{"id":{"repo_id":"ohiolink","oai_identifier":"oai:etd.ohiolink.edu:osu1366131746"},"canonical_url":"https://search.dev.ndltd.org/etd/ohiolink/oai:etd.ohiolink.edu:osu1366131746","repository":{"repo_id":"ohiolink","name":"OhioLINK","base_url":"https://etd.ohiolink.edu/acprod/odb_etd/ws/oai/oai"},"display":{"title":"The Simultaneous Spatial Autoregressive Model and Its Application in the Housing and Pharmaceutical Markets","abstract":"My research focuses on the extension of the spatial autoregressive (SAR) model into a system of simultaneous equations. The resulting new model is useful in studying problems involving multiple networks where individuals are not only linked to members of the same network but also interact with members of the other networks. The behavior of each individual is affected by the behavior of those to whom he is linked. The magnitude of such effects, which are referred to as spatial effects, depends on the strength of the links.As the foundation of the dissertation, I first introduce the simultaneous SAR model in a theoretical paper. This paper extends the high-order spatial autoregressive model to a multiple-equation system in which the dependent variable in each equation exerts a spatial effect on the dependent variables in all the equations. Although researchers have studied the estimation methods for some similar models, an efficient estimation approach is still lacking. Due to the infeasibility of maximum likelihood estimation (MLE) in this framework, I develop a generalized method of moments (GMM) estimation procedure which yields estimators for the unknown parameters in both the main system and the covariance matrix. These estimators achieve the efficiency of MLE.As an empirical application of the model, I investigate the price competition between two major pharmaceutical chains in the state of New York in a second paper. The prices of standardized prescription drugs vary considerably, both within each chain and across the two chains. This market is a good fit for the simultaneous SAR model because each chain store interacts with other stores that belong to the same chain and those that belong to the rival chain. The estimation results reveal that each store competes not only against the rival stores but also against the stores in the same chain. Furthermore, the spatial coefficients indicate that the price competition within the same chain is softer than the price competition between chains.In the third chapter, I apply my simultaneous SAR methodology to construct a simultaneous spatial model to study the relationship between the housing price and the racial composition in several U.S. metropolitan areas at the neighborhood level. By using the simultaneous SAR model, I can address an important issue that has not yet been studied extensively in the housing literature. Specifically, I call into question the exogeneity of racial composition, which is routinely included as an explanatory variable in the hedonic housing price equation. The potential endogeneity of this variable stems from the simultaneous nature of the housing price and the racial composition in each neighborhood and causes the traditional estimators to be biased. According to empirical estimation, black renters and homeowners have significantly higher price elasticities of housing demand than their white counterparts. Assuming that the distribution of price sensitivity among blacks first-order stochastically dominates the distribution of price sensitivity among whites, I use a self-selection model to show that blacks tend to concentrate in areas where housing prices are lower. Thus, we can use the housing price in each neighborhood as an explanatory variable for the racial composition of the neighborhood in another regression equation. By simultaneously estimating a housing price equation and a set of neighborhood composition equations in the same model, we can correct the biased estimators in the hedonic housing price analysis. In addition, the spatial structure of the model reveals each ethnic group’s preferences for integrating with other ethnic groups. These help explain the high level of racial and ethnic segregation that is typical of U.S. metropolitan areas. Using census 2000 sample data measured at the block group level from five MSAs, I confirm the endogeneity of neighborhood composition in the housing price equation. While the estimation bias in the single-equation model is relatively small in MSAs with a simple racial composition, it becomes much larger in MSAs with a high level of racial and ethnic diversity and drastically changes the interpretation of the regression coefficients. Furthermore, the estimates of the spatial coefficients indicate that each minority group strongly desires to live among their own race or ethnicity and generally prefers to stay away from the other groups.","abstract_html":"My research focuses on the extension of the spatial autoregressive (SAR) model into a system of simultaneous equations. The resulting new model is useful in studying problems involving multiple networks where individuals are not only linked to members of the same network but also interact with members of the other networks. The behavior of each individual is affected by the behavior of those to whom he is linked. The magnitude of such effects, which are referred to as spatial effects, depends on the strength of the links.As the foundation of the dissertation, I first introduce the simultaneous SAR model in a theoretical paper. This paper extends the high-order spatial autoregressive model to a multiple-equation system in which the dependent variable in each equation exerts a spatial effect on the dependent variables in all the equations. Although researchers have studied the estimation methods for some similar models, an efficient estimation approach is still lacking. Due to the infeasibility of maximum likelihood estimation (MLE) in this framework, I develop a generalized method of moments (GMM) estimation procedure which yields estimators for the unknown parameters in both the main system and the covariance matrix. These estimators achieve the efficiency of MLE.As an empirical application of the model, I investigate the price competition between two major pharmaceutical chains in the state of New York in a second paper. The prices of standardized prescription drugs vary considerably, both within each chain and across the two chains. This market is a good fit for the simultaneous SAR model because each chain store interacts with other stores that belong to the same chain and those that belong to the rival chain. The estimation results reveal that each store competes not only against the rival stores but also against the stores in the same chain. Furthermore, the spatial coefficients indicate that the price competition within the same chain is softer than the price competition between chains.In the third chapter, I apply my simultaneous SAR methodology to construct a simultaneous spatial model to study the relationship between the housing price and the racial composition in several U.S. metropolitan areas at the neighborhood level. By using the simultaneous SAR model, I can address an important issue that has not yet been studied extensively in the housing literature. Specifically, I call into question the exogeneity of racial composition, which is routinely included as an explanatory variable in the hedonic housing price equation. The potential endogeneity of this variable stems from the simultaneous nature of the housing price and the racial composition in each neighborhood and causes the traditional estimators to be biased. According to empirical estimation, black renters and homeowners have significantly higher price elasticities of housing demand than their white counterparts. Assuming that the distribution of price sensitivity among blacks first-order stochastically dominates the distribution of price sensitivity among whites, I use a self-selection model to show that blacks tend to concentrate in areas where housing prices are lower. Thus, we can use the housing price in each neighborhood as an explanatory variable for the racial composition of the neighborhood in another regression equation. By simultaneously estimating a housing price equation and a set of neighborhood composition equations in the same model, we can correct the biased estimators in the hedonic housing price analysis. In addition, the spatial structure of the model reveals each ethnic group’s preferences for integrating with other ethnic groups. These help explain the high level of racial and ethnic segregation that is typical of U.S. metropolitan areas. Using census 2000 sample data measured at the block group level from five MSAs, I confirm the endogeneity of neighborhood composition in the housing price equation. While the estimation bias in the single-equation model is relatively small in MSAs with a simple racial composition, it becomes much larger in MSAs with a high level of racial and ethnic diversity and drastically changes the interpretation of the regression coefficients. Furthermore, the estimates of the spatial coefficients indicate that each minority group strongly desires to live among their own race or ethnicity and generally prefers to stay away from the other groups.","abstract_has_math":false,"creators":["Bao, Yan"],"institution":"The Ohio State University","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Economics","degree_department":null,"school":null,"contributors":["Lee, Lung-Fei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-08-09","date_published":"2013-08-09","updated_at":"2026-07-24T03:37:46Z","subjects":["Economics"],"languages":["English"],"rights":["unrestricted","This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1366131746","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lee, Lung-Fei"]},{"key":"dc:creator","label":"Author","values":["Bao, Yan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013-08-09"]},{"key":"dc:publisher","label":"Institution","values":["The Ohio State University / OhioLINK"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Economics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["The Ohio State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Economics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["unrestricted","This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://rave.ohiolink.edu/etdc/view?acc_num=osu1366131746"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["My research focuses on the extension of the spatial autoregressive (SAR) model into a system of simultaneous equations. The resulting new model is useful in studying problems involving multiple networks where individuals are not only linked to members of the same network but also interact with members of the other networks. The behavior of each individual is affected by the behavior of those to whom he is linked. The magnitude of such effects, which are referred to as spatial effects, depends on the strength of the links.As the foundation of the dissertation, I first introduce the simultaneous SAR model in a theoretical paper. This paper extends the high-order spatial autoregressive model to a multiple-equation system in which the dependent variable in each equation exerts a spatial effect on the dependent variables in all the equations. Although researchers have studied the estimation methods for some similar models, an efficient estimation approach is still lacking. Due to the infeasibility of maximum likelihood estimation (MLE) in this framework, I develop a generalized method of moments (GMM) estimation procedure which yields estimators for the unknown parameters in both the main system and the covariance matrix. These estimators achieve the efficiency of MLE.As an empirical application of the model, I investigate the price competition between two major pharmaceutical chains in the state of New York in a second paper. The prices of standardized prescription drugs vary considerably, both within each chain and across the two chains. This market is a good fit for the simultaneous SAR model because each chain store interacts with other stores that belong to the same chain and those that belong to the rival chain. The estimation results reveal that each store competes not only against the rival stores but also against the stores in the same chain. Furthermore, the spatial coefficients indicate that the price competition within the same chain is softer than the price competition between chains.In the third chapter, I apply my simultaneous SAR methodology to construct a simultaneous spatial model to study the relationship between the housing price and the racial composition in several U.S. metropolitan areas at the neighborhood level. By using the simultaneous SAR model, I can address an important issue that has not yet been studied extensively in the housing literature. Specifically, I call into question the exogeneity of racial composition, which is routinely included as an explanatory variable in the hedonic housing price equation. The potential endogeneity of this variable stems from the simultaneous nature of the housing price and the racial composition in each neighborhood and causes the traditional estimators to be biased. According to empirical estimation, black renters and homeowners have significantly higher price elasticities of housing demand than their white counterparts. Assuming that the distribution of price sensitivity among blacks first-order stochastically dominates the distribution of price sensitivity among whites, I use a self-selection model to show that blacks tend to concentrate in areas where housing prices are lower. Thus, we can use the housing price in each neighborhood as an explanatory variable for the racial composition of the neighborhood in another regression equation. By simultaneously estimating a housing price equation and a set of neighborhood composition equations in the same model, we can correct the biased estimators in the hedonic housing price analysis. In addition, the spatial structure of the model reveals each ethnic group’s preferences for integrating with other ethnic groups. These help explain the high level of racial and ethnic segregation that is typical of U.S. metropolitan areas. Using census 2000 sample data measured at the block group level from five MSAs, I confirm the endogeneity of neighborhood composition in the housing price equation. While the estimation bias in the single-equation model is relatively small in MSAs with a simple racial composition, it becomes much larger in MSAs with a high level of racial and ethnic diversity and drastically changes the interpretation of the regression coefficients. Furthermore, the estimates of the spatial coefficients indicate that each minority group strongly desires to live among their own race or ethnicity and generally prefers to stay away from the other groups."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","3.45 MB"]},{"key":"dc:title","label":"Title","values":["The Simultaneous Spatial Autoregressive Model and Its Application in the Housing and Pharmaceutical Markets"]}]}],"canonical_facts":{"dc:contributor":["Lee, Lung-Fei"],"dc:creator":["Bao, Yan"],"dc:date":["2013-08-09"],"dc:description":["My research focuses on the extension of the spatial autoregressive (SAR) model into a system of simultaneous equations. The resulting new model is useful in studying problems involving multiple networks where individuals are not only linked to members of the same network but also interact with members of the other networks. The behavior of each individual is affected by the behavior of those to whom he is linked. The magnitude of such effects, which are referred to as spatial effects, depends on the strength of the links.As the foundation of the dissertation, I first introduce the simultaneous SAR model in a theoretical paper. This paper extends the high-order spatial autoregressive model to a multiple-equation system in which the dependent variable in each equation exerts a spatial effect on the dependent variables in all the equations. Although researchers have studied the estimation methods for some similar models, an efficient estimation approach is still lacking. Due to the infeasibility of maximum likelihood estimation (MLE) in this framework, I develop a generalized method of moments (GMM) estimation procedure which yields estimators for the unknown parameters in both the main system and the covariance matrix. These estimators achieve the efficiency of MLE.As an empirical application of the model, I investigate the price competition between two major pharmaceutical chains in the state of New York in a second paper. The prices of standardized prescription drugs vary considerably, both within each chain and across the two chains. This market is a good fit for the simultaneous SAR model because each chain store interacts with other stores that belong to the same chain and those that belong to the rival chain. The estimation results reveal that each store competes not only against the rival stores but also against the stores in the same chain. Furthermore, the spatial coefficients indicate that the price competition within the same chain is softer than the price competition between chains.In the third chapter, I apply my simultaneous SAR methodology to construct a simultaneous spatial model to study the relationship between the housing price and the racial composition in several U.S. metropolitan areas at the neighborhood level. By using the simultaneous SAR model, I can address an important issue that has not yet been studied extensively in the housing literature. Specifically, I call into question the exogeneity of racial composition, which is routinely included as an explanatory variable in the hedonic housing price equation. The potential endogeneity of this variable stems from the simultaneous nature of the housing price and the racial composition in each neighborhood and causes the traditional estimators to be biased. According to empirical estimation, black renters and homeowners have significantly higher price elasticities of housing demand than their white counterparts. Assuming that the distribution of price sensitivity among blacks first-order stochastically dominates the distribution of price sensitivity among whites, I use a self-selection model to show that blacks tend to concentrate in areas where housing prices are lower. Thus, we can use the housing price in each neighborhood as an explanatory variable for the racial composition of the neighborhood in another regression equation. By simultaneously estimating a housing price equation and a set of neighborhood composition equations in the same model, we can correct the biased estimators in the hedonic housing price analysis. In addition, the spatial structure of the model reveals each ethnic group’s preferences for integrating with other ethnic groups. These help explain the high level of racial and ethnic segregation that is typical of U.S. metropolitan areas. Using census 2000 sample data measured at the block group level from five MSAs, I confirm the endogeneity of neighborhood composition in the housing price equation. While the estimation bias in the single-equation model is relatively small in MSAs with a simple racial composition, it becomes much larger in MSAs with a high level of racial and ethnic diversity and drastically changes the interpretation of the regression coefficients. Furthermore, the estimates of the spatial coefficients indicate that each minority group strongly desires to live among their own race or ethnicity and generally prefers to stay away from the other groups."],"dc:format":["application/pdf","3.45 MB"],"dc:identifier":["http://rave.ohiolink.edu/etdc/view?acc_num=osu1366131746"],"dc:language":["English"],"dc:publisher":["The Ohio State University / OhioLINK"],"dc:rights":["unrestricted","This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws."],"dc:subject":["Economics"],"dc:title":["The Simultaneous Spatial Autoregressive Model and Its Application in the Housing and Pharmaceutical Markets"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_discipline":["Economics"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["The Ohio State University"]},"updated_at":"2026-07-24T03:37:46Z"}