Modelling the disability severity score in motor insurance claims: an application to the Spanish case

Bodily injury claims have the greatest impact on the claim costs of motor insurance companies. The disability severity of motor claims is assessed in numerous European countries by means of score systems. In this paper a zero inflated generalized Poisson regression model is implemented to estimate the disability severity score of victims in-volved in motor accidents on Spanish roads. We show that the injury severity estimates may be automatically converted into financial terms by insurers at any point of the claim handling process. As such, the methodology described may be used by motor insurers operating in the Spanish market to monitor the size of bodily injury claims. By using insurance data, various applications are presented in which the score estimate of disability severity is of value to insurers, either for computing the claim compensation or for claim reserve purposes.

Estudo do coeficiente de partição octanol-água de bifenilas policloradas (PCBs) utilizando parâmetros topológicos

A model based on chemical structure was developed for the accurate prediction of octanol/water partition coefficient (K OW) of polychlorinated biphenyls (PCBs), which are molecules of environmental interest. Partial least squares (PLS) was used to build the regression model. Topological indices were used as molecular descriptors. Variable selection was performed by Hierarchical Cluster Analysis (HCA). In the modeling process, the experimental K OW measured for 30 PCBs by thin-layer chromatography - retention time (TLC-RT) has been used. The developed model (Q² = 0,990 and r² = 0,994) was used to estimate the log K OW values for the 179 PCB congeners whose K OW data have not yet been measured by TLC-RT method. The results showed that topological indices can be very useful to predict the K OW.

Tilastollinen tutkimus ohjelmiston laatuun vaikuttavista tekijöistä

Tämä työ on tehty osana MASTO-tutkimushanketta, jonka tarkoituksena on kehittää ohjelmistotestauksen adaptiivinen referenssimalli. Työ toteutettiin tilastollisena tutkimuksena käyttäen survey-menetelmää. Tutkimuksessa haastateltiin 31 organisaatioyksikköä eri puolelta suomea, jotka tekevät keskikriittisiä sovelluksia. Tutkimuksen hypoteeseina oli laadun riippuvuus ohjelmistokehitysmenetelmästä, asiakkaan osallistumisesta, standardin toteutumisesta, asiakassuhteesta, liiketoimintasuuntautuneisuudesta, kriittisyydestä, luottamuksesta ja testauksen tasosta. Hypoteeseista etsittiin korrelaatiota laadun kanssa tekemällä korrelaatio ja regressioanalyysi. Lisäksi tutkimuksessa kartoitettiin minkälaisia ohjelmistokehitykseen liittyviä käytäntöjä, menetelmiä ja työkaluja organisaatioyksiköissä käytettiin, ongelmia ja parannusehdotuksia liittyen ohjelmistotestaukseen, merkittävimpiä tapoja asiakkaan vaikuttamiseksi ohjelmiston laatuun sekä suurimpia hyötyjä ja haittoja ohjelmistokehityksen tai testauksen ulkoistamisessa. Tutkimuksessa havaittiin, että laatu korreloi positiivisesti ja tilastollisesti merkitsevästi testauksen tason, standardin toteutumisen, asiakasosallistumisen suunnitteluvaiheessa sekä asiakasosallistumisen ohjaukseen kanssa, luottamuksen ja yhden asiakassuhteeseen liittyvän osakysymyksen kanssa. Regressioanalyysin perusteella muodostettiin regressioyhtälö, jossa laadun todettiin positiivisesti riippuvan standardin toteutumisesta, asiakasosallistumisesta suunnitteluvaiheessa sekä luottamuksesta.

Association between Long-Term Exposure to Traffic-Related Air Pollution and Subclinical Atherosclerosis: The REGICOR Study

Background: Epidemiological evidence of the effects of long-term exposure to air pollu tion on the chronic processes of athero genesis is limited. Objective: We investigated the association of long-term exposure to traffic-related air pollu tion with subclinical atherosclerosis, measured by carotid intima media thickness (IMT) and ankle–brachial index (ABI). Methods: We performed a cross-sectional analysis using data collected during the reexamination (2007–2010) of 2,780 participants in the REGICOR (Registre Gironí del Cor: the Gerona Heart Register) study, a population-based prospective cohort in Girona, Spain. Long-term exposure across residences was calculated as the last 10 years’ time-weighted average of residential nitrogen dioxide (NO2) estimates (based on a local-scale land-use regression model), traffic intensity in the nearest street, and traffic intensity in a 100 m buffer. Associations with IMT and ABI were estimated using linear regression and multinomial logistic regression, respectively, controlling for sex, age, smoking status, education, marital status, and several other potential confounders or intermediates. Results: Exposure contrasts between the 5th and 95th percentiles for NO2 (25 μg/m), traffic intensity in the nearest street (15,000 vehicles/day), and traffic load within 100 m (7,200,000 vehicle-m/day) were associated with differences of 0.56% (95% CI: –1.5, 2.6%), 2.32% (95% CI: 0.48, 4.17%), and 1.91% (95% CI: –0.24, 4.06) percent difference in IMT, respectively. Exposures were positively associated with an ABI of > 1.3, but not an ABI of < 0.9. Stronger associations were observed among those with a high level of education and in men ≥ 60 years of age. Conclusions: Long-term traffic-related exposures were associated with subclinical markers of atherosclerosis. Prospective studies are needed to confirm associations and further examine differences among population subgroups.key words: ankle–brachial index, average daily traffic, cardiovascular disease, exposure assessment, exposure to tailpipe emissions, intima media thickness, land use regression model, Mediterranean diet, nitrogen dioxide

Commodity Price Driven Risk Management from Viewpoint of High Grade Steel Alloys

The study of price risk management concerning high grade steel alloys and their components was conducted. This study was focused in metal commodities, of which nickel, chrome and molybdenum were in a central role. Also possible hedging instruments and strategies for referred metals were studied. In the literature part main themes are price formation of Ni, Cr and Mo, the functioning of metal exchanges and main hedging instruments for metal commodities. This section also covers how micro and macro variables may affect metal prices from the viewpoint of short as well as longer time period. The experimental part consists of three sections. In the first part, multiple regression model with seven explanatory variables was constructed to describe price behavior of nickel. Results were compared after this with information created with comparable simple regression model. Additionally, long time mean price reversion of nickel was studied. In the second part, theoretical price of CF8M alloy was studied by using nickel, ferro-chrome and ferro-molybdenum as explanatory variables. In the last section, cross hedging possibilities for illiquid FeCr -metal was studied with five LME futures. Also this section covers new information concerning possible forthcoming molybdenum future contracts as well. The results of this study confirm, that linear regression models which are based on the assumption of market rationality, are not able to reliably describe price development of metals at issue. Models fulfilling assumptions for linear regression may though include useful information of statistical significant variables which have effect on metal prices. According to the experimental part, short futures were found to incorporate the most accurate information concerning the price movements in the future. However, not even 3M futures were able to predict turning point in the market before the faced slump. Cross hedging seemed to be very doubtful risk management strategy for illiquid metals, because correlations coefficients were found to be very sensitive for the chosen time span.

Sensor Fusion of Proprioception, Force and Vision in Estimation and Robot

Sensor-based robot control allows manipulation in dynamic environments with uncertainties. Vision is a versatile low-cost sensory modality, but low sample rate, high sensor delay and uncertain measurements limit its usability, especially in strongly dynamic environments. Force is a complementary sensory modality allowing accurate measurements of local object shape when a tooltip is in contact with the object. In multimodal sensor fusion, several sensors measuring different modalities are combined to give a more accurate estimate of the environment. As force and vision are fundamentally different sensory modalities not sharing a common representation, combining the information from these sensors is not straightforward. In this thesis, methods for fusing proprioception, force and vision together are proposed. Making assumptions of object shape and modeling the uncertainties of the sensors, the measurements can be fused together in an extended Kalman filter. The fusion of force and visual measurements makes it possible to estimate the pose of a moving target with an end-effector mounted moving camera at high rate and accuracy. The proposed approach takes the latency of the vision system into account explicitly, to provide high sample rate estimates. The estimates also allow a smooth transition from vision-based motion control to force control. The velocity of the end-effector can be controlled by estimating the distance to the target by vision and determining the velocity profile giving rapid approach and minimal force overshoot. Experiments with a 5-degree-of-freedom parallel hydraulic manipulator and a 6-degree-of-freedom serial manipulator show that integration of several sensor modalities can increase the accuracy of the measurements significantly.

Description of epidemics of coffee rust with neural networks

The objective of this paper was to evaluate the potential of neural networks (NN) as an alternative method to the basic epidemiological approach to describe epidemics of coffee rust. The NN was developed from the intensities of coffee (Coffea arabica) rust along with the climatic variables collected in Lavras-MG between 13 February 1998 and 20 April 2001. The NN was built with climatic variables that were either selected in a stepwise regression analysis or by the Braincel® system, software for NN building. Fifty-nine networks and 26 regression models were tested. The best models were selected based on small values of the mean square deviation (MSD) and of the mean prediction error (MPE). For the regression models, the highest coefficients of determination (R²) were used. The best model developed with neural networks had an MSD of 4.36 and an MPE of 2.43%. This model used the variables of minimum temperature, production, relative humidity of the air, and irradiance 30 days before the evaluation of disease. The best regression model was developed from 29 selected climatic variables in the network. The summary statistics for this model were: MPE=6.58%, MSE=4.36, and R²=0.80. The elaborated neural networks from a time series also were evaluated to describe the epidemic. The incidence of coffee rust at four previous fortnights resulted in a model with MPE=4.72% and an MSD=3.95.

Ostotapahtuman ennustemallin kehittäminen ajoneuvomarkkinoinnin tueksi

Perinteisesti ajoneuvojen markkinointikampanjoissa kohderyhmät muodostetaan yksinkertaisella kriteeristöllä koskien henkilön tai hänen ajoneuvonsa ominaisuuksia. Ennustavan analytiikan avulla voidaan tuottaa kohderyhmänmuodostukseen teknisesti kompleksisia mutta kuitenkin helppokäyttöisiä menetelmiä. Tässä työssä on sovellettu luokittelu- ja regressiomenetelmiä uuden auton ostajien joukkoon. Tämän työn menetelmiksi on rajattu tukivektorikone sekä Coxin regressiomalli. Coxin regression avulla on tutkittu elinaika-analyysien soveltuvuutta ostotapahtuman tapahtumahetken mallintamiseen. Luokittelu tukivektorikonetta käyttäen onnistuu tehtävässään noin 72% tapauksissa. Tukivektoriregressiolla mallinnetun hankintahetken virheen keskiarvo on noin neljä kuukautta. Työn tulosten perusteella myös elinaika-analyysin käyttö ostotapahtuman tapahtumahetken mallintamiseen on menetelmänä käyttökelpoinen.

Establishment of Xaraés and Marandu grasses under levels of soil compaction

In Cerrado soils under grazing, changes occur in physical attributes, such as increased density, decreasing on the size of water stable aggregates, and macroporosity reduction. Thus, the aim of this study was to study the effect of compaction on the establishment of two forages. It was adopted a completely randomized design with three replications, in 2 x 4 factorial design, and two forages (Xaraés grass and Marandu grass), and four levels of compaction (soil densities of 1.0, 1.2, 1.4, and 1.6 Mg m-3). The following variables were evaluated 48 days after sowing: tiller population, plant height, dry matter production of shoots and components, leaf and stem, as well as the root dry mass. The stem dry mass decreased with soil density in a similar manner for both forages. It was observed that the leaf dry mass and shoots dry mass of Xaraés grass remained constant in the levels of soil compaction, not adjusting to any regression model. The establishment of Xaraés grass has not been negatively affected by compaction, which may be suitable for situations where there may be layers that restrict the growth of different forages.

Technical and economic analysis of irrigation of asparagus bean in protected environment

This experiment was conducted in Lavras - state of Minas Gerais (MG), Brazil, in a protected environment, and aims to estimate the irrigation depths that maximize productivity and economic returns in the cultivation of asparagus bean and analyze the economic viability of irrigation management. The experimental delineation was randomized blocks with five treatments and four replications. The treatments consisted of five drip irrigation depths: 40, 70, 100, 130 and 160% of water replacement depth up to field capacity. The depths of water that maximize productivity and economic returns were obtained from the regression model adjusted to productivity data, cost of product relations and water cost. The economic viability was achieved on the benefit/cost ratio basis. The depth with the maximum economic return was estimated in 434.4mm, with a productivity of 35,160.6kg ha-1, which is economically viable for the cultivation of asparagus bean, with a expected profitability of R$ 1.70 for every real invested.

The use of ALOS/PALSAR data for estimating sugarcane productivity

Some models have been developed using agrometeorological and remote sensing data to estimate agriculture production. However, it is expected that the use of SAR images can improve their performance. The main objective of this study was to estimate the sugarcane production using a multiple linear regression model which considers agronomic data and ALOS/PALSAR images obtained from 2007/08, 2008/09 and 2009/10 cropping seasons. The performance of models was evaluated by coefficient of determination, t-test, Willmott agreement index (d), random error and standard error. The model was able to explain 79%, 12% and 74% of the variation in the observed productions of the 2007/08, 2008/09 and 2009/10 cropping seasons, respectively. Performance of the model for the 2008/09 cropping season was poor because of the occurrence of a long period of drought in that season. When the three seasons were considered all together, the model explained 66% of the variation. Results showed that SAR-based yield prediction models can contribute and assist sugar mill technicians to improve such estimates.

Predictors of "occult" intra-abdominal injuries in blunt trauma patients

Objective: to assess predictors of intra-abdominal injuries in blunt trauma patients admitted without abdominal pain or abnormalities on the abdomen physical examination. Methods: We conducted a retrospective analysis of trauma registry data, including adult blunt trauma patients admitted from 2008 to 2010 who sustained no abdominal pain or abnormalities on physical examination of the abdomen at admission and were submitted to computed tomography of the abdomen and/or exploratory laparotomy. Patients were assigned into: Group 1 (with intra-abdominal injuries) or Group 2 (without intra-abdominal injuries). Variables were compared between groups to identify those significantly associated with the presence of intra-abdominal injuries, adopting p<0.05 as significant. Subsequently, the variables with p<0.20 on bivariate analysis were selected to create a logistic regression model using the forward stepwise method. Results: A total of 268 cases met the inclusion criteria. Patients in Group I were characterized as having significantly (p<0.05) lower mean AIS score for the head segment (1.0±1.4 vs. 1.8±1.9), as well as higher mean AIS thorax score (1.6±1.7 vs. 0.9±1.5) and ISS (25.7±14.5 vs. 17,1±13,1). The rate of abdominal injuries was significantly higher in run-over pedestrians (37.3%) and in motorcyclists (36.0%) (p<0.001). The resultant logistic regression model provided 73.5% accuracy for identifying abdominal injuries. The variables included were: motorcyclist accident as trauma mechanism (p<0.001 - OR 5.51; 95%CI 2.40-12.64), presence of rib fractures (p<0.003 - OR 3.00; 95%CI 1.47-6.14), run-over pedestrian as trauma mechanism (p=0.008 - OR 2.85; 95%CI 1.13-6.22) and abnormal neurological physical exam at admission (p=0.015 - OR 0.44; 95%CI 0.22-0.85). Conclusion Intra-abdominal injuries were predominantly associated with trauma mechanism and presence of chest injuries.

A seroepidemiological survey of Mycobacterium avium subsp. paratuberculosis in sheep from North of Portugal

The aim of this study was evaluate the risk factors for Mycobacterium avium subsp. paratuberculosis (Map) seroprevalence in sheep in the North of Portugal. The effects on seroprevalence of several variables such as individual characteristics, management practices, farm characteristics, animal health, and available veterinary services were evaluated. This information was then used in a multivariable logistic regression model in order to identify risk factors for Map seropositivity. Univariable analysis was used to screen the variables used in the logistic regression model. Variables that showed p values of <0.15 were retained for the multivariable analysis. Fifteen variables were associated with paratuberculosis in univariable analysis. The multivariable logistic regression model identified a number of variables as risk factors for seropositivity like sheep pure local and/or a cross of a local breed (OR=2.02), herd size with 31-60 head (OR=2.14), culling during the Spring-Summer season (OR=1.69) and the use of an anti-parasitic treatment such as Ivermectin as the only anti-parasitic medication (OR=5.60). Potential risk factors identified in this study support current recommendations for the control of paratuberculosis.

Exchange rate volatility and the use of foreign currency derivatives: Impact of 2008 global financial crisis

This thesis examines the impact of foreign exchange rate volatility to the extent of use of foreign currency derivatives. Especially the focus is on the impacts of 2008 global financial crisis. The crisis increased risk level in the capital markets greatly. The change in the currency derivatives use is analyzed by comparing means between different periods and in addition, by linear regression that enables to analyze the explanatory power of the model. The research data consists of financial statements figures from fiscal years 2006-2011 published by firms operating in traditional Finnish industrial sectors. Volatilities of the chosen three currency pairs is calculated from the daily fixing rates of ECB. Based on the volatility the sample period is divided into three sub-periods. The results suggest that increased FX market volatility did not increase the use foreign currency derivatives. Furthermore, the increased foreign exchange rate volatility did not increase the power of linear regression model to estimate the use foreign currency derivatives compared to previous studies.

Seroprevalence and risk factors associated with Chlamydophila abortus infection in dairy goats in the Northeast of Brazil

Few data are available on the prevalence and risk factors of Chlamydophila abortus infection in goats in Brazil. A cross-sectional study was carried out to determine the flock-level prevalence of C. abortus infection in goats from the semiarid region of the Paraíba State, Northeast region of Brazil, as well as to identify risk factors associated with the infection. Flocks were randomly selected and a pre-established number of female goats > 12 mo old were sampled in each of these flocks. A total of 975 serum samples from 110 flocks were collected, and structured questionnaire focusing on risk factors for C. abortus infection was given to each farmer at the time of blood collection. For the serological diagnosis the complement fixation test (CFT) using C. abortus S26/3 strain as antigen was performed. The flock-level factors for C. abortus prevalence were tested using multivariate logistic regression model. Fifty-five flocks out of 110 presented at least one seropositive animal with an overall prevalence of 50.0% (95%; CI: 40.3%, 59.7%). Ninety-one out of 975 dairy goats examined were seropositive with titers >32, resulting in a frequency of 9.3%. Lend buck for breeding (odds ratio = 2.35; 95% CI: 1.04-5.33) and history of abortions (odds ratio = 3.06; 95% CI: 1.37-6.80) were associated with increased flock prevalence.