Loading [MathJax]/jax/output/SVG/jax.js
Research article Special Issues

Univariate and multivariate analyses of the asset returns using new statistical models and penalized regression techniques

  • Received: 27 March 2023 Revised: 16 May 2023 Accepted: 22 May 2023 Published: 09 June 2023
  • MSC : 62F09, 62G34

  • The COVID-19 epidemic has had a profound effect on almost every aspect of daily life, including the financial sector, education, transportation, health care, and so on. Among these sectors, the financial and health sectors are the most affected areas by COVID-19. Modeling and predicting the impact of the COVID-19 epidemic on the financial and health care sectors is particularly important these days. Therefore, this paper has two aims, (i) to introduce a new probability distribution for modeling the financial data set (oil prices data), and (ii) to implement a machine learning approach to predict the oil prices. First, we introduce a new approach for developing new probability distributions for the univariate analysis of the oil price data. The proposed approach is called a new reduced exponential-X (NRE-X) family. Based on this approach, two new statistical distributions are introduced for modeling the oil price data and its log returns. Based on certain statistical tools, we observe that the proposed probability distributions are the best competitors for modeling the prices' data sets. Second, we carry out a multivariate analysis while considering some covariates of oil price data. Dual well-known machine learning algorithms, namely, the least absolute shrinkage and absolute deviation (Lasso) and Elastic net (Enet) are utilized to achieve the important features for oil prices based on the best model. The best model is established through forecasting performance.

    Citation: Huda M. Alshanbari, Zubair Ahmad, Faridoon Khan, Saima K. Khosa, Muhammad Ilyas, Abd Al-Aziz Hosni El-Bagoury. Univariate and multivariate analyses of the asset returns using new statistical models and penalized regression techniques[J]. AIMS Mathematics, 2023, 8(8): 19477-19503. doi: 10.3934/math.2023994

    Related Papers:

    [1] Zenan Du, Lihua You, Hechao Liu, Yufei Huang . The Sombor index and coindex of two-trees. AIMS Mathematics, 2023, 8(8): 18982-18994. doi: 10.3934/math.2023967
    [2] Chenxu Yang, Meng Ji, Kinkar Chandra Das, Yaping Mao . Extreme graphs on the Sombor indices. AIMS Mathematics, 2022, 7(10): 19126-19146. doi: 10.3934/math.20221050
    [3] Fan Wu, Xinhui An, Baoyindureng Wu . Sombor indices of cacti. AIMS Mathematics, 2023, 8(1): 1550-1565. doi: 10.3934/math.2023078
    [4] Akbar Ali, Sadia Noureen, Akhlaq A. Bhatti, Abeer M. Albalahi . On optimal molecular trees with respect to Sombor indices. AIMS Mathematics, 2023, 8(3): 5369-5390. doi: 10.3934/math.2023270
    [5] Qiaozhi Geng, Shengjie He, Rong-Xia Hao . On the extremal cacti with minimum Sombor index. AIMS Mathematics, 2023, 8(12): 30059-30074. doi: 10.3934/math.20231537
    [6] Juan C. Hernández, José M. Rodríguez, O. Rosario, José M. Sigarreta . Extremal problems on the general Sombor index of a graph. AIMS Mathematics, 2022, 7(5): 8330-8343. doi: 10.3934/math.2022464
    [7] Akbar Ali, Ivan Gutman, Boris Furtula, Abeer M. Albalahi, Amjad E. Hamza . On chemical and mathematical characteristics of generalized degree–based molecular descriptors. AIMS Mathematics, 2025, 10(3): 6788-6804. doi: 10.3934/math.2025311
    [8] Yufei Huang, Hechao Liu . Bounds of modified Sombor index, spectral radius and energy. AIMS Mathematics, 2021, 6(10): 11263-11274. doi: 10.3934/math.2021653
    [9] Xiuwen Wang, Maoqun Wang . Sombor index of uniform hypergraphs. AIMS Mathematics, 2024, 9(11): 30174-30185. doi: 10.3934/math.20241457
    [10] Shabana Anwar, Muhammad Kamran Jamil, Amal S. Alali, Mehwish Zegham, Aisha Javed . Extremal values of the first reformulated Zagreb index for molecular trees with application to octane isomers. AIMS Mathematics, 2024, 9(1): 289-301. doi: 10.3934/math.2024017
  • The COVID-19 epidemic has had a profound effect on almost every aspect of daily life, including the financial sector, education, transportation, health care, and so on. Among these sectors, the financial and health sectors are the most affected areas by COVID-19. Modeling and predicting the impact of the COVID-19 epidemic on the financial and health care sectors is particularly important these days. Therefore, this paper has two aims, (i) to introduce a new probability distribution for modeling the financial data set (oil prices data), and (ii) to implement a machine learning approach to predict the oil prices. First, we introduce a new approach for developing new probability distributions for the univariate analysis of the oil price data. The proposed approach is called a new reduced exponential-X (NRE-X) family. Based on this approach, two new statistical distributions are introduced for modeling the oil price data and its log returns. Based on certain statistical tools, we observe that the proposed probability distributions are the best competitors for modeling the prices' data sets. Second, we carry out a multivariate analysis while considering some covariates of oil price data. Dual well-known machine learning algorithms, namely, the least absolute shrinkage and absolute deviation (Lasso) and Elastic net (Enet) are utilized to achieve the important features for oil prices based on the best model. The best model is established through forecasting performance.



    Ostrowski's Inequality. Let f:I[0,+)R be a differentiable function on int(I), such that fL[a,b], where a,bI with a<b. If |f(x)|M for all x[a,b], then the inequality:

    |f(x)1babaf(t)dt|M(ba)[14+(xa+b2)2(ba)2],     x[a,b] (1.1)

    holds for all x[a,b]. This inequality was introduced by Alexander Ostrowski in [26], and with the passing of the years, generalizations on the same, involving derivatives of the function under study, have taken place. It is playing a very important role in all the fields of mathematics, especially in the theory approximations. Thus such inequalities were studied extensively by many researches and numerous generalizations, extensions and variants of them for various kind of functions like bounded variation, synchronous, Lipschitzian, monotonic, absolutely continuous and n-times differentiable mappings etc.

    For recent results and generalizations concerning Ostrowski's inequality, we refer the reader to the recent papers [1,3,4,31,32]. The convex functions play a significant role in many fields, for example in biological system, economy, optimization and so on [2,16,19,24,29,34,39]. And many important inequalities are established for these class of functions. Also the evolution of the concept of convexity has had a great impact in the community of investigators. In recent years, for example, generalized concepts such as s-convexity (see[10]), h-convexity (see [30,33]), m-convexity (see [7,15]), MT-convexity (see[21]) and others, as well as combinations of these new concepts have been introduced.

    The role of convex sets, convex functions and their generalizations are important in applied mathematics specially in nonlinear programming and optimization theory. For example in economics, convexity plays a fundamental role in equilibrium and duality theory. The convexity of sets and functions have been the object of many studies in recent years. But in many new problems encountered in applied mathematics the notion of convexity is not enough to reach favorite results and hence it is necessary to extend the notion of convexity to the new generalized notions. Recently, several extensions have been considered for the classical convex functions such that some of these new concepts are based on extension of the domain of a convex function (a convex set) to a generalized form and some of them are new definitions that there is no generalization on the domain but on the form of the definition. Some new generalized concepts in this point of view are pseudo-convex functions [22], quasi-convex functions [5], invex functions [17], preinvex functions [25], B-vex functions [20], B-preinvex functions [8], E-convex functions [38], Ostrowski Type inequalities for functions whose derivatives are (m,h1,h2)-convex [35], Féjer Type inequalities for (s,m)-convex functions in the second sense [36] and Hermite-Hadamard-Féjer Type inequalities for strongly (s,m)-convex functions with modulus C, in the second sense [9]. In numerical analysis many quadrature rules have been established to approximate the definite integrals. Ostrowski inequality provides the bounds of many numerical quadrature rules [13].

    In this paper we have established new Ostrowski's inequality given by Badreddine Meftah in [23] for s-φ-convex functions with fCn([a,b]) such that f(n)L([a,b]) and we give some applications to some special means, the midpoint formula and some examples for the case n=2.

    Recall that a real-valued function f defined in a real interval J is said to be convex if for all x,yJ and for any t[0,1] the inequality

    f(tx+(1t)y)tf(x)+(1t)f(y) (2.1)

    holds. If inequality 2.1 is strict when we say that f is strictly convex, and if inequality 2.1 is reversed the function f is said to be concave. In [37] we introduced the notion of s-φ-convex functions as a generalization of s-convex functions in first sense.

    Definition 1. Let 0<s1. A function f:IRR is called s-φ-convex with respect to bifunction φ:R×RR (briefly φ-convex), if

    f(tx+(1t)y)f(y)+tsφ(f(x),f(y)) (2.2)

    for all x,yI and t[0,1].

    Example 1. Let f(x)=x2, then f is convex and 12-φ- convex with φ(u,v)=2u+v, indeed

    f(tx+(1t)y)=(tx+(1t)y)2=t2x2+2t(1t)xy+(1t)2y2y2+tx2+2txy=y2+t12[t12x2+2t12xy].

    On the other hand;

    0<t<10<t12<1t12x2+2t12xyx2+2xyx2+x2+y2.

    Hence,

    f(tx+(1t)y)y2+t12[2x2+y2]=f(y)+t12φ(f(x),f(y)).

    Example 2. Let f(x)=xn and 0<s1, then f is convex and s-φ- convex with φ(u,v)=nk=1(nk)v1kn(u1nv1n)n, indeed

    f(tx+(1t)y)=f(y+t(xy))=(y+t(xy))n=yn+nk=1(nk)ynk(t(xy))n=yn+ts[nk=1(nk)tnsynk(xy)n]yn+ts[nk=1(nk)(yn)nkn((xn)1n(yn)1n)n].

    Remark 1. If f is increasing monotone in [a,b], then f is s-φ- convex for φ(x,y)=K, where K[0,+) and s(0,1].

    In this section, we give some integral approximation of fCn([a,b]) such that f(n)L([a,b]), for n1 using the following lemma as the main tool (see [11]).

    Lemma 1. Let f:[a,b]R be a differentiable mapping such that f(n1) is absolutely continuous on [a,b]. Then for all x[a,b] we have the identity

    baf(t)dt=nk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)+(1)nbaKn(x,t)f(n)(t)dt,

    where the kernel Kn:[a,b]2R is given by

    Kn(x,t)={(ta)nn!ift[a,x](tb)nn!ift(x,b]

    with x[a,b] and n is natural number, n1.

    Theorem 1. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1 and 0<s1. If |f(n)| is s-φ-convex, then the following inequality

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1n!(1n+1|f(n)(a)|+1n+s+1φ(|f(n)(a)|,|f(n)(x)|))+(bx)n+1n![|f(n)(x)|n+1+nk=0(nk)(1)k1k+s+1φ(|f(n)(x)|,|f(n)(b)|)]

    holds for all x[a,b].

    Proof. From Lemma 1, properties of modulus, making the changes of variables u=(1t)a+tx in the first integral and u=(1t)x+tb in the second integral we have that,

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|xa(ua)nn!|f(n)(u)|du+bx(bu)nn!|f(n)(u)|du=(xa)n+1n!10tn |f(n)((1t)a+tx)|dt+(bx)n+1n!10(1t)n |f(n)((1t)x+tb)|dt.

    Since |f(n)| is s-φ- convex (2.2) gives

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1n!10tn(|f(n)(a)|+tsφ(|f(n)(a)|,|f(n)(x)|))dt+(bx)n+1n!10(1t)n(|f(n)(x)|+tsφ(|f(n)(x)|,|f(n)(b)|))dt=(xa)n+1n!(1n+1|f(n)(a)|+1n+s+1φ(|f(n)(a)|,|f(n)(x)|))+(bx)n+1n![|f(n)(x)|n+1+nk=0(nk)(1)k1k+s+1φ(|f(n)(x)|,|f(n)(b)|)]

    which is the desired result. The proof is completed.

    Remark 2. If we take s=1 then obtain a result of Meftah B. (see Theorem 2.1 in [23]).

    Corollary 1. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1 and 0<s1. If |f(n)| is s-convex in the first sense, we have the following estimate

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|s(n+1)!(n+s+1)|f(n)(a)|+(bx)n+1n!|f(n)(b)|nk=0(nk)(1)kk+s+1+(n+1)[(xa)n+1(n+s+1)(n+1)!+(bx)n+1(n+1)!(1n+1nk=0(nk)(1)kk+s+1)]|f(n)(x)|.

    Proof. Taking φ(u,v)=vu in Theorem 1.

    Remark 3. It is important to notice that if s=1 we have that |f(n)| is convex and then obtain the corollary 2.2 of Meftah see [23].

    Theorem 2. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1 with 1p+1q=1. If |f(n)|q is s-φ-convex, then the following inequality holds

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1(s+1)1q(np+1)1pn!((s+1)|f(n)(a)|q+φ(|f(n)(a)|q,|f(n)(x)|q))1q+(bx)n+1(s+1)1q(np+1)1pn!((s+1)|f(n)(x)|q+φ(|f(n)(x)|q,|f(n)(b)|q))1q.

    Proof. From Lemma 1, properties of modulus, and Holder's inequality, we have

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|xa(ua)nn!|f(n)(u)|du+bx(bu)nn!|f(n)(u)|du=(xa)n+1n!10tn |f(n)((1t)a+tx)|dt+(bx)n+1n!10(1t)n |f(n)((1t)x+tb)|dt(xa)n+1n!(10tnpdt)1p(10|f(n)((1t)a+tx)|qdt)1q+(bx)n+1n!(10(1t)npdt)1p(10|f(n)((1t)x+tb)|qdt)1q=(xa)n+1(np+1)1pn!(10|f(n)((1t)a+tx)|qdt)1q+(bx)n+1(np+1)1pn!(10|f(n)((1t)x+tb)|qdt)1q.

    Since |f(n)|q is s-φ-convex, we deduce

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1(np+1)1pn!(10(|f(n)(a)|q+tsφ(|f(n)(a)|q,|f(n)(x)|q))dt)1q+(bx)n+1(np+1)1pn!(10(|f(n)(x)|q+tsφ(|f(n)(x)|q,|f(n)(b)|q))dt)1q
    =(xa)n+1(s+1)1q(np+1)1pn!((s+1)|f(n)(a)|q+φ(|f(n)(a)|q,|f(n)(x)|q))1q+(bx)n+1(s+1)1q(np+1)1pn!((s+1)|f(n)(x)|q+φ(|f(n)(x)|q,|f(n)(b)|q))1q.

    Corollary 2. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1 with 1p+1q=1. If |f(n)|q is s-convex in the first sense, then the following inequality holds

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1(s+1)1q(np+1)1pn!(s|f(n)(a)|q+|f(n)(x)|q)1q+(bx)n+1(s+1)1q(np+1)1pn!(s|f(n)(x)|q+|f(n)(b)|q)1q. (3.1)

    Proof. Taking φ(u,v)=vu in Theorem 1.

    Corollary 3. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1 with 1p+1q=1. If |f(n)|q is s-convex in the first sense, then the following inequality holds

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1(s+1)1q(np+1)1pn!(s|f(n)(a)|+|f(n)(x)|)+(bx)n+1(s+1)1q(np+1)1pn!(s|f(n)(x)|+|f(n)(b)|).

    Proof. Taking φ(u,v)=vu in Theorem 1, we obtain 3.1. Then using the following algebraic inequality for all a,b0, and 0α1 we have (a+b)αaα+bα, we get the desired result.

    Theorem 3. Let q>1 and f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1. If |f(n)|q is s-φconvex, then the following inequality

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(n+1)1q(xa)n+1(n+1)!(1n+1|f(n)(a)|q+1n+s+1φ(|f(n)(a)|q,|f(n)(x)|q))1q+(n+1)1q(bx)n+1(n+1)!(1n+1|f(n)(x)|q+φ(|f(n)(x)|q,|f(n)(b)|q)nk=0(nk)(1)kk+s+1)1q

    holds for all x[a,b].

    Proof. From Lemma 1, properties of modulus, and power mean inequality, we have

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|xa(ua)nn!|f(n)(u)|du+bx(bu)nn!|f(n)(u)|du=(xa)n+1n!10tn |f(n)((1t)a+tx)|dt+(bx)n+1n!10(1t)n |f(n)((1t)x+tb)|dt
    (xa)n+1n!(10tndt)11q(10tn |f(n)((1t)a+tx)|qdt)1q+(bx)n+1n!(10(1t)ndt)11q(10(1t)n |f(n)((1t)x+tb)|qdt)1q=(n+1)1q(xa)n+1(n+1)!(10tn |f(n)((1t)a+tx)|qdt)1q+(n+1)1q(bx)n+1(n+1)!(10(1t)n |f(n)((1t)x+tb)|qdt)1q.

    Since |f(n)|q is s-φ-convex, we deduce

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(n+1)1q(xa)n+1(n+1)!(|f(n)(a)|q10tndt+φ(|f(n)(a)|q,|f(n)(x)|q)10tn+sdt)1q+(n+1)1q(bx)n+1(n+1)!(|f(n)(x)|q10(1t)ndt+φ(|f(n)(x)|q,|f(n)(b)|q)10ts(1t)ndt)1q=(n+1)1q(xa)n+1(n+1)!(1n+1|f(n)(a)|q+1n+s+1φ(|f(n)(a)|q,|f(n)(x)|q))1q+(n+1)1q(bx)n+1(n+1)!(1n+1|f(n)(x)|q+φ(|f(n)(x)|q,|f(n)(b)|q)nk=0(nk)(1)kk+s+1)1q.

    The proof is completed.

    Remark 4. If we take s=1 then obtain a result of Meftah B. (see Theorem 2.6 in [23]).

    Corollary 4. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1. If |f(n)|q is s-convex in the first sense, then the following inequality

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(n+1)1q(xa)n+1(n+s+1)1q(n+1)!(s|f(n)(a)|qn+1+|f(n)(x)|q)1q+(n+1)1q(bx)n+1(n+1)!(1n+1|f(n)(x)|q+[|f(n)(b)|q|f(n)(x)|q]nk=0(nk)(1)kk+s+1)1q

    holds for all x[a,b].

    Proof. Taking φ(u,v)=vu in Theorem 3.

    Theorem 4. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1. If |f(n)|q is s-φ-convex, then the following inequality

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1n!(1qn+1|f(n)(a)|q+1qn+s+1φ(|f(n)(a)|q,|f(n)(x)|q))1q+(bx)n+1n!(1qn+1|f(n)(x)|q+qnk=0(qnk)(1)kk+s+1φ(|f(n)(x)|q,|f(n)(b)|q))1q

    holds for all x[a,b].

    Proof. From Lemma 1, properties of modulus, and power mean inequality, we have

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|xa(ua)nn!|f(n)(u)|du+bx(bu)nn!|f(n)(u)|du=(xa)n+1n!10tn |f(n)((1t)a+tx)|dt+(bx)n+1n!10(1t)n |f(n)((1t)x+tb)|dt(xa)n+1n!(10dt)11q(10tqn |f(n)((1t)a+tx)|qdt)1q+(bx)n+1n!(10dt)11q(10(1t)qn |f(n)((1t)x+tb)|qdt)1q=(xa)n+1n!(10tqn |f(n)((1t)a+tx)|qdt)1q+(bx)n+1n!(10(1t)qn |f(n)((1t)x+tb)|qdt)1q.

    Since |f(n)|q is s-φ-convex, we deduce

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1n!(|f(n)(a)|q10tqndt+φ(|f(n)(a)|q,|f(n)(x)|q)10tqn+sdt)1q+(bx)n+1n!(|f(n)(x)|q10(1t)qndt+φ(|f(n)(x)|q,|f(n)(b)|q)10ts(1t)qndt)1q
    =(xa)n+1n!(1qn+1|f(n)(a)|q+1qn+s+1φ(|f(n)(a)|q,|f(n)(x)|q))1q+(bx)n+1n!(1qn+1|f(n)(x)|q+qnk=0(qnk)(1)kk+s+1φ(|f(n)(x)|q,|f(n)(b)|q))1q

    which in the desired result.

    Remark 5. If we take s=1 then obtain a result of Meftah B. (see Theorem 2.9 in [23]).

    Corollary 5. Let f:IR be n-times differentiable on [a,b] such that f(n)L([a,b]) with n1, 0<s1 and let q>1. If |f(n)|q is s-convex in the first sense, then the following inequality

    |baf(t)dtnk=0[(bx)k+1+(1)k(xa)k+1(k+1)!]f(k)(x)|(xa)n+1n!(1qn+1|f(n)(a)|q+|f(n)(x)|q|f(n)(a)|qqn+s+1)1q+(bx)n+1n!(1qn+1|f(n)(x)|q+qnk=0(qnk)(1)kk+s+1(|f(n)(b)|q|f(n)(x)|q))1q

    holds for all x[a,b].

    Proof. Taking φ(u,v)=vu in Theorem 4.

    In this section, using [12] we define s-φb-convex function as generalized form of s-φ convex functions [37] and give some results.

    Definition 2. Let R+ be the set of nonnegative real numbers and b:R×R×[0,1]R+ be a function with tsb(x,y,t)[0,1] for all x,yR, t[0,1] and s(0,1]. A function f:IR is called s-φb-convex if

    f(tx+(1t)y)f(y)+tsb(x,y,t)φ(f(x),f(y))

    for all x,yR and t[0,1].

    Remark 6. If b(x,y,z)=1 then the definition of s-φb-convex function matches the definition of s-φ-convex function.

    Theorem 5. Consider a function f:IR and b:R×R×[0,1]R+ be a function with tsb(x,y,t)[0,1] for all x,yR and s,t[0,1]. Then the following assertions are equivalent:

    (i) f is s-φb-convex for some b and s[0,1].

    (ii) f is φ-quasiconvex.

    Proof. (i)(ii) For any x,yI and t[0,1],

    f(tx+(1t)y)f(y)+tsb(x,y,t)φ(f(x),f(y))max{f(y),f(y)+φ(f(x),f(y))}.

    (ii)(i) For x,yI and t[0,1], define

    b(x,y,t)={1ts if t[0,1] and f(y)f(y)+φ(f(x),f(y))0 if t=0 or f(y)>f(y)+φ(f(x),f(y))

    Notice that tsb(x,y,t)[0,1]. For a such function b we have

    f(tx+(1t)y)max{f(y),f(y)+φ(f(x),f(y))}=tsb(x,y,t)[f(y)+φ(f(x),f(y))+(1tsb(x,y,t))]f(y)=f(y)+tsb(x,y,t)φ(f(x),f(y)).

    Remark 7. Let f:IR be a s-φ-convex function. For x1,x2I and α1+α2=1, we have f(α1x1+α2x2)f(x2)+αs1φ(f(x1),f(x2)). Aso when n>2, for x1,x2,...,xnI, ni=1αi=1 and Ti=ij=1αj, we have

    f(ni=1αixi)=f((Tn1n1i=1αiTn1xi)+αnxn)f(xn)+Tsn1φ(f(n1i=1αiTn1xi),f(xn)). (4.1)

    Theorem 6. Let f:IR be a s-φ-convex function and φ be nondecreasing nonnegatively sublinear in first variable. If Ti=ij=1αj for i=1,2,...,n such that Tn=1, then

    f(ni=1αixi)f(xn)+n1i=1Tsiφf(xi,xi+1,...,xn),

    where φf(xi,xi+1,...,xn)=φ(φf(xi,xi+1,...,xn1),f(xn)) and φf(x)=f(x) for all xI.

    Proof. Since φ is nondecreasing nonnegatively sublinear on first variable, so from (4.1) it follows that:

    f(ni=1αixi)=f((Tn1n1i=1αiTn1xi)+αnxn)f(xn)+Tsn1φ(f(n1i=1αiTn1xi),f(xn))=f(xn)+(Tn1)sφ(f(Tn2Tn1n2i=1αiTn2xi+αn1Tn1xn1),f(xn))f(xn)+(Tn1)sφ(f(xn1)+(Tn2Tn1)sφ(f(n2i=1αiTn2xi),f(xn1)),f(xn))f(xn)+(Tn1)sφ(f(xn1),f(xn))+(Tn2)sφ(φ(f(n2i=1αiTn2xi),f(xn1)),f(xn))...
    f(xn)+(Tn1)sφ(f(xn1),f(xn))+(Tn2)sφ(φ(f(xn2),f(xn1)),f(xn))+...+Ts1φ(φ(...φ(φ(f(x1),f(x2)),f(x3)...),f(xn1)),f(xn))=f(xn)+(Tn1)sφf(xn1,xn)+(Tn2)sφf(xn2,xn1,xn)+...+(T1)sφf(x1,x2,...,xn1,xn)=f(xn)+n1i=1Tsiφf(xi,xi+1,...,xn).

    Example 3. Consider f(x)=x2 and φ(x,y)=2x+y for x,yR+=[0,+). The function φ is nondecreasing nonnegatively sublinear in first variable and f is 12-φ-convex (see Example 1). Now for x1,x2,...,xnR+ and α1,α2,...,αn with ni=1αi=1 according to Theorem 6 we have

    (ni=1αixi)2(xn)2+n1i=1T12iφf(xi,xi+1,...,xn)(xn)2+n1i=1T12i[2[...2[2x2i+x2i+1]+x2i+2]+...+x2n].

    In this section we give some applications for the special case where n=2 and the function φ(f(x),f(y))=f(y)f(x), in this case we have that f is s-convex in the first sense.

    Example 4. Let s(0,1) and p,q,rR, we define the function f:[0,+)R as

    f(t)={pift=0qts+rift>0,

    we have that if q0 and rp, then f is s-convex in the first sense (see [18]). If we do φ(f(x),f(y))=f(x)f(y), then f is s-φ-convex, but is not φ-convex because f is not convex.

    Example 5. In the previous example if s=12, p=1, q=2 and r=1 we have that f:[0,+)R,f(t)=2t12+1 is 12-φ-convex. Then if we define g:[0,+)R, g(t)=815t52+t22, we have to g(t)=2t12+1 is 12-φ-convex in [0,+) with φ(f(x),f(y))=f(x)f(y). Using Theorem 1, for a,b[0,+) with a<b and x[a,b], we get

    |16(b72a72)+35(a3b3)x+35(b2a2)x32+21(ab)x52|352(1+2b)(bx)3103(72+a+6b)(ax)3.

    Remark 6. In particular if we choose a=0 and b=1, we have for x[0,1], we get a graphic representation of the Example 5.

    Example 6. If we define g(t)=t412 we have that g(t) is 12-φ- convex with φ(u,v)=2u+v (see example 1) and by Theorem 1, for a,bR with a<b and x[a,b], we have that

    |b5a560(ba)12x4[b22x(ba)a23]x3[(bx)3+(xa)36]x2|(xa)3[x256a2]+(bx)3[19210x2+8105b2].

    Moreover, if choose x=a+b2, we obtain that

    |b5a560(ba)(a+b)4192(ba)3(a+b)296|(ba)316[a23+9a2+2ab+b214+(a+b)212+8a2+16ab+24b2105].

    Then

    |(ab)5|(ba)37(477a2+194ab+161b2).

    Therefore

    (ab)2477a2+194ab+161b27.

    Example 7. If we define g(t)=369132 t136 we have that |g(t)|3 is 12-φ-convex with φ(u,v)=2u+v (see example 1) and by Theorem 4, for a,bR with a<b and x[a,b], we have

    |2161729[b196a196]36x13691(ba)+6x7614[(bx)2(xa)2]+x166[(bx)3+(xa)3]|(xa)32348(a12+2x12)13+(bx)32348(x12+2b12)13.

    In this paper we have established new Ostrowski's inequality given by Badreddine Meftah in [23] for sφconvex functions with fCn([a,b]) such that f(n)L([a,b]) with n1 and we give some applications to some special means, the midpoint formula and some examples for the case n=2. We expect that the ideas and techniques used in this paper may inspire interested readers to explore some new applications of these newly introduced explore some new applications of these newly introduced functions in various fields of pure and applied sciences.

    The authors want to give thanks to the Dirección de investigación from Pontificia Universidad Católica del Ecuador for technical support to our research project entitled: "Algunas desigualdades integrales para funciones convexas generalizadas y aplicaciones".

    The authors declare that they have no conflicts of interest.



    [1] B. B. Ahundjanov, S. B. Akhundjanov, B. B. Okhunjanov, Risk perception and oil and gasoline markets under COVID-19, J. Econ. Bus., 115 (2021), 105979. https://doi.org/10.1016/j.jeconbus.2020.105979 doi: 10.1016/j.jeconbus.2020.105979
    [2] C. T. Vidya, K. P. Prabheesh, Implications of COVID-19 pandemic on the global trade networks, Emerg. Mark. Financ. Tr., 56 (2020), 2408–2421. https://doi.org/10.1080/1540496X.2020.1785426 doi: 10.1080/1540496X.2020.1785426
    [3] M. Ali, N. Alam, S. A. R. Rizvi, Coronavirus (COVID-19). An epidemic or pandemic for financial markets, J. Behav. Expe. Financ., 27 (2020), 100341. https://doi.org/10.1016/j.jbef.2020.100341 doi: 10.1016/j.jbef.2020.100341
    [4] W. Zhao, S. K. Khosa, Z. Ahmad, M. Aslam, A. Z. Afify, Type-Ⅰ heavy tailed family with applications in medicine, engineering and insurance, Plos One, 15 (2020), e0237462. https://doi.org/10.1371/journal.pone.0237462 doi: 10.1371/journal.pone.0237462
    [5] R. Gerlagh, R. J. Heijmans, K. E. Rosendahl, COVID-19 tests the market stability reserve, Environ. Resour. Econ., 76 (2020), 855–865. https://doi.org/10.1007/s10640-020-00441-0 doi: 10.1007/s10640-020-00441-0
    [6] C. Gharib, S. Mefteh-Wali, S. B. Jabeur, The bubble contagion effect of COVID-19 outbreak: Evidence from crude oil and gold markets, Financ. Res. Lett., 38 (2021), 101703. https://doi.org/10.1016/j.frl.2020.101703 doi: 10.1016/j.frl.2020.101703
    [7] Z. Ahmad, E. Mahmoudi, S. Dey, S. K. Khosa, Modeling vehicle insurance loss data using a new member of TX family of distributions, J. Stat. Theory Appl., 19 (2020), 133–147. https://doi.org/10.2991/jsta.d.200421.001 doi: 10.2991/jsta.d.200421.001
    [8] D. Zhang, M. Hu, Q. Ji, Financial markets under the global pandemic of COVID-19, Financ. Res. Lett., 36 (2020), 101528. https://doi.org/10.1016/j.frl.2020.101528 doi: 10.1016/j.frl.2020.101528
    [9] E. Arrigo, C. Liberati, P. Mariani, Social media data and users' preferences: A statistical analysis to support marketing communication, Big Data Res., 24 (2021), 100189. https://doi.org/10.1016/j.bdr.2021.100189 doi: 10.1016/j.bdr.2021.100189
    [10] M. Z. Rashid, A. S. Akhter, Survival weighted power function distribution with applications to medical, oceanology and metrology data, Adv. Appl. Stat., 67 (2021), 117–253. https://doi.org/10.17654/AS067020133 doi: 10.17654/AS067020133
    [11] W. Wang, Z. Ahmad, O. Kharazmi, C. B. Ampadu, E. H. Hafez, M. M. M. El-Din, New generalized-X family: Modeling the reliability engineering applications, Plos One, 16 (2021), e0248312. https://doi.org/10.1371/journal.pone.0248312 doi: 10.1371/journal.pone.0248312
    [12] C. S. Kumar, S. R. Nair, A generalized Log-Weibull distribution with bio-medical applications, Int. J. Stat. Med. Res., 10 (2021), 10–21. https://doi.org/10.6000/1929-6029.2021.10.02 doi: 10.6000/1929-6029.2021.10.02
    [13] H. S. Bakouch, C. Chesneau, O. A. Elsamadony, The Gumbel kernel for estimating the probability density function with application to hydrology data, J. Data Inform. Manag., 3 (2021), 261–269. https://doi.org/10.1007/s42488-021-00058-y doi: 10.1007/s42488-021-00058-y
    [14] D. Bhati, S. Ravi, On generalized log-Moyal distribution: A new heavy tailed size distribution, Insur. Math. Econ., 79 (2018), 247–259. https://doi.org/10.1016/j.insmatheco.2018.02.002 doi: 10.1016/j.insmatheco.2018.02.002
    [15] Z. Ahmad, E. Mahmoudi, G. G. Hamedani, O. Kharazmi, New methods to define heavy-tailed distributions with applications to insurance data, J. Taibah Univ. Sci., 14 (2020), 359–382. https://doi.org/10.1080/16583655.2020.1741942 doi: 10.1080/16583655.2020.1741942
    [16] Z. Li, J. Beirlant, S. Meng, Generalizing the log-Moyal distribution and regression models for heavy-tailed loss data, ASTIN Bull. J. IAA, 51 (2021), 57–99. https://doi.org/10.1017/asb.2020.35 doi: 10.1017/asb.2020.35
    [17] Ł. Bielak, A. Grzesiek, J. Janczura, A. Wyłomańska, Market risk factors analysis for an international mining company. Multi-dimensional, heavy-tailed-based modelling, Resour. Policy, 74 (2021), 102308. https://doi.org/10.1016/j.resourpol.2021.102308 doi: 10.1016/j.resourpol.2021.102308
    [18] D. B. Madan, Multivariate distributions for financial returns, Int. J. Theor. Appl. Fin., 23 (2020), 20500417. https://doi.org/10.1142/S0219024920500417 doi: 10.1142/S0219024920500417
    [19] C. O. Cepoi, Asymmetric dependence between stock market returns and news during COVID-19 financial turmoil, Financ. Res. Lett., 36 (2020), 101658. https://doi.org/10.1016/j.frl.2020.101658 doi: 10.1016/j.frl.2020.101658
    [20] W. Wang, W. Li, N. Zhang, K. Liu, Portfolio formation with preselection using deep learning from long-term financial data, Expert Syst. Appl., 143 (2020), 113042. https://doi.org/10.1016/j.eswa.2019.113042 doi: 10.1016/j.eswa.2019.113042
    [21] S. M. Carta, S. Consoli, A. S. Podda, D. R. Recupero, M. M. Stanciu, Ensembling and dynamic asset selection for risk-controlled statistical arbitrage, IEEE Access, 9 (2021), 29942–29959. https://doi.org/10.1109/ACCESS.2021.3059187 doi: 10.1109/ACCESS.2021.3059187
    [22] L. W. Cong, K. Tang, J. Wang, Y. Zhang, Deep sequence modeling: Development and applications in asset pricing, J. Financ. Data Sci., 3 (2021), 28–42. https://doi.org/10.3905/jfds.2020.1.053 doi: 10.3905/jfds.2020.1.053
    [23] F. Schuhmacher, H. Kohrs, B. R. Auer, Justifying mean-variance portfolio selection when asset returns are skewed, Manag. Sci., 67 (2021), 7812–7824. https://doi.org/10.1287/mnsc.2020.3846 doi: 10.1287/mnsc.2020.3846
    [24] S. Karim, M. U. Akhtar, R. Tashfeen, M. R. Rabbani, A. A. A. Rahman, A. AlAbbas, Sustainable banking regulations pre and during coronavirus outbreak: The moderating role of financial stability, Econ. Res.-Ekon. Istraž., 35 (2022), 3360–3377. https://doi.org/10.1080/1331677X.2021.1993951 doi: 10.1080/1331677X.2021.1993951
    [25] Z. Ahmad, G. G. Hamedani, N. S. Butt, Recent developments in distribution theory: A brief survey and some new generalized classes of distributions, Pak. J. Stat. Oper. Res., 15 (2019), 87–110. https://doi.org/10.18187/pjsor.v15i1.2803 doi: 10.18187/pjsor.v15i1.2803
    [26] A. Alzaatreh, C. Lee, F. Famoye, A new method for generating families of continuous distributions, Metron, 71 (2013), 63–79. https://doi.org/10.1007/s40300-013-0007-y doi: 10.1007/s40300-013-0007-y
    [27] J. L. Castle, J. A. Doornik, D. F. Hendry, Modelling non-stationary 'big data', Int. J. Forecasting, 37 (2021), 1556–1575. https://doi.org/10.1016/j.ijforecast.2020.08.002 doi: 10.1016/j.ijforecast.2020.08.002
    [28] F. Khan, A. Urooj, K. Ullah, B. Alnssyan, Z. Almaspoor, A comparison of Autometrics and penalization techniques under various error distributions: Evidence from Monte Carlo simulation, Complexity, 2021. https://doi.org/10.1155/2021/9223763 doi: 10.1155/2021/9223763
    [29] R. Tibshirani, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. B, 58 (1996), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x doi: 10.1111/j.2517-6161.1996.tb02080.x
    [30] F. Khan, A. Urooj, S. A. Khan, S. K. Khosa, S. Muhammadullah, Z. Almaspoor, Evaluating the performance of feature selection methods using huge big data: A Monte Carlo simulation approach, Math. Prob. Eng., 2022. https://doi.org/10.1155/2022/6607330 doi: 10.1155/2022/6607330
    [31] S. Smeekes, E. Wijler, Macroeconomic forecasting using penalized regression methods, Int. J. Forecasting, 34 (2018), 408–430. https://doi.org/10.1016/j.ijforecast.2018.01.001 doi: 10.1016/j.ijforecast.2018.01.001
    [32] J. H. Stock, M. W. Watson, Macroeconomic forecasting using diffusion indexes, J. Bus. Econ. Stat., 20 (2002), 147–162. https://doi.org/10.1198/073500102317351921 doi: 10.1198/073500102317351921
  • This article has been cited by:

    1. Heng YANG, Jiang ZHOU , Necessary and sufficient conditions for boundedness of commutators of parametric Marcinkiewicz integrals with weighted Lipschitz functions, 2024, 25, 14549069, 277, 10.59277/PRA-SER.A.25.4.03
  • Reader Comments
  • © 2023 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)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(1995) PDF downloads(61) Cited by(6)

Figures and Tables

Figures(19)  /  Tables(9)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog