Applied Multivariate Analysis

By David E. Booth. Technometrics, 2003

1,023 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7bea3613539667642050b0b426cd60c7b5aff66c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Independence test for high dimensional data based on regularized canonical correlation coefficients (2015, neutral): “o employ sample covariance matrices. That is, H= 24 Y. YANG AND G. PAN AyxA−1 xxAxy and E=Ayy −AyxA−xx1Axy, so that det(H−λE)=0 becomes det(AyxA−1 xxAxy −λ(Ayy −AyxA−xx1Axy))=0. From Theorem 2.6.8 of [18], we have det(H−θ(H+E))=det(AyxA−1 xxAxy −θAyy)=0 so that Λ= Ys i=1 (1+λi)−1 = Ys i=1 (1−θi)= de”
OPLS discriminant analysis: combining the strengths of PLS‐DA and SIMCA classification (2006, background): “For the two-class case, a straightforward 0.5 threshold has frequently been employed (see, for instance Reference [20]) to determine class belonging.”
Putting the precision in precision cosmology: How accurate should your data covariance matrix be? (2012, background): “The covariance of the sample precision matrix, again assuming the mean is unknown, is (Kaufman, 1967; see also Press, 1982, Matsumoto, 2011) 〈 ∆Ψ̂ij∆Ψ̂mn 〉 = A [ 2ΨijΨmn + (NS −ND − 2) (ΨimΨjn +ΨinΨjm) ] , (26) where A = (NS − 1)2 (NS −ND − 1)(NS −ND − 2)2(NS −ND − 4) .”
A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics (2016, background): “(13) Several methods exist for testing for covariance equality [20] and for mean equality [24], however we wish to test for both covariance and location equality.”
Test Case Prioritization: A Family of Empirical Studies (2002, background): “Third, principal components analysis [19] reduces the set of standardized metrics to a smaller set of domain values, simplifying the dimensionality of the problem and removing the metrics colinearity.”
Portfolio Modeling with Heavy Tailed Random Vectors (2003, methodology): “Eigenvalues and eigenvectors of Mn are easily computed using standard numerical routines, see for example Press et al. [61].”
Safe Exploration for Active Learning with Gaussian Processes (2015, background): “Besides, the posterior covariance can be expressed as Σ = W + K −1 −1 = K − K W −1 + K −1 K with the help of the matrix inversion lemma, see Press (2005).”
Analyzing Fluctuating Asymmetry with Geometric Morphometrics: Concepts, Methods, and Applications (2015, methodology): “To avoid the assumption of isotropic variation, it is possible to conduct tests with the classical test statistics for MANOVA, such as Pillai’s trace, the Lawley-Hotelling trace, or Wilks lambda [240–242].”
Tourist Satisfaction and Destination Loyalty intention: A Structural and Categorical Analysis (2006, background): “Scharma (1996) considers 0.7 as the adequate minimum acceptance level for the composite reliability and 0.5 for the variance extracted.”
A Quantitative Review of the Comprehensiveness of the Five-Factor Model in Relation to Popular Personality Inventories (2002, methodology): “When only factor loadings were available from previous reports, the interbattery correlations were obtained by multiplying a loading matrix by its transpose (Bernstein, 1988; Gorsuch, 1983, which is a reconstruction method that has been used in other reviews, e.g., Watson & Tellegen, 1985).”
On the Dimensionality of the Attachment Style Questionnaire in Italian Clinical and Nonclinical Participants (2003, methodology): “Following Bernstein’s method (Bernstein, 1988; Nunnally & Bernstein, 1994), the fit of the multiple-component analysis was compared with a like number of components defined, respectively, by item means, standard deviations, and Fossati et al.”
Direct and Mediated Associations among Earnings Quality, Information Asymmetry, and the Cost of Equity (2012, methodology): “29 Path analysis models that include a feedback loop are called non-recursive; see, for example, Timm (2002) for a more thorough discussion.”
Linear dimensionality reduction: survey, insights, and generalizations (2014, methodology): “(7) CCA was originally derived in Hotelling (1936); more modern treatments include Muirhead (2005); Timm (2002); Hardoon et al. (2004); Hardoon and Shawe-Taylor (2009).”