Statistical Inference in Factor Analysis

By Theodore W. Anderson, H. Rubin. 1956

How researchers see this paper

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

Citations in the corpus

Principal Components and Regularized Estimation of Factor Models (2017, background): “Under the assumption that T tends to inﬁnity with N ﬁxed, Anderson and Rubin (1956), Joreskog (1967), and Lawley and Maxwell (1971) show that the factor loadings estimated by maximum likelihood or covariance structure methods are √ T consistent and asymptotically normal.”
Analysis of elliptical copula correlation factor model with Kendall's tau (2013, background): “We leave the solution to this problem to the literature, e.g., [2].”
Item Response Theory—A Statistical Framework for Educational and Psychological Measurement (2021, unknown): “IRT models are closely related to linear factor models (see e.g., Anderson and Rubin, 1956; Bai and Li, 2012).”
Moment-based dimension reduction for multivariate response regression (2006, background): “They have wide applicability in fields such as chemometrics (Frank and Friedman 1993), psychometrics (Anderson and Rubin 1956), and econometrics (Velu, Reinsel and Wichern 1986) among others.”
Factor analysis with (mixed) observed and latent variables in the exponential family (2001, background): “Anderson and Rubin (1956) and Gill (1977) have investigated consistency and asymptotic normality of ML estimators in factor analysis.”
Factor models for multivariate count data (2003, background): “Anderson and Rubin [3] have investigated consistency and asymptotic normality of ML estimators in factor analysis.”
Student Satisfaction with Online Learning: Is It a Psychological Contract?. (2015, methodology): “Once the final dimensionality of the data set was determined, factor scores for each subject in the sample were derived using the Anderson and Rubin (1956) method.”
Generalized Non-Parametric Deconvolution with an Application to Earnings Dynamics (2010, background): “In the four panels of Figure 5, factors follow a Gamma distribution, with parameters (5, 1) and (2, 1), respectively.”
The Economics of Human Development and Social Mobility (2014, unknown): “28See Anderson and Rubin (1956) and Williams (2012).”
From BIS/BAS to the big five (2006, methodology): “The factor scores were computed in LISREL by an extension of a formula given by Anderson & Rubin (1956).”
A New Linearized Formula for the Law of Total Effective Temperature and the Evaluation of Line-Fitting Methods with Both Variables Subject to Error (2000, methodology): “This solution is obtained by the maximum likelihood method, although, strictly speaking, it is not the maximum likelihood estimate but the likelihood equation estimate ( Anderson and Rubin 1956, Solari 1969, Willassen 1979, Cheng and Van Ness 1999).”
On estimation of the noise variance in high dimensional probabilistic principal component analysis (2013, methodology): “Following Anderson and Rubin (1956), the LRT statistic is Tn =−nLÅ, LÅ = p∑ j=m+1 log ( λn,j σ̂2 ) , and σ̂2 is the MLE (3) of the variance.”
Understanding and Using Factor Scores: Considerations for the Applied Researcher (2009, methodology): “The method proposed by Anderson and Rubin (1956) is a variation of the Bartlett procedure, in which the least squares formula is adjusted to produce factor scores that are not only uncorrelated with other factors, but also uncorrelated with each other.”