General asymptotic representations of indexes based on the functional empirical process and the residual functional empirical process and applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915433210183680 |
|---|---|
| author | Lo, Gane Samb Kpanzou, Tchilabalo Abozou Da, Gandasor Bonyiri Onesiphore |
| author_facet | Lo, Gane Samb Kpanzou, Tchilabalo Abozou Da, Gandasor Bonyiri Onesiphore |
| contents | The objective of this paper is to establish a general asymptotic representation (\textit{GAR}) for a wide range of statistics, employing two fundamental processes: the functional empirical process (\textit{fep}) and the residual functional empirical process introduced by Lo and Sall (2010a, 2010b), denoted as \textit{lrfep}. The functional empirical process (\textit{fep}) is defined as follows:
$$ \mathbb{G}_n(h)=\frac{1}{\sqrt{n}} \sum_{j=1}^{n} \{h(X_j)-\mathbb{E}h(X_j)\}, $$
\Bin [where $X$, $X_1$, $\cdots$, $X_n$ is a sample from a random $d$-vectors $X$ of size $(n+1)$ with $n\geq 1$ and $h$ is a measurable function defined on $\mathbb{R}^d$ such that $\mathbb{E}h(X)^2<+\infty$]. It is a powerful tool for deriving asymptotic laws. An earlier and simpler version of this paper focused on the application of the (\textit{fep}) to statistics $J_n$ that can be turned into an asymptotic algebraic expression of empirical functions of the form
$$ J_n=\mathbb{E}h(X) + n^{-1/2} \mathbb{G}_n(h) + o_{\mathbb{P}}(n^{-1/2}). \ \ \ \textit{SGAR} $$
\Bin However, not all statistics, in particular welfare indexes, conform to this form. In many scenarios, functions of the order statistics $X_{1,n}\leq$, $\cdots$, $\leq X_{n,n}$ are involved, resulting in $L$-statistics. In such cases, the (\textit{fep}) can still be utilized, but in combination with the related residual functional empirical process introduced by Lo and Sall (2010a, 2010b). This combination leads to general asymptotic representations (GAR) for a wide range of statistical indexes
$$ J_n=\mathbb{E}h(X) + n^{-1/2} \biggr(\mathbb{G}_n(h) + \int_{0}^{1} \mathbb{G}_n(\tilde{f}_s) \ell(s) \ ds + o_{\mathbb{P}}(1)\biggr), \ \ \textit{FGAR} $$ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | General asymptotic representations of indexes based on the functional empirical process and the residual functional empirical process and applications Lo, Gane Samb Kpanzou, Tchilabalo Abozou Da, Gandasor Bonyiri Onesiphore Statistics Theory Probability The objective of this paper is to establish a general asymptotic representation (\textit{GAR}) for a wide range of statistics, employing two fundamental processes: the functional empirical process (\textit{fep}) and the residual functional empirical process introduced by Lo and Sall (2010a, 2010b), denoted as \textit{lrfep}. The functional empirical process (\textit{fep}) is defined as follows: $$ \mathbb{G}_n(h)=\frac{1}{\sqrt{n}} \sum_{j=1}^{n} \{h(X_j)-\mathbb{E}h(X_j)\}, $$ \Bin [where $X$, $X_1$, $\cdots$, $X_n$ is a sample from a random $d$-vectors $X$ of size $(n+1)$ with $n\geq 1$ and $h$ is a measurable function defined on $\mathbb{R}^d$ such that $\mathbb{E}h(X)^2<+\infty$]. It is a powerful tool for deriving asymptotic laws. An earlier and simpler version of this paper focused on the application of the (\textit{fep}) to statistics $J_n$ that can be turned into an asymptotic algebraic expression of empirical functions of the form $$ J_n=\mathbb{E}h(X) + n^{-1/2} \mathbb{G}_n(h) + o_{\mathbb{P}}(n^{-1/2}). \ \ \ \textit{SGAR} $$ \Bin However, not all statistics, in particular welfare indexes, conform to this form. In many scenarios, functions of the order statistics $X_{1,n}\leq$, $\cdots$, $\leq X_{n,n}$ are involved, resulting in $L$-statistics. In such cases, the (\textit{fep}) can still be utilized, but in combination with the related residual functional empirical process introduced by Lo and Sall (2010a, 2010b). This combination leads to general asymptotic representations (GAR) for a wide range of statistical indexes $$ J_n=\mathbb{E}h(X) + n^{-1/2} \biggr(\mathbb{G}_n(h) + \int_{0}^{1} \mathbb{G}_n(\tilde{f}_s) \ell(s) \ ds + o_{\mathbb{P}}(1)\biggr), \ \ \textit{FGAR} $$ |
| title | General asymptotic representations of indexes based on the functional empirical process and the residual functional empirical process and applications |
| topic | Statistics Theory Probability |
| url | https://arxiv.org/abs/2508.04905 |