Nonparametric harmonic regression for estuarine water quality data

Autin, Melanie; Edwards, Don

doi:10.1002/env.1013

Cited by 8 publications

(5 citation statements)

References 5 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para auxiliar este tipos de estudo buscam-se recursos a fim de superar tais dificuldades, como exemplo, a Análise Multivariada, especificamente neste artigo, a Análise Fatorial e Análise de Componentes Principais AF/ACP. Este tipo de análise promove a extração de informações significativas de grandes quantidades de dados e assim, a redução do número de variáveis com o mínimo de perdas das informações (AUTIN; EDWARDS, 2010;VANZELA et al, 2010;AKBAR et al, 2011;AWADALLAH et al, 2011;MENDONÇA;SOUZA, 2011;SPEZIA et al, 2011;TU, 2011;BABOROWSKI et al, 2012;GUEDES et al, 2012;SHEELA et al, 2012;ROCHA et al, 2014).…”

Section: Introductionunclassified

Variação temporal de parâmetros limnológicos em manancial de abastecimento em Juiz de Fora, MG

Rocha¹,

Costa²

2015

RBRH

View full text Add to dashboard Cite

A disponibilidade de bases de dados temporal dos parâmetros limnológicos de um manancial pode ser tratada estatisticamente para entender como está a sua qualidade. A Companhia de Saneamento Municipal de Juiz de Fora monitora mensalmente a captação da Represa de São Pedro, disponibilizando os dados de 1998 a 2012, os quais foram tratados estatisticamente por meio do teste t de Student e da Análise Fatorial / Análise de Componentes Principais (AF/ACP). Através do primeiro teste, foi possível constatar a influência sazonal sobre os parâmetros cor, demanda bioquímica de oxigênio, ferro, oxigênio consumido e condutividade. A AF/ACP excluiu as três últimas variáveis citadas e o pH, resultando na extração de três componentes principais que juntas explicaram 73% da variação total dos dados. A primeira componente refletiu o aporte de material alóctone carreado pelo escoamento superficial e erosão; a segunda e terceira componentes estão associadas à contribuição orgânica como lançamento de esgotos, excrementos de animais e fertilizantes, respectivamente, acentuados principalmente pelo uso do solo e pela ausência ou fragmentação das matas ciliares. Estes fatores sugerem interferência antrópica negativa sobre a água do manancial estudado. Palavras Chave: AF/ACP. Uso da terra. Bacia hidrográficaThe availability of temporal data bases of limnological parameters of a catchment can be treated statistically to understand the quality status. The Municipal Sanitation Company of Juiz de Fora monitors the water catchment of São Pedro Reservoir monthly, providing data from 1998 to 2012, which were statistically treated using Student's t test and Factor Analysis / Principal Components Analysis (FA/PCA). The first test determined the seasonal influence on the color, biochemical oxygen demand, iron, oxygen consumed and conductivity parameters. The AF / ACP excluded the last three mentioned variables and pH, resulting in the extraction of three major components that together explained 73 % of the total variation in the data. The first component reflected the contribution of allochthonous material carried by runoff and erosion; the second and third components are associated with the organic contribution such as the discharge of sewage, animal excrement and fertilizers, respectively, increased mostly by land use and by the absence or fragmentation of riparian forests. These factors suggest negative human interference in the water of the studied catchment.

show abstract

Section: Introductionunclassified

Variação temporal de parâmetros limnológicos em manancial de abastecimento em Juiz de Fora, MG

Rocha¹,

Costa²

2015

RBRH

View full text Add to dashboard Cite

show abstract

“…Several variants of the aforementioned harmonic regression models have been applied recently for modelling water quality (Autin and Edwards, 2010), economic recessions (Bujosa, García-Ferrer, and de Juan, 2013), and chirp signals Mitra, 2013, 2014). For such models, Mitra, Mitra, and Kundu (2011) developed robust M -estimates for sequential estimation of sinusoidal signals while (Lahiri et al, 2014) considered least absolute deviations (LADs) estimation of one-dimensional chirp signals.…”

Section: Example 13 a More General Form Of The Model (3) Is The Freqmentioning

confidence: 99%

Generalised signed-rank estimation for nonlinear models with multidimensional indices

Nguelifack

Kwessi

Abebe

2015

Journal of Nonparametric Statistics

View full text Add to dashboard Cite

We consider a nonlinear regression model when the index variable is multidimensional. Such models are useful in signal processing, texture modelling, and spatio-temporal data analysis. A generalised form of the signed-rank estimator of the nonlinear regression coefficients is proposed. This general form of the signed-rank (SR) estimator includes L p estimators and hybrid variants. Sufficient conditions for strong consistency and asymptotic normality of the estimator are given. It is shown that the rate of convergence to normality can be different from √ n. The sufficient conditions are weak in the sense that they are satisfied by harmonic-type functions for which results in the current literature may not apply. A simulation study shows that certain generalised SR estimators (e.g. signed rank) perform better in recovering signals than others (e.g. least squares) when the error distribution is contaminated or is heavy-tailed.

show abstract

“…However, generalized additive models (GAMs) afford more flexibility in the response function since they accept parametric, semiparametric, and nonparametric regression functions of the predictor variables. A comparative study of the use of harmonic regression, GAMs with cubic regression splines, and GAMs with cyclic regression splines in simulations and water quality data from the US National Estuarine Research Reserve System (NERRS) was reported . While the classical harmonic regression model worked well with clean, near-sinusoidal data, GAMs proved competitive and highly promising for more complex data.…”

Section: Environmetricsmentioning

confidence: 99%

“…A comparative study of the use of harmonic regression, GAMs with cubic regression splines, and GAMs with cyclic regression splines in simulations and water quality data from the US National Estuarine Research Reserve System (NERRS) was reported. 226 While the classical harmonic regression model worked well with clean, near-sinusoidal data, GAMs proved competitive and highly promising for more complex data. In addition, GAMs are more adaptive and require less intervention.…”

Section: ' Environmetricsmentioning

confidence: 99%