Browsing by Subject "korrelaatio"

Asymmetric information in insurance markets is the result of policyholders, the buyers of insurance, having more information about their own risk types and preferences than the insurer. Informational asymmetry between the insurer and policyholders can lead to non-optimal insurance prices and quantities which reduce market efficiency. While the presence of asymmetric information has been widely studied in several insurance markets, it has not been empirically studied in the Finnish automobile insurance market before. This thesis aims to fill this gap in literature. The Finnish automobile insurance market consists of two types of insurance. Motor liability insurance is required by law from all vehicles used for driving in traffic. Also, voluntary automobile insurance can be acquired in addition to the mandatory motor liability insurance. In this thesis, the presence of asymmetric information is studied by comparing the occurrence of motor liability insurance claims, conditioned with the pricing variables used by the insurer, between policyholders who only have a motor liability insurance policy and policyholders with an additional automobile insurance policy. The data set used in this thesis is from a single Finnish insurance company. The data set is from the year 2019 and it contains nearly 105,000 motor liability insurance policies. The data include all variables observed by the insurer. Several regression specifications and the widely used positive correlation test are used in this thesis to study the correlation between insurance coverage and motor liability insurance claims. The results of this thesis suggest that signs of asymmetric information are not present at aggregate level in the Finnish automobile insurance market in question. However, different subgroups of policyholders show signs of asymmetric information: After controlling for the pricing variables, policyholders with an automobile insurance policy with the largest coverage show a positive correlation between buying automobile insurance and motor liability insurance claims whereas policyholders with an automobile insurance policy with the third largest coverage show a negative coverage-claims correlation. However, the results from different regression specifications regarding different automobile insurance coverages were not unanimous and thus the results are left ambiguous. In addition, new policyholders considered as experienced drivers show a negative correlation between motor liability insurance claims and having automobile insurance coverage. On the contrary, policyholders considered as experienced drivers with 1–2 years of company experience do not show signs of asymmetric information. The result suggests that the insurer learns from its repeat customers as signs of informational asymmetry disappear over time. Moreover, policyholders considered as unexperienced drivers do not show signs of asymmetric information regardless of the length of their customership in the firm. The results are in line with previous research.

This study examines the relationship between wealth and environmental contributions at individual and country levels by using survey data from EVS, WVS and ISSP and panel data from OECD. For the analysis I use correlation tests, and in the case of panel data, pooled OLS regression and two-way fixed effects regression, and with survey data I use OLS regression and generalized ordered logit model. The aim of this study is to clarify if wealthier countries or individuals contribute more to environment than countries and individuals with lower wealth. Environmental contributions at country level are measured as environmental policy stringency, environmental protection expenditure and environmentally related tax revenues. At individual level environmental contributions are measured as willingness to pay for environmental protection. At country level a positive relationship between wealth and environmental contributions is found, but in individual level the relationship is weak. Also relationship between national wealth and individual willingness to pay is minor. On average individuals willingness to pay for environmental protection stayed standard regardless of wealth, but some differences in averages can be seen comparing the results of different surveys. Results suggests that in wealthier countries the environmental policy is more strict and environmental protection expenditure can be expect to be higher than in lower GDP per capita level countries. The relationship between wealth and environmentally related tax revenues differs from other two variables, because tax base for environmentally related taxes change whit economic development. Previous literature offers inconclusive findings and comprehensive theoretical framework is difficult to form. One of the biggest challenges of this study is the sparseness of suitable and comparable data and thus, results have to be interpreted with caution.

Glacial meltwater potholes are cylindrical and often remarkably smooth-walled pits in the bedrock, formed as a result of the evorsion caused by eddy currents of water released by the melting of the continental glacier, and possibly also by the cavitation due to the meltwater rushing to a glacial moulin or crevasse. This study examines how the location, topography, orientation according to the direction of ice movement, bedrock and the distance from the fault lines and eskers explain the occurrence and abundance of potholes in the province of Uusimaa in southern Finland. This study also provides a unified database of potholes that have been found in Uusimaa, which have not been compiled to this extent before. The research material with location and characteristic data was collected in July-October 2020 and in May-June 2021. A total of 320 potholes were selected for the research group, of which 206 were determined from fieldwork and 114 from source data. There were a total of 116 sites around Uusimaa, where the number of potholes varied from one to twenty (1–20). Moreover, especially in the archipelago spreading off the southern coast of the study area, there are numerous potholes marked only in sporadic old articles. As some potholes were located in areas that were too difficult to reach or in private yards, for example, the work also required the use of databases and reports published by research institutes and municipalities. The above-mentioned sources were also utilized in the field when searching for potholes and later in slope and distance analyses. In addition, one hundred (100) comparison sites were drawn from somewhat evenly across the study area in order to interpret how the location and characteristic data of pothole sites differ from rock formations where potholes are not known to occur. The location and characteristic data of pothole and comparison sites were compiled into a material. Based on the data, diagrams as well as regression and correlation analyses were made to visualize the results and their interrelationships, and statistical models (generalized linear model, GLM) were used to model several variables simultaneously. The results showed that many physical geography-related factors simultaneously affect the occurrence and abundance of potholes. Since potholes are glaciofluvial landforms, they often occur in north-south or northwest-southeast queues because these directions are equivalent to the direction of ice movement. The proximity of bedrock faults of tectonic origin strongly explains the occurrence of potholes, as the faults, like glacial moulins and crevasses, were favourable locations for meltwater flows. On average, there are more potholes in the sites located on the lee sides (downstream sides) compared with those on the stoss sides or central parts, because there were cavities and cracks as well as more space between the ice and the rock in the rough and plucked lee sides. The thin, non-uniform soil and the abundance of rock outcrops have led to the discovery of many more potholes in the lower southern parts of the study area and especially in the archipelago than in the higher northern parts. A significant proportion of potholes, which were not known to be located near bedrock faults, were located in the archipelago. In contrast, inland potholes typically occurred in steeper and rugged terrain near the fault lines. However, there was a weak negative correlation between the proximity of the eskers and the occurrence of potholes, which is probably due to the fact that the formation of potholes requires faster flows in glacier rivers than the formation of eskers. Most of the potholes in Uusimaa are quite small, up to about 120 centimetres in diameter and depth, but approximately one in eight potholes were more than three (3) meters deep or wide. The steepness of the slope was most strongly associated with the occurrence of large potholes. Potholes formed on rock consisted of granodiorite were, on average, larger than potholes formed on microcline granite, probably due to the granodiorite minerals are more prone to dissolve.

During the past few decades, online shopping has grown steadily and increased its share of all retail sales. As internet connections have become more common and the selection of available online services has diversified, an increasing number of consumers have started to purchase different products online. Buying online has many time-related benefits compared to traditional retail as it enables the consumer to make purchases whenever and wherever. Yet, online grocery retailing has been relatively small-scale in both Finland and abroad compared with other product categories. In the past few years, however, the competition has become more intense as the few dominant Finnish grocery retailers and several smaller businesses have developed their online business models. In this study, I focused on one of Finland's leading grocery retailers, Kesko, and the customers and spatial characteristics of its online grocery services. The aim of this study was to find out 1) whether the accessibility of services affects the choice between an online store and a physical retail outlet in the case of grocery retail, 2) whether the widely accepted socio-economic characteristics of typical online shoppers find evidence in the case of choosing online grocery retail over a physical store or the frequency of online purchases and 3) how Kesko's online grocery retail has spread in the Helsinki region during the couple of years it has been in operation and where its potential new market areas in the region are. The MetropAccess time-cost-matrix for the Helsinki Region was used for the accessibility calculations. Travel times were calculated from all inhabited cells in the area and only from Kesko's online store's customer cells to the closest Kesko grocery store and separately to the closest store when all grocery stores were taken into account in the Helsinki Region. In some previous studies, urban living environment and dense service network have been observed to increase the probability of being an online shopper whereas poor accessibility to services increases the intensity of online shopping. In other studies and national statistics data, a variety of socio-economic attributes have stood out as prominent characteristics of e-shoppers. These include: young age (age groups 25-34 and 35-39), higher education, student status and high income. In addition, I have included the percentage of underage children of a cell's inhabitants in the analyses as Kesko's own data points very clearly in the direction that families with children are an important customer group to online groceries. The socio-economic variables of the region's inhabitants were mostly drawn from HSY's SeutuCD 2015 and Tilastokeskus' Paavo zip code data. I made correlation analyses on the YKR-grid level where the other variables were 1) the percentage of online customer households proportioned to cell's population in the whole region and 2) the intensity of online shopping in customer cells proportioned to population, and the other variables were the socio-economic variables of the population and the travel-time accessibility of grocery stores. The statistically significant Spearman's correlation coefficients were not very high, but weak connections between variables could be found. Customership of the online grocery store correlates negatively with travel time accessibility and the intensity of online shopping correlates positively with accessibility, which is in line with previous findings in the literature. Of the socio-economic variables chosen for this study, the ones that correlate the most with online shopping are income (with shopping intensity) and the percentage of 25-34- year olds (with customership). Finally, I analysed some potential future areas for growth for Kesko's online grocery business in the Helsinki Region based on the previously mentioned socioeconomic variables and accessibility of grocery stores in the study area. One weakness of the study was the availability of detailed enough socio-economic data when compared to Kesko's own YKR grid-level customer data. Some of the socioeconomic variables where derived from larger spatial units such as zip codes, which weakens the reliability of the correlation analyses. However, the grid-level examination is quite coarse for the capital region as well, and especially in this case, when the customer dataset itself was quite small. The accessibility of grocery stores is relatively good in the whole study area, so the study might not bring out the impacts of accessibility of physical services to online shopping as explicitly as might really be the case if the study was carried out in an area or with product categories where physical accessibility varies more. Moreover, the study may not have sufficiently considered the special characteristics of online grocery retailing when compared with other product types. Due to the marginal status of online grocery retailing, it has not yet been studied extensively in research literature. The results, however, do partly support previous findings of the connections between specific socioeconomic variables and the accessibility of services, and the customership of online stores and the intensity of online shopping activities.

Tutkielmassa tutustutaan aikariippuvaisia korrelaatioita mallintavaan DCC-malliin. Aluksi kuvaillaan mallin linkittyminen rahoitusteorian peruspilareihin, minkä jälkeen itse malli. Mallin toimivuutta arvioidaan empiirisessä osiossa käyttäen vertailukohtana otoskorrelaatiota. Mallin toimivuutta tutkitaan neljän alueellisen indeksin viikottaisen tuottodatan avulla. Päätelmät mallien suoriutumisesta tehdään VaR – tunnuslukujen osuvuuden sekä mallien avulla tehtyjen sijoitusten tuottojen perusteella. Lopputulemana on, että DCC-malli toimii kohtalaisen hyvin VaR-tunnuslukujen ennustamisessa ja otoskorrelaatioon verrattuna myös sijoitusallokaatioiden muodostamisessa. Erot testituloksissa korrelaatioennusteiden välillä olivat kuitenkin pieniä ja korrelaatioita määräävämpänä tekijänä on todennäköisesti kovarianssien muodostamisessa käytetty varianssiennuste.

Tutkimuksessa tarkastellaan Metsä Fibren kehittämää laatuindeksiä, jonka tavoitteena on tehostaa sahatavaran teknisen laadun kuvaamista ja raportointia. Tehokkaampi sahatavaran laadun raportointi helpottaa mm. tuotantolaitosten ongelmakohtien tunnistamista, sekä mahdollistaa tuotteiden tehokkaamman ohjaamisen optimaalisiin käyttökohteisiin. Tässä tutkimuksessa keskitytään jälkimmäiseen, eli tuotelaadun kuvaamiseen sahatavaran jatkojalostuksen näkökulmasta; kuinka hyvin sahatavaran laatuominaisuudet ennakoivat sen käytettävyyttä jatkojalostuskohteissa. Laatuindeksissä sahatavaraerälle muodostetaan laatuarvo perustuen sen sisältämien sahatavarakappaleiden mitattuun kosteuteen, paksuuteen ja leveyteen, sekä muotovikaisuuteen ja halkeiluprosenttiin. Kukin teknisen laadun osatekijä saa arvon väliltä 0–100 riippuen siitä, kuinka hyvin mitattu arvo vastaa sille asetettua tavoitetta. Tuotantoerälle muodostetaan lisäksi kaikki laatutekijät yhdistävä kokonaisindeksi laskemalla kaikkien laatutekijöiden pisteet yhteen niille asetetuin painoarvoin. Tutkimuksen tavoitteena oli selvittää pystytäänkö laatuindeksin ja sahatavaran teknisen laadun avulla mallintamaan sahatavaraerän soveltuvuutta sormijatkoslinjalla valmistettavien ikkunakomponenttien valmistusprosessiin. Prosessissa sahatavarakappaleet höylätään ja niistä katkotaan oksat ym. vikakohdat pois, minkä jälkeen vikoja sisältämättömiin kappaleisiin jyrsitään sormiliitokset ja ne liimataan yhteen. Sahatavaran soveltuvuuden mittarina käytettiin komponenttisaantoa, eli sitä osuutta, joka prosessiin syötetyn sahatavaran juoksumetreistä päätyy valmiiksi ikkunakomponentiksi. Tutkimuksessa haluttiin selvittää, onko sahatavaran teknisen laadun ja komponenttisaannon välillä havaittavissa selvää yhteyttä, ja minkä suuruinen on kunkin teknisen laadun tekijän erillisvaikutus komponenttisaantoon. Yhteyttä tarkasteltiin korrelaatiokertoimen ja regressioanalyysin avulla. Aineistoon valittiin 27 ajoerää, sekä näitä vastaavat komponenttisaantoprosentit ja sahatavaraerien teknisen laadun keskiarvot, sekä niiden perusteella muodostetut laatuindeksiarvot. Kokonaislaatuindeksin ja komponenttisaannon välillä havaittiin kohtalaisen voimakasta lineaarista korrelaatiota. Yksittäisten laatutekijöiden indeksiarvojen ja komponenttisaannon välillä ei havaittu tilastollisesti merkitsevää yhteyttä. Sahatavaraerän absoluuttisen paksuuden – eli sen sisältämien sahatavarakappaleiden mitattujen paksuuksien keskiarvon – ja komponenttisaannon välillä havaittiin tilastollisesti erittäin merkitsevää epälineaarista korrelaatiota. Paksuus oli myös ainoa laatutekijä, joka valikoitui lopulliseen regressiomalliin. Tutkimustulosten perusteella laatuindeksi ei ole sellaisenaan hyvä työkalu komponenttisaannon mallintamiseen. Komponenttisaantoa kuitenkin pystytään ennakoimaan luotettavasti sahatavaran teknisen laadun – erityisesti paksuuden – avulla. Säätämällä indeksin laskentasääntöjä ja raja-arvoja tämän tutkimuksen tulosten perusteella, voitaisiin myös laatuindeksistä saada hyvä työkalu asiakaslähtöiseen tuotelaadun kuvaamiseen.