BACON: blocked adaptive computationally efficient outlier nominators

Billor, Nedret; Hadi, Ali S.; Velleman, Paul F.

doi:10.1016/s0167-9473(99)00101-2

Cited by 444 publications

(277 citation statements)

References 26 publications

Supporting

Mentioning

271

Contrasting

Unclassified

Order By: Relevance

“…2 We think it is important not to, a priori, drop what may seem to be outliers without direct evidence. In this paper, outliers are only dropped when experiencing problems in running regressions, by using the BACON procedure in STATA (Billor et al 2000). 3 We found a significant number of firms were allocated the wrong firm ID marker in the original data, which we corrected using company name, detailed location and 5-digit industry SIC codes.…”

mentioning

confidence: 99%

The determinants of productivity in Chinese large and medium-sized industrial firms, 1998–2007

2015

View full text Add to dashboard Cite

Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract Using a large firm-level dataset, this paper examines total factor productivity (TFP) and its determinants in China. Our preferred GMM estimation results indicate increasing returns to scale in most industries and a usually large positive trend representing technical change.Various firm characteristics such as age, ownership, political affiliation, export behavior, liquidity, and geographic location are included in the production function. Our results show that in the context of China's institutional background, including such factors is important when estimating TFP. The average TFP growth in Chinese industries is 9.6 % per annum during the period 1998-2007, and is mainly driven by firm entry. The subsector decomposition exercises show that the inter-firm resource reallocations are more prominent across industries than across provinces.

show abstract

mentioning

confidence: 99%

The determinants of productivity in Chinese large and medium-sized industrial firms, 1998–2007

2015

View full text Add to dashboard Cite

show abstract

“…The great advantage of using HAT, compared to other methods, is the joint identification of OUTs, IPs, and OUT+IPs. Billor et al (2000), Habshah et al (2009), Nurunnabi, Imon, and Nasser (2011), and Nurunnabi, Imon, and Nasser (2016 used various methods of IP identification and observed that IPs as undesirable values should be characterised with caution, because the removal of these values may worsen the analysed adjustment.…”

Section: Discussionmentioning

confidence: 99%

Software for the detection of outliers and influential points based on the HAT method

Moraes¹,

Rolim²,

Aparecido³

2017

Aust J Crop Sci

View full text Add to dashboard Cite

We developed software in Visual Basic for application in Microsoft Excel that identifies outliers (OUTs) and influential datapoints (IPs) of scattered data using the HAT method (Hoaglin and Welsch). OUTs are commonly identified visually, which is susceptible to errors. The identification of IPs is not trivial, and using statistical tests is necessary. HAT is the most common statistical method to select OUTs and IPs in regression analyses and identifies four groups of data: 1) data within the standard range of variability, 2) OUTs, 3) IPs, and 4) both OUTs and IPs (OUT+IPs). The decision to remove or not remove data from the database depends on the researcher, and the HAT method helps to make these decisions. The removal of an OUT usually improves the accuracy of models. The removal of IPs, however, may or may not improve the accuracy. A small hypothetical data set of rainfall from automatic and conventional rain gauges was used to extensively test the software. The amount of data that can be used in the software is limited by the number of lines of the Excel spreadsheet (65 518). The first step in identifying OUTs and IPs is to analyse all the data, which produced an R 2 for the raw data in our example of 0.11, indicating weak relationships between the variables. The HAT test identified two OUTs, three IPs, and one OUT+IP in the data. If all OUTs were removed, R 2 would increase to 0.19. If the OUT+IP was removed, R 2 would increase to 0.86. If all IPs were also removed, R 2 would decrease to 0.45. The software is free and can be requested by email from reinaldojmoraes@gmail.com.

show abstract

“…Essa exclusão teve impacto significativo no ano e no setor de onde foi retirado. Apesar de persistirem 15 observações com valores extremos (Bacon outliers, p = 0,05) decidiu-se pela sua manutenção, dado que a eliminação destes produzia outros outliers (Billor, Hadi & Velleman, 2000).…”

Section: Estudo Empíricounclassified

A utilidade do resultado integral: caso Euronext Lisbon

Gonçalves

Andraz

Guerreiro

et al. 2018

Innovar

View full text Add to dashboard Cite

RESUMO: Analisa-se a relevância do resultado integral versus resultado líquido das componentes do outro resultado integral, considerando os fatores ano e setor, para o preço e retorno dos títulos cotados na Euronext Lisbon. Com base nos relatórios e contas consolidadas do período 2010-2015 (36 empresas e 211 observações), procura-se aferir se as componentes do resultado integral acrescentam poder explicativo ao resultado líquido e, recorrendo aos modelos do preço e do retorno, se são incorporadas no valor de mercado. A análise comparada dos modelos permite conclusões mais robustas e pertinentes sobre a utilidade do outro resultado integral. Confirma-se uma diferença estatisticamente significativa entre o resultado integral e o resultado líquido. Numa análise anual e sectorial, essa diferença não é consistente, sugerindo o efeito das características de cada setor e a natureza irregular (valor e sinal) das componentes do outro resultado integral em cada ano. Essa informação é refletida no valor das ações quando é material ou sinaliza riscos de mercado. As conclusões são consistentes com outros estudos e são pertinentes para as entidades normalizadoras e reguladoras, por permitir equacionar a informação a detalhar no resultado integral, para analistas e investidores, pela natureza dos impactos esperados na formação do valor de mercado. PALAVRAS-CHAVE:Euronext Lisbon, outro resultado integral, resultado integral, resultado líquido, valor de mercado. Contabilidad y Finanzas USEFULNESS OF THE OVERALL RESULT FOR MARKET VALUE: THE CASE OF EURONEXT LISBONABSTRACT: This research aims to study the importance of the global result compared to the net result of the components of another global result, considering the year and the sector factors, for the price and return of the securities traded on the Euronext Lisbon. Based on the reports and consolidated accounts (36 companies and 211 observations) with quoted securities (2010)(2011)(2012)(2013)(2014)(2015), the goal is to know if the components of the comprehensive financial results have an explanatory power, and if such results are valued by investors in the price and return model. The option for the comparative analysis of models allows more solid and relevant conclusions. A statistically significant difference between the global result and the net result is confirmed. A statistically significant difference between the overall result and the net result is confirmed. However, it is not consistent within the analysis for each year or sector, which shows the influence of each sector's characterictics and the irregular nature (value and signal) of the components of other global results for each year. It is confirmed this information is reflected on the market value when it is material or signals market risks. The results of this research are consistent with other studies, but limited by the size of the sample and the small size of some sectors. However, this study contributes to the literature on this subject since results validate the controversy about the relevance of a glo...

show abstract

BACON: blocked adaptive computationally efficient outlier nominators

Cited by 444 publications

References 26 publications

The determinants of productivity in Chinese large and medium-sized industrial firms, 1998–2007

The determinants of productivity in Chinese large and medium-sized industrial firms, 1998–2007

Software for the detection of outliers and influential points based on the HAT method

A utilidade do resultado integral: caso Euronext Lisbon

Contact Info

Product

Resources

About