<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T09:19:03Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/99" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/99</identifier><datestamp>2026-05-14T13:54:11Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Ghosh, Soumyadip</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2004-04-23T16:07:06Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2004-04-23T16:07:06Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2004-04-23T16:07:06Z</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/99</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">6475927</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">There is a growing need for the ability to model and generate samples&#xd;
of dependent random variables as primitive inputs to stochastic&#xd;
models. We consider the case where this dependence is modeled in terms&#xd;
of a partially-specified finite-dimensional random vector. A random&#xd;
vector sampler is commonly required to match a given set of&#xd;
distributions for each of its components (the marginal&#xd;
distributions) and values of their pairwise covariances. The NORTA&#xd;
method, which produces samples via a transformation of a joint-normal&#xd;
random vector sample, is considered the state-of-the-art method for&#xd;
matching this specification. We begin by showing that the NORTA method&#xd;
has certain flaws in its design which limit its applicability.&#xd;
&#xd;
A covariance matrix is said to be feasible for a given set of marginal&#xd;
distributions if a random vector exists with these properties. We&#xd;
develop a computational tool that can establish the feasibility of&#xd;
(almost) any covariance matrix for a fixed set of marginals. This tool&#xd;
is used to rigorously establish that there are feasible combinations&#xd;
of marginals and covariance matrices that the NORTA method cannot&#xd;
match. We further determine that as the dimension of the random vector&#xd;
increases, this problem rapidly becomes acute, in the sense that NORTA&#xd;
becomes increasingly likely to fail to match feasible specifications.&#xd;
As part of this analysis, we propose a random matrix sampling&#xd;
technique that is possibly of wider interest.&#xd;
&#xd;
We extend our study along two natural paths. First, we investigate&#xd;
whether NORTA can be modified to approximately match a desired&#xd;
covariance matrix that the original NORTA procedure fails to match.&#xd;
Results show that simple, elegant modifications to the NORTA procedure&#xd;
can help it achieve close approximations to the desired covariance matrix,&#xd;
and these modifications perform well with increasing dimension.&#xd;
&#xd;
Second, the feasibility testing procedure suggests a random vector&#xd;
sampling technique that can exactly match (almost) any given feasible&#xd;
set of marginals and covariances, i.e., be free of the limitations of&#xd;
NORTA. We develop a strong characterization of the computational&#xd;
effort needed by this new sampling technique. This technique is&#xd;
computationally competitive with NORTA in low to moderate dimensions,&#xd;
while matching the desired covariances exactly.</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="extent">609633 bytes</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en_US</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">simulation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">random variate generation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">random vector sampling</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Input Modeling</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">NORTA</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Dependence in Stochastic Simulation Models</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Ghosh, Soumyadip</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="803783d5-e6e3-4025-a693-4f21303f5de6">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en_US&lt;/Language>
   	&lt;Title>Dependence in Stochastic Simulation Models&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2004-04-23T16:07:06Z&lt;/PublicationDate>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Ghosh, Soumyadip&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;Keyword>simulation&lt;/Keyword>
    &lt;Keyword>random variate generation&lt;/Keyword>
    &lt;Keyword>random vector sampling&lt;/Keyword>
    &lt;Keyword>Input Modeling&lt;/Keyword>
    &lt;Keyword>NORTA&lt;/Keyword>
   	&lt;Abstract>There is a growing need for the ability to model and generate samples&#xd;
of dependent random variables as primitive inputs to stochastic&#xd;
models. We consider the case where this dependence is modeled in terms&#xd;
of a partially-specified finite-dimensional random vector. A random&#xd;
vector sampler is commonly required to match a given set of&#xd;
distributions for each of its components (the marginal&#xd;
distributions) and values of their pairwise covariances. The NORTA&#xd;
method, which produces samples via a transformation of a joint-normal&#xd;
random vector sample, is considered the state-of-the-art method for&#xd;
matching this specification. We begin by showing that the NORTA method&#xd;
has certain flaws in its design which limit its applicability.&#xd;
&#xd;
A covariance matrix is said to be feasible for a given set of marginal&#xd;
distributions if a random vector exists with these properties. We&#xd;
develop a computational tool that can establish the feasibility of&#xd;
(almost) any covariance matrix for a fixed set of marginals. This tool&#xd;
is used to rigorously establish that there are feasible combinations&#xd;
of marginals and covariance matrices that the NORTA method cannot&#xd;
match. We further determine that as the dimension of the random vector&#xd;
increases, this problem rapidly becomes acute, in the sense that NORTA&#xd;
becomes increasingly likely to fail to match feasible specifications.&#xd;
As part of this analysis, we propose a random matrix sampling&#xd;
technique that is possibly of wider interest.&#xd;
&#xd;
We extend our study along two natural paths. First, we investigate&#xd;
whether NORTA can be modified to approximately match a desired&#xd;
covariance matrix that the original NORTA procedure fails to match.&#xd;
Results show that simple, elegant modifications to the NORTA procedure&#xd;
can help it achieve close approximations to the desired covariance matrix,&#xd;
and these modifications perform well with increasing dimension.&#xd;
&#xd;
Second, the feasibility testing procedure suggests a random vector&#xd;
sampling technique that can exactly match (almost) any given feasible&#xd;
set of marginals and covariances, i.e., be free of the limitations of&#xd;
NORTA. We develop a strong characterization of the computational&#xd;
effort needed by this new sampling technique. This technique is&#xd;
computationally competitive with NORTA in low to moderate dimensions,&#xd;
while matching the desired covariances exactly.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>