1,720,962 research outputs found
Insurance company's sales analysis of motor products during a global pandemic.
No full textThe aim of this work is to determine what factors effect the weekly sales of insurance company's MOD and MTPL policies. The weekly data collected from March 2020 till April 2021, was taken from the company's database, Lithuania's Statistics Department, and other online databases. The main goal is to determine which of indicators have a significant impact on the company's weekly sales and is there an impact of the global pandemic. The following methods are used for data analysis: moving average model, linear regression model, autocorrelation test, cointegration test, Shapiro-Wolf test, Bresco-Pagan test, and Durbin-Watson test. The models obtained after the analysis explain only a part of the data variation. 4 models were developed and it was found that each model explains the sales volume through different explanatory variables, and it was also concluded that the effect of quarantine on sales did not have a strong effect
Estimating housing price imbalances in lithuania.
No full textThis bachelor thesis analyses housing price imbalances in Lithuania by estimating fundamental housing prices and identifying housing demand and supply shifters and their effect on price changes. Housing price misalignments are estimated using different statistical and econometric methods. Price to rent and price to income ratios are calculated and compared to their long-term averages and model-based trends. Nominal and real house price departures from long-term tendencies are measured as deviations from Hodrick-Prescott filtered trend. Disequilibrium model for housing is estimated and used to identify supply and demand shifters and their effect on housing price changes. This model is also employed in estimating fundamental house prices and house price deviations from these fundamentals. All of the above-mentioned methods indicate housing price overvaluation at the time of real estate market boom in 2006-2008, but show differing results during recent years. Price to rent and price to income ratios indicate housing price undervaluation as gaps from their long-term averages in year 2020 were negative. Housing price deviations from Hodrick-Prescott filtered trend and disequilibrium model based fundamental values were positive and, therefore, indicate price overvaluation. Based on the disequilibrium model results, main factors contributing to house price growth during the boom years were high flow of housing credit, high interest rates on business loans, growth of monthly net wages and positive expectations. The effect of these factors on house price growth in recent years was still positive, although much smaller. Other factors, such as rising construction input prices, urbanization and remittances also had an influence on recent housing price growth
Body mass index analysis using panel data of european countries.
No full textMean Body Mass Index (BMI) of European countries is analysed in this work. Annual panel data from twenty-nine European countries for 2010-2019 was used. The data was collected from "Euromonitor International" Passport database. The main goal of this work is to identify the main factors that affect the average BMI in countries. Methods applied for data analysis: pooled model, fixed effect model, random effect model, Shapiro–Wilk test, Hausman test, Breusch–Pagan test, Durbin-Watson test and cluster analysis. This work has shown that models that were made for clusters evaluated average body mass index in countries better than the model that was made when all European countries were pooled together. Analysis has shown that average body mass index in countries depends on the proportion of the population using the Internet, prevalence of insufficient physical activity, soft drinks consumption per capita and disposable income per capita. An increase in the aforementioned indicators results in an increase in the average body mass index. Average BMI is decreasing while the proportion of women population and percentage of urbanization is increasing
Estimating the productivity of the 2016-2020 lithuanian republic seimas members.
No full textLithuanian Republic Seimas is a democratically elected legislative institution. The work of this institution influences the life of the population of the Lithuania and the economy of the state, therefore it is important that the elected representatives of the nation represent their voters productively. In this bachelor thesis different (economic and statistical) methods are used to evaluate the productivity of each member of the 2016-2020 Lithuanian Republic Seimas, compared to other Seimas members. The formula for calculating people's labor productivity was used for economic calculation, and logistic regression was applied for statistical calculation and probability of being productive was estimated. Comparing the mentioned methods, it was noticed that they evaluate the productivity of the members of the Seimas differently
Jungčių taikymas paskolų modeliavime.
No full textApplications of Copulas in Loan Modelling. Copula applications for discrete data with autocorrelation are not widely studied. In this thesis, a bivariate integer-valued autoregressive process of order 1 (BINAR(1)) with copula-joint innovations is analysed. Model properties and their proofs are provided. Different estimation methods are analysed and comparisons are carried out via Monte Carlo simulations with emphasis on estimation of the copula dependence parameter. An empirical application on defaulted and non-defaulted loan daily data is carried out using different combinations of copula functions and marginal distribution functions covering the cases when both marginal distributions are from the same family and when they are from different distribution families
Daugiamačiai jungtimis grįstų sveikareikšmių laiko eilučių modeliai: teorija ir taikymai.
No full textInteger-valued time series comprising count observations at regular time intervals can be observed in various applications, such as the amount of crimes committed in a city per hour, the amount of insurance claims in a firm per year, the number of defaulted loans issued by a bank per week, the number of infected people per day, etc. Different time series can also be dependent on one another. This dependence can be described via a copula. In this thesis, a class of bivariate integer-valued autoregressive processes of order 1 (BINAR(1)) with copula-joint innovations are analysed. Model properties are derived and different parameter estimation methods are analysed. Estimation methods are compared via Monte Carlo simulation and an empirical application on loan default data is carried out. Integer-valued time series can also exhibit seasonal fluctuations. A univariate integer-valued autoregressive process for seasonality with period d (SINAR(1)_d) is introduced in this thesis, which allows for intra-seasonal dependence of the innovations to be described by a copula. Such a univariate process can also be written as a multivariate specification. Model properties are derived. Parameter estimation methods are analysed and compared via Monte Carlo simulation. An empirical application on Chicago crime data is carried out
Multivariate copula‐based integer‐valued time series models: theory and applications.
No full textInteger-valued time series comprising count observations at regular time intervals can be observed in various applications, such as the amount of crimes committed in a city per hour, the amount of insurance claims in a firm per year, the number of defaulted loans issued by a bank per week, the number of infected people per day, etc. Different time series can also be dependent on one another. This dependence can be described via a copula. In this thesis, a class of bivariate integer-valued autoregressive processes of order 1 (BINAR(1)) with copula-joint innovations are analysed. Model properties are derived and different parameter estimation methods are analysed. Estimation methods are compared via Monte Carlo simulation and an empirical application on loan default data is carried out. Integer-valued time series can also exhibit seasonal fluctuations. A univariate integer-valued autoregressive process for seasonality with period d (SINAR(1)_d) is introduced in this thesis, which allows for intra-seasonal dependence of the innovations to be described by a copula. Such a univariate process can also be written as a multivariate specification. Model properties are derived. Parameter estimation methods are analysed and compared via Monte Carlo simulation. An empirical application on Chicago crime data is carried out
A copula-based bivariate integer-valued autoregressive process with application /
No full textA bivariate integer-valued autoregressive process of order 1 (BINAR(I)) with copula-joint innovations is studied. Different parameter estimation methods are analyzed and compared via Monte Carlo simulations with emphasis on estimation of the copula dependence parameter. An empirical application on defaulted and non-defaulted loan data is carried out using different combinations of copula functions and marginal distribution functions covering the cases where both marginal distributions are from the same family, as well as the case where they are from different distribution families
Valstybės garantijos teikiant smulkiojo ir vidutinio verslo paskolas
No full textĮžanga -- 1. Valstybės garantijų teikimo tikslai ir taikymo geroji praktika -- 2. Garantijų programų priemonių taikymas Lietuvoje -- 3. Kiekybinis garantijų taikymo Lietuvoje vertinimas: 3.1. Duomenų šaltiniai; 3.2. Įžvalgos remiantis duomenimis; 3.3. Ekonometrinis modeliavimas; 3.4. Panašių įmonių palyginimas -- Išvados -- Literatūra -- Priedas.2021 m. Lietuvos bankas ir Konkurencijos taryba paskelbė tyrimą, kuriame įvertintos smulkiojo ir vidutinio verslo (SVV) įmonių prieigos prie finansavimo šaltinių Lietuvoje 2018–2019 m. galimybės ir jas ribojantys veiksniai. Tyrimo rezultatai parodė, kad SVV finansavimo galimybes Lietuvoje gali riboti įvairūs ilgalaikiai trikdžiai, tarp jų – tinkamo įmonių užstato trūkumas ir didesnė kai kurių įmonių grupių rizika, į kurią ne visada efektyviai atsižvelgiama valstybės pagalbos priemonėmis. Siekdamos gauti pakankamą finansavimą, SVV įmonės susiduria su užstato reikalavimu, kuris dažnai joms yra sunkiau įgyvendinamas dėl per mažo turimo tinkamo turto. Viena iš priemonių, leidžiančių spręsti nepakankamo SVV užstato problemą, yra paskolų garantijos. Šia priemone garantuotojas prisiima dalį kredito rizikos, o tai leidžia sumažinti kredito įstaigos prisiimamą riziką ir įgalinti SVV įmones gauti pakankamą finansavimą. Tačiau ankstesniame Lietuvos banko ir Konkurencijos tarybos tyrime, kuriame nagrinėta SVV įmonių prieiga prie finansavimo šaltinių 2018–2019 m. laikotarpiu, taikyto ekonometrinio modeliavimo rezultatai neparodė reikšmingo valstybės garantijų poveikio kredito davėjų prašomo užstato dydžiui. Šiuo tyrimu siekiama išsamiau apžvelgti tarptautinę valstybės garantijų taikymo praktiką (1 skyrius) ir Lietuvos patirtį (2 skyrius), įvertinti garantijų priemonių efektyvumą Lietuvoje, atsižvelgiant į tai, kokių grupių įmonės gavo garantiją, į garantijų poveikį paskolų teikimo sąlygoms (3 skyrius). Atsižvelgus į rezultatus, pasiūlomos kryptys, kaip būtų galima prisidėti prie šių priemonių tobulinimo (4 skyrius)
- …
