Bridging the gap between different statistical approaches: An integrated framework for modelling

This paper proposes a template for modelling complex datasets that integrates traditional statistical modelling approaches with more recent advances in statistics and modelling through an exploratory framework. Our approach builds on the well-known and long standing traditional idea of 'good practice in statistics' by establishing a comprehensive framework for modelling that focuses on exploration, prediction, interpretation and reliability assessment, a relatively new idea that allows individual assessment of predictions. The integrated framework we present comprises two stages. The first involves the use of exploratory methods to help visually understand the data and identify a parsimonious set of explanatory variables. The second encompasses a two step modelling process, where the use of non-parametric methods such as decision trees and generalized additive models are promoted to identify important variables and their modelling relationship with the response before a final predictive model is considered. We focus on fitting the predictive model using parametric, non-parametric and Bayesian approaches. This paper is motivated by a medical problem where interest focuses on developing a risk stratification system for morbidity of 1,710 cardiac patients given a suite of demographic, clinical and preoperative variables. Although the methods we use are applied specifically to this case study, these methods can be applied across any field, irrespective of the type of response.

Effect of changing data collection parameters on statistical motor unit number estimates

The effect of number of samples and selection of data for analysis on the calculation of surface motor unit potential (SMUP) size in the statistical method of motor unit number estimates (MUNE) was determined in 10 normal subjects and 10 with amyotrophic lateral sclerosis (ALS). We recorded 500 sequential compound muscle action potentials (CMAPs) at three different stable stimulus intensities (10–50% of maximal CMAP). Estimated mean SMUP sizes were calculated using Poisson statistical assumptions from the variance of 500 sequential CMAP obtained at each stimulus intensity. The results with the 500 data points were compared with smaller subsets from the same data set. The results using a range of 50–80% of the 500 data points were compared with the full 500. The effect of restricting analysis to data between 5–20% of the CMAP and to standard deviation limits was also assessed. No differences in mean SMUP size were found with stimulus intensity or use of different ranges of data. Consistency was improved with a greater sample number. Data within 5% of CMAP size gave both increased consistency and reduced mean SMUP size in many subjects, but excluded valid responses present at that stimulus intensity. These changes were more prominent in ALS patients in whom the presence of isolated SMUP responses was a striking difference from normal subjects. Noise, spurious data, and large SMUP limited the Poisson assumptions. When these factors are considered, consistent statistical MUNE can be calculated from a continuous sequence of data points. A 2 to 2.5 SD or 10% window are reasonable methods of limiting data for analysis. Muscle Nerve 27: 320–331, 2003

Comparative analysis between statistical and artificial intelligence models in business failure prediction

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context. The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003–09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure. Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context. The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003–09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure. Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.

Statistical classification of road pavements using near field vehicle rolling noise measurements

Low noise surfaces have been increasingly considered as a viable and cost-effective alternative to acoustical barriers. However, road planners and administrators frequently lack information on the correlation between the type of road surface and the resulting noise emission profile. To address this problem, a method to identify and classify different types of road pavements was developed, whereby near field road noise is analyzed using statistical learning methods. The vehicle rolling sound signal near the tires and close to the road surface was acquired by two microphones in a special arrangement which implements the Close-Proximity method. A set of features, characterizing the properties of the road pavement, was extracted from the corresponding sound profiles. A feature selection method was used to automatically select those that are most relevant in predicting the type of pavement, while reducing the computational cost. A set of different types of road pavement segments were tested and the performance of the classifier was evaluated. Results of pavement classification performed during a road journey are presented on a map, together with geographical data. This procedure leads to a considerable improvement in the quality of road pavement noise data, thereby increasing the accuracy of road traffic noise prediction models.

Statistical motion learning for improved transform domain Wyner-Ziv video coding

Wyner - Ziv (WZ) video coding is a particular case of distributed video coding (DVC), the recent video coding paradigm based on the Slepian - Wolf and Wyner - Ziv theorems which exploits the source temporal correlation at the decoder and not at the encoder as in predictive video coding. Although some progress has been made in the last years, WZ video coding is still far from the compression performance of predictive video coding, especially for high and complex motion contents. The WZ video codec adopted in this study is based on a transform domain WZ video coding architecture with feedback channel-driven rate control, whose modules have been improved with some recent coding tools. This study proposes a novel motion learning approach to successively improve the rate-distortion (RD) performance of the WZ video codec as the decoding proceeds, making use of the already decoded transform bands to improve the decoding process for the remaining transform bands. The results obtained reveal gains up to 2.3 dB in the RD curves against the performance for the same codec without the proposed motion learning approach for high motion sequences and long group of pictures (GOP) sizes.

Comparação de softwares para análise de dados de levantamentos complexos

OBJETIVO: Comparar "softwares" específicos para análise de dados de levantamentos amostrais complexos, em relação às características: facilidade de aplicação, eficiência computacional e exatidão dos resultados. MÉTODOS: Utilizaram-se dados secundários da Pesquisa Nacional sobre Demografia e Saúde, de 1996, cuja população-alvo foram as mulheres de 15 a 49 anos de idade, pertencentes a uma subamostra probabilística selecionada em dois estágios, estratificada, com probabilidade proporcional ao tamanho no primeiro estágio. Foram selecionadas da subamostra as regiões Norte e Centro-oeste do País. Os parâmetros analisados foram: a média, para a variável idade, e a proporção, para cinco outras variáveis qualitativas, utilizando os "softwares" Epi Info, Stata e WesVarPC. RESULTADOS: Os programas apresentam duas opções em comum para importação de arquivos: o dBASE e arquivos tipo texto. O número de passos anteriores à execução das análises foram 21, 11 e 9, respectivamente para o Epi Info, Stata e WesVarPC. A eficiência computacional foi alta em todos eles, inferior a três segundos. Os erros padrão estimados utilizando-se o Epi Info e o Stata foram os mesmos, com aproximação até a terceira casa decimal; os do WesVarPC foram, em geral, superiores. CONCLUSÕES: O Epi Info é o mais limitado em termos das análises disponíveis, porém ele é simples de usar e gratuito. O Stata e o WesVarPC são bem mais completos nos recursos de análises, porém há a desvantagem do custo. A escolha do programa dependerá principalmente das necessidades específicas do usuário.

Desenvolvimento e validação de um sistema de recolha de sinal eletromiográfico baseado em placa de aquisição

A eletromiografia é, hoje em dia, uma das técnicas mais utilizadas no estudo dos músculos, estando presente em áreas como a medicina, a biomecânica e a fisiologia, possibilitando o desenvolvimento científico e contribuindo para proporcionar melhorias na qualidade da vida humana. Sendo assim, este trabalho apresenta um protótipo de um aparelho de aquisição de sinais eletromiográficos, explicando também toda a teoria, técnicas, componentes utilizadas e softwares que estiveram presentes na sua implementação. De uma forma sucinta, para a aquisição do sinal eletromiográfico usou-se uma placa de aquisição NI-USB 6009 e para a visualização do mesmo recorreu-se ao software LabVIEW. Para validar o sinal adquirido com o equipamento desenvolvido, utilizou-se um outro equipamento, o Biopac MP36 Student Lab System, fazendo-se assim recolhas de sinais eletromiográficos com ambos os equipamentos. Os sinais recolhidos pelos dois equipamentos foram analisados no software Acknowledge 3.9.0 (Biopac Systems, Inc.), podendo observar-se os espetros de frequência correspondentes a cada sinal e retirar valores para posterior análise estatística. Feita essa análise, concluiu-se que não foram detetadas diferenças significativas entre os sinais eletromiográficos recolhidos com ambos os equipamentos, validando-se assim, o equipamento desenvolvido.

Variabilidade introduzida pelo operador no processamento dos estudos Gated-SPECT do miocárdio

Introdução – Os estudos Gated – Single Photon Emission Computed Tomography (SPECT) são uma das técnicas de imagiologia cardíaca que mais evoluiu nas últimas décadas. Para a análise das imagens obtidas, a utilização de softwares de quantificação leva a um aumento da reprodutibilidade e exatidão das interpretações. O objetivo deste estudo consiste em avaliar, em estudos Gated-SPECT, a variabilidade intra e interoperador de parâmetros quantitativos de função e perfusão do miocárdio, obtidos com os softwares Quantitative Gated SPECT (QGS) e Quantitative Perfusion SPECT (QPS). Material e métodos – Recorreu-se a uma amostra não probabilística por conveniência de 52 pacientes, que realizaram estudos Gated-SPECT do miocárdio por razões clínicas e que integravam a base de dados da estação de processamento da Xeleris da ESTeSL. Os cinquenta e dois estudos foram divididos em dois grupos distintos: Grupo I (GI) de 17 pacientes com imagens com perfusão do miocárdio normal; Grupo II (GII) de 35 pacientes que apresentavam defeito de perfusão nas imagens Gated-SPECT. Todos os estudos foram processados 5 vezes por 4 operadores independentes (com experiência de 3 anos em Serviços de Medicina Nuclear com casuística média de 15 exames/semana de estudos Gated-SPECT). Para a avaliação da variabilidade intra e interoperador foi utilizado o teste estatístico de Friedman, considerando α=0,01. Resultados e discussão – Para todos os parâmetros avaliados, os respectivos valores de p não traduziram diferenças estatisticamente significativas (p>α). Assim, não foi verificada variabilidade intra ou interoperador significativa no processamento dos estudos Gated-SPECT do miocárdio. Conclusão – Os softwares QGS e QPS são reprodutíveis na quantificação dos parâmetros de função e perfusão avaliados, não existindo variabilidade introduzida pelo operador.

Analysis of tongue shape and motion in speech production using statistical modeling

The mechanisms of speech production are complex and have been raising attention from researchers of both medical and computer vision fields. In the speech production mechanism, the articulator’s study is a complex issue, since they have a high level of freedom along this process, namely the tongue, which instigates a problem in its control and observation. In this work it is automatically characterized the tongues shape during the articulation of the oral vowels of Portuguese European by using statistical modeling on MR-images. A point distribution model is built from a set of images collected during artificially sustained articulations of Portuguese European sounds, which can extract the main characteristics of the motion of the tongue. The model built in this work allows under standing more clearly the dynamic speech events involved during sustained articulations. The tongue shape model built can also be useful for speech rehabilitation purposes, specifically to recognize the compensatory movements of the articulators during speech production.

Statistical analysis of quality control measurements in IMRT for head and neck and prostate cancer

Intensity Modulated Radiotherapy (IMRT) is a technique introduced to shape more precisely the dose distributions to the tumour, providing a higher dose escalation in the volume to irradiate and simultaneously decreasing the dose in the organs at risk which consequently reduces the treatment toxicity. This technique is widely used in prostate and head and neck (H&N) tumours. Given the complexity and the use of high doses in this technique it’s necessary to ensure as a safe and secure administration of the treatment, through the use of quality control programmes for IMRT. The purpose of this study was to evaluate statistically the quality control measurements that are made for the IMRT plans in prostate and H&N patients, before the beginning of the treatment, analysing their variations, the percentage of rejected and repeated measurements, the average, standard deviations and the proportion relations.

A few what-ifs on using statistical analysis of stochastic simulation runs to extract timeliness properties

Modern real-time systems, with a more flexible and adaptive nature, demand approaches for timeliness evaluation based on probabilistic measures of meeting deadlines. In this context, simulation can emerge as an adequate solution to understand and analyze the timing behaviour of actual systems. However, care must be taken with the obtained outputs under the penalty of obtaining results with lack of credibility. Particularly important is to consider that we are more interested in values from the tail of a probability distribution (near worst-case probabilities), instead of deriving confidence on mean values. We approach this subject by considering the random nature of simulation output data. We will start by discussing well known approaches for estimating distributions out of simulation output, and the confidence which can be applied to its mean values. This is the basis for a discussion on the applicability of such approaches to derive confidence on the tail of distributions, where the worst-case is expected to be.