Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2017-08-01T16:51:38Z No. of bitstreams: 1 Tiago Henrique Lenhard_.pdf: 599231 bytes, checksum: 3887a7a17e0d823268ecff3b91709a7b (MD5) / Made available in DSpace on 2017-08-01T16:51:38Z (GMT). No. of bitstreams: 1 Tiago Henrique Lenhard_.pdf: 599231 bytes, checksum: 3887a7a17e0d823268ecff3b91709a7b (MD5) Previous issue date: 2017-05-15 / Nenhuma / O objetivo deste trabalho é verificar o efeito da aplicação de taxa de coparticipação como mecanismo de regulação da demanda por serviços de saúde, mais especificamente na frequência e nos custos de consultas médicas, em consultas de plantão hospitalar, em exames laboratoriais e de diagnóstico por imagem. Os dados utilizados para este trabalho são provenientes de uma operadora de planos de saúde (OPS) da modalidade de Cooperativa Médica A metodologia utilizada para avaliar os resultados da aplicação de taxa de coparticipação dos planos é o Propensity Score Matching (PSM) a partir de estimadores One to one Matching (OM), Nearest Neighbor Matching (NNM), Radius Matching (RM) e Kernel Matching (KM). Os resultados indicam a existência de risco moral em indivíduos que possuem plano sem taxa de coparticipação na demanda por consultas médicas e em plantão hospitalar. Para os custos gerados para a OPS por esses serviços o resultado é semelhante. Para os exames laboratoriais o risco moral não foi evidenciado pela ausência de coparticipação nos planos. Já para os exames de diagnóstico por imagem o risco moral foi evidenciado. Os custos para a OPS nesses exames apresentaram um aumento significativo para os indivíduos sem taxa nos dois grupos de exames. Os resultados obtidos por este trabalho indicam que o efeito causado pela taxa de coparticipação é positivo para a OPS, pois a aplicação desse mecanismo reduz significativamente a demanda e os custos para os serviços considerados nesta análise, evidenciando a ocorrência do risco moral em planos sem taxa de coparticipação. / The goal of our study is to investigate the role of copayment as a regulatory mechanism in health services demand. Specifically, we want to understand the effect of copayment on the number and costs related to appointments, emergency appointments, and laboratory and imaging tests. Our dataset was obtained from a health insurance cooperative company (HIC). To evaluate the effects of copayment application in the health care utilization we apply a Propensity Score Matching (PSM) method, using the following estimators: One to one Matching (OM), Nearest Neighbor Matching (NNM), Radius Matching (RM) and Kernel Matching (KM). The results indicate the evidence of moral hazard effects in appointments and emergency appointments demand for those individuals with health insurance without copayment. Similar results are obtained when we consider the costs incurred by the HIC when providing these services. As for laboratory tests, there was no evidence on moral hazard effects. However, when we consider imaging tests, moral hazard effects were evidenced. HIC provision costs of laboratory and imaging tests showed a significant increase for those individuals with health care plan without copayment. Our results indicate that charging a copayment reduces demand and costs of those health care services considered in out study, highlighting the incentives due to the moral hazard existence in the health care insurance market.

Este trabalho emprega métodos quantitativos a dados de Demonstrações Financeiras para avaliar a existência de relação de causalidade entre a Lei 12.249 de 11 de junho de 2010, que institui normas de subcapitalização no Brasil, e a estrutura de capital de empresas brasileiras que possuem partes vinculadas no exterior. Esta lei estabeleceu limites ao endividamento oriundo de tais partes vinculadas para que os respectivos juros pagos sejam considerados dedutíveis para fins da apuração de tributos sobre o lucro e foi usada como intervenção exógena na análise proposta. Os dados são oriundos de empresas fechadas e de empresas públicas, coletados manualmente, em jornais publicamente disponíveis, e na base de dados Economatica® e foi obtida uma amostra inicial de 2,070 observações. Após exclusão daquelas com Patrimônio Líquido negativo, restaram 1,816 observações em um painel não balanceado, subamostra usada para estimação com o método principal de investigação deste trabalho, que foi o de Diferenças-em-diferenças (DD). Neste, a variável dependente consistiu da razão entre dívida onerosa total e Ativo Total, observados anualmente no período compreendido entre o ano de 2006 e ano de 2014. Este método foi estimado por OLS seus resultados foram complementados com o pareamento de observações por meio de quatro procedimentos de propensity score matching (PSM), one-to-one, nearest neighbour, radius e kernel, em que a variável resposta consistiu da diferença, observada entre o ano de 2011 e o ano de 2009, dos valores da variável resposta descrita anteriormente. Para estimação por meio de matching, foram excluídas observações de empresas que variaram a composição societária ao longo do período de forma a possuir partes vinculadas estrangeiras em determinado momento e não possuí-las mais tarde e também foram excluídas aquelas empresas que não possuem observações durante todo o período avaliado, obtendo-se um painel balanceado com 114 empresas e 1,026 observações. O propensity score obtido foi ainda empregado para ponderar as observações no modelo previamente estimado com o método DD. As variáveis de controle empregadas tanto no DD quanto na estimação do propensity score consistiram dos valores de Ativo Imobilizado, Vendas Líquidas, Lucro Bruto e Patrimônio Líquido, obsevados anualmente e dividido pelo Ativo Total. Os resultados obtidos não foram significantes aos níveis convencionais de confiança, apontando para possível redução da relação entre dívida total e Ativo Total das empresas do grupo tratamento em valores que variaram entre 4.17% e 0.5% em termos de Ativo Total, dependendo do método e modelo estimados. Observa-se que tanto a variável resposta quanto o endividamento oneroso total das empresas de ambos os grupos parecem ter aumentado durante o período investigado, mas a variável resposta, aparentemente, já apresentava crescimento menos acentuado nas empresas do grupo tratamento antes do advento da lei, não sendo possível concluir que esta seja a causa da tendência de decréscimo da relação entre dívida e Ativo Total no grupo de empresas que possuem partes vinculadas estrangeiras. Ressalvadas as limitações do estudo, conclui-se que a lei não teve efeito sobre o endividamento total e, portanto, sem efeitos sobre a arrecadação de tributos sobre o lucro destas empresas. / This work applies quantitative methods to data from Financial Statements to assess the existence of a causal relationship between the Law 12,249 of June 11, 2010, which establishes thin capitalization rules in Brazil, and the capital structure of Brazilian companies that keep foreign related parties. This law established limits to the tax deductibility arising from interest payments to such related parties and was here employed as a source of exogenous variation to perform the proposed analysis. The data came from private and public companies, were manually collected, from publicly available newspapers, and obtained from the Economatica database. An initial sample of 2,070 observations was obtained. After the exclusion of those with negative Equity, there were 1,816 observations composing an unbalanced panel, sub-sample which was used for estimation with the main research method of this investigation, which was the Differences-in-differences (DD) method. A dependent variable consisted of the ratio between total costly debt and Total Asset, observed annually in the period between the years 2006 and 2014. This method has been estimated by OLS and its results were complemented with the pairing of companies by means of four matching methods: One-to-one, nearest neighbour, radius, and kernel, where the response variable consisted of the difference between the dependent variable\'s values observed in the years 2011 and 2009. To estimate the laws\' effects by means of matching procedures, data from companies that showed variation at the societal composition in such a way that led them to have foreign related parties in less than the whole period and from those companies that do not have data throughout the whole period evaluated were excluded, and a balanced panel with 114 companies and 1,026 observations remained. Yet again, the obtained propensity score was applied as weight for another OLS DD estimation. Control variables consisted of the values of Fixed Assets, Net Sales, Gross Profits and Shareholders\' Equity, reported annually and divided by Total Assets. The results obtained were not significant at any conventional confidence levels, nevertheless pointing to a reduction of the treatment group companies\' ratio between debt and Total Assets which varied between 4.17% and 0.5% of Total Assets, depending on the estimated method and model. It appears that the companies\' both response variable and total costly indebtedness increased during the period analysed, but the response variable seems to have already presented a less pronounced growth in the treatment group\'s companies before the existence of the law, therefore making it not possible to conclude that this legislation piece is the cause of the downward trend in the ratio between debt and Total Assets of companies that keep foreign related parties. Subject to this study\'s limitations, it is possible to conclude that the law had no effect on total indebtedness and, therefore, had no effect on profit taxes base erosion regarding this group of companies.

Submitted by Franciele Moreira (francielemoreyra@gmail.com) on 2017-09-06T20:23:31Z No. of bitstreams: 2 Dissertação - Rafael dos Reis Costa - 2017.pdf: 2132575 bytes, checksum: 36e395f611d898ae6dc8ac7f39bca0a5 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-09-15T15:40:36Z (GMT) No. of bitstreams: 2 Dissertação - Rafael dos Reis Costa - 2017.pdf: 2132575 bytes, checksum: 36e395f611d898ae6dc8ac7f39bca0a5 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-09-15T15:40:36Z (GMT). No. of bitstreams: 2 Dissertação - Rafael dos Reis Costa - 2017.pdf: 2132575 bytes, checksum: 36e395f611d898ae6dc8ac7f39bca0a5 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-07-04 / The State School Program of Full Time, started in 2006 in the state of Goiás. It have 135 schools attended in 2013. This program offers cultural and sports activities, besides school reinforcement. The study intends to evaluate the project impacts on the academic performance in portuguese language and math of the 5th and 9th graders with data from the Brazil Proof (Prova Brasil) of 2013. To achieve this goal was used the method of propensity score matching. The results found point to non-significant effects in mathematics and portuguese language for the 5th graders. On the other hand, the 9th graders who study in schools that participated in the program before 2013 the effects are positive. Those in schools that started the program in 2013 did not have a significant difference in math, but did a negative and significant performance in comparison with the control group in portuguese language. / O Programa Escola Estadual de Tempo Integral, implementado desde 2006 no estado de Goiás, alcançou o número de 135 unidades escolares atendidas em 2013. Este programa oferece no contra turno atividades artísticas, culturais, esportivas, além do reforço escolar. O trabalho pretende avaliar o impacto do projeto sobre o desempenho escolar em português e matemática dos estudantes dos 5º e 9º anos com dados da Prova Brasil de 2013. Para alcançar este objetivo foi utilizado o método de propensity score matching. Os resultados encontrados apontam para efeitos não significativos em matemática e português para os alunos do 5º ano. Por outro lado, os alunos do 9º que estudam em escolas que participam do programa antes de 2013 apresentaram desempenho positivo. Aqueles que estão em escolas que começaram no programa em 2013 não tiveram efeito significativo em matemática, mas obtiveram um desempenho negativo e significativo na comparação com o grupo de controle em português.

nÃo hà / O objetivo deste trabalho à avaliar a ocorrÃncia de risco moral na demanda por consultas mÃdicas e serviÃos de apÃio ao diagnÃstico e tratamento (exames) no sistema de saÃde suplementar brasileiro. Especificamente, visamos à comparaÃÃo quantitativa da utilizaÃÃo desses serviÃos de saÃde entre dois tipos de planos: com e sem coparticipaÃÃo. Para isso, utilizamos dois mÃtodos de matching baseado no propensity score, onde os estimadores sÃo calculados a partir de grupos ou estratos (Stratification Matching) e a partir de uma funÃÃo densidade (Kernel Matching). No modelo de estratos o efeito estimado da coparticipaÃÃo em consultas mÃdicas ficou entre -0,358 e -0,979 per capita por ano. No modelo a partir de uma funÃÃo Kernel, o efeito da coparticipaÃÃo foi de -0,286 a -1,031 per capita por ano. No caso dos exames, o efeito da coparticipaÃÃo ficou entre -2,965 e -4,652 (Stratification Matching) e -2,621 e -5,057 (Kernel Matching). Em ambos os modelos a regiÃo Nordeste apresentou o maior efeito de coparticipaÃÃo, tanto para consultas quanto para exames, enquanto a regiÃo Sul teve o menor efeito. Os resultados alcanÃados com o trabalho evidenciam a ocorrÃncia de risco moral, ou seja, a utilizaÃÃo de serviÃos de saÃde à sensÃvel à imposiÃÃo de mecanismos de regulaÃÃo, onde indivÃduos com coparticipaÃÃo demandam consultas mÃdicas e exames em quantidade inferior aqueles sem coparticipaÃÃo. / The objective of this study is to evaluate the occurrence of moral hazard in the demand for medical and support services for diagnosis and treatment (tests) in the Brazilian supplementary health system. Specifically, we aim at the quantitative comparison of the use of health services between two types of plans: with and without coparticipaÃÃo. For this, we use two methods of matching based on propensity score, where the estimators are derived from groups or strata (Stratification Matching) and from a density function (Kernel Matching). In the model of strata the estimated effect of coparticipaÃÃo medical appointments was between -0.358 and -0.979 per capita per year. In the model from a kernel function, the effect of coparcenary was -0.286 to -1.031 per capita per year. In the case of examinations, the effect of coparcenary was between -2.965 and -4.652 (Stratification Matching) and -2.621 and -5.057 (Kernel Matching). In both models the Northeast had the highest effect coparcenary, both for consultations and for examinations, while the South had the smallest effect. The results achieved through the study show the occurrence of moral hazard, ie the use of health services is sensitive to the imposition of regulatory mechanisms where individuals coparticipaÃÃo require medical examinations and in quantities not exceeding those without coparcenary

A compreensão da dinâmica de persistência e evasão da atividade exportadora é fundamental para o desenho de incentivos adequados às firmas estreantes no mercado internacional e encontra respaldo nos modelos da nova teoria do comércio internacional. O propósito deste trabalho é investigar os determinantes do desempenho de firmas industriais brasileiras estreantes no mercado internacional, em termos de probabilidade de sobrevivência e evolução do valor exportado, com especial atenção aos impactos dos instrumentos de apoio Drawback, BNDES Exim e Proex. Para tanto, serão analisadas empresas estreantes no comércio exterior entre os anos de 1998 e 2003, configurando um painel desbalanceado com 8,5 mil firmas. Por meio de análise econométrica para dados em painel e estimação de modelos de duração, verificou-se que a função de sobrevivência e crescimento do valor médio exportado no tempo difere claramente entre firmas que utilizam um dos benefícios e aquelas que não o fazem. Também se pode afirmar que custos irreversíveis de entrada no comércio internacional não sejam desprezíveis entre as firmas industriais analisadas, o que indica que os programas públicos de promoção de exportações devam se concentrar na (i) redução da taxa de abandono das recém-exportadoras e (ii) na minimização dos custos fixos associados aos investimentos para entrada no mercado exportador. / Understanding the dynamics of persistence and evasion of export activity is essential for the design of export promotion for new exporters and international trade policies. Several results point to the importance of taking into account the specific sector of the industry in the implementation of public policies, which is supported by the new models of international trade theory. The purpose of this work is to investigate the determinants of the performance of Brazilian industrial new exporters, with particular attention to the impacts of Drawback, BNDES Exim and Proex. For this, we analyzed firms between the 1998 and 2003, constituting an unbalanced panel with 8500 firms. By panel data analysis and estimation of duration models, we found that the survival function and the growth of exports clearly differs among companies that use one of the programs and those that do not. One can also say that sunk costs are not negligible among the industrial firms analyzed, which indicates that public export promotion should focus on (i) reducing the dropout rate of new exporters and (ii) minimize the fixed sunk costs related with initial investments to begin the export activty.

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2016-04-18T13:47:12Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) TESE_BRUNA DA NÓBREGA GERMANO_DIGITAL.pdf: 1843966 bytes, checksum: e3760059e9c9caf7b2b5e9854e1b340e (MD5) / Made available in DSpace on 2016-04-18T13:47:12Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) TESE_BRUNA DA NÓBREGA GERMANO_DIGITAL.pdf: 1843966 bytes, checksum: e3760059e9c9caf7b2b5e9854e1b340e (MD5) Previous issue date: 2015-07-14 / CAPEs / O objetivo do presente trabalho consiste em avaliar se a política de gestão por resultados do Pacto pela educação – PPE gerou impacto nas escolas da rede pública estadual de Pernambuco que oferecem o ensino médio, no período de 2008 a 2013 (sendo 2011 o ano de implementação da política avaliada), considerando como indicadores de sucesso escolar os índices de aprovação e abandono, as notas médias obtidas no Sistema de Avaliação Educacional de Pernambuco – SAEPE em Língua Portuguesa e Matemática, e a nota média no Índice de Desenvolvimento da Educação de Pernambuco – IDEPE. Como a implementação dessa política foi realizada com base em características observáveis e não de forma experimental, a análise desenvolvida neste estudo é fundamentada em dois métodos econométricos: pareamento com propensity score e diferenças em diferenças (DD). Dessa forma, são considerados dois cenários: no Cenário 1 apenas o método DD é aplicado; no Cenário 2 os dois métodos são combinados. No primeiro cenário, os resultados mostraram que o monitoramento pelo PPE gera impacto positivo e significativo considerando as notas médias no SAEPE e no IDEPE. Ou seja, a participação na política de gestão por resultados do PPE eleva a nota média das escolas nesses indicadores. Considerando os índices de aprovação e abandono, o monitoramento pelo PPE não exerce influência sobre os mesmos. O efeito do Programa de Educação Integral – PEI também precisou ser avaliado, uma vez que a política de gestão por resultados do PPE utilizou a participação neste programa como condicionante para o tratamento. Assim, no Cenário 1, o efeito da participação no PEI é significativo para os indicadores de fluxo escolar (maior aprovação e menor abandono) e para a nota média no IDEPE. No entanto, não há resultado significativo quando se avaliam as notas médias no SAEPE. É importante destacar que o IDEPE, fruto da multiplicação do índice de aprovação pelas notas médias no SAEPE, foi o único indicador para o qual se observou resultados positivos e significativos, tanto para o monitoramento pelo PPE quanto para a participação no PEI. Os resultados obtidos no Cenário 2, independente do critério de pareamento utilizado e do indicador avaliado, ratificaram aqueles já encontrados no Cenário 1, conferindo assim maior robustez à análise desenvolvida neste estudo. Avaliando as duas políticas conjuntamente, tem-se impactos positivos sobre a maior permanência dos alunos na escola, tanto para aos indicadores de fluxo escolar como para as notas médias no SAEPE. / This work aims to evaluate whether the management by results policy used by the Pacto pela Educação - PPE (Pact for Education) had any impacts on Pernambuco state funded (public) schools that offer secondary education (ensino médio), between the years of 2008 and 2013 - the mentioned policy began in 2011. The following indexes were used to measure school success: pass and dropout rates, average grades on SAEPE (Sistema de Avaliação Educacional de Pernambuco) in the subjects of portuguese and mathematics and average grades on IDEPE (Índice de Desenvolvimento da Educação de Pernambuco). The policy was implemented based on observable characteristics and not in a experimental way, therefore the analysis will consist of the use of two econometric methods: Propensity Score Matching and Difference-in-Differences (DID). Two scenarios were considered: the first uses the DID method; the second combines the use of the Propensity Score Matching with the DID methods. In the first scenario, results show that PPE monitoring generates considerable, positive impact regarding average grades on SAEPE and IDEPE. In other words, participation in PPE's management by results policy results in a improvement of such indexes. As for pass and dropout rates, PPE has no influence on them. The effect of the Educação Integral program - PEI (Full Time Education program) also deserved attention since PPE's management by results policy required schools to be part of this program. So, in scenario 1, effects of PEI are significant in respect to pass and dropout rates (higher passing and lower dropout) and average grade on IDEPE. It was not possible to find, however, any significant improvement on SAEPE the average grades. It is important to highlight that IDEPE (which is the product of pass rates by average SAEPE grades) was the only index in which positive and significant results were observed for both PPE monitoring and PEI participation. The results of the second scenario, no matter which matching criteria is used or what index considered, corroborated with those already found on the first scenario, thus providing more substance to the analysis performed by this work. Seeing both policies combined, positive impacts are found when students stay in school for longer periods of time. This is true for pass and dropout rates as well as average performance of students on SAEPE.

The aim of the study is to compare health outcomes of migrants and the native German population, testing for the existence of a Healthy Immigrant Effect (HIE). The study contributes a broad theoretical analysis of the HIE and makes use of a wide spectrum of variables to model health (using the SF-12). The HIE is marked by an observed health advantage for migrants, when compared to the host population, which declines with the years since migration. Assessing different types of selection processes, it is assumed that mass migration to post-industrial countries is characterized by favouring the inflow of healthy individuals from weaker economies working in the low-wage sector due to the cost aspect of migration and differences in wages for adequate work. Socioeconomic and -structural differences of migrant and host population as well as psychosocial stressors like acculturation cause the deteroriation of the health adavantage with increasing years since migration. Using cross-sectional data from the 2016 wave of the Socio-Economic Panel this study compares health outcomes (generated from the SF-12) between recent migrants (≤ 10 years since migration), non-recent migrants (> 10 years since migration) and the German native population. Propensity score matching analyses reveal a health advantage for recent migrants compared to non-recent migrants as well as to the German native population, while non-recent migrants remain statistically indistinguishable from the native German population, implying a health assimilation effect.

This study was intended to evaluate the impact of socioeconomically disadvantaged children's participation in the Texas Home Instruction for Parents of Preschool Youngsters (TX HIPPY) Program on their school readiness and academic achievement. The study used a quasi-experimental design and applied full and optimal propensity score matching (PSM) to address the evaluation concern of the impact of the TX HIPPY program on HIPPY participants' academic achievement compared to non-HIPPY participants. This evaluation targeted former HIPPY participants and tracked them in the Dallas ISD database through Grade Levels K-8. Data were obtained by administering Istation's Indicators of Progress (ISIP) for kindergarten, TerraNova/SUPERA for Grades K-2, and State of Texas Assessments of Academic Readiness for math and reading (STAAR) for Grades 3-8. HIPPY and non-HIPPY groups were matched using propensity score analysis procedures. The evaluation findings show that the TX HIPPY program positively influences kindergarten students to start school ready to learn. The findings of math and reading achievements suggest that HIPPY children scored at the same level or higher than non-HIPPY children did on math and reading achievement, indicating that TX HIPPY program has achieved its goal of helping children maintain long-term academic success. However, the evaluation findings also indicated that the impact evaluation framework must be designed with attention to higher-level factors beyond academic achievement that influence children's academic success.

This is a study in two parts. In part-1, I identify several methods of estimating long-run abnormal returns prevalent in the finance literature and present an alternative using propensity score matching. I first demonstrate the concept with a simple simulation using generated data. I then employ historical returns from CRSP and randomly select events from the dataset using various alternating criteria. I test the efficacy of different methods in terms of type-I and type-II errors in detecting abnormal returns over 12- 36- and 60- month periods. I use various forms of propensity score matching: 1--5 Nearest Neighbors in Caliper using distance defined alternatively by Propensity Scores and the Mahalanobis Metric, and Caliper Matching. I show that overall, Propensity Score Matching with two nearest neighbors provides much better performance than traditional methods, especially when the occurence of events is dictated by the presence of certain firm characteristics. In part-2, I demonstrate an application of Propensity Score Matching in the context of open-market share repurchase announcements. I show that traditional methods are ill-suited for the calculation of long-run abnormal returns following such events. Consequently, I am able to improve upon such methods on two fronts. First, I improve upon traditional matching methods by providing better matches on multiple dimensions and by being able to retain a larger sample of firms from the dataset. Second, I am able to eliminate much of the bias inherent in the Fama-French type methods for this particular application. I show this using simulations on samples based on firms that resemble a typical repurchasing firm. As a result, I obtain a statistically significant 1-, 3-, and 5- year abnormal return of about 2%, 5%, and 10% respectively, which is much lower than what prior literature has shown using traditional methods. Further investigation revealed that much of these returns are unique to small and unprofitable firms.

Multicollinearity can be present in the propensity score model when estimating average treatment effects (ATEs). In this thesis, logistic ridge regression (LRR) and principal components logistic regression (PCLR) are evaluated as an alternative to ML estimation of the propensity score model. ATE estimators based on weighting (IPW), matching and stratification are assessed in a Monte Carlo simulation study to evaluate LRR and PCLR. Further, an empirical example of using LRR and PCLR on real data under multicollinearity is provided. Results from the simulation study reveal that under multicollinearity and in small samples, the use of LRR reduces bias in the matching estimator, compared to ML. In large samples PCLR yields lowest bias, and typically was found to have the lowest MSE in all estimators. PCLR matched ML in bias under IPW estimation and in some cases had lower bias. The stratification estimator was heavily biased compared to matching and IPW but both bias and MSE improved as PCLR was applied, and for some cases under LRR. The specification with PCLR in the empirical example was usually most sensitive as a strongly correlated covariate was included in the propensity score model.