Comparative evaluation of spectroscopic models using different multivariate statistical tools in a multicancer scenario

2011 ◽  
Vol 16 (2) ◽  
pp. 025003 ◽  
Author(s):  
A. D. Ghanate ◽  
S. Kothiwale ◽  
S. P. Singh ◽  
Dominique Bertrand ◽  
C. Murali Krishna
2017 ◽  
Vol 50 (3) ◽  
pp. 723-746 ◽  
Author(s):  
Ariane Blais-Lacombe ◽  
Marc André Bodet

AbstractUsing official electoral results from provincial elections since 1973, we evaluate the incumbency effect in Quebec by measuring the impact of a combination of characteristics related to candidates and political parties. We verify whether the presence of an incumbent candidate is necessary to ensure that the incumbent party benefits from an electoral advantage. We also compare the magnitude of the incumbency effect between governing and opposition parties. Making use of parametric multivariate statistical tools, we conclude that political parties benefit from an electoral advantage in Quebec. Except for ministers who make a small difference, simple Members of the National Assembly (MNAs) do not improve their electoral performance, while in some cases new candidates with incumbent parties perform better.


Author(s):  
Sean B. Eom

Over the past decades, there has been a wide range of empirical research in the e-learning literature. The use of multivariate statistical tools has been a staple of the research stream throughout the decade. Path analysis modeling is part of four related multivariate statistical models, including regression, path analysis, confirmatory factor analysis, and structural equation models. This chapter focuses on path analysis modeling for beginners using LISREL 8.70. Several topics covered in this chapter include foundational concepts, assumptions, and steps of path analysis modeling. The major steps in path analysis modeling explained in this chapter consist of specification, identification, estimation, testing, and modification of models.


2012 ◽  
Vol 66 (9) ◽  
Author(s):  
Raúl González-Domínguez ◽  
Tamara García-Barrera ◽  
José-Luis Gómez-Ariza

AbstractAlzheimer’s disease is the most common neurodegenerative disease, but there is still no cure and early diagnosis remains very difficult. For this reason, the discovery of new biomarkers is of great importance. The application of metabolomics is emerging in this field, based on the use of mass spectrometry as a technique of analysis. In this work, blood serum samples (from Alzheimer’s disease patients and healthy controls) were analysed by mass spectrometry in order to search for potential metabolomic biomarkers. The application of multivariate statistical tools (PLS-DA) enabled us to discriminate between groups. In addition, some phosphatidylcholine compounds were identified as markers of the disease.


2017 ◽  
Vol 36 (2) ◽  
pp. 243-260 ◽  
Author(s):  
Roberta Ascrizzi ◽  
Guido Flamini ◽  
Mario Giusiani ◽  
Fabio Stefanelli ◽  
Viviana Deriu ◽  
...  

2020 ◽  
Author(s):  
Insha Ullah ◽  
Kerrie Mengersen ◽  
Anthony Pettitt ◽  
Benoit Liquet

AbstractHigh-dimensional datasets, where the number of variables ‘p’ is much larger compared to the number of samples ‘n’, are ubiquitous and often render standard classification and regression techniques unreliable due to overfitting. An important research problem is feature selection — ranking of candidate variables based on their relevance to the outcome variable and retaining those that satisfy a chosen criterion. In this article, we propose a computationally efficient variable selection method based on principal component analysis. The method is very simple, accessible, and suitable for the analysis of high-dimensional datasets. It allows to correct for population structure in genome-wide association studies (GWAS) which otherwise would induce spurious associations and is less likely to overfit. We expect our method to accurately identify important features but at the same time reduce the False Discovery Rate (FDR) (the expected proportion of erroneously rejected null hypotheses) through accounting for the correlation between variables and through de-noising data in the training phase, which also make it robust to outliers in the training data. Being almost as fast as univariate filters, our method allows for valid statistical inference. The ability to make such inferences sets this method apart from most of the current multivariate statistical tools designed for today’s high-dimensional data. We demonstrate the superior performance of our method through extensive simulations. A semi-real gene-expression dataset, a challenging childhood acute lymphoblastic leukemia (CALL) gene expression study, and a GWAS that attempts to identify single-nucleotide polymorphisms (SNPs) associated with the rice grain length further demonstrate the usefulness of our method in genomic applications.Author summaryAn integral part of modern statistical research is feature selection, which has claimed various scientific discoveries, especially in the emerging genomics applications such as gene expression and proteomics studies, where data has thousands or tens of thousands of features but a limited number of samples. However, in practice, due to unavailability of suitable multivariate methods, researchers often resort to univariate filters when it comes to deal with a large number of variables. These univariate filters do not take into account the dependencies between variables because they independently assess variables one-by-one. This leads to loss of information, loss of statistical power (the probability of correctly rejecting the null hypothesis) and potentially biased estimates. In our paper, we propose a new variable selection method. Being computationally efficient, our method allows for valid inference. The ability to make such inferences sets this method apart from most of the current multivariate statistical tools designed for today’s high-dimensional data.


Sign in / Sign up

Export Citation Format

Share Document