Results 31 to 40 of about 222 (103)

Exponential inequalities for nonstationary Markov chains

Dependence Modeling, 2019
Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables.
Alquier Pierre, Doukhan Paul, Fan Xiequan   +2 more
doaj   +1 more source

Discussion of “High-dimensional autocovariance matrices and optimal linear prediction”

, 2015
: In this note I provide some discussion on the paper by “High-dimensional auto covariance matrices and optimal linear prediction” by T. McMurry and D. Politis. MSC 2010 subject classifications: Primary 62M10; secondary 62H12.
Xiaohui Chen
semanticscholar   +1 more source

MONTE CARLO AND NUMERICAL METHODS TO SOLVE THE TIME SERIES MODEL

Analele Universitatii Bucuresti. Informatica
In this paper we will solve the nonlinear system of equations in the parameters of the time series model by Monte Carlo methods and by numerical methods.
Daniel Ciuiu
semanticscholar   +1 more source

Pronóstico de series de tiempo con tendencia y ciclo estacional usando el modelo airline y redes neuronales artificiales

Ingeniería y Ciencia, 2012
Muchas series de tiempo con tendencia y ciclos estacionales son exitosamente modeladas y pronosticadas usando el modelo airline de Box y Jenkins; sin embargo, la presencia de no linealidades en los datos son despreciadas por este modelo. En este artículo,
J D Velásquez, C J Franco
doaj   +1 more source

Modelo en series de tiempo para la tasa de penetración de un pozo de petróleo de referencia: Caso Puerto Boyacá - Colombia

Ingeniería y Ciencia, 2015
En este trabajo se identificó un modelo en series de tiempo para el control de la tasa de penetración (ROP) en un pozo de referencia denominado V∗∗∗ que pertenece al campo en desarrollo VEL que está ubicado en la cuenca del Valle del Magdalena Medio (VMM)
Henry Daniel Hernández Martínez, Diego Fernando Lemus Polanía   +1 more
doaj   +1 more source

Functional limit theorems in Hölder space for residuals of nearly nonstationary AR1 process

, 2018
We investigate the polygonal line process built on the residuals of the first order nearly nonstationary autoregressive process. We prove functional limit theorems in Hölder space in two cases: the autoregressive coefficient φn is defined as e, γ < 0 is ...
J. Markevičiūtė
semanticscholar   +1 more source

Recursiveness in Hilbert spaces and application to mixed $ARMA(p,q)$ process

, 2014
In this paper, the gap between the nonhomogeneous linear recurrence relation and the mixed ARMA(p; q) process in Hilbert spaces is provided. We focus ourselves on the case when the ARMA(p; q) process is of Fibonacci type. Notably, involving properties of
R. B. Taher, M. Rachidi, M. Samih
semanticscholar   +1 more source

Maximum likelihood estimators in linear regression models with Ornstein-Uhlenbeck process

, 2014
The paper studies the linear regression model yt=xtTβ+εt,t=1,2,…,n, where dεt=λ(μ−εt)dt+σdBt, with parameters λ,σ∈R+, μ∈R and {Bt,t≥0} the standard Brownian motion. Firstly, the maximum likelihood (ML) estimators of β, λ and σ2 are given.
Hongchang Hu, Xiong Pan, Lifeng Xu
semanticscholar   +1 more source

Single proxy synthetic control

Journal of Causal Inference
Synthetic control methods are widely used to estimate the treatment effect on a single treated unit in time-series settings. A common approach to estimate synthetic control weights is to regress the treated unit’s pretreatment outcome and covariates ...
Park Chan, Tchetgen Tchetgen Eric J.
doaj   +1 more source

Optimal precision of coarse structural nested mean models to estimate the effect of initiating ART in early and acute HIV infection

Journal of Causal Inference
Time-dependent coarse structural nested mean models (coarse SNMMs) were developed to estimate treatment effects from longitudinal observational data. Coarse SNMMs estimate the combined effect of multiple treatment dosages and are thus useful to estimate ...
Lok Judith J.
doaj   +1 more source