0 = 3$ and $l_0 = 5$ respectively, then, the approximations of $u, v$ and $w$ are illustrated in Figure 2.

Figure 2. Power-series solution of Eq (4.6).

DownLoad: Full-Size Img PowerPoint

illustrates that, when $t\in(0, 1)$ , the values of $u, v$ and $w$ are stable first and mutate over time. When $u$ and $v$ decrease at the same time, $w$ increases. The rate of change of $u$ is the same as that of $v$ , and the rate of change of $w$ is slightly slower than them. This indicates that when healthy cells and cancer cells decrease at the same time, $H^+$ ions will increase. We find that $H^+$ ions are sensitive to changes in healthy cells and cancer cells.

4.5. Power-series solutions of Eq (3.3)

For Case $3.3$ , the power-series solution to Eq (1.1) is described as follows:

$\begin{eqnarray} &&{} u(x, t) = p_0+p_1x+\sum\limits_{n = 2}^\infty p_nx^n\\&&{} \; \; \; \; \; \; \; \; = p_0+\frac{ap_0l_1}{1-2p_0-al_0}x+\sum\limits_{n = 2}^\infty\frac{ap_0l_n+\sum\limits_{k = 1}^{n-1} p_k(p_{n-k}+al_{n-k})}{1-2p_0-al_0}x^n, \\&&{} v(x, t) = q_0+q_1x+q_2x^2+\sum\limits_{n = 1}^\infty q_{n+2}x^{n+2} = q_0+q_1x+\frac{dp_1q_1-bq_0(1-q_0)}{2d(1-p_0)}x^2\\&&{} \; \; \; \; \; \; \; \; \; \; \; +\sum\limits_{n = 1}^\infty\frac{1}{(n+1)(n+2)d(1-p_0)}\{d[(n+1)p_1q_{n+1}+\sum\limits_{k = 1}^n(n-k+1)((k+1)p_{k+1}q_{n-k+1}\\&& \; \; \; \; \; \; \; \; \; \; +(n-k+2)p_kq_{n-k+2})]-b(q_n-\sum\limits_{k = 0}^nq_kq_{n-k})\}x^{n+2}, \\&&{} w(x, t) = l_0+l_1x+\sum\limits_{n = 0}^\infty l_{n+2}x^{n+2} = l_0+l_1x+\sum\limits_{n = 0}^\infty \frac{c(l_n-q_n)}{(n+1)(n+2)}x^{n+2}, \end{eqnarray}$

(4.7)

where $p_0, l_0, q_0, q_1$ and $l_1$ are arbitrary constants and that satisfy $1-2p_0-al_0\neq0$ and $1-p_0\neq0$ .

4.6. Numerical simulation of power-series solutions of Eq (3.3)

We acquire the first six terms of the power-series solutions of Eq (4.7) as approximate to $u, v$ and $w$ for $a = 0.1, \; b = 1, \; c = 2, \; d = 4\times10^{-10}, \; p_0 = 0.5, \; q_0 = 3, \; l_0 = 5, \; q_1 = 4$ and $l_1 = 6$ respectively; then, the approximations of $u, v$ and $w$ are portrayed in Figure 3.

Figure 3. Power-series solution of Eq (4.7).

DownLoad: Full-Size Img PowerPoint

shows that, when $x\in(0, 1)$ , the values of $u, v$ and $w$ are initially stable and mutate in the same direction. The rate of change of $v$ is the fastest, and the rates of change of $u$ and $w$ are basically the same. It describes that cancer cells decline faster than healthy cells. This shows a process of complete destruction of healthy tissue after tumor tissue invasion.

Remark 4.1. For Case $3.2$ and Case $3.3$ , the proofs of convergence of the power series solutions are similar to that for Case $3.1$ . The details have been omitted here.

5. Conclusions

In this study, we applied the Lie group analysis method to an acid-mediated cancer invasion model. An important feature of this model is that tumor progression is mediated by acidification of the surrounding tissue. Especially, the model presumes that an excess of $H^+$ ions is produced by tumor cells as a consequence of their anaerobic, glycolytic metabolism. Based on this method, the symmetries and reduced equations of Eq (1.1) were derived. Furthermore, explicit solutions of the reduced equations were obtained using the power-series method. Finally, this paper also demonstrates the stability behavior of the model for different parameters as achieved through the use of graphical analysis. In this way, we have found that $H^+$ is decreased ahead of the advancing tumor front. Moreover, for certain parameter values, healthy tissue could be destroyed prior to the arrival of malignant cells. In the future, we can use this method to solve more tumor-related mathematical problems.

Acknowledgments

This research was supported by the Natural Science Foundation of Shanxi (No. 202103021224068).

Conflict of interest

The authors declare that they have no competing interests.

References

[1]	B. S. Everitt, A finite mixture model for the clustering of mixed-mode data, Stat. Probabil. Lett., 6 (1988), 305-309. https://doi.org/10.1016/0167-7152(88)90004-1 doi: 10.1016/0167-7152(88)90004-1
[2]	B. G. Lindsay, Mixture models: Theory, geometry and applications. In: NSF-CBMS regional conference series in probability and statistics (pp. i-163), Institute of Mathematical Statistics and the American Statistical Association, 1995, January. https://doi.org/10.1214/cbms/1462106013
[3]	G. J. McLachlan, K. E. Basford, Mixture models: Inference and applications to clustering, New York: M. Dekker, 38 (1988). https://doi.org/10.2307/2348072
[4]	G. McLachlan, D. Peel, Finite Mixture Models, John Wiley & Sons: New York, 2000. https://doi.org/10.1002/0471721182
[5]	J. Q. Shi, R. Murray-Smith, D. M. Titterington, Bayesian regression and classification using mixtures of Gaussian processes, Int. J. Adapt. Control., 17 (2003), 149-161. https://doi.org/10.1002/acs.744 doi: 10.1002/acs.744
[6]	D. Mohammad, A. Muhammad, On the Mixture of BurrXⅡ and Weibull Distribution, J. Sta. Appl. Pro, 3 (2014), 251-267. https://doi.org/10.12785/jsap/030215 doi: 10.12785/jsap/030215
[7]	K. S. Sultan, M. A. Ismail, A. S. Al-Moisheer, Mixture of two inverse Weibull distributions: Properties and estimation, Comput. Stat. Data An., 51 (2007), 5377-5387. https://doi.org/10.1016/j.csda.2006.09.016 doi: 10.1016/j.csda.2006.09.016
[8]	R. Jiang, D. N. P. Murthy, P. Ji, Models involving two inverse Weibull distributions, Reliab. Eng. Syst. Safe., 73 (2001), 73-81. https://doi.org/10.1016/S0951-8320(01)00030-8 doi: 10.1016/S0951-8320(01)00030-8
[9]	A. Mohammadi, A. M. R. Salehi-Rad, E. C. Wit, Using mixture of Gamma distributions for Bayesian analysis in an M/G/1 queue with optional second service, Computation. Stat., 28 (2013), 683-700. https://doi.org/10.1007/s00180-012-0323-3 doi: 10.1007/s00180-012-0323-3
[10]	S. F. Ateya, Maximum likelihood estimation under a finite mixture of generalized exponential distributions based on censored data, Stat. Pap., 55 (2014), 311-325. https://doi.org/10.1007/s00362-012-0480-z doi: 10.1007/s00362-012-0480-z
[11]	M. M. Mohamed, E. Saleh, S. M. Helmy, Bayesian prediction under a finite mixture of generalized exponential lifetime model, Pak. J. Stat. Oper. Res., (2014), 417-433. https://doi.org/10.18187/pjsor.v10i4.620 doi: 10.18187/pjsor.v10i4.620
[12]	T. N. Sindhu, M. Aslam, Preference of prior for Bayesian analysis of the mixed Burr type X distribution under type Ⅰ censored samples, Pak. J. Stat. Oper. Res., (2014), 17-39. https://doi.org/10.18187/pjsor.v10i1.649 doi: 10.18187/pjsor.v10i1.649
[13]	H. Zhang, Y. Huang, Finite mixture models and their applications: A review, Austin Biom. Biostat., 2 (2015), 1-6.
[14]	T. N. Sindhu, M. Riaz, M. Aslam, Z. Ahmed, Bayes estimation of Gumbel mixture models with industrial applications, T. I. Meas. Control, 38 (2016), 201-214. https://doi.org/10.1177/0142331215578690 doi: 10.1177/0142331215578690
[15]	T. N. Sindhu, M. Aslam, Z. Hussain, A simulation study of parameters for the censored shifted Gompertz mixture distribution: A Bayesian approach, J. Stat. Manag. Syst., 19 (2016), 423-450. https://doi.org/10.1080/09720510.2015.1103462 doi: 10.1080/09720510.2015.1103462
[16]	T. N. Sindhu, N. Feroze, M. Aslam, A. Shafiq, Bayesian inference of mixture of two Rayleigh distributions: A new look, Punjab Univ. J. Math., 48 (2020).
[17]	T. N. Sindhu, H. M. Khan, Z. Hussain, B. Al-Zahrani, Bayesian inference from the mixture of half-normal distributions under censoring, J. Natl. Sci. Found. Sri., 46 (2018), 587-600. https://doi.org/10.4038/jnsfsr.v46i4.8633 doi: 10.4038/jnsfsr.v46i4.8633
[18]	T. N. Sindhu, Z. Hussain, M. Aslam, Parameter and reliability estimation of inverted Maxwell mixture model, J. Stat. Manag. Syst., 22 (2019), 459-493. https://doi.org/10.1080/09720510.2018.1552412 doi: 10.1080/09720510.2018.1552412
[19]	S. Ali, Mixture of the inverse Rayleigh distribution: Properties and estimation in a Bayesian framework, Appl. Math. Modell., 39 (2015), 515-530. https://doi.org/10.1016/j.apm.2014.05.039 doi: 10.1016/j.apm.2014.05.039
[20]	H. Zakerzadeh, A. Dolati, Generalized Lindley distribution, J. Math. Ext., 3 (2009), 1-17.
[21]	B. O. Oluyede, T. Yang, A new class of generalized Lindley distributions with applications, J. Stat. Comput. Sim., 85 (2015), 2072-2100. https://doi.org/10.1080/00949655.2014.917308 doi: 10.1080/00949655.2014.917308
[22]	S. Nadarajah, H. S. Bakouch, R. Tahmasbi, A generalized Lindley distribution, Sankhya B, 73 (2011), 331-359. https://doi.org/10.1007/s13571-011-0025-9 doi: 10.1007/s13571-011-0025-9
[23]	D. V. Lindley, Bayesian statistics: A review, Society for industrial and applied mathematics, New York, United States, 1972. https://doi.org/10.1137/1.9781611970654.ch1
[24]	M. E. Ghitany, B. Atieh, S. Nadarajah, Lindley distribution and its application, Math. Comput. Simulat., 78 (2008), 493-506. https://doi.org/10.1016/j.matcom.2007.06.007 doi: 10.1016/j.matcom.2007.06.007
[25]	R. Shanker, F. Hagos, S. Sujatha, On modeling of Lifetimes data using exponential and Lindley distributions, Biometrics Biostatistics Int. J., 2 (2015), 1-9. https://doi.org/10.15406/bbij.2015.02.00042 doi: 10.15406/bbij.2015.02.00042
[26]	J. Mazucheli, J. A. Achcar, The Lindley distribution applied to competing risks lifetime data, Comput. Meth. Prog. Bio., 104 (2011), 188-192. https://doi.org/10.1016/j.cmpb.2011.03.006 doi: 10.1016/j.cmpb.2011.03.006
[27]	D. K. Al-Mutairi, M. E. Ghitany, D. Kundu, Inferences on stress-strength reliability from Lindley distributions, Commun. Stat.-Theory M., 42 (2013), 1443-1463. https://doi.org/10.1080/03610926.2011.563011 doi: 10.1080/03610926.2011.563011
[28]	M. A. E. Damsesy, M. M. El Genidy, A. M. El Gazar, Reliability and failure rate of the electronic system by using mixture Lindley distribution, J. Appl. Sci., 15 (2015), 524-530. https://doi.org/10.3923/jas.2015.524.530 doi: 10.3923/jas.2015.524.530
[29]	A. H. Khan, T. R. Jan, Estimation of stress-strength reliability model using finite mixture of two parameter Lindley distributions, J. Stat. Appl. Probab., 4 (2015), 147-159.
[30]	A. S. Al-Moisheer, A. F. Daghestani, K. S. Sultan, Mixture of two one-parameter Lindley distributions: properties and estimation, J. Stat. Theory Pract., 15 (2021), 1-21. https://doi.org/10.1007/s42519-020-00133-4 doi: 10.1007/s42519-020-00133-4
[31]	S. Dey, D. Kumar, P. L. Ramos, F. Louzada, Exponentiated Chen distribution: properties and estimation, Comm. Stat. Simul. C., 46 (2017), 8118-8139. https://doi.org/10.1080/03610918.2016.1267752 doi: 10.1080/03610918.2016.1267752
[32]	S. Dey, A. Alzaatreh, C. Zhang, D. Kumar, A new extension of generalized exponential distribution with application to ozone data, Ozone Sci. Eng., 39 (2017), 273-285. https://doi.org/10.1080/01919512.2017.1308817 doi: 10.1080/01919512.2017.1308817
[33]	G. C. Rodrigues, F. Louzada, P. L. Ramos, Poisson exponential distribution: different methods of estimation, J. Appl. Stat., 45 (2018), 128-144. https://doi.org/10.1080/02664763.2016.1268571 doi: 10.1080/02664763.2016.1268571
[34]	S. Dey, F. A. Moala, D. Kumar, Statistical properties and different methods of estimation of Gompertz distribution with application. J. Stat. Manag. Syst., 21 (2018), 839-876. https://doi.org/10.1080/09720510.2018.1450197 doi: 10.1080/09720510.2018.1450197
[35]	S. Dey, M. J. Josmar, S. Nadarajah, Kumaraswamy distribution: different methods of estimation, Comput. Appl. Math., 37 (2018), 2094-2111. https://doi.org/10.1007/s40314-017-0441-1 doi: 10.1007/s40314-017-0441-1
[36]	J. J. Swain, S. Venkatraman, J. R. Wilson, Least-squares estimation of distribution functions in Johnson's translation system, J. Stat. Comput. Sim., 29 (1988), 271-297. https://doi.org/10.1080/00949658808811068 doi: 10.1080/00949658808811068
[37]	R. D. Gupta, D. Kundu, Generalized exponential distribution: different method of estimations, J. Stat. Comput. Sim., 69 (2001), 315-337. https://doi.org/10.1080/00949650108812098 doi: 10.1080/00949650108812098
[38]	T. N. Sindhu, A. Shafiq, Q. M. Al-Mdallal, On the analysis of number of deaths due to Covid- 19 outbreak data using a new class of distributions, Results Phys., 21 (2021), 103747. https://doi.org/10.1016/j.rinp.2020.103747 doi: 10.1016/j.rinp.2020.103747
[39]	T. N. Sindhu, A. Shafiq, Q. M. Al-Mdallal, Exponentiated transformation of Gumbel Type-Ⅱ distribution for modeling COVID-19 data, Alex. Eng. J., 60 (2021), 671-689. https://doi.org/10.1016/j.aej.2020.09.060 doi: 10.1016/j.aej.2020.09.060
[40]	A. Shafiq, S. A. Lone, T. N. Sindhu, Q. M. Al-Mdallal, T. Muhammad, A New Modified Kies Fréchet Distribution: Applications of Mortality Rate of Covid-19, Results Phys., (2021), 104638. https://doi.org/10.1016/j.rinp.2021.104638 doi: 10.1016/j.rinp.2021.104638
[41]	S. A. Lone, T. N. Sindhu, F. Jarad, Additive Trinomial Fréchet distribution with practical application, Results Phys., (2021), 105087. https://doi.org/10.1016/j.rinp.2021.105087 doi: 10.1016/j.rinp.2021.105087
[42]	S. A. Lone, T. N. Sindhu, A. Shafiq, F. Jarad, A novel extended Gumbel Type Ⅱ model with statistical inference and Covid-19 applications, Results Phys., 35 (2022), 105377. https://doi.org/10.1016/j.rinp.2022.105377 doi: 10.1016/j.rinp.2022.105377
[43]	A. Shafiq, T. N. Sindhu, N. Alotaibi, A novel extended model with versatile shaped failure rate: Statistical inference with Covid-19 applications, Results Phys., 2022. https://doi.org/10.1016/j.rinp.2022.105398 https://doi.org/10.1016/j.rinp.2022.105398 doi: 10.1016/j.rinp.2022.105398DOI:10.1016/j.rinp.2022.105398
[44]	X. Liu, Z. Ahmad, A. M. Gemeay, A. T. Abdulrahman, E. H. Hafez, N. Khalil, Modeling the survival times of the COVID-19 patients with a new statistical model: A case study from China, Plos one, 16 (2021), e0254999. https://doi.org/10.1371/journal.pone.0254999 doi: 10.1371/journal.pone.0254999

This article has been cited by:

Bing Tan, Wei Ma, Structured backward errors for block three-by-three saddle point systems with Hermitian and sparsity block matrices, 2025, 25, 25900374, 100546, 10.1016/j.rinam.2025.100546

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)