Testing homogeneity of several covariance matrices and multi-sample sphericity for high-dimensional data under non-normality

Ahmad, M. Rauf

doi:10.1080/03610926.2015.1073310

Cited by 11 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This test was statistically significant in all cases of examined evaluation measures and time (p < 0.05). It means that the assumption was violated because unless the assumption of covariance matrix sphericity is not met, the I. type error increases (Ahmad, 2013;Haverkamp & Beauducel, 2017;Munkova et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

Using of n-grams from morphological tags for fake news classification

Kapusta

Drlík

Munk

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Research of the techniques for effective fake news detection has become very needed and attractive. These techniques have a background in many research disciplines, including morphological analysis. Several researchers stated that simple content-related n-grams and POS tagging had been proven insufficient for fake news classification. However, they did not realise any empirical research results, which could confirm these statements experimentally in the last decade. Considering this contradiction, the main aim of the paper is to experimentally evaluate the potential of the common use of n-grams and POS tags for the correct classification of fake and true news. The dataset of published fake or real news about the current Covid-19 pandemic was pre-processed using morphological analysis. As a result, n-grams of POS tags were prepared and further analysed. Three techniques based on POS tags were proposed and applied to different groups of n-grams in the pre-processing phase of fake news detection. The n-gram size was examined as the first. Subsequently, the most suitable depth of the decision trees for sufficient generalization was scoped. Finally, the performance measures of models based on the proposed techniques were compared with the standardised reference TF-IDF technique. The performance measures of the model like accuracy, precision, recall and f1-score are considered, together with the 10-fold cross-validation technique. Simultaneously, the question, whether the TF-IDF technique can be improved using POS tags was researched in detail. The results showed that the newly proposed techniques are comparable with the traditional TF-IDF technique. At the same time, it can be stated that the morphological analysis can improve the baseline TF-IDF technique. As a result, the performance measures of the model, precision for fake news and recall for real news, were statistically significantly improved.

show abstract

Section: Methodsmentioning

confidence: 99%

Using of n-grams from morphological tags for fake news classification

Kapusta

Drlík

Munk

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…, g. To extend T 2 in Eqn. (2) for g samples, we consider τ g = g i<j τ ij , sum of Frobenius norms over all distinct pairs, with τ g = 0 under H 0g . Then…”

Section: Multi-sample Extensionmentioning

confidence: 99%

“…Under H 0g , an extension to testing multi-sample sphericity or identity structures of the common covariance matrix is also provided. The present article extends the homogeneity test in [2] to the location-invariant case which is valid whether the mean vectors are assumed DOI: 10.14736/kyb-2018-5-0908 zero or not; in other words, for the proposed test, the mean vectors can be assumed zero without any loss of generality. A corresponding extension of tests for multi-sample sphericity and identity to the location-invariant setting is given in [1].…”

Section: Introductionmentioning

confidence: 97%

“…Some recent modifications include [5,6,13,14,20,24]; for more details and a review, see [7]. [2] also present a test statistic for H 0g , using the component estimators of the test statistic defined as U -statistics of second order symmetric kernels. The kernels are noninvariant bilinear forms of the vectors coming from g independent samples, which makes the test statistic also non-invariant which, in turn, implies that the validity of the test statistic depends on assuming zero centroids for all populations, i. e. µ i = 0 ∀ i.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A homogeneity test of large dimensional covariance matrices under non-normality

Ahmad¹

2018

Kybernetika

Self Cite

View full text Add to dashboard Cite

“…10 presented a robust estimation procedures and hypothesis tests about the mean relationship and the covariance structure within the rows and columns of multi-tissue gene expression data. For testing the hypotheses (1), based on the U -statistics Ahmad 27 presented multi-sample sphericity test T k for high-dimensional data under non-normality. However, the T k test needs to assume that 0<ai=lim⁡p→∞tr(Σj)/p<∞, j=1,2,3,4, or 0<tr(Σ2)/p2=δ1<∞ for all p and infp{tr(Σ4)/[tr(Σ2)]2}>0.…”

Section: Introductionmentioning

confidence: 99%

High-dimensional covariance matrices tests for analyzing multi-tumor gene expression data

Qayed

Han

2021

Stat Methods Med Res

View full text Add to dashboard Cite

By collecting multiple sets per subject in microarray data, gene sets analysis requires characterize intra-subject variation using gene expression profiling. For each subject, the data can be written as a matrix with the different subsets of gene expressions (e.g. multiple tumor types) indexing the rows and the genes indexing the columns. To test the assumption of intra-subject (tumor) variation, we present and perform tests of multi-set sphericity and multi-set identity of covariance structures across subjects (tumor types). We demonstrate by both theoretical and empirical studies that the tests have good properties. We applied the proposed tests on The Cancer Genome Atlas (TCGA) and tested covariance structures for the gene expressions across several tumor types.

show abstract

Testing homogeneity of several covariance matrices and multi-sample sphericity for high-dimensional data under non-normality

Cited by 11 publications

References 23 publications

Using of n-grams from morphological tags for fake news classification

Using of n-grams from morphological tags for fake news classification

A homogeneity test of large dimensional covariance matrices under non-normality

High-dimensional covariance matrices tests for analyzing multi-tumor gene expression data

Contact Info

Product

Resources

About