This thesis provides a comprehensive ranking of 11 Czech statistical and 4 foreign credit scoring models. The ranking is based on the predictive performance of individual models, as measured by the area under curve, evaluated on a randomly sampled set of 250 training and validation samples. After establishing a baseline comparison, 3 avenues of estimation setup optimization are explored, namely missing value treatment, estimation method and the use of additional non-financial variables. After being optimized, the models are once again ranked based on their predictive performance. Statistical inference is drawn using ANOVA and the Friedman test, along with the corresponding Tukey and Nemeyi pos-hoc tests. In their baseline form, the Czech credit scoring models are found to be outperformed by the foreign benchmark model. Treating the missing values by OLS imputation and estimating the models by probit, significantly is found to significantly improve their predictive performance. In their optimized form, the difference in predictive performance between Czech and foreign credit scoring model is found to be only marginal. JEL Classification G28, G32, G33, G38 Keywords credit scoring, multiple discriminant analysis, logit analysis, probit analysis Author's e-mail 71247263@fsv.cuni.cz Supervisor's e-mail...

För att beslutsfattare och dagligvaruaktörer ska kunna fatta välgrundade beslut vid etablering av nya butiker är det viktigt att känna till hur demografiska faktorer påverkar dagligvarumarknaden. I denna uppsats analyserar vi med data för 2016 hur demografiska faktorer påverkar förekomsten av olika butikssegment på lokala marknader i Sverige samt hur demografi påverkar butikssegmentens omsättningsandelar. Segmenten skapades inom ramen för uppsatsen baserat på tidigare forskning och dagligvaruaktörernas egna butiksdefinitioner. Med logistiska regressioner på stadsdelsnivå finner vi (i) att en ökande andel befolkning med utrikes bakgrund påverkar sannolikheten positivt att minst en lågprisbutik finns etablerad i ett område, men påverkar sannolikheten att minst en traditionell mindre butik finns etablerad negativt. Vidare, med hjälp av OLS-regressioner på stadsdelsnivå finner vi (ii) att en högre andel befolkning med utrikes bakgrund påverkar lågprisbutikers andel av ett områdes totala omsättning positivt, men påverkar traditionella mindre butikers andel negativt. Till sist, indikerar resultatet (iii) att framförallt flödet av människor påverkar traditionella större butiker, både dess geografiska plats samt deras andel av ett områdes totala omsättning. På kommunnivå visar OLS-regressionerna delvis otydliga resultat, förmodligen till följd av allt för aggregerad data. Vår studie bidrar till den existerande litteraturen genom att analysera butiksetableringar och demografi i en svensk kontext. Tidigare forskning har främst undersökt den amerikanska och olika europeiska marknader. / It is important for policy makers and retail chains to recognise how demographics affect the non- durable goods business in order to make qualified decisions about establishing new grocery stores. In this thesis, using data from 2016, we analyse how demographics affect the presence of different store segments at local markets in Sweden and how it affects the turnover share of different store segments. The segments were defined as a part of this thesis and are based on previous literature and the concept description made by each included company. Using logit regressions on urban districts, we find (i) that a larger share of population with foreign background increases the probability that at least one discount store is established in the district but decreases the probability that at least one traditional small store is established. Further, using an OLS-regression on urban districts we find (ii) that a larger share of population with foreign background increases the share of total turnover in discount stores and decreases the share of total turnover for traditional small stores. Finally, our result indicates (iii) that the flow of people significantly affects traditional large stores, both regarding their presence on local markets as well as their share of the total turnover. When using municipalities as local markets, our OLS-regression provides partly indefinite results, probably a consequence of the aggregated data. Our thesis contributes to the existent literature by analysing store establishment and demography in a Swedish context. Previous literature has mainly evaluated American and European markets.

Ma thèse se compose de deux parties indépendantes. La première traite decrypto-économie et la seconde d’économétrie théorique. Dans le premier chapitre, je présente un modèle qui prédit la puissance de calcul totale déployée par les mineurs en utilisant le taux de change bitcoin / dollar. Le deuxième chapitre s’appuie sur une version simplifiée du précédent modèle pour faire le constat de l’inefficacité du protocole Bitcoin actuel et proposer un moyen simple de réduire la consommation d’électricité engendrée par cette cryptomonnaie. Le troisième chapitre explique comment identifier et estimer les bornes exactes de la région d’identification de l’effet marginal moyen dans un modèle logit avec effets fixes sur données de panel. / My dissertation concatenates two independent parts. The first one dealswith crypto-economics whereas the second one is about theoretical econometrics. In the first chapter, I present a model which predicts bitcoin miners’ total computing power using the bitcoin / dollar exchange rate. The second chapter builds on a simplified version of the preceeding model to show to which extent the current Bitcoin protocol is inefficient and suggest a simple solution to lower the cryptocurrency’s electricity consumption. The third chapter explains how to identify and estimate the sharp bounds of the average marginal effect’s identification region in a fixed effects logit model with panel data.

The global decline of pollinators, insects and animals that assist in pollination and fertilizing plants, poses a great risk to global food supply. This study investigates if people have preferences for a program to abate decline in a region along the East Coast of the United States. A survey is used to investigate these preferences and connections to the region to understand if individual connections can explain preferences. The majority of people were found to not have preferences to help increase pollinator abundance. Additionally, measures of connection to the region were found to be insignificant in explain individual preferences. / Master of Science

個體選擇模式(discrete choice model)廣泛應用於國外的交通運輸及行銷領域，而國內交通運輸領域，也長期以此模式分析個體的運具選擇行為。反觀國內的行銷領域，因較難取得消費者的商品品牌購買紀錄，而鮮少應用個體選擇模式分析消費者的選擇行為。有鑒於此，本研究嘗試以問卷收集消費者對三個洗髮精品牌的選擇行為，以個體選擇模式中的多項邏輯模式(multinomial logit model)、巢狀邏輯模式(nested multinomial logit model)、混合多項邏輯模式(mixed logit model)進行分析，檢驗問卷設計中的促銷活動、消費者特性對選擇行為的影響性。 實證分析的結果發現，洗髮精的原價格及促銷折扣、贈品容量、加量不加價等促銷活動，皆對消費者的選擇行為有顯著的影響力，其中促銷折扣與贈品容量影響的程度較大，是較具有效果的促銷活動。而消費者的性別、年齡、職業及品牌更換的頻率，皆影響洗髮精的選擇行為。此外，消費者若固定選擇自己最常購買的洗髮精，此類型的消費者與其他人的品牌選擇行為，也有顯著的不同。 此外，根據本研究樣本，我們也發現海倫仙度絲與潘婷間的替代、互補性較強。 / Discrete choice model has been demonstrated to be a useful tool for analyzing consumers’ choice behavior data in the area of transportation and marketing research. However, since a complete data set containing consumers’ history of purchase behavior was rarely available to public, the model was less popular in the marketing research area than in the transportation research in Taiwan. Based on limited survey data on consumers’ choice among three different brands of shampoo, we applied multinomial logit model、nested multinomial logit model、mixed logit model in this study to understand promotion program’s effect on consumers’ choice behavior , the result showed that shampoos’ original price、discount、volume of hair conditioner bestowal、more volume with the same price all had significant impacts on consumers’ choice behavior, among them, discount and volume of hair conditioner bestowel influenced more .In addition, consumers’ gender、age、occupation and frequency of changing brands also affected consumers on choosing brands of shampoos. The study also found that a consumer who chose the same brand regularly behaved notably differently.

The dissertation consists of four essays that treat different aspects or the evaluation of public policy. Two essays are applications of the travel cost method. In the first of these, recreational travel to the Swedish coast is studied to obtain estimates of the social benefits from reduced eutrophication of the sea. The second travel cost essay attempts at estimating how the probability that a woman will undergo mammographic screening for breast cancer is affected by the distance she has to travel to undergo such an examination. Using these estimated probabilities, the woman's valuation of the examination is obtained. The two other essays deal with automobile taxation. One essay analyzes how taxation and the Swedish eco-labeling system of automobiles have affected the sale of different car models. The last essay treats the effects of taxes and of scrappage premiums on the life length of cars. / Diss. Stockholm : Handelshögskolan, 1999

The very specific features of the spot prices, especially occurrence of severe jumps, create a spot price risk for retailers who purchase electricity at unregulated highly volatile prices but resell it to consumers at fixed price. Therefore, it is of high im- portance to forecast whether jump is likely to occur during the next hour. However, to the best of our knowledge, such research has not been devoted to the Czech power market yet. Therefore, the aim of this thesis is to forecast the jump occurrence in the Czech day-ahead market. For this purpose we suggest four logit model spec- ifications, each containing various independent variables (for example, electricity demand, outside temperature, lagged price and various dummy variables) where the variable selection is supported by the previous literature and by the characteristic features of the spot prices. Within the in-sample period we compare the suggested models based on the values of pseudo-R squared and Bayesian information criterion. When evaluating the out-of sample performance of suggested models we apply jump prediction accuracy and confidence, but opposed to the previous literature we sug- gest a kind of sensitivity analysis which, to the best of our knowledge, has not be proposed by any other power research. JEL Classification C25, C32, C51,...

La première partie de cette thèse a consisté à proposer des modèles d'insertion de trafic sur une bretelle d'entrée d'autoroute. Deux types de modélisation ont été élaborés. Une approche statistique utilisant les techniques de régression logistique nous a permis de sélectionner les variables jouant un rôle dans le choix par les véhicules provenant de la voie d'accélération du lieu où ils s'insèrent. Dans un second temps, nous effectuons une modélisation comportementale basée sur le principe d'acceptation de créneaux. Les modèles proposés ont été validés à l'aide de données issues d'un site d'observations expérimentales situé près d'Angers, le site SAROT. La seconde partie est consacrée au développement d'une méthode particulaire probabiliste permettant de simuler un modèle mésoscopique de trafic : le modèle cinétique de Paveri-Fontana. La complexité algorithmique de cette méthode proposée comme alternative aux méthodes déterministes couramment utilisées est optimisée. La comparaison des résultats obtenus à ceux d'une méthode déterministe plus standard de différences finies sur des cas-tests bien choisis a permis de valider la méthode particulaire. Ces expériences numériques ont mis en valeur ses qualités notamment sa rapidité (coût numérique) par rapport à la méthode déterministe ainsi que sa capacité à mieux reproduire certains phénomènes observés dans le trafic / The first part of this thesis is dedicated to the optimization of the lengths of acceleration lanes using microscopic data collected from real traffic. The insertions on the highway junctions can indeed be especially dangerous considering the difference between the speeds on the on ramp merge lane and those on the highway lanes. We develop and analyse some microscopic merging models. We first propose a statistical model based on the logistic regression techniques. Statistical hypothesis tests allow to select the most significant descriptive variables in the merging decision process. A behavioural modelling taking those variables into account is next proposed to better capture the interactions by including some thresholds on the gaps between the merging vehicles and freeway vehicles. The models are validated using real traffic data collected at the SAROT site near Angers. Secondly, traffic simulation at the mesoscopic scale is mostly based on deterministic numerical schemes. However, these methods have a high computational cost. The objective of the second part of this thesis is to present a new method to simulate the Paveri-Fontana kinetic model through a probabilistic approach. We interpret the evolution equation in this model as a Fokker-Planck equation and deduce an approximation based on a system of interacting particles. The algorithmic complexity of this method is optimized. We have performed a numerical comparison between the probabilistic method and a deterministic method on some cases study. The qualitative analysis highlights the benefits of the particle method such as its computation cost and its ability to reproduce some typical traffic effects

Neste trabalho foram revisados os principais modelos, para a avaliação do risco de crédito e para o provisionamento de perdas com clientes, concluindo-se com uma proposta de adoção de um modelo estatístico, com o objetivo de medir o risco associado ao financiamento e empréstimo a clientes, com o conseqüente impacto na mensuração dos ativos. Sem o objetivo de exaurir o assunto, foram adotados os passos relacionados a seguir para o desenvolvimento do tema até a proposição final. Na introdução, são feitas as justificativas sobre o tema, qual a questão problema associada ao tema e os desafios da contabilidade quanto à mensuração dos ativos. Em relação à gestão de riscos, são relacionados os tipos de riscos em geral, detalhado o risco de crédito em particular e avaliados os modelos de concessão de crédito. Sobre a constituição da Provisão para Devedores Duvidosos, foram pesquisados os principais autores de contabilidade e de finanças, onde se constatou proposições semelhantes, que podem ser resumidas em 4 modelos de provisionamento para Perdas com Devedores Duvidosos: 1. Baixa – "Write-off"; 2. Percentual sobre as vendas; 3. Percentual sobre o montante de contas a receber; 4. Idade da carteira – "aging". Em seguida são analisadas as correlações entre os modelos de previsão de insolvência e as perdas com crédito, onde é possível identificar que os modelos de insolvência são úteis para a concessão do crédito, mas pouco utilizados para a estimativa da perda provável com devedores duvidosos. Em 21 de dezembro de 1999, o Banco Central do Brasil, emitiu a Resolução 2.682, na qual recomenda às instituições financeiras que alterem suas metodologias de provisionamento para perdas com devedores duvidosos. O Banco Central, entretanto, não indica qual modelo utilizar, deixando a cargo de cada instituição o desenvolvimento dos modelos. Utilizando a norma do Banco Central como referência, e procurando um embasamento científico para a constituição da PDD, é proposto um modelo para a sua constituição, modelo esse testado e avaliado, tanto em conformidade às normas do Banco Central, como com orientação gerencial. Para tanto, foi desenvolvido um modelo estatístico, aplicando-se a técnica da regressão logística, a 202 clientes de uma instituição financeira, onde foi possível concluir-se que o uso do modelo, na constituição da Provisão para Devedores Duvidosos, poderá trazer benefícios na mensuração do real valor dos investimentos em contas a receber. / This project aims at evaluating the used models and proposing the adoption of new models, for the Allowance for Doubtful Accounts, with the objective of measuring the risk related to customers financing and loan activities, and the resulting impact in assets measurements. In order to achieve this goal and try not to over exploit the subject, the following steps related to the development of the theme were adopted. In the introduction the theme is explained; the main issue associated to the theme and the challenges the accounting has to face concerning the assets measurements. As for the risk management the general kinds of risks are described, particularly the credit risk and the credit concession models are evaluated. Referring to the Allowance for Doubtful Accounts constitution, most meaningful authors in the field of Accounting and Finance were researched and similar propositions underlined their writings; that can be summarized in 4 allowance models for Doubtful Accounts. 1. Write off; 2. Percentage over the sales; 3. Percentage over receivables; 4. Aging. Then the correlations between the models of insolvency prediction and the credit losses are analyzed where it is possible to verify that the insolvency models are useful for credit concession, though not very much used for estimating probable loss with Doubtful Accounts. The Central Bank of Brazil (Banco Central do Brasil) issued the act number 2682 on the 21st of December, 1999, that urges all financial institutions to change their methodologies of Allowance for Doubtful Accounts. The Central Bank, however, does not indicate the model to be used, leaving the task of developing the models to each institution. Based on the policy of Central Bank and keeping a scientific approach to the constitution of Allowance for Doubtful Accounts, a model for their constitution in the portfolio is proposed. Such model is tested and evaluated not only, according to the rules of Central Bank of Brazil, but also in terms of management orientation. Having this purpose in mind a statistic model was developed, using LOGIT Regression applied to 202 customers of a financial institution where it was possible to come to the conclusion that the use of the model in the constitution of the Allowance for Doubtful Accounts can bring benefits in measuring the real value of investments in Receivables.

Apresenta-se um procedimento para estimativa da matriz origem-destino (O/D) a partir de um modelo de escolha discreta em combinação com uma matriz O/D de transporte público, a qual pode ser estimada de maneira relativamente fácil e rápida. O modelo de escolha discreta utilizado para realizar a divisão modal é o modelo logit multinomial. A calibração do modelo logit é realizada com base em 505 observações e considerando três situações: a população de viajantes sem segmentação, com segmentação segundo posse de automóvel no domicílio, e com segmentação segundo a distância de viagem. Analisa-se a precisão da estimativa do número de viagens quando as zonas de controle que formam a área de estudo são divididas segundo o critério de distância de acesso às linhas de ônibus. Na verificação realizada são empregados dados obtidos da pesquisa domiciliar realizada na cidade de Bauru, SP. Os erros cometidos na estimativa são medidos e comparados com os resultados obtidos na pesquisa domiciliar sem expansão. O trabalho demostrou experimentalmente que o procedimento proposto é uma alternativa viável para se obter a distribuição de viagens e, portanto, para determinar a matriz O/D. / A procedure is presented for estimating an origin-destination (O/D) matrix using a discrete choice model jointly with a public transport O/D matrix; the latter being relatively easy and fast to obtain. A multinomial logit discrete choice model is used to determine the mode split of travelers among several available modes. The model is estimated using a sample of 505 observations chosen from a household 0/D survey in the city of Bauru, state of Sao Paulo. This survey is used throughout to verify the results of the proposed methodology. Three different models are considered: one without segmentation of the population, one with segmentation according to car ownership and one with segmentation according to travel distance. An examination is made of the changes on the level of precision of the number of trips estimated with the division of the control zones that conform the study area; the aforementioned division was carried out on the basis of an access distance to the bus network criterion. The estimation errors are measured and compared to the unexpanded O/D survey results. The research shows empirically that the proposed procedure can be used to obtain the distribution of trips and hence to determine an aggregate O/D matrix.