The choice of product indicators in latent variable interaction models: Post hoc analyses.

© 2020 Australian and New Zealand Marketing Academy Covariance Based – Structural Equation Modelling (CB-SEM) is often used to investigate moderation and latent interaction effects. This study illustrates and compares the application of constrained, unconstrained and orthogonalized CB-SEM approaches to latent variable interaction analysis using AMOS. Although all three techniques provided similar parameter estimates, the orthogonalized approach provided reduced standard errors resulting in identifying a significant latent interaction, suggesting the orthogonalized approach may be better suited for exploratory research. The illustrated example demonstrates three CB-SEM techniques, and the simplicity of the three approaches to test for interaction effects. The three approaches can be comfortably implemented in available software programs. Guidelines and recommendations for the use of the three approaches are identified with a step-wise process of assessing the latent interaction effect in CB-SEM. As far as we are aware this is the first investigation comparing and recommending specific CB-SEM latent variable moderation analysis techniques in marketing research.

Download Full-text

Genetic Programming Based Variable Interaction Models for Classification of Process and Biological Systems

Industrial & Engineering Chemistry Research ◽

10.1021/ie801147m ◽

2009 ◽

Vol 48 (10) ◽

pp. 4899-4907 ◽

Cited By ~ 7

Author(s):

Raghuraj K. Rao ◽

Kyaw Tun ◽

S. Lakshminarayanan

Keyword(s):

Genetic Programming ◽

Biological Systems ◽

Interaction Models ◽

Variable Interaction

Download Full-text

Efficient and scalable integration of single-cell data using domain-adversarial and variational approximation

10.1101/2021.04.06.438733 ◽

2021 ◽

Author(s):

Jialu Hu ◽

Yuanke Zhong ◽

Xuequn Shang

Keyword(s):

Single Cell ◽

Latent Variable ◽

Real Data ◽

Variational Approximation ◽

Data Sets ◽

Single Cell Sequencing ◽

Sequencing Technologies ◽

Non Linear ◽

Post Hoc ◽

Cell Data

Single-cell data provides us new ways of discovering biological truth at the level of individual cells, such as identification of cellular sub-populations and cell development. With the development of single-cell sequencing technologies, a key analytical challenge is to integrate these data sets to uncover biological insights. Here, we developed a domain-adversarial and variational approximation framework, DAVAE, to integrate multiple single-cell data across samples, technologies and modalities without any post hoc data processing. We fit normalized gene expression into a non-linear model, which transforms a latent variable of a lower-dimension into expression space with a non-linear function, a KL regularizier and a domain-adversarial regularizer. Results on five real data integration applications demonstrated the effectiveness and scalability of DAVAE in batch-effect removing, transfer learning, and cell type predictions for multiple single-cell data sets across samples, technologies and modalities. DAVAE was implemented in the toolkit package scbean in the pypi repository, and the source code can be also freely accessible at https://github.com/jhu99/scbean.

Download Full-text