The main purpose of this degree project is to reveal the Airbnb customer’s preferences and quantify the impact of non-market factors on the market price of tourist accommodation in Berlin, Germany. The data retrieved from Airbnb listings, publicly available on Inside Airbnb (2017), was supplemented on indicator of sharing economy accommodation using machine learning method in order to distinguish between amateur and business-running professional hosts. The main aim is to examine the consumers’ preferences and quantify the marginal effect of "real sharing economy" accommodation and other key variables on market price. This is accomplished by model approach using hedonic pricing method, which is used to estimate the economic value of particular attribute. Surprisingly, our data indicates the negative impact of sharing economy indicator on price. The set of motivations of consumers, which determine their valuation of Airbnb listings, was identified. The trade-off between encompass and parsimony of the set was desired in order to build an effective model. Calculation of proportion of explained variance showed that the price is affected mainly by number of accommodated persons, degree of privacy, number of bedrooms, cancellation policy, distance from the city centre and sharing economy indicator in decreasing order.

Submitted by joao barbosa campbell penna (joao.penna@vale.com) on 2015-02-20T19:44:37Z No. of bitstreams: 1 TESEFINAL_20022015.pdf: 1480842 bytes, checksum: 11e3f73bc5b243b7ed4a73b63fe90c59 (MD5) / Approved for entry into archive by GILSON ROCHA MIRANDA (gilson.miranda@fgv.br) on 2015-06-08T18:42:08Z (GMT) No. of bitstreams: 1 TESEFINAL_20022015.pdf: 1480842 bytes, checksum: 11e3f73bc5b243b7ed4a73b63fe90c59 (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2015-06-12T17:55:33Z (GMT) No. of bitstreams: 1 TESEFINAL_20022015.pdf: 1480842 bytes, checksum: 11e3f73bc5b243b7ed4a73b63fe90c59 (MD5) / Made available in DSpace on 2015-06-12T17:56:53Z (GMT). No. of bitstreams: 1 TESEFINAL_20022015.pdf: 1480842 bytes, checksum: 11e3f73bc5b243b7ed4a73b63fe90c59 (MD5) Previous issue date: 2014-12-20 / Medimos a validade da paridade descoberta de juros – PDJ - para o mercado brasileiro no período de janeiro de 2010 a julho de 2014. Testamos a equação clássica da PDJ usando o Método dos Mínimos Quadrados Ordinários. Após a estimação dos parâmetros, aplicamos o Teste de Wald e verificamos que a paridade descoberta de juros não foi validada. Estendemos a equação tradicional da PDJ para uma especificação alternativa que captura medidas de risco Brasil e de alteração na liquidez internacional. Especificamente, acrescentamos três variáveis de controle: duas variáveis dummy que capturam condições de liquidez externa e o índice de commoditie CRB, que captura o risco Brasil. Com a especificação alternativa, a hipótese de que os retornos das taxas de juros em Real, dolarizadas, são iguais aos retornos da taxas de juros contratadas em dólares, ambas sujeitas ao risco Brasil, não foi rejeitada. Em complemento à análise das taxas representativas do mercado brasileiro, procurou-se avaliar a predominância da PDJ nas operações de swap cambial realizadas pela Vale S.A.. Para tanto, a série de taxa de juros em dólares do mercado brasileiro foi substituída pela taxa em dólar dos swaps contratados pela Vale. Os resultados encontrados demonstram que, quando comparado ao comportamento do mercado, as taxas em dólares da VALE são mais sensíveis às variações das taxas em Reais. / We measure the validity of uncovered interest parity - UIP - for the Brazilian market from January, 2010 to July, 2014. We tested the classical equation of UIP using the ordinary least squares method. After the estimation, we apply the Wald test and we verify that the uncovered interest parity has not been validated. We extend the traditional UIP equation for an alternative specification that captures Brazil risk and changes in liquidity of the international market. Specifically, we add three control variables: two dummy variables that capture external liquidity conditions and the commodity index CRB, which captures Brazil risk. With the alternative specification, the hypothesis that the returns in interest rates in Real, dollarized, are equal to the return of interest rate contracted in dollars, both subject to Brazil risk, was not rejected. To complement the analysis using the interest rates existing in the Brazilian market, we tried to evaluate the prevalence of UIP in cross currency interest rate swaps carried out by Vale SA. The interest rate in dollar of the Brazilian market was replaced by the dollar rate of swaps contracted by Vale. The results show that, when compared to market behavior, the dollar rates of Vale SA. are more sensitive to changes in Reais interest rates.

Made available in DSpace on 2016-06-02T20:06:02Z (GMT). No. of bitstreams: 1 2567.pdf: 3332442 bytes, checksum: 1e03b44e1c1f61f90b947fdca5682355 (MD5) Previous issue date: 2009-03-06 / Financiadora de Estudos e Projetos / Several techniques are proposed to determine the lag length of a dynamic regression model. However, none of them is completely satisfactory and a wrong choice could imply serious problems in the estimation of the parameters. This dissertation presents a review of the main criteria for models selection used in the classical methodology and presents a way for determining the lag length from the perspective Bayesian. A Monte Carlo simulation study is conducted to compare the performance of the significance tests, R2 adjusted, final prediction error, Akaike information criterion, Schwarz information criterion, Hannan-Quinn criterion, corrected Akaike information criterion and fractional Bayesian approach. Two estimation methods are also compared, the ordinary least squares and the Almon approach. / Na literatura, muitas técnicas são propostas para determinar o tamanho da defasagem de um modelo de regressão dinâmico. Entretanto, nenhuma delas é completamente satisfatória e escolhas erradas implicam em sérios problemas na estimação dos parâmetros. Este trabalho apresenta uma revisão dos principais critérios de seleção de modelos disponíveis na metodologia clássica, assim como aborda uma maneira de determinar o tamanho da defasagem sob a perspectiva Bayesiana. Um estudo de simulação Monte Carlo é conduzido para comparar a performance dos testes de significância, do R2 ajustado, do erro de predição final, dos critérios de informação de Akaike, Schwarz, Hannan-Quinn e Akaike corrigido e da aproximação Bayesiana fracionada. Também serão comparados os métodos de estimação de Mínimos Quadrados Ordinários e de Almon.