The maximum likelihood threshold of a path diagram
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
The maximum likelihood threshold of a path diagram. / Drton, Mathias; Fox, Christopher; Kaeufl, Andreas; Pouliot, Guillaume.
I: Annals of Statistics, Bind 47, Nr. 3, 06.2019, s. 1536-1553.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - The maximum likelihood threshold of a path diagram
AU - Drton, Mathias
AU - Fox, Christopher
AU - Kaeufl, Andreas
AU - Pouliot, Guillaume
PY - 2019/6
Y1 - 2019/6
N2 - Linear structural equation models postulate noisy linear relationships between variables of interest. Each model corresponds to a path diagram, which is a mixed graph with directed edges that encode the domains of the linear functions and bidirected edges that indicate possible correlations among noise terms. Using this graphical representation, we determine the maximum likelihood threshold, that is, the minimum sample size at which the likelihood function of a Gaussian structural equation model is almost surely bounded. Our result allows the model to have feedback loops and is based on decomposing the path diagram with respect to the connected components of its bidirected part. We also prove that if the sample size is below the threshold, then the likelihood function is almost surely unbounded. Our work clarifies, in particular, that standard likelihood inference is applicable to sparse high-dimensional models even if they feature feedback loops.
AB - Linear structural equation models postulate noisy linear relationships between variables of interest. Each model corresponds to a path diagram, which is a mixed graph with directed edges that encode the domains of the linear functions and bidirected edges that indicate possible correlations among noise terms. Using this graphical representation, we determine the maximum likelihood threshold, that is, the minimum sample size at which the likelihood function of a Gaussian structural equation model is almost surely bounded. Our result allows the model to have feedback loops and is based on decomposing the path diagram with respect to the connected components of its bidirected part. We also prove that if the sample size is below the threshold, then the likelihood function is almost surely unbounded. Our work clarifies, in particular, that standard likelihood inference is applicable to sparse high-dimensional models even if they feature feedback loops.
KW - Covariance matrix
KW - graphical model
KW - maximum likelihood
KW - normal distribution
KW - path diagram
KW - structural equation model
U2 - 10.1214/18-AOS1724
DO - 10.1214/18-AOS1724
M3 - Journal article
VL - 47
SP - 1536
EP - 1553
JO - Annals of Statistics
JF - Annals of Statistics
SN - 0090-5364
IS - 3
ER -
ID: 242777651