The generalized scale mixtures of asymmetric generalized normal distributions with application to stock data

Ruijie Guan; Aidi Liu; Weihu Cheng; Ruijie Guan; Aidi Liu; Weihu Cheng

doi:10.3934/math.2024064

AIMS Mathematics

2024, Volume 9, Issue 1: 1291-1322. doi: 10.3934/math.2024064

Previous Article Next Article

Research article

The generalized scale mixtures of asymmetric generalized normal distributions with application to stock data

Faculty of Science, Beijing University of Technology, Beijing 100124, China

Received: 11 August 2023 Revised: 23 November 2023 Accepted: 30 November 2023 Published: 07 December 2023
MSC : 62E15, 62F10, 62G30, 62P05

In this paper, we introduced a family of distributions with a very flexible shape named generalized scale mixtures of generalized asymmetric normal distributions (GSMAGN). We investigated the main properties of the new family including moments, skewness, kurtosis coefﬁcients and order statistics. A variant of the expectation maximization (EM)-type algorithm was established by combining the proflie likihood approach (PLA) with the classical expectation conditional maximization (ECM) algorithm for parameter estimation of this model. This approach with analytical expressions in the E-step and tractable M-step can greatly improve the computational speed and efficiency of the algorithm. The performance of the proposed algorithm was assessed by some simulation studies. The feasibility of the proposed methodology was illustrated through two real datasets.

Keywords:

generalized asymmetric normal distribution,
generalized scale mixtures,
EM-type algorithm,
order statistics

Citation: Ruijie Guan, Aidi Liu, Weihu Cheng. The generalized scale mixtures of asymmetric generalized normal distributions with application to stock data[J]. AIMS Mathematics, 2024, 9(1): 1291-1322. doi: 10.3934/math.2024064

Related Papers:

[1]	Cuiying Li, Rui Wu, Ranzhuo Ma . Existence of solutions for Caputo fractional iterative equations under several boundary value conditions. AIMS Mathematics, 2023, 8(1): 317-339. doi: 10.3934/math.2023015
[2]	Ahmed Alsaedi, Fawziah M. Alotaibi, Bashir Ahmad . Analysis of nonlinear coupled Caputo fractional differential equations with boundary conditions in terms of sum and difference of the governing functions. AIMS Mathematics, 2022, 7(5): 8314-8329. doi: 10.3934/math.2022463
[3]	Murat A. Sultanov, Vladimir E. Misilov, Makhmud A. Sadybekov . Numerical method for solving the subdiffusion differential equation with nonlocal boundary conditions. AIMS Mathematics, 2024, 9(12): 36385-36404. doi: 10.3934/math.20241726
[4]	Naimi Abdellouahab, Keltum Bouhali, Loay Alkhalifa, Khaled Zennir . Existence and stability analysis of a problem of the Caputo fractional derivative with mixed conditions. AIMS Mathematics, 2025, 10(3): 6805-6826. doi: 10.3934/math.2025312
[5]	Xinwei Su, Shuqin Zhang, Lixin Zhang . Periodic boundary value problem involving sequential fractional derivatives in Banach space. AIMS Mathematics, 2020, 5(6): 7510-7530. doi: 10.3934/math.2020481
[6]	Ayub Samadi, Chaiyod Kamthorncharoen, Sotiris K. Ntouyas, Jessada Tariboon . Mixed Erdélyi-Kober and Caputo fractional differential equations with nonlocal non-separated boundary conditions. AIMS Mathematics, 2024, 9(11): 32904-32920. doi: 10.3934/math.20241574
[7]	Karim Guida, Lahcen Ibnelazyz, Khalid Hilal, Said Melliani . Existence and uniqueness results for sequential $\psi$ -Hilfer fractional pantograph differential equations with mixed nonlocal boundary conditions. AIMS Mathematics, 2021, 6(8): 8239-8255. doi: 10.3934/math.2021477
[8]	Nichaphat Patanarapeelert, Thanin Sitthiwiratthame . On nonlocal fractional symmetric Hanh integral boundary value problems for fractional symmetric Hahn integrodifference equation. AIMS Mathematics, 2020, 5(4): 3556-3572. doi: 10.3934/math.2020231
[9]	Abdelkader Amara . Existence results for hybrid fractional differential equations with three-point boundary conditions. AIMS Mathematics, 2020, 5(2): 1074-1088. doi: 10.3934/math.2020075
[10]	Yige Zhao, Yibing Sun, Zhi Liu, Yilin Wang . Solvability for boundary value problems of nonlinear fractional differential equations with mixed perturbations of the second type. AIMS Mathematics, 2020, 5(1): 557-567. doi: 10.3934/math.2020037

Abstract

1. Introduction

In graph theory, graph labeling is an assignment of labels or weights to the vertices and edges of a graph. Graph labeling plays an important role in many fields such as computer science, coding theory and physics ^[32]. Baca et al. ^[10] have introduced the definition of an edge irregular total $\ell$ -labeling of any graph as a labeling $\mathcal{L}:V \cup E\to \left\{\mathrm{1, 2}, 3, \dots, \ell\right\}$ in which every two distinct edges $fh$ and ${f}^{*}{h}^{*}$ of a graph $G$ have distinct weights, this means that ${w}_{\mathcal{L}}\left(fh\right)\ne {w}_{\mathcal{L}}\left({f}^{*}{h}^{*}\right)$ where ${w}_{\mathcal{L}}\left(fh\right) = \mathcal{L}\left(f\right)+\mathcal{L}\left(h\right)+\mathcal{L}\left(fh\right)$ . They have deduced inequality which gives a lower bound of $tes\left(G\right)$ for a graph $G$ ,

$tes\left(G\right)\ge max\left\{\left\lceil {\frac{\left|E\left(G\right)\right|+2}{3}} \right\rceil , \left\lceil {\frac{\Delta +1}{2}} \right\rceil \right\}$

(1)

Also, they have introduced the exact value of TEIS, $tes\left(G\right)$ for some families of graphs like fan graph ${F}_{n}$ and wheel graph ${W}_{n}$ ,

$tes\left({F}_{n}\right) = \left\lceil {\frac{3n+2}{3}} \right\rceil \text{, }$

$tes\left({W}_{n}\right) = \left\lceil {\frac{2n+2}{3}} \right\rceil \text{.}$

In ^[15] authors have proved that for any tree $T$

$tes\left(T\right) = max\left\{\left\lceil {\frac{k+1}{3}} \right\rceil , \left\lceil {\frac{\Delta +1}{2}} \right\rceil \right\},$

where $\Delta$ is maximum degree on $k$ vertices. In addition, Salama ^[26] investigated the exact value of TEIS for a polar grid graph,

$tes\left({P}_{m, n}\right) = \left\lceil {\frac{2mn+2}{3}} \right\rceil \text{.}$

Authors in ^[1] determined $\mathrm{T}\mathrm{E}\mathrm{I}\mathrm{S}$ for zigzag graphs. Also, the exact value of TEIS of the generalized web graph ${W}_{n, m}$ and some families has been determined, see ^[14]. Tilukay et al. ^[31] have investigated total irregularity strength for a wheel graph, a fan graph, a triangular Book graph and a friendship graph. On the other hand, in ^{[2,3,8,17,20,24,29]} the total edge irregularity strengths for hexagonal grid graphs, centralized uniform theta graphs, generalized helm graph, series parallel graphs, disjoint union of isomorphic copies of generalized Petersen graph, disjoint union of wheel graphs, subdivision of star ${S}_{n}$ and categorical product of two cycles have been investigated. For more details, see ^{[4,5,6,7,9,11,12,13,16,18,19,21,23,25,27,28,30]}.

A generalized theta graph $\theta ({t}_{1}, {t}_{2}, \dots, {t}_{n})$ is a pair of $n$ internal disjoint paths with lengths at least two joined by end vertices where the end vertices are named south pole $S$ and north pole $N$ and ${t}_{i}$ is the number of vertices in the nth path. Uniform theta graph $\theta (t, m)$ is a generalized theta graph in which all paths have the same numbers of internal vertices, for more details see ^[22].

In this paper, we have defined a new type of family of graph called uniform theta snake graph, ${\theta }_{n}(t, m)$ . Also, the exact value of TEIS for some special types of the new family has been determined.

2. Main results

In the following, we define a new type of graph which is called uniform theta snake graph.

Definition 1. If we replace each edge of a path ${P}_{n}$ by a uniform theta graph $\theta (t, m)$ , we have a uniform theta snake graph ${\theta }_{n}(t, m)$ . See Figure 1.

Figure 1. Uniform theta snake graph θ(t, m).

DownLoad: Full-Size Img PowerPoint

It is clear that for a uniform theta snake graph $\left|\mathrm{E}\left({\mathtt{θ }}_{\mathrm{n}}\right(\mathrm{t}, \mathrm{m}\left)\right)\right| = \mathrm{t}\left(\mathrm{m}+1\right)\mathrm{n}$ and $\left|\mathrm{V}\left({\mathtt{θ }}_{\mathrm{n}}\right(\mathrm{t}, \mathrm{m}\left)\right)\right| = \left(\mathrm{t}\mathrm{m}+1\right)\mathrm{n}+1$ . In this section, we determine the exact value of TEIS for uniform theta snake graph ${\mathtt{θ }}_{\mathrm{n}}\left(\mathrm{3, 3}\right)$ , ${\mathtt{θ }}_{\mathrm{n}}\left(3, \mathrm{m}\right)$ , ${\mathtt{θ }}_{\mathrm{n}}(\mathrm{t}, 3)$ , ${\mathtt{θ }}_{\mathrm{n}}\left(4, \mathrm{m}\right)$ , and ${\mathtt{θ }}_{\mathrm{n}}(\mathrm{t}, 4)$ .

Theorem 1. For a uniform theta snake graph ${\theta }_{n}\left(\mathrm{3, 3}\right)$ with 10 $n+1$ vertices and 12 $n$ edges, we have

$tes\left({\theta }_{n}\left(\mathrm{3, 3}\right)\right) = 4n+1\text{.}$

Proof. Since a uniform theta snake graph ${\theta }_{n}\left(\mathrm{3, 3}\right)$ has 12 $n$ edges and $\left({\theta }_{n}\left(\mathrm{3, 3}\right)\right) = 6$ , then from (1) we have:

$tes\left({\theta }_{n}\left(\mathrm{3, 3}\right)\right)\ge 4n+1\text{.}$

To prove the invers inequality, we show that $ħ-$ labeling is an edge irregular total for ${\theta }_{n}\left(\mathrm{3, 3}\right)$ , see , and $ħ = 4n+1$ . Let $ħ = 4n+1$ and a total $ħ-$ labeling $\alpha :V{(\theta }_{n}\left(\mathrm{3, 3}\right)) \cup E({\theta }_{n}\left(\mathrm{3, 3}\right))\to \left\{\mathrm{1, 2}, 3, \dots, \mathrm{ħ}\right\}$ is defined as:

Figure 2. Uniform theta snake graph θ(3, 3).

DownLoad: Full-Size Img PowerPoint

$\mathtt{α }\left({\mathrm{c}}_{0}\right) = 1,$

$\mathtt{α }\left({\mathrm{c}}_{\mathrm{s}}\right) = 4\mathrm{s}\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\mathrm{ }\;\mathrm{f}\mathrm{o}\mathrm{r}\;\mathrm{ }1\le \mathrm{s}\le \mathrm{n}-1$

$\mathtt{α }\left({\mathrm{c}}_{\mathrm{n}}\right) = \mathrm{ħ},$

$\alpha \left({x}_{i, j}\right) = \left\{\begin{array}{cc}j& for\;1\le j\le 3\\ j+1& for\;4\le j\le 6\\ .& .\\ .& .\\ j+n-1& for\;3n-2\le j\le 3n-1\end{array}, i = 1, \mathrm{ }2, \mathrm{ }3\right.\text{, }$

$\alpha \left({x}_{i, 3n}\right) = ħ-1 \; for\; i = 1, 2, 3$

$\alpha \left({c}_{0}{x}_{i, 1}\right) = i \; for\; i = i1, 2, 3$

$\alpha \left({c}_{S}{x}_{i, 3S}\right) = 4S+i \; for\; 1\le S\le n-1, i = 1, 2, 3$

$\alpha \left({c}_{S}{x}_{i, 3S+1}\right) = 4S+i+1 \; for\; 1\le S\le n-1, i = 1, 2, 3$

$\alpha \left({c}_{n}{x}_{i, 3n}\right) = \left\{\begin{array}{cc}ħ-2& for\; i = 1\\ ħ-1& for\; i = 2\\ ħ& for\; i = 3\end{array}\right.\text{, }$

$\alpha \left({{x}_{i, j}x}_{i, j+1i}\right) = \left\{\begin{array}{cc}j+i+1& for\; 1\le j\le 2\\ j+i+2& for\; 4\le j\le 5\\ .& .\\ .& .\\ j+i+n-\mathrm{I}1& for\; 3n-5\le j\le 3n-4\\ ħ+i-3& for\; 3n-2\le j\le 3n-1\end{array}, i = 1, 2, 3\right..$

It is clear that $ħ$ is the greatest used label. The weights of edges of ${\theta }_{n}\left(\mathrm{3, 3}\right)$ are given by:

${w}_{\alpha }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, 3\text{, }$

${w}_{\alpha }\left({c}_{S}{x}_{i, 3S}\right) = 12S+i-1 \; for\; 1\le S\le n-1 , i = 1, 2, 3$

${w}_{\alpha }\left({c}_{S}{x}_{i, 3S+1}\right) = 12S+i+2\; for\; 1\le S\le n-1, i = 1, 2, 3,$

${w}_{\alpha }\left({c}_{n}{x}_{i, 3n}\right) = \left\{\begin{array}{cc}3\left(ħ-1\right)& for\; i = 1\\ 3ħ-2& for\; i = 2\\ 3ħ-1& for\; i = 3\end{array}\right.\text{, }$

${w}_{\alpha }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}3j+i+2& for\; 1\le j\le 2\\ 3j+i+5& for\; 4\le j\le 5\\ .& .\\ .& .\\ 3j+i+3n-4& for\; 3n-5\le j\le 3n-4\\ 3ħ+i-10& for\; j = 3n-2\\ 3ħ+i-7& for\; j = 3n-1\end{array}, i = 1, 2, 3\right.$

Obviously, the weights of edges are distinct. So $\alpha$ is an edge irregular total $\mathrm{ħ}-$ labeling. Hence

$tes\left({\theta }_{n}\left(\mathrm{3, 3}\right)\right) = 4n+1\text{.}$

Theorem 2. For ${\theta }_{n}\left(3, m\right), m>3$ be a uniform theta snake graph. Then

$tes\left({\theta }_{n}(3, m)\right) = (m+1)n+1\text{.}$

Proof. Since $\left|E\left({\theta }_{n}\right(3, m\left)\right)\right| = 3\left(m+1\right)n$ and $\Delta \left({\theta }_{n}\right(3, m\left)\right) = 6$ . Substituting in (1), we find

$tes\left({\theta }_{n}(3, m)\right)\ge (m+1)n+1\text{.}$

The existence of an edge irregular total $ƛ-$ labeling for ${\theta }_{n}(3, m)$ , See , $m>3$ will be shown, with $ƛ = (m+1)n+1$ . Define a total $ƛ-$ labeling $\beta :V\left({\theta }_{n}(3, m)\right)\cup E\left({\theta }_{n}(3, m)\right)\to \left\{\mathrm{1, 2}, 3, \dots, ƛ\right\}$ for ${\theta }_{n}(3, m)$ as:

Figure 3. Uniform theta snake graph θ(3, m).

DownLoad: Full-Size Img PowerPoint

$\beta \left({c}_{0}\right) = 1,$

$\beta \left({c}_{s}\right) = (m+1)s \; for\; 1\le s\le n-1\text{, }$

$\beta \left({c}_{n}\right) = ƛ$

$\beta \left({x}_{i, j}\right) = \left\{\begin{array}{cc}j& for\; 1\le j\le m\\ j+1& for\; m+1\le j\le 2m\\ .& .\\ .& .\\ j+n-1& for\; m\left(n-1\right)+1\le j\le mn-1\end{array}\right.\text{, }$

$\beta \left({x}_{i, mn}\right) = ƛ-1 \; for\; i = 1, 2, 3$

$\beta \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, 3$

$\beta \left({c}_{S}{x}_{i, mS}\right) = (m+1)S+i \; for\; 1\le S\le n-1, i = 1, 2, 3$

$\beta \left({c}_{S}{x}_{i, mS+1}\right) = (m+1)S+i+1 \; for\; 1\le S\le n-1, i = 1, 2, 3$

$\beta \left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}ƛ-2& for\; i = 1\\ ƛ-1& for\; i = 2\\ ƛ& for\; i = 3\end{array}\right.\text{, }$

$\beta \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}j+i+1& for\; 1\le j\le m-1\\ j+i+2& for\; m+1\le j\le 2m-1\\ .& .\\ .& .\\ j+i+n& for\; m\left(n-1\right)+1\le j\le mn-2\\ j+i+n-1& for\; j = mn-1\end{array}.\right.$

Clearly, $ƛ$ is the most label of edges and vertices. The edges weights are given as follows:

${w}_{\beta }\left({c}_{0}{x}_{i, 1}\right) = i+2\; for\; i = 1, 2, 3\text{, }$

${w}_{\beta }\left({c}_{S}{x}_{i, mS}\right) = 3\left(m+1\right)S+i-1 \; for\; 1\le S\le n-1, i = 1, 2, 3$

${w}_{\beta }\left({c}_{S}{x}_{i, mS+1}\right) = 3\left(m+1\right)S+i+2 \; for\; 1\le S\le n-1, i = 1, 2, 3\text{, }$

${w}_{\beta }\left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}3ƛ-3& for\; i = 1\\ 3ƛ-2& for\; i = 2\\ 3ƛ-1& for\; i = 3\end{array}\right.\text{, }$

${w}_{\beta }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}3j+i+2& for\; 1\le j\le m-1\\ 3j+i+5& for\; m+1\le j\le 2m-1\\ .& .\\ .& .\\ 3j\mathrm{I}+i+3n-1& for\; m\left(n-1\right)+1\le j\le mn-2\\ 3ƛ+i-7& for\; j = mn-1\end{array}, \right.$

It is obvious that the weights of edges are different, thus $\beta$ is an edge irregular total $ƛ-$ labeling of ${\theta }_{n}(3, m)$ . Hence

$tes\left({\theta }_{n}(3, m)\right) = (m+1)n+1\text{.}$

Theorem 3. Let ${\theta }_{n}\left(t, 3\right)$ be a theta snake graph for $t>3$ . Then

$tes\left({\theta }_{n}(t, 3)\right) = \left\lceil {\frac{4tn+2}{3}} \right\rceil \text{.}$

Proof. A size of the graph ${\theta }_{n}(t, 3)$ equals $4tn$ and $\Delta \left({\theta }_{n}\left(t, 3\right)\right) = 2t$ , then from (1) we have

$tes\left({\theta }_{n}(t, 3)\right)\ge \left\lceil {\frac{4tn+2}{3}} \right\rceil \text{.}$

We define an edge irregular total $ħ-$ labeling for ${\theta }_{n}(t, 3)$ to get upper bound. So, let $ħ = \left\lceil {\frac{4tn+2}{3}} \right\rceil$ and a total $ħ-$ labeling $\gamma :V\left({\theta }_{n}(t, 3)\right)\cup E\left({\theta }_{n}(t, 3)\right)\to \left\{\mathrm{1, 2}, 3, \dots, ħ\right\}$ is defined in the following three cases:

Case 1. $4tn+2\equiv 0\left(mod \; 3\right)$

$\gamma$ is defined as:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S\; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right)\mathrm{I} = \left\{\begin{array}{cc}i& for\; 1\le j\le 3, i = 1, 2, \dots , t\\ i+t+1& for\; 4\le j\le 6, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 7\le j\le 9, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+(n-1)(t+1)& for\; 3n-5\le j\le 3n-3, i = 1, 2, \dots , t\\ ħ-1& for\; 3n-2\le j\le 3n, i = 1\\ ħ& for\; 3n-2\le j\le 3n, i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 3S}\right) = 2St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({c}_{n}{x}_{i, 3n}\right) = \left\{\begin{array}{cc}ħ-t+2& for\; i = 1\\ ħ-t+i& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 3S+1}\right) = 2St-2S+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({{c}_{n-1}x}_{i, 3n-2}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}\left(t+2\right)n-t-5& for\; i = 1\\ \left(t+2\right)n-t+i-7& for\; i = 2, 3, \dots , t\end{array}, n = 2, 3\right.\\ \begin{array}{c}\left\{\begin{array}{cc}\left(t+1\right)n-t-1& for\; i = 1\\ \left(t+1\right)n-t+i-3& for\; i = 2, 3, \dots , t\end{array}, n\ne 2, 3\right.\end{array}\end{array}\right.$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 2\\ 3t+j-5& for\; 4\le j\le 5\\ 5t+j-10& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5\left(n-2\right)& for\; 3n-5\le j\le 3n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}ħ-3\left(t+n\right)+j+5& for\; 3n-2\le j\le 3n-1, i = 1\\ ħ-3\left(t+n\right)+j+5+2(i-2)& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

Obviously, $ħ$ is the greatest label. The edges weights of ${\theta }_{n}(t, 3)$ can be expressed as:

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 3S}\right) = t\left(4S-1\right)+i+2\; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 3S+1}\right) = 4St+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n-1}{x}_{i, 3n-2}\right) = \left\{\begin{array}{cc}2nt+3n-2t+ħ+i-8& for\; n = 2, 3\\ 2nt+2n-2t+ħ+i-4& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 2\\ 5t+j+2i-4& for\; 4\le j\le 5\\ 9t+j+2i-6& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 3ni-5\le j\le 3n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-3\left(t+in\right)+j+3& for\; 3n-2\le j\le 3n-1, i = 1\\ 3ħ-3\left(t+in\right)+j+2i+3& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It implies that the edges weights have distinct values. So $\gamma$ is the desired edge irregular total $ħ-$ labeling, $ħ = \left\lceil {\frac{4tn+2}{3}} \right\rceil$ . Hence

$tes\left({\theta }_{n}(t, 3)\right) = \left\lceil {\frac{4tn+2}{3}} \right\rceil \text{.}$

Case 2. $4tn+2\equiv 1\left(mod \; 3\right)$

$\mathrm{D}\mathrm{e}\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{e}\;\gamma$ as:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S \; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right) = \left\{\begin{array}{cc}i& for\; 1\le j\le 3, i = 1, 2, \dots , t\\ i+t+1& for\; 4\le j\le 6, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 7\le j\le 9, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+(n+1)(t+1)& for\; 3n-5\le j\le 3n-3, i = 1, 2, \dots , t\\ ħ-1& for\; 3n-2\le j\le 3n, i = 1\\ ħ& for\; 3n-2\le j\le 3n, i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1\; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 3S}\right) = 2St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots,\rm{t}$

$\gamma \left({c}_{n}{x}_{i, 3n}\right) = \left\{\begin{array}{cc}ħ-t& for\; i = 1\\ ħ-t+i-2& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 3S+1}\right) = 2St-2S+2 \; for\; 1\le \mathrm{I}S\le n-1, i = 1, 2, \dots t$

$\gamma \left({{c}_{n-1}x}_{i3n-2}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}\left(t+2\right)n-t-5& for\; i = 1\\ \left(t+2\right)n-t+i-7& for\; i = 2, 3, \dots , t\end{array}, n = 2, 3\right.\\ \begin{array}{c}\left\{\begin{array}{cc}\left(t+1\right)n-t-1& for\; i = 1\\ \left(\mathrm{I}t+\mathrm{I}1\right)n-t+i-3& for\; i = 2, 3, \dots , t\end{array}, n\ne 2, 3\right.\end{array}\end{array}\right.$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 2\\ 3t+j-5& for\; 4\le j\le 5\\ 5t+j-10& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5(n-2)& for\; 3n-5\le j\le 3n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}ħ-3\left(t+n\right)+j+3& for\; 3n-2\le j\le 3n-1, i = 1\\ ħ-3\left(t+n\right)+j+2(i-2)& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is clear that the greatest label is $ħ$ . We define the weights of edges of ${\theta }_{n}(t, 3)$ as:

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2\; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 3S}\right) = t\left(4S-1\right)+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t{w}_{\gamma }\left({c}_{n}{x}_{i, 3n}\right) = 3ħ-t+i-2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 3S+1}\right) = 4St+i+2\; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n-1}{x}_{i, 3n-2}\right) = \left\{\begin{array}{cc}2nt+3n-2t+ħ+i-8& for\; n = 2, 3\\ 2nt+2n-2t+ħ+i-4& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 2\\ 5t+j+2i-4& for\; 4\le j\le 5\\ 9t+j+2i-6& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 3n-5\le j\le 3n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-3\left(t+n\right)+j+1& for\; 3n-2\le j\le 3n-1, i = 1\\ 3ħ-3\left(t+n\right)+j+2(i-2)& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is obvious that the edges weights are different. Then

$tes\left({\theta }_{n}(t, 3)\right) = \left\lceil {\frac{4tn+2}{3}} \right\rceil \text{.}$

Case 3. $4tn+2\equiv 2\left(mod \; 3\right)$

$\gamma$ is defined as follows:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S \; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right) = \left\{\begin{array}{cc}i& for\; 1\le j\le 3, i = 1, 2, \dots , t\\ i+t+1& for\; 4\le j\le 6, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 7\le j\le 9, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+\left(n-1\right)\left(t+1\right)& for\; 3n-5\le j\le 3n-3, i = 1, 2, \dots , t\\ ħ-1& for\; 3n-2\le j\le 3n, i = 1\\ ħ& for\; 3n-2\le j\le 3n, i = 2, 3, \dots , t\end{array}, \right.$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1\; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 3S}\right) = 2St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({c}_{n}{x}_{i, 3n}\right) = \left\{\begin{array}{cc}ħ-t+1& for\; i = 1\\ ħ-t+i-1& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 3S+1}\right) = 2St-2S+2 \; for\; 1\le S\le n-2, i = 1, 2, \dots , t$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 2\\ 3t+j-5& for\; 4\le j\le 5\\ 5t+j-10& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5(n-2)& for\; 3n-5\le j\le 3n-4\end{array}, i = 1, 2, \dots t\right.\\ \begin{array}{cc}ħ-3\left(t+i\right)+j+4& for\; 3n-2\le j\le 3ni-1, i = 1\\ ħ-3\left(t+n\right)+j+2i& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

We can see that $ħ$ is the greatest label. For edges weights of ${\theta }_{n}(t, 3)$ , we have

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{0}{x}_{i, 3S}\right) = t\left(4S-1\right)+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t{w}_{\gamma }\left({c}_{n}{x}_{i, 3n}\right) = 3ħ-t+i-1 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 3S+1}\right) = 4St+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n}{x}_{i, 3n-2}\right) = \left\{\begin{array}{cc}2nt-3n-2t+ħ+i-8& for\; n = 2, 3\\ 2nt+2n-2t+ħ+i-4& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 2\\ 5t+j+2i-4& for\; 4\le j\le 5\\ 9t+j+2i-6& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 3n-5\le j\le 3n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-3\left(t+n\right)+j+2& for\; 3n-2\le j\le 3n-1, i = 1\\ 3ħ-3\left(t+n\right)+j+2i& for\; 3n-2\le j\le 3n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It clears that the edges weights are i distinct. So $\gamma$ is the desired edge irregular total $ħ-$ labeling, $ħ = \left\lceil {\frac{4tn+2}{3}} \right\rceil$ . Hence

$tes\left({\theta }_{n}(t, 3)\right) = \left\lceil {\frac{4tn+2}{3}} \right\rceil \text{.}$

Theorem 4. For ${\theta }_{n}\left(4, m\right)$ be a theta snake graph for $t>3$ . Then

$tes\left({\theta }_{n}(4, m)\right) = \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil \text{.}$

Proof. Since $\left|E\left({\theta }_{n}\left(4, m\right)\right)\right| = 4(m+1)n$ and $\Delta \left({\theta }_{n}\left(4, m\right)\right) = 8$ , then from (1) we have

$tes\left({\theta }_{n}(4, m)\right)\ge \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil \text{.}$

The existence of an edge irregular total $ƛ-$ labeling for ${\theta }_{n}(4, m)$ , $m>3$ will be shown, with $ƛ = \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil$ . Define a total $ƛ-$ labeling $\beta :V\left({\theta }_{n}(4, m)\right)\cup E\left({\theta }_{n}(4, m)\right)\to \left\{\mathrm{1, 2}, 3, \dots, ƛ\right\}$ for ${\theta }_{n}(4, m)$ in the following three cases as:

Case 1. $4\left(m+1\right)n+2\equiv 0\left(mod \; 3\right)$ , $i = 1, 2, \mathrm{3, 4}$

$\beta$ is defined as:

$\beta \left({c}_{s}\right) = \left\{\begin{array}{c}\begin{array}{c}1 \; for\; s = 0\\ \left(m+1\right)s \; for\; 1\le s\le \left\lceil {\frac{n}{2}} \right\rceil \end{array}\\ ƛ+s-n \; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n\end{array}\right.\text{, }$

$\beta \left({x}_{i, j}\right) = \left\{\begin{array}{cc}j& for\; 1\le j\le m\\ j+1& for\; m+1\le j\le 2m\\ .& .\\ .& .\\ \begin{array}{c}j+\left\lceil {\frac{n}{2}} \right\rceil -1\\ ƛ-j+22\\ ƛ\end{array}& \begin{array}{c}for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\le j\le m\left\lceil {\frac{n}{2}} \right\rceil +1\\ for\; m\left\lceil {\frac{n}{2}} \right\rceil +2\le j\le m\left(n-1\right)\\ for\; m\left(n-1\right)+1\le j\le mn-1\end{array}\end{array}, \right.$

$\beta \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \mathrm{3, 4}$

$\beta \left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}{2c}_{S}+i-1\; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1\\ \begin{array}{c}{c}_{S}+i-4\left(m+1\right)for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\\ ƛ-4+i \; for\; s = n\end{array}\end{array}\right., i = 1, 2, \mathrm{3, 4}$

$\beta \left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}{2c}_{S}+i+1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil , i = 1, 2, \mathrm{3, 4}\\ {c}_{S}+i-4\left(m+1\right)+2 \; for\;\left\lceil {\frac{n}{2}} \right\rceil +1\le s\le n-1\end{array}\right.$

$\beta \left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}ƛ-3& for\; i = 1\\ ƛ-2& for\; i = 2\\ \begin{array}{c}ƛ-1\\ ƛ\end{array}& \begin{array}{c}for\; i = 3\\ for\; i = 4\end{array}\end{array}\right.\text{, }$

$\beta \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}j+i+1& for\; 1\le j\le m-1\\ j+i+2& for\; m+1\le j\le 2m-1\\ .& .\\ .& .\\ j+i+\left\lceil {\frac{n}{2}} \right\rceil & for\; j = m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\\ 2j+i-2[nm\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1]& for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+2\le j\le mn-1\end{array}.\right.$

It is clear that $ƛ$ is the greatest used label. The weights of edges of ${\theta }_{n}(4, m)$ are given by:

${w}_{\beta }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, \mathrm{3, 4}\text{, }$

${w}_{\beta }\left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}{2ms+s+2c}_{S}+i-1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, \\ \begin{array}{c}{c}_{S}+i+ƛ+\left(s-4\right)\left(m+1\right)-n+\left\lceil {\frac{n}{2}} \right\rceil -1\; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\\ 3ƛ-4+i+s-n\; for\; s = n\end{array}\end{array}\right., i = 1, \mathrm{2, 3}, 4$

${w}_{\beta }\left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}\left(2m+1\right)s+{2c}_{S}+i+1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil, \\ 2ƛ+s-n+{c}_{S}+i-4\left(m+1\right)+2 \;for\; \left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\end{array}\right.i = 1, 2, \mathrm{3, 4},$

${w}_{\beta }\left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}3ƛ+s-n-3& for\; i = 1\\ 3ƛ+s-n-2& for\; i = 2\\ \begin{array}{c}3ƛ+s-n-1\\ 3ƛ+s-n\end{array}& \begin{array}{c}for\; i = 3\\ for\; i = 4\end{array}\end{array}\right.\text{, }$

${w}_{\beta }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}3j+i+2& for\; 1\le j\le m-1\\ 3j+i+4& for\; m+1\le j\le 2m-1\\ .& .\\ .& .\\ 3j+i+3\left\lceil {\frac{n}{2}} \right\rceil -1& for\; j = m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\\ \begin{array}{c}4j+2ƛ+45+i-2[nm\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1]\\ 2j+2ƛ+i-2[nm\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1]\end{array}& \begin{array}{c}for\; m\left\lceil {\frac{n}{2}} \right\rceil +2\le j\le m\left(n-1\right)\\ for\; m\left(n-1\right)+1\le j\le mn-1\end{array}\end{array}, \right.$

It is obvious that the weights of edges are different, thus $\beta$ is an edge irregular total $ƛ-$ labeling of ${\theta }_{n}(4, m)$ . Hence

$tes\left({\theta }_{n}(4, m)\right) = \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil \text{.}$

Case 2. $4\left(m+1\right)n+2\equiv 1\left(mod \; 3\right)$ , $i = 1, 2, \mathrm{3, 4}$

$\beta$ is defined as:

$\beta \left({c}_{s}\right) = \left\{\begin{array}{c}\begin{array}{c}1\; for\; s = 0\\ \left(m+1\right)s \; for\; 1\le s\le \left\lceil {\frac{n}{2}} \right\rceil \end{array}\\ ƛ+s-n \; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n\end{array}\right.\text{, }$

$\beta \left({x}_{i, j}\right) = \left\{\begin{array}{cc}j& for\; 1\le j\le m\\ j+1& for\; m+1\le j\le 2m\\ .& .\\ .& .\\ \begin{array}{c}j+\left\lceil {\frac{n}{2}} \right\rceil -1\\ ƛ-j+22\\ ƛ\end{array}& \begin{array}{c}for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\le j\le m\left\lceil {\frac{n}{2}} \right\rceil \\ for\; m\left\lceil {\frac{n}{2}} \right\rceil +1\le j\le m\left(n-1\right)\\ for\; m\left(n-1\right)+1\le j\le mn-1\end{array}\end{array}, \right.$

$\beta \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \mathrm{3, 4}$

$\beta \left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}{2c}_{S}+i-1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, \\ \begin{array}{c}\begin{array}{c}ƛ-7+i \; for\; s = \left\lceil {\frac{n}{2}} \right\rceil \\ {c}_{S}+i-4m-2 \; for\;\left\lceil {\frac{n}{2}} \right\rceil +1\le s\le n-1\end{array}\\ ƛ-6+i \; for\; s = n\end{array}\end{array}\right., i = 1, 2, \mathrm{3, 4}$

$\beta \left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}{2c}_{S}+i+1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil \\ {c}_{S}+i-4m \; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\end{array}, i = 1, 2, \mathrm{3, 4}\right.$

$\beta \left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}ƛ-5& for\; i = 1\\ ƛ-4& for\; i = 2\\ \begin{array}{c}ƛ-3\\ ƛ-2\end{array}& \begin{array}{c}for\; i = 3\\ for\; i = 4\end{array}\end{array}\right.\text{, }$

It is clear that $ƛ$ is the greatest used label. The weights of edges of ${\theta }_{n}(4, m)$ are given by:

${w}_{\beta }\left({c}_{0}{x}_{i, 1}\right) = i+2\; for\; i = 1, 2, \mathrm{3, 4}\text{, }$

${w}_{\beta }\left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}\begin{array}{c}{2ms+s+2c}_{S}+i-1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, \\ 2ƛ-m\left\lceil {\frac{n}{2}} \right\rceil +\left(m+1\right)s+i+15 \; for\; s = \left\lceil {\frac{n}{2}} \right\rceil \end{array}\\ \begin{array}{c}{c}_{S}+i+ƛ+(s-4)\left(m+1\right)-n+\left\lceil {\frac{n}{2}} \right\rceil -1 \; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\\ 3ƛ-4+i+s-n \; for\; s = n\end{array}\end{array}\right.$

${w}_{\beta }\left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}\left(2m+1\right)s+{2c}_{S}+i+1\; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil , i = 1, 2, \mathrm{3, 4}\\ 2ƛ+s-n+{c}_{S}+i-4m\; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\end{array}\right.i = 1, 2, \mathrm{3, 4},$

${w}_{\beta }\left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}3ƛ+s-n-5& for\; i = 1\\ 3ƛ+s-n-4& for\; i = 2\\ \begin{array}{c}3ƛ+s-n-3\\ 3ƛ+s-n-2\end{array}& \begin{array}{c}for\; i = 3\\ for\; i = 4\end{array}\end{array}\right.\text{, }$

It is obvious that the weights of edges are different, thus $\beta$ is an edge irregular total $ƛ-$ labeling of ${\theta }_{n}(4, m)$ . Hence

$tes\left({\theta }_{n}(4, m)\right) = \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil \text{.}$

Case 3. $4\left(m+1\right)n+2\equiv 2\left(mod \; 3\right)$ , $i = 1, 2, \mathrm{3, 4}$

$\beta$ is defined as:

$\beta \left({x}_{i, j}\right) = \left\{\begin{array}{cc}j& for\; 1\le j\le m\\ j+1& for\; m+1\le j\le 2m\\ .& .\\ .& .\\ \begin{array}{c}j+\left\lceil {\frac{n}{2}} \right\rceil -1\\ ƛ-j+22\\ ƛ\end{array}& \begin{array}{c}for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -2\right)+1\le j\le m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)\\ for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\le j\le m\left(n-1\right)\\ for\; m\left(n-1\right)+1\le j\le mn-1\end{array}\end{array}, \right.$

$\beta \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \mathrm{3, 4}$

$\beta \left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}{2c}_{S}+i-1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, i = 1, 2, \mathrm{3, 4}\\ \begin{array}{c}\begin{array}{c}ƛ-7+i \; for\; s = \left\lceil {\frac{n}{2}} \right\rceil \\ {c}_{S}+i-4m-2 \; for\;\left\lceil {\frac{n}{2}} \right\rceil +1\le s\le n-1\end{array}\\ ƛ-5+i \; for\; s = n\end{array}\end{array}\right.$

$\beta \left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}{2c}_{S}+i+1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, i = 1, 2, \mathrm{3, 4}\\ \begin{array}{c}{c}_{S}+1+i \; for\; s = \left\lceil {\frac{n}{2}} \right\rceil \\ {c}_{S}+i-4m+1 \; for\;\left\lceil {\frac{n}{2}} \right\rceil +1\le s\le n-1\end{array}\end{array}\right.$

$\beta \left({c}_{n}{x}_{i, mn}\right) = \left\{\begin{array}{cc}ƛ-4& for\; i = 1\\ ƛ-3& for\; i = 2\\ \begin{array}{c}ƛ-2\\ ƛ-1\end{array}& \begin{array}{c}for\; i = 3\\ for\; i = 4\end{array}\end{array}\right.\text{, }$

$\beta \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{cc}j+i+1& for\; 1\le j\le m-1\\ j+i+2& for\; m+1\le j\le 2m-1\\ .& .\\ .& .\\ j+i+\left\lceil {\frac{n}{2}} \right\rceil & for\; j = m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\\ 2j+i-2\left[nm\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+1\right]+1& for\; m\left(\left\lceil {\frac{n}{2}} \right\rceil -1\right)+2\le j\le mn-1\end{array}.\right.$

It is clear that $ƛ$ is the greatest used label. The weights of edges of ${\theta }_{n}(4, m)$ are given by:

${w}_{\beta }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, \mathrm{3, 4}\text{, }$

${w}_{\beta }\left({c}_{S}{x}_{i, mS}\right) = \left\{\begin{array}{c}\begin{array}{c}{2ms+s+2c}_{S}+i-1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil -1, \\ 2ƛ-m\left\lceil {\frac{n}{2}} \right\rceil +\left(m+1\right)s+i+15 \; for\; s = \left\lceil {\frac{n}{2}} \right\rceil \end{array}\\ \begin{array}{c}{c}_{S}+i+ƛ+(s-4)\left(m+1\right)-n+\left\lceil {\frac{n}{2}} \right\rceil -1 \; for\;\left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\\ 3ƛ-3+i+s-n \; for\; s = n\end{array}\end{array}\right.$

${w}_{\beta }\left({c}_{S}{x}_{i, mS+1}\right) = \left\{\begin{array}{c}\left(2m+1\right)s+{2c}_{S}+i+1 \; for\; 1\le S\le \left\lceil {\frac{n}{2}} \right\rceil, i = 1, 2, \mathrm{3, 4}\\ \begin{array}{c}\\ 2ƛ+s-n+{c}_{S}+i-4m+1\; for\; \left\lceil {\frac{n}{2}} \right\rceil \le s\le n-1\end{array}\end{array}\right.,$

It is obvious that the weights of edges are different, thus $\beta$ is an edge irregular total $ƛ-$ labeling of ${\theta }_{n}(4, m)$ . Hence

$tes\left({\theta }_{n}(4, m)\right) = \left\lceil {\frac{4(m+1)n+2}{3}} \right\rceil$

Theorem 5. If ${\theta }_{n}\left(t, 4\right)$ is theta snake graph for $t>3$ . Then

$tes\left({\theta }_{n}(t, 4)\right) = \left\lceil {\frac{5tn+2}{3}} \right\rceil \text{.}$

Proof. Since $\left|E\left({\theta }_{n}\right(t, 4\left)\right)\right| = 5tn$ and $\Delta \left({\theta }_{n}\right(t, 4\left)\right) = 2t$ . Substituting in (1), we have

$tes\left({\theta }_{n}(t, 4)\right)\ge \left\lceil {\frac{5tn+2}{3}} \right\rceil \text{.}$

We define an edge irregular total $ħ-$ labeling for ${\theta }_{n}(t, 4)$ to get upper bound. Let $ħ = \left\lceil {\frac{5tn+2}{3}} \right\rceil$ and a total $ħ-$ labeling $\gamma :V\left({\theta }_{n}(t, 4)\right)\cup E\left({\theta }_{n}(t, 4)\right)\to \left\{\mathrm{1, 2}, 3, \dots, ħ\right\}$ is defined in the following three cases:

Case 1. $5tn+2\equiv 0\left(mod \; 3\right)$

$\mathrm{D}\mathrm{e}\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{e}\; \gamma$ as:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S \; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right) = \left\{\begin{array}{cc}i& for\; 1\le j\le 4, i = 1, 2, \dots , t\\ i+t+1& for\; 5\le j\le 8, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 9\le j\le 12, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+(n-1)(t+1)& for\; 4n-7\le j\le 4n-4, i = 1, 2, \dots , t\\ ħ-1& for\; 4n-3\le j\le 4n, i = 1\\ ħ& for\; 4n-3\le j\le 4n, i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 4S}\right) = 3St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({c}_{n}{x}_{i, 4n}\right) = \left\{\begin{array}{cc}ħ-t+2& for\; i = 1\\ ħ-t+i& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 4S+1}\right) = 3St-2S+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({{c}_{n-1}x}_{i, 4n-3}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}\left(t+2\right)n-t-5& for\; i = 1\\ \left(t+2\right)n-t+i-7& for\; i = 2, 3, \dots , t\end{array}, n = 2, 3\right.\\ \left(t+1\right)n-t+i-3 \; for\; i = 2, 3, \dots , t , n\ne 2, 3\end{array}\right.$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 2\\ 3t+j-5& for\; 4\le j\le 5\\ 5t+j-10& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5\left(n-2\right)& for\; 4n-5\le j\le 4n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}ħ-3\left(t+n\right)+j+5& for\; 4n-2\le j\le 4n, i = 1\\ ħ-3\left(t+n\right)+j+5+2(i-2)& for\; 4n-2\le j\le 4n, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is clear that, $ħ$ is the greatest label. The edges weights of ${\theta }_{n}(t, 4)$ can be expressed as:

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2 \; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 4S}\right) = t\left(5S-1\right)+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t{w}_{\gamma }\left({c}_{n}{x}_{i, 4n}\right) = 3ħ-t+i \; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 4S+1}\right) = 5St+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n-1}{x}_{i, 4n-2}\right) = \left\{\begin{array}{cc}2nt+3n-2t+ħ+i-8& for\; n = 2, 3\\ 2nt+2n-2t+ħ+i-6& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 2\\ 5t+j+2i-4& for\; 4\le j\le 5\\ 9t+j+2i-6& for\; 7\le j\le 8\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 4n-5\le j\le 4n-4\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-3\left(t+n\right)+j+3& for\; 4n-2\le j\le 4n-1, i = 1\\ 3ħ-3\left(t+n\right)+j+2i+3& for\; 4n-2\le j\le 4n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It implies that the edges weights have distinct values. So $\gamma$ is the desired edge irregular total $ħ-$ labeling, $ħ = \left\lceil {\frac{5tn+2}{3}} \right\rceil$ . Hence

$tes\left({\theta }_{n}(t, 4)\right) = \left\lceil {\frac{5tn+2}{3}} \right\rceil \text{.}$

Case 2. $5tn+2\equiv 1\left(mod \; 3\right)$

$\mathrm{D}\mathrm{e}\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{e}\; \gamma$ as:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S \; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right) = \left\{\begin{array}{cc}i& for\; 1\le j\le 4, i = 1, 2, \dots , t\\ i+t+1& for\; 5\le j\le 8, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 9\le j\le 12, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+(n+1)(t+1)& for\; 4n-7\le j\le 4n-4, i = 1, 2, \dots , t\\ ħ-1& for\; 4n-3\le j\le 4n, i = 1\\ ħ& for\; 4n-3\le j\le 4n, i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 4S}\right) = 3St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots, \rm{t}$

$\gamma \left({c}_{n}{x}_{i, 4n}\right) = \left\{\begin{array}{cc}ħ-t& for\; i = 1\\ ħ-t+i-2& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 4S+1}\right) = 3St-2S+2$

$for\; 1\le S\le n-1, i = 1, 2, \dots t$

$\gamma \left({{c}_{n-1}x}_{i, 4n-3}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}\left(t+2\right)n-t-5& for\; i = 1\\ \left(t+2\right)n-t+i-7& for\; i = 2, 3, \dots , t\end{array}, n = 2, 3\right.\\ \begin{array}{c}\left\{\begin{array}{cc}\left(t+1\right)n-t-1& for\; i = 1\\ \left(t+1\right)n-t+i-3& for\; i = 2, 3, \dots , t\end{array}, n\ne 2, 3\right.\end{array}\end{array}\right.$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 3\\ 3t+j-5& for\; 5\le j\le 7\\ 5t+j-10& for\; 9\le j\le 11\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5(n-2)& for\; 4n-7\le j\le 4n-5\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}ħ-4\left(t+n\right)+j+3& for\; 4n-3\le j\le 4n-1, i = 1\\ ħ-4\left(t+n\right)+j+2(i-2)& for\; 4n-3\le j\le 4n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is clear that the i greatest label is $ħ$ . We define the weights of edges of ${\theta }_{n}(t, 4)$ as:

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2\; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 4S}\right) = t\left(5S-1\right)+i+2\; for\; 1\le S\le n-1, i = 1, 2, \dots , t{w}_{\gamma }\left({c}_{n}{x}_{i, 4n}\right) = 3ħ-t+i-2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 4S+1}\right) = 5St+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n-1}{x}_{i, 4n-3}\right) = \left\{\begin{array}{cc}3nt+3n-2t+ħ+i-8& for\; n = 2, 3\\ 3nt+2n-2t+ħ+i-6& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 3\\ 5t+j+2i-4& for\;i 5\le j\le 7\\ 9t+j+2i-6& for\; 9\le j\le 11\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 4n-7\le j\le 4n-5\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-4\left(t+n\right)+j+1& for\; 4n-3\le j\le 4n-1, i = 1\\ 3ħ-4\left(t+n\right)+j+2(i-2)& for\; 4n-3\le j\le 4n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is obvious that the edges weights are different. Then

$tes\left({\theta }_{n}(t, 4)\right) = \left\lceil {\frac{5tn+2}{3}} \right\rceil \text{.}$

Case 3. $5tn+2\equiv 2\left(mod \; 3\right)$

$\mathrm{D}\mathrm{e}\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{e} \; \gamma$ as:

$\gamma \left({c}_{0}\right) = 1,$

$\gamma \left({c}_{S}\right) = \left(t+1\right)S \; for\; 1\le S\le n-1\text{, }$

$\gamma \left({c}_{n}\right) = ħ$

$\gamma \left({x}_{i, j}\right) = \left\{\begin{array}{cc}i& for\; 1\le j\le 4, i = 1, 2, \dots , t\\ i+t+1& for\; 5\le j\le 8, i = 1, 2, \dots , t\\ i+2(t+1)& for\; 9\le j\le 12, i = 1, 2, \dots , t\\ .& .\\ .& .\\ .& .\\ i+(in-1)(t+1)& for\; 4n-7\le j\le 4n-4, i = 1, 2, \dots , t\\ ħ-1& for\; 4n-3\le j\le 4n, i = 1\\ ħ& for\; 4n-3\le j\le 4n, i = 2, 3, \dots , t\end{array}, \right.$

$\gamma \left({c}_{0}{x}_{i, 1}\right) = 1 \; for\; i = 1, 2, \dots , t$

$\gamma \left({c}_{S}{x}_{i, 4S}\right) = 3St-2S+3 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t$

$\gamma \left({c}_{n}{x}_{i, 4n}\right) = \left\{\begin{array}{cc}ħ-t+1& for\; i = 1\\ ħ-t+i-1& for\; i = 2, 3, \dots , t\end{array}\right.\text{, }$

$\gamma \left({c}_{S}{x}_{i, 4S+1}\right) = 3St-2S+2 \; for\; 1\le S\le n-2, i = 1, 2, \dots , t$

$\gamma \left({{c}_{n-1}x}_{i, 4n-3}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}\left(t+2\right)n-t-5& for\; i = 1\\ \left(t+2\right)n-t+i-7& for\; i = 2, 3, \dots , t\end{array}, n = 2, 3\right.\\ \begin{array}{c}\left\{\begin{array}{cc}\left(t+1\right)n-t-1& for\; i = 1\\ \left(t+1\right)n-t+i-3& for\; i = 2, 3, \dots , t\end{array}, n\ne 2, 3\right.\end{array}\end{array}\right.$

$\gamma \left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j& for\; 1\le j\le 3\\ 3t+j-5& for\; 5\le j\le 7\\ 5t+j-10& for\; 9\le j\le 11\\ .& .\\ .& .\\ .& .\\ \left(2n-3\right)t+j-5(n-2)& for\; 4n-7\le j\le 4n-5\end{array}, i = 1, 2, \dots t\right.\\ \begin{array}{cc}ħ-4\left(t+n\right)+j+4& for\; 4n-3\le j\le 4n-1, i = 1\\ ħ-4\left(t+n\right)+j+2i& for\; 4n-3\le j\le 4n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

We can see that $ħ$ is the greatest label. For edges weights of ${\theta }_{n}(t, 4)$ , we have:

${w}_{\gamma }\left({c}_{0}{x}_{i, 1}\right) = i+2\; for\; i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{0}{x}_{i, 4S}\right) = t\left(5S-1\right)+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t{w}_{\gamma }\left({c}_{n}{x}_{i, 4n}\right) = 3ħ-t+i-1 \; for\; 1\le S\le in-1, i = 1, 2, \dots , t$

${w}_{\gamma }\left({c}_{S}{x}_{i, 4S+1}\right) = 5St+i+2 \; for\; 1\le S\le n-1, i = 1, 2, \dots , t\text{, }$

${w}_{\gamma }\left({c}_{n}{x}_{i, 4n-3}\right) = \left\{\begin{array}{cc}2nt-3n-2t+ħ+i-8& for\; n = 2, 3\\ 2nt+2n-2t+ħ+i-6& for\; n\ne 2, 3\end{array}, i = 1, 2, \dots , t\right.$

${w}_{\gamma }\left({{x}_{i, j}x}_{i, j+1}\right) = \left\{\begin{array}{c}\left\{\begin{array}{cc}t+j+2i& for\; 1\le j\le 3\\ 5t+j+2i-4& for\; 5\le j\le 7\\ 9t+j+2i-6& for\; 9\le j\le 11\\ .& .\\ .& .\\ .& .\\ \left(4n-5\right)t+j+2i-3n+8& for\; 4n-7\le j\le 4n-5\end{array}, i = 1, 2, \dots , t\right.\\ \begin{array}{cc}3ħ-4\left(t+n\right)+j+2& for\; 4n-3\le j\le 3n-1, i = 1\\ 3ħ-4\left(t+n\right)+j+2i& for\; 4n-3\le j\le 4n-1, i = 2, 3, \dots , t\end{array}\end{array}\right.$

It is obvious that the edges weights are distinct. So $\gamma$ is the desired edge irregular total $ħ-$ labeling, $ħ = \; \left\lceil {\frac{5tn+2}{3}} \right\rceil$ . Hence

$tes\left({\theta }_{n}(t, 4)\right) = \left\lceil {\frac{5tn+2}{3}} \right\rceil \text{.}$

The previous results lead us to introduce the following conjecture for a general case of a uniform theta snake graph ${\theta }_{n}(t, m)$ .

Conjecture. For uniform theta snake graph ${\theta }_{n}(t, m)$ , $n\ge 2, t\ge 3, and m\ge 3$ we have

$tes\left({\theta }_{n}(t, m)\right) = \left\lceil {\frac{(m+1)tn+2}{3}} \right\rceil \text{.}$

3. Conclusions

In the current paper, we have defined a new type of a family of graph called uniform theta snake graph, ${\theta }_{n}(t, m)$ . Also, the exact i value of TEISs for ${\mathtt{θ }}_{\mathrm{n}}\left(\mathrm{3, 3}\right)$ , ${\mathtt{θ }}_{\mathrm{n}}(3, \mathrm{m})$ and ${\mathtt{θ }}_{\mathrm{n}}(\mathrm{t}, 3)$ has been determined. Finally, we have generalized for t, m and found TEIS of a uniform theta snake graph ${\mathtt{θ }}_{\mathrm{n}}(\mathrm{t}, \mathrm{m})$ for $\mathrm{m}\ge 3$ , $\mathrm{t}\ge 3$ .

$tes\left({\theta }_{n}\left(\mathrm{3, 3}\right)\right) = 4n+1\text{.}$

$tes\left({\theta }_{n}(3, im)\right) = (im+1)in+1\text{.}$

$tes\left({\theta }_{n}(t, 3)\right) = \left\lceil {\frac{4tn+2}{3}} \right\rceil$

$tes\left({\theta }_{n}(t, m)\right) = \left\lceil {\frac{(m+1)tn+2}{3}} \right\rceil \text{.}$

Conflict of interest

All authors declare no conflict of interest in this paper.

Acknowledgment

We are so grateful to the reviewer for his many valuable suggestions and comments that significantly improved the paper.

References

[1]	D. F. Andrews, C. L. Mallows, Scale mixtures of normal distribution, J. R. Stat. Soc. Ser. B Methodol., 36 (1974), 99–102. https://doi.org/10.1111/j.2517-6161.1974.tb00989.x doi: 10.1111/j.2517-6161.1974.tb00989.x
[2]	M. West, On scale mixtures of normal distributions, Biometrika, 74 (1987), 646–648. https://doi.org/10.1093/biomet/74.3.646 doi: 10.1093/biomet/74.3.646
[3]	M. D. Branco, D. K. Dey, A general class of multivariate skew-elliptical distributions, J. Multivar. Anal., 79 (2001), 99–113. https://doi.org/10.1006/jmva.2000.1960 doi: 10.1006/jmva.2000.1960
[4]	C. S. Ferreira, H. Bolfarine, V. H. Lachos, Linear mixed models based on skew scale mixtures of normal distribution, Commun. Stat. Simul. Comput., 51 (2020), 7194–7214. https://doi.org/10.1080/03610918.2020.1827265 doi: 10.1080/03610918.2020.1827265
[5]	R. M. Basso, V. H. Lachos, C. R. B. Cabral, P. Ghosh, Robust mixture modeling based on scale mixtures of skew-normal distributions, Comput. Stat. Data Anal., 54 (2010), 2926–2941. https://doi.org/10.1016/j.csda.2009.09.031 doi: 10.1016/j.csda.2009.09.031
[6]	H. M. Kim, M. G. Genton, Characteristic functions of scale mixtures of multivariate skew-normal distributions, Comput. Stat. Data Anal., 102 (2011), 1105–1117. https://doi.org/10.1016/j.jmva.2011.03.004 doi: 10.1016/j.jmva.2011.03.004
[7]	T. I. Lin, J. C. Lee, W. J. Hsieh, Robust mixture modeling using the skew t distribution, Stat. Comput., 17 (2007), 81–92. https://doi.org/10.1007/s11222-006-9005-8 doi: 10.1007/s11222-006-9005-8
[8]	T. I. Lin, H. J. Ho, C. R. Lee, Flexible mixture modelling using the multivariate skew-t-normal distribution, Stat. Comput., 24 (2014), 531–546. https://doi.org/10.1007/s11222-013-9386-4 doi: 10.1007/s11222-013-9386-4
[9]	I. Lin, J. C. Lee, Y. Y. Shu, Finite mixture modelling using the skew normal distribution, Stat. Sin., 17 (2007), 909–927. https://doi.org/10.2307/24307705 doi: 10.2307/24307705
[10]	A. Mahdavi, V. Amirzadeh, A. Jamalizadeh, T. I. Lin, Maximum likelihood estimation for scale-shape mixtures of flexible generalized skew normal distributions via selection representation, Comput. Stat., 36 (2021), 2201–2230. https://doi.org/10.1007/s00180-021-01079-2 doi: 10.1007/s00180-021-01079-2
[11]	A. Azzalini, A class of distributions which includes the normal ones, Scand. J. Stat., 12 (1985), 171–178.
[12]	A. Azzalini, A. Dalla Valle, The multivariate skew-normal distribution, Biometrika, 83 (1996), 715–726. https://doi.org/10.1093/biomet/83.4.715 doi: 10.1093/biomet/83.4.715
[13]	A. Azzalini, A. Capitanio, Statistical applications of the multivariate skew normal distribution, J. R. Stat. Soc. Ser. B Methodol., 61 (1999), 579–602. https://doi.org/10.1111/1467-9868.00194 doi: 10.1111/1467-9868.00194
[14]	R. B. Arellano-Valle, A. Azzalini, On the unification of families of skew-normal distributions, Scand. J. Stat., 33 (2006), 561–574. https://doi.org/10.1111/j.1467-9469.2006.00503.x doi: 10.1111/j.1467-9469.2006.00503.x
[15]	R. B. Arellano-Valle, M. G. Genton, On fundamental skew distributions, J. Multivar. Anal., 96 (2005), 93–116. https://doi.org/10.1016/j.jmva.2004.10.002 doi: 10.1016/j.jmva.2004.10.002
[16]	A. Azzalini, The skew-normal distribution and related multivariate families, Scand. J. Stat., 32 (2005), 159–188. https://doi.org/10.1111/j.1467-9469.2005.00426.x doi: 10.1111/j.1467-9469.2005.00426.x
[17]	C. Fernandez, M. F. J. Steel, Reference priors for non-normal two-sample problems, Test, 7 (1988), 179–205. https://doi.org/10.1007/BF02565109 doi: 10.1007/BF02565109
[18]	D. M. Zhu, V. Zinde-Walsh, Properties and estimation of asymmetric exponential power distribution, J. Econom., 148 (2009), 86–99. https://doi.org/10.1016/j.jeconom.2008.09.038 doi: 10.1016/j.jeconom.2008.09.038
[19]	R. J. Guan, X. Zhao, C. H. Cheng, Y. H. Rong, A new generalized t distribution based on a distribution construction method, Mathematics, 9 (2021), 2413. https://doi.org/10.1016/10.3390/math9192413 doi: 10.1016/10.3390/math9192413
[20]	H. Exton, Handbook of hypergeometric integrals: Theory, applications, tables, computer programs, New York: Halsted Press, 1978.
[21]	A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum likelihood from incomplete data via the em algorithm, J. R. Stat. Soc. Ser. B Methodol., 39 (1977), 1–22. https://doi.org/10.1111/j.2517-6161.1977.tb01600.x doi: 10.1111/j.2517-6161.1977.tb01600.x
[22]	K. Lange, The EM algorithm, New York: Springer, 2013.
[23]	X. L. Meng, D. B. Rubin, Maximum likelihood estimation via the ecm algorithm: A general framework, Biometrika, 80 (1993), 267–278. https://doi.org/10.2307/2337198 doi: 10.2307/2337198
[24]	P. Huber, Robust statistics, New York: Wiley, 1981.
[25]	L. L. Wen, Y. J. Qiu, M. H. Wang, J. L. Yin, P. Y. Chen, Numerical characteristics and parameter estimation of finite mixed generalized normal distribution, Commun. Stat. Simul. Comput., 51 (2022), 3596–3620. https://doi.org/10.1080/03610918.2020.1720733 doi: 10.1080/03610918.2020.1720733

Reader Comments

Your name:*

Email:*
© 2024 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)