Momentum, or the basic idea of the momentum effect in finance, is that there is a tendency for rising asset prices to continue rising, while the falling prices continue to fall. As such, a momentum strategy is based on the idea that previous returns will predict future returns. In order to follow this line of thought, a momentum strategy is generally based on buying past winners and taking short positions in past losers. This quantitative study addresses the phenomenon of momentum crashes, which is a moment in time when a momentum strategy fails, and past losers outperform past winners. In our study we are setting out to study the momentum crash phenomenon during the years of 2006-2012 on NASDAQ OMX Stockholm, focusing specifically on the Small- and Large Cap segments. As we intend to explore the concept of momentum crashes as thoroughly as possible, we will also be researching momentum itself during this time period, as these two concepts are inevitably intertwined. In order to do this, we will be applying commonly used portfolio construction methods used in previous momentum research. These portfolios will be based on past winners and past losers, and their performance will then be tracked for different lengths of time, which will allow us to identify points in time where momentum crashes have occurred. What we found in our research was that, while we gathered data indicative of momentum trends during our chosen time period, we could not prove that momentum existed to any statistically meaningful degree. As for momentum crashes, we identified many different points in time where the past-loser portfolios outperformed the past-winner portfolios, thus resulting in negative winner-minus-loser portfolios and momentum crashes. The most interesting aspect of these findings was that the highest frequencies of momentum crashes were found in the years of 2008 and 2009, where we made the most negative winner-minus-loser portfolio observations. This finding is in line with similar research on other populations, as momentum crashes are theorized to occur at a higher frequency during times of market stress and high volatility. Furthermore, we also made some interesting connections between our findings and behavioral finance; we identified certain patterns which could be indicative of a relationship between the two. As for the research gap and the ultimate contribution of this study, we have increased the knowledge, understanding and awareness of momentum crashes in Sweden, and we have shown during which times these are likely to occur in a Swedish context. Additionally, we have also increased the general knowledge of momentum by exploring it from a Swedish perspective.

As one of the major data analysis methods, statistical models play an important role in traffic safety analysis. A common situation associated with crash data is the phenomenon known as overdispersion which has been discussed and investigated frequently in recent years. As such, researchers have proposed several models, such as the Poisson Gamma (PG) or Negative Binomial (NB), the Poisson-lognormal, or the Poisson-Weibull, to handle the overdispersion. Unfortunately, very few models have been proposed for specifically analyzing the sources of dispersions in the data. Better understanding of sources of variation and overdispersion could help in managing safety, such as establishing relationships and applying appropriate treatments or countermeasures, more efficiently. Given the limitations of existing models for exploring the source of overdispersion of crash data, this research examined a new model function that could be applied to explore sources of extra variability through the use of the Generalized Waring (GW) models. This model, which was recently introduced by statisticians, divides the observed variability into three components: randomness, internal differences between road segments or intersections, and the variances caused by other external factors that have not been included as covariates in the model. To evaluate these models, GW models were examined using both simulated and empirical crash datasets, and the results were compared to the most commonly used NB model and the recently developed NB-Lindley models. For model parameter estimation, both the maximum likelihood method and a Bayesian approach were adopted for better comparison. A simulation study was used to show the better performance of this model compared to NB model for overdispersed data, and then an application in the empirical crash data illustrates its capability of modeling data sets with great accuracy and exploring the source of overdispersion. The performances of hotspot identification for these two kinds of models (i.e., GW models and NB models) were also examined and compared based on the estimated models from the empirical dataset. Finally, bias properties related to the choice of prior distributions for parameters in GW model were examined by using a simulation study. In addition, the suggestions on the choice of minimum sample size and priors were presented for different kinds of datasets.

La prise de conscience de l’implication des médicaments dans la genèse des accidents de la route date d’une vingtaine d’années. Les médicaments psycho-actifs peuvent altérer les capacités de conduite par leur action sur le système nerveux (par exemple, un effet sédatif le lendemain d’une prise d’hypnotique). D’autres médicaments sont susceptibles d’affecter les fonctions psychomotrices par leur action sur les fonctions physiologiques (tel que les hypoglycémies liées à un traitement antidiabétique). L’étude CESIR-A a été mise en place pour contribuer à la connaissance du lien épidémiologique entre médicaments et accidents de la route. L’étude utilise trois bases de données françaises : le Système National d’Information Inter-Régimes de l’Assurance Maladie (SNIIR-AM), les Procès Verbaux d’accidents (PV) et les Bulletins d’Analyse des Accidents Corporels de la circulation (BAAC). L’appariement de ces données a conduit à l’inclusion de 72,685 conducteurs impliqués dans un accident corporel sur la période juillet 2005-mai 2008. L’analyse a été réalisée grâce à deux méthodes: une analyse cas-témoin comparant les responsables aux non-responsables des accidents et une analyse dite en case-crossover. Les périodes d’exposition aux médicaments ont été estimées à partir des dates de délivrances de médicaments prescrits, puis remboursés par l’assurance maladie. L’étude des médicaments regroupés selon les quatre niveaux de risque sur la conduite définis par l’Agence Française de Sécurité Sanitaire des Produits de Santé (AFSSAPS) [du niveau 0 (pas de risque) au niveau 3 (risque élevé)], a montré que les utilisateurs de médicaments prescrits de niveau 2 et de niveau 3 ont un risque significativement plus élevé d’être responsables de leur accident (OR=1,31 [1,24-1,40] et OR=1,25 [1,12-1,40], respectivement). La fraction de risque attribuable à l’utilisation de ces médicaments était de 3,3% [2,7%-3,9%]. Le risque d’être responsable d’un accident était augmenté chez les utilisateurs de zolpidem (OR=1,28 [1,07-1,53]) mais pas chez les utilisateurs de zopiclone ou de benzodiazépines hypnotiques. Plus particulièrement, ce risque était augmenté chez les 139 conducteurs ayant eu plus d’un comprimé de zolpidem délivré par jour au cours des cinq mois précédant l’accident (OR=2,38 [1,61-3,52]). L’analyse case-crossover a mis en évidence un sur-risque d’accident de la route chez les utilisateurs de benzodiazépines hypnotiques seulement (OR=1,42 [1,09-1,85]). Les conducteurs exposés aux hypnotiques partagent les mêmes caractéristiques au regard du type d’accident, qui survenaient plus fréquemment sur autoroute. Dans notre base de données, 196 conducteurs ont été exposés à la buprénorphine et/ou à la méthadone, le jour de leur accident. Cette population spécifique était jeune, essentiellement masculine, avec d’importantes co-consommations, notamment d’alcool de médicaments de niveau 3. Les conducteurs exposés à la buprénorphine et/ou à la méthadone présentaient un risque accru d’être responsables de leur accident (OR= 2,19 [1,51-3,16]). Notre étude fournit des informations importantes sur la contribution des médicaments au risque d’accident de la route. D’après nos résultats, la classification de l’AFSSAPS semble appropriée concernant les médicaments de niveaux 2 et 3. Les sur-risques d’être responsable d’un accident chez les exposés au zolpidem ou aux traitements de substitution pourraient être liés, au moins en partie, au comportement à risque de ces conducteurs. L’amélioration du comportement des conducteurs représente un des défis pour la sécurité routière. L’objectif de la classification française et de la signalétique apposée sur les boîtes de médicaments est donc de fournir aux patients une information appropriée sur les effets des médicaments sur leur capacité de conduite. / In recent decades, attention has been increasingly focused on the impact of disabilities and medicinal drug use on road safety. Psychoactive medicines may impair driving abilities due to their action on the central nervous system (e.g. sedation in the morning following administration of a hypnotic), while other medicines may affect psychomotor functions by their action on physiological functions (e.g hypoglycaemic seizures related to diabetic treatment). The CESIR-A project was set up to improve the epidemiological knowledge on medicines and the risk of road traffic crashes. The study matched three French nationwide databases: the national healthcare insurance database, police reports, and the police national database of injurious crashes, leading to the inclusion of 72,685 drivers involved in an injurious road traffic crash from July 2005 to May 2008. Two methods were performed for data analysis: a case-control analysis in which cases where responsible drivers and controls non-responsible ones and a case-crossover analysis. Medicine exposures were estimated from prescription drug dispensations in the healthcare reimbursement database. The study of medicines grouped according to the four levels of driving impairment risk of the French classification system [from 0 (no risk) to 3 (high risk)], showed that users of level 2 and level 3 prescribed medicines were at higher risk of being responsible for the crash (OR=1.31 [1.24-1.40] and OR=1.25 [1.12-1.40], respectively). The fraction of road traffic crashes attributable to levels 2 and 3 medicines was 3.3% [2.7%-3.9%]. Zolpidem use was associated with an increased risk of being responsible for a road traffic crash (OR=1.28 [1.07-1.53]) whereas use of zopiclone and benzodiazepine hypnotics use was not. Responsibility risk was only increased in the 139 drivers with dispensing of more than one pill of zolpidem a day during the five months before the crash (OR=2.38 [1.61-3.52]). Case-crossover analysis showed an increased risk of crash for benzodiazepine hypnotic users only (OR=1.42 [1.09-1.85]). Hypnotic users shared similar crash characteristics, with crashes more likely to occur on highways. In our database, 196 drivers were exposed to buprenorphine and/or methadone on the day of crash. This specific population was young, essentially males, with important co-consumption of other substances, in particular alcohol and level 3 medicines. Injured drivers exposed to buprenorphine and/or methadone on the day of crash, had an increased risk of being responsible (OR=2.19 [1.51-3.16]). The case cross-over analysis did not demonstrate any association (OR=1.26 [0.93 - 1.70]). Our study provides evidence of the contribution of medicines to the risk of road traffic crashes. According to our results, the French risk classification seems relevant regarding medicines classified as levels 2 and 3 of risk for road traffic crashes. The observed increased risks of being responsible for a crash for zolpidem and substitution maintenance treatment users may be linked to risky behaviors. Improving driver behaviour is one of the challenges for road safety. Providing patients with proper information on the potential effect of medicines on their driving abilities is the main objective of drug and risk classifications such as the French one.

Previous red light camera (RLC) studies have shown reductions in violations and overall and right angle collisions, however, they may also result in increases in rear-end crashes (Retting & Kyrychenko, 2002; Retting & Ferguson, 2003). Despite their apparent effectiveness, many RLC studies have produced imprecise findings due to inappropriate study designs and/or statistical techniques to control for biases (Retting & Kyrychenko, 2002), therefore, a more comprehensive approach is needed to accurately assess whether they reduce motor vehicle injury collisions. The objective of this proposal is to assess whether RLC’s improve safety at signalized intersections within Miami-Dade County, Florida. Twenty signalized intersections with RLC’s initiating enforcement on January 1st, 2011 were matched to two comparison sites located at least two miles from camera sites to minimize spillover effect. An Empirical Bayes analysis was used to account for regression to the mean. Incidences of all injury, red light running related injury, right-angle/turning, and rear-end collisions were examined. An index of effectiveness along with 95% CI’s were calculated. During the first year of camera enforcement, RLC sites experienced a marginal decrease in right-angle/turn collisions, a significant increase in rear-end collisions, and significant decreases in all-injury and red light running-related injury collisions. An increase in right-angle/turning and rear-end collisions at the RLC sites was observed after two years despite camera enforcement. A significant reduction in red light running-related injury crashes, however, was still observed after two years. A non-significant decline in all injury collisions was also noted. Findings of this research indicate RLC’s reduced red light running-related injury collisions at camera sites, yet its tradeoff was a large increase in rear-end collisions. Further, there was inconclusive evidence whether RLC’s affected right-angle/turning and all injury collisions. Statutory changes in crash reporting during the second year of camera enforcement affected the incidence of right-angle and rear-end collisions, nevertheless, a novelty effect could not be ruled out. A limitation of this study was the small number of injury crashes at each site. In conclusion, future research should consider events such as low frequencies of severe injury/fatal collisions and changes in crash reporting requirements when conducting RLC analyses.

Vehicular crashes are the leading cause of death for young adult drivers, however, very little life course research focuses on drivers in their 20s. Moreover, most data analyses of crash data are limited to simple correlation and regression analysis. This thesis proposes a data-driven approach and usage of machine-learning techniques to further enhance the quality of analysis. We examine over 10 years of data from the Iowa Department of Transportation by transforming all the data into a format suitable for data analysis. From there, the ages of drivers present in the crash are discretized depending on the ages of drivers present for better analysis. In doing this, we hope to better discover the relationship between driver age and factors present in a given crash. We use machine learning algorithms to determine important attributes for each age group with the goal of improving predictivity of individual methods. The general format of this thesis follows a Knowledge Discovery workflow, preprocessing and transforming the data into a usable state, from which we perform data mining to discover results and produce knowledge. We hope to use this knowledge to improve the predictivity of different age groups of drivers with around 60 variables for most sets as well as 10 variables for some. We also explore future directions this data could be analyzed in.

Crashes occur every day on Utah’s roadways. Curves can be particularly dangerous as they require driver focus due to potentially unseen hazards. Often, crashes occur on curves due to poor curve geometry, a lack of warning signs, or poor surface conditions. This can create conditions in which vehicles are more prone to leave the roadway, and possibly roll over. These types of crashes are responsible for many severe injuries and a few fatalities each year, which could be prevented if these areas are identified. This highlights a need for identification of curves with high crash occurrences, particularly on a network-wide scale. The Horizontal Alignment Finder (HAF) Algorithm, originally created by a Brigham Young University team in 2014, was improved to achieve 87-100 percent accuracy in finding curved segments of Utah Department of Transportation (UDOT) roadways, depending on roadway type. A tool was then developed through Microsoft Excel Visual Basic for Applications (VBA) to sort through curve and crash data to determine the number of severe and total crashes that occurred along each curve. The tool displays a list of curves with high crash occurrences. The user can sort curves by several different parameters, including various crash rates and numbers of crashes. Many curves with high crash rates have already been identified, some of which are shown in this thesis. This tool will help UDOT determine which roadway curves warrant improvement projects.

No description available.

BACKGROUND- Motor vehicle crashes pose a serious public health problem. Many serious crashes are due to faulty driving by unfit operators, including several categories of neurological patients. Unfortunately, there seems to be little agreement among health professionals, driving experts, and state government on how to advise these individuals. REVIEW SUMMARY- This article reviews the question of driving in neurological patients. Decisions on driver fitness should be based on empirical observations of performance and not on criteria of age or medical diagnosis, which alone are unreliable predictors. Relevant data can be collected either on a road test or off-road, using different probes of vision and cognition, in the setting of a Department of Motor Vehicles office or medical clinic. The use of a driving simulator is also feasible. The predictive value of these performance assessments is a topic of active research. CONCLUSION- Understanding how performance data from off-road and on-road observations correlate with real-life crash risk is a key step toward developing safe, fair, and accurate means of predicting driver fitness. One potential benefit is the prevention of injury, and another is the preservation of mobility and independence of individuals whose licenses are being unduly revoked because of old age or illness.

Red light running is one of the main contributing factors of crashes in urban areas in Florida and the United States. Nationwide, according to preliminary estimates by the Federal Highway Administration (FHWA) 2001, there were nearly 218,000 red-light running crashes at intersections. These crashes resulted in as many as 181,000 injuries and 880 fatalities, and an economic loss estimated at $14 billion per year nationwide, According to the Community Traffic Safety Team Florida Coalition (A statewide traffic safety group) there were 9,348 crashes involving red-light running in Florida and 127 fatalities in 1999. This research study focused on studying the red light running crashes and violations in the State of Florida. There were three primary objectives for this research. The first primary objective was to analyze the red light running crashes in Florida from 2002 to 2004. The data for this part was collected from the Crash Analysis Reporting System of the Florida Department of Transportation. These crashes are reported as "disregarded traffic signal" as far as the first contributing cause. The analysis focused on the influences of different factors on red light running crashes including the driver (age group, gender, and DUI history) and the environment (time of day, day of week, type of road, and weather). However, not all red light crashes are reported as "disregarded traffic signal". Therefore, representing red light running crashes only through "disregard traffic signal" noted reports would underestimate the extent of red light running effects at a given intersection. Therefore, the second objective was to review the long form crash reports to determine the actual number of crashes related to red light running. The analysis for a random sample of the crashes on the sate roads of Florida on the year 2004 showed that the percentage of crashes related to red light running reported on the database was found to be (3.13%), and the percentage of crashes related to red light running reported in the original crash repot filled by the police officer are much higher than reported(5.63%), which shows the importance of standardizing the format and coding process for the long form crashes conducted by the police officers to help accurately identify the real cause of the crash at the studied location. The third objective was to analyze the violations data given for five intersections and find if there is a correlation between the average rate of violations per hour and the frequency of red light running crashes. The analysis showed that utilizing the limited number of intersections used in the study, it appears that there is no correlation between the average violations per hour and the red light running crashes at the studied locations.

No description available.