Compare methods

	MRQAP Network Regression	Dyadic Analysis
Field	Sociology	Sociology
Family	Regression model	Regression model
Year of origin	1988 (MRQAP); 2007 (double-semipartialing test)	1981
Originator	David Krackhardt; David Dekker, David Krackhardt & Tom Snijders	Holland & Leinhardt (p1); Kenny (Social Relations Model)
Type	Permutation-based multiple regression for dyadic (matrix) outcomes	Analysis of the dyad as the unit, decomposing relational effects
Seminal source	Krackhardt, D. (1988). Predicting with networks: Nonparametric multiple regression analysis of dyadic data. Social Networks, 10(4), 359–381.	Holland, P. W., & Leinhardt, S. (1981). An exponential family of probability distributions for directed graphs. Journal of the American Statistical Association, 76(373), 33–50.
Aliases	MRQAP, multiple regression QAP, Dekker double-semipartialing, QAP regression	dyad analysis, dyadic data analysis, social relations model, dyad census
Related	4	4
Summary	Multiple regression quadratic assignment procedure (MRQAP) extends QAP to the regression setting: it predicts a dependent relational matrix from several independent relational matrices on the same actors — for example, modeling who collaborates with whom as a function of who is co-located, who shares a department, and who has prior friendship. Coefficients are estimated by ordinary least squares on the vectorized matrices, but significance is assessed by permutation, because dyadic dependence invalidates the standard regression standard errors.	Dyadic analysis treats the dyad — the pair of actors and the relation between them — as the unit of analysis, separating the relational outcome into what each actor brings to all their relationships and what is unique to the specific pair. It spans the descriptive dyad census of network analysis and statistical frameworks such as Holland and Leinhardt's p1 model and Kenny's Social Relations Model, all of which respect the structural non-independence inherent in relational data.