Generalizing hierarchical and variation partitioning in multiple regression and canonical analyses using the rdacca.hp R package

Author(s):  
Jiangshan Lai ◽  
Yi Zou ◽  
Jinlong Zhang ◽  
Pedro R. Peres‐Neto
2021 ◽  
Author(s):  
Jiangshan Lai ◽  
Yi Zou ◽  
Jinlong Zhang ◽  
Pedro Peres-Neto

SummaryCanonical analysis, a generalization of multiple regression to multiple response variables, is widely used in ecology. Because these models often involve large amounts of parameters (one slope per response per predictor), they pose challenges to model interpretation. Currently, multi-response canonical analysis is constrained by two major challenges. Firstly, we lack quantitative frameworks for estimating the overall importance of single predictors. Secondly, although the commonly used variation partitioning framework to estimate the importance of groups of multiple predictors can be used to estimate the importance of single predictors, it is currently computationally constrained to a maximum of four predictor matrices.We established that commonality analysis and hierarchical partitioning, widely used for both estimating predictor importance and improving the interpretation of single-response regression models, are related and complementary frameworks that can be expanded for the analysis of multiple-response models.In this application, we aim at: a) demonstrating the mathematical links between commonality analysis, variation and hierarchical partitioning; b) generalizing these frameworks to allow the analysis of any number of responses, predictor variables or groups of predictor variables in the case of variation partitioning; and c) introducing and demonstrating the usage of the R package rdacca.hp that implements these generalized frameworks.


2015 ◽  
Vol 7 (1) ◽  
Author(s):  
Georgia Tsiliki ◽  
Cristian R. Munteanu ◽  
Jose A. Seoane ◽  
Carlos Fernandez-Lozano ◽  
Haralambos Sarimveis ◽  
...  

2008 ◽  
Vol 40 (2) ◽  
pp. 457-466 ◽  
Author(s):  
Kim Nimon ◽  
Mitzi Lewis ◽  
Richard Kane ◽  
R. Michael Haynes

2021 ◽  
Author(s):  
Timon Elmer

The netglm R-package estimates generalized linear models for network data based on the Multiple Regression Quadratic Assignment Procedure (MRQAP; Krackhardt, 1988). This package allows to investigate associations between characteristics of dyads in networks (e.g., the level of homophily between two actors) and a binary or continuous tie variable (e.g., friendship, amount of time spent together). One unique feature of this package is that it allows to estimate multi-group MRQAP models, where multiple networks are analyzed simultaneously (e.g., networks of multiple classrooms). Furthermore, parallel processing is implemented.


2020 ◽  
Vol 51 (3) ◽  
pp. 807-820
Author(s):  
Lena G. Caesar ◽  
Marie Kerins

Purpose The purpose of this study was to investigate the relationship between oral language, literacy skills, age, and dialect density (DD) of African American children residing in two different geographical regions of the United States (East Coast and Midwest). Method Data were obtained from 64 African American school-age children between the ages of 7 and 12 years from two geographic regions. Children were assessed using a combination of standardized tests and narrative samples elicited from wordless picture books. Bivariate correlation and multiple regression analyses were used to determine relationships to and relative contributions of oral language, literacy, age, and geographic region to DD. Results Results of correlation analyses demonstrated a negative relationship between DD measures and children's literacy skills. Age-related findings between geographic regions indicated that the younger sample from the Midwest outscored the East Coast sample in reading comprehension and sentence complexity. Multiple regression analyses identified five variables (i.e., geographic region, age, mean length of utterance in morphemes, reading fluency, and phonological awareness) that accounted for 31% of the variance of children's DD—with geographic region emerging as the strongest predictor. Conclusions As in previous studies, the current study found an inverse relationship between DD and several literacy measures. Importantly, geographic region emerged as a strong predictor of DD. This finding highlights the need for a further study that goes beyond the mere description of relationships to comparing geographic regions and specifically focusing on racial composition, poverty, and school success measures through direct data collection.


Sign in / Sign up

Export Citation Format

Share Document