Statistical inference of causal and ordinary differential equation models

Seyed Mahdi Mahmoudi

Statistical inference of causal and ordinary differential equation models

Seyed Mahdi Mahmoudi

Probability and Statistics

Onderzoeksoutput

418 Downloads (Pure)

Samenvatting

Netwerken komen voort uit het modelleren van complexe systemen in verschillende gebieden van de wetenschap. Analyseren van de structuur van een netwerk helpt ons om deze complexe systemen beter te begrijpen en er bruikbare informatie uit te halen. Een belangrijk probleem in netwerk-analyse is het modelleren van het onderliggende genererende mechanisme van een netwerk
gebaseerd op datastructuren en het vervolgens vaststellen van het karakter van afhankelijkheid.
Het is een uitdaging om oorzakelijke verbanden af te leiden tussen knopen van waargenomen data of een mix van waargenomen data en experimentele data, met name op het gebied van grafisch causaal modelleren. Bijvoorbeeld het begrijpen van de structuur van biologische netwerken en het
ontrafelen van netwerken van gen-interacties van onderliggende complexe menselijke fenotypes is een grote uitdaging in de systeembiologie. Een van de interessante onderwerpen na het construeren van een netwerk is het ontdekken van de dynamica van zo’n netwerk. Een veel gebruikte klasse van modellen voor de dynamica van netwerken wordt gevormd door de gewone differentiaalvergeli-
jkingen. In dit proefschrift dragen we bij aan de methodologie om de schatting van oorzakelijk netwerken en dynamische systemen te verbeteren.

Originele taal-2	English
Kwalificatie	Doctor of Philosophy
Toekennende instantie	Rijksuniversiteit Groningen
Begeleider(s)/adviseur	Wit, Ernst, Supervisor
Datum van toekenning	15-mei-2017
Plaats van publicatie	[Groningen]
Uitgever	University of Groningen
Gedrukte ISBN's	978-90-367-9777-1
Elektronische ISBN's	978-90-367-9778-8
Status	Published - 2017

Toegang tot document

Complete thesisFinal publisher's version, 2,51 MB
PropositionsFinal publisher's version, 76,8 KB

Handle.net

Permanente koppeling

Citeer dit

@phdthesis{38bc790d54a54b0aae4466fef7bed575,

title = "Statistical inference of causal and ordinary differential equation models",

abstract = "Networks arise from modeling complex systems in various aspects in the science. Analysing the network structure help us better understand these complex systems and extract useful information.One important problem in network analysis is to model the underlying generating mechanism of networks based on data structures and then establish the nature of the dependence. Inferring causal relationship among the nodes from observational sample data or a mixture of observational sample and experimental data, particularly in the area of graphical causal modelling, is challenging.For instance, understanding the structure of biological networks and elucidating networks of gene interactions underlying complex human phenotypes represents a major challenge in systems biology.One of the interesting subjects after constructing the network is detecting the dynamics of the network. Ordinary differential equations provide an attractive class of models for the dynamics of these networks. In this thesis we contributes methodology for improve the estimation of causal networks and dynamical systems.",

author = "Mahmoudi, {Seyed Mahdi}",

year = "2017",

language = "English",

isbn = "978-90-367-9777-1",

publisher = "University of Groningen",

school = "University of Groningen",

}

TY - BOOK

T1 - Statistical inference of causal and ordinary differential equation models

AU - Mahmoudi, Seyed Mahdi

PY - 2017

Y1 - 2017

N2 - Networks arise from modeling complex systems in various aspects in the science. Analysing the network structure help us better understand these complex systems and extract useful information.One important problem in network analysis is to model the underlying generating mechanism of networks based on data structures and then establish the nature of the dependence. Inferring causal relationship among the nodes from observational sample data or a mixture of observational sample and experimental data, particularly in the area of graphical causal modelling, is challenging.For instance, understanding the structure of biological networks and elucidating networks of gene interactions underlying complex human phenotypes represents a major challenge in systems biology.One of the interesting subjects after constructing the network is detecting the dynamics of the network. Ordinary differential equations provide an attractive class of models for the dynamics of these networks. In this thesis we contributes methodology for improve the estimation of causal networks and dynamical systems.

AB - Networks arise from modeling complex systems in various aspects in the science. Analysing the network structure help us better understand these complex systems and extract useful information.One important problem in network analysis is to model the underlying generating mechanism of networks based on data structures and then establish the nature of the dependence. Inferring causal relationship among the nodes from observational sample data or a mixture of observational sample and experimental data, particularly in the area of graphical causal modelling, is challenging.For instance, understanding the structure of biological networks and elucidating networks of gene interactions underlying complex human phenotypes represents a major challenge in systems biology.One of the interesting subjects after constructing the network is detecting the dynamics of the network. Ordinary differential equations provide an attractive class of models for the dynamics of these networks. In this thesis we contributes methodology for improve the estimation of causal networks and dynamical systems.

M3 - Thesis fully internal (DIV)

SN - 978-90-367-9777-1

PB - University of Groningen

CY - [Groningen]

ER -

Statistical inference of causal and ordinary differential equation models

Samenvatting

Toegang tot document

Handle.net

Vingerafdruk

Citeer dit