|
|
Modeling insurance claims of vehicles with extended warranty
Škorňa, Šimon ; Zouhar, Jan (advisor) ; Frýd, Lukáš (referee)
The aim of this bachelor thesis is to introduce reader to possibilities of empirical analysis of insurance claims. Benefit of this thesis is description of effects that certain variables have on occurrence of insurance claims, while using wide range of suitable modelling techniques. Before the techniques are presented, reader is briefly introduced to issues of car insurance company. Insurance claims are modelled by most common techniques such as models with binary response variable and count models as well as survival analysis, which uses variable capturing number of days until claim occur. Results of above mentioned models are discussed and subsequently compared, which allows to demonstrate robustness of these results.
|
|
|
The supplementary pension savings scheme in the Czech Republic: Microeconomic evidence of the 2013 policy change
Rückl, Adam ; Janský, Petr (advisor) ; Soudek, Jan (referee)
The thesis investigates determinants of participation in the supplementary pension savings scheme in the Czech Republic and estimates their change with respect to the policy intervention realized in 2013. Using the time series of cross-sectional microeconomic data provided by the Statistics on Income and Living Conditions, the probability of participation and the level of contributions are estimated separately by probit and multiple linear regressions, respectively. The estimated coefficients of both models are tested for structural differences caused by the policy change, employing the pooled dataset of multiple years with additional coefficients to treat the compared period. The analysis confirms that income, age, education and economic activity have a positive effect on both the probability of participation and expected level of contributions. Whereas gender differences for the level of contributions have not been detected, single women on average show, ceteris paribus, 4.6 percentage points higher probability of participation than single men. Unexpectedly high level of activity was observed in case of retired individuals, who in 2014 represented approximately 15% of all participants and collected 20% of the credited direct state subsidy. With respect to the 2013 policy change, no evidence of a...
|
|
|
Geomarketing methods
Voráč, Michal ; Chrobok, Viktor (advisor) ; Černý, Michal (referee)
Aim of this application-oriented master's thesis is to prove a benefits from using data analysis techniques connected with geodata processing to support business decisions. As a conclusion two solutions are given which are more attractive then starting situation. Since the first solution proposed is oriented on giving maximum success ratio while considering transactions, the second one is oriented on business value of each transaction. In this thesis R programming language is widely used together with ArcGIS Online in its final part.
|
|
|
Commuting patterns of Czech households exposed to flood risk
Vikhrov, Dmytro ; Stojanov, Robert ; Duží, Barbora ; Jakubínský, Jiří
Using unique data collected in October – December 2012 we estimate the link between commuting to work and the level of household exposure to fl oods. Th e result suggests an empirical puzzle – individuals aff ected by only one fl ood are roughly 10% more likely to engage in commuting, whereas those aff ected by two fl oods are 13% less likely to do so. We explain the result by the fact that individuals commute to work to accumulate resources in order to decrease the household’s vulnerability to fl ood risk, amongst other reasons. When the fl ood risk is high, some households out – migrate, and stayers commute less, probably for similar reasons as why they stay. Further, we fi nd evidence in support of the “network eff ect” hypothesis – an individual with an active commuter in the household is 47% more likely to commence commuting.
|
|
|
Evaluation of the Impact of Wind Turbines on a Landscape
Urbášková, Martina ; Melichar, Jan (advisor) ; Kaprová, Kateřina (referee)
The goal of the work is to provide monetary valuation of changes in visual aspects of the landscape as a result of construction of an additional wind turbine in the village Maletín. For a suitable method for achieving the goal is being selected the contingent valuation method. A key element of this method is being considered the carefully compiled questionnaire, on which basis is made the quantification and evaluation of collected data. The representative sample consists of 112 households and the selected payment method is the increase of the monthly bill for electricity. The questionnaire reports that 54.3% of households consider the impact of wind turbines on the landscape Maletín to be positive. With the construction of additional wind turbine agree less than 74.3% of households and the most common reason is to obtain grants for the village and to produce cleaner energy from wind turbines. With the construction of new wind turbine while increasing monthly bill agrees 28.6% of all households living in the village Maletín. Estimation of changes in a welfare, thus improving the quality of the environment, is based on estimated central values, that has been calculated from selected characteristics and nonparametric estimation. The average household's willingness to pay for construction of wind turbine is estimated to be between 77 CZK - 200 CZK per month.
|
|
|
The influence of the taxation on donating to non-profit organizations
Špetla, Ondřej ; Slintáková, Barbora (advisor) ; Klazar, Stanislav (referee)
The thesis examines the influence of the tax deduction by reason of granting the donation on the taxpayers' behavior. The examination is working with Household Expenditure Survey (2004, 2005) of Czech Statistical Office and with author's own questionnaire survey (2007). In the first part the regression of demographical and economic characteristics on the amount of donation and its probability is run. There are the internal opinions of informant according to the filled questionnaire described in the second part. The regression was processed using Logit, Probit and Tobit models; the following section consists of frequency analysis.
|
|
|
Discrete binary choice models
Lejnarová, Šárka ; Hušek, Roman (advisor) ; Pánková, Václava (referee)
Ve své diplomové práci se zabývám modely diskrétní binární volby. Zkoumám je nejprve z teoretického hlediska, jaká je jejich podstata, jaká jsou jejich specifika a problémy. Postupně rozebírám jednotlivé modely diskrétní binární volby a to lineární pravděpodobnostní model, logitový model a probitový model. Zabývám se jejich odhadem, testováním významnosti jednotlivých koeficientů a shodou modelů s daty. V praktické části se zaměřuji na problematiku životního prostředí a třídění odpadu. Aplikuji jednotlivé modely na získaná data a snažím se vysvětlit, na čem závisí volba jedince mezi ?třídím odpad? a nebo ?netřídím odpad?. Na základě analýzy poté doporučuji, na koho a jakým způsobem zacílit osvětu.
|
guest ::
