Every day, individuals commit acts which are considered immoral, unethical, even criminal, often to gain material advantage. Many people consider cheating on taxes, cheating on tests, claiming false benefits, or avoiding transport fare to be wrong, but they do them anyway. While some of these acts may not be formally illegal, they are, at best, considered morally dubious and is labeled “everyday crime.” Anomie theory holds that individuals make decisions based on socialized values, which separately may be contradictory but together, balances each other out, producing behavior considered “normal” by society. When one holds an imbalanced set of values, decisions made on that set may produce deviant behavior, such as everyday crime. RD theory holds that individuals who perceive their own deprivation, relative to someone else, will feel frustration and injustice, and may attempt to ameliorate that feeling with deviant behavior. Data from the 2006 World Values Survey were analyzed using logistic regression, testing both constructs concurrently. An individual was 1.55 times more likely to justify everyday crime for each calculated unit of anomie; and 1.10 times more likely for each calculated unit of RD. It was concluded from this study that anomie and relative deprivation were both associated with the tendency towards everyday crime.

This dissertation develops, applies, and investigates new methods to improve the analysis of logistic regression mixture models. An interesting dose-response experiment was previously carried out on a mixed population, in which the class membership of only a subset of subjects (survivors) were subsequently labeled. In early analyses of the dataset, challenges with separation of points and asymmetric confidence intervals were encountered. This dissertation extends the previous analyses by characterizing the model in terms of a mixture of penalized (Firth) logistic regressions and developing methods for constructing profile likelihood-based confidence and inverse intervals, and confidence bands in the context of such a model. The proposed methods are applied to the motivating dataset and another related dataset, resulting in improved inference on model parameters. Additionally, a simulation experiment is carried out to further illustrate the benefits of the proposed methods and to begin to explore better designs for future studies. The penalized model is shown to be less biased than the traditional model and profile likelihood-based intervals are shown to have better coverage probability than Wald-type intervals. Some limitations, extensions, and alternatives to the proposed methods are discussed.

Indiana University-Purdue University Indianapolis (IUPUI) / Forensic DNA phenotyping is an up and coming area in forensic DNA analyses that enables the prediction of physical appearance of an individual from DNA left at a crime scene. At present, there has been substantial work performed in understanding what genes/markers are required to produce a reliable prediction of categorical eye and hair color from the DNA of an individual of interest. These pigmentation markers (variants from HERC2, OCA2, TYR, SLC24A4, SLC45A2, IRF4 to name a few) are at the core of several prediction systems for eye and hair color such as IrisPlex, HIrisPlex, and the Snipper 2.5 suite. The contribution of these markers towards prediction in most cases however, only factors in an independent effect and do not take into account potential interactions or epistasis in the production of the final phenotypic color. Epistasis is a phenomenon that occurs when a gene’s effect relies on the presence of ‘modifier genes’, and can display different effects (enhance/repress a particular color) in genotype combinations rather than individually. In an effort to detect such epistatic interactions and their influence on hair color prediction models, for this current study, 872 individuals were genotyped at 61 associative and predictive pigmentation markers from several diverse population subsets. Individuals were phenotypically evaluated for eye and hair color by three separate independent assessments. Several analyses were performed using statistical approaches such as multifactor dimensionality reduction (MDR) for example, in an effort to detect if there are any SNP- SNP epistatic interactions present that could potentially enhance eye and hair color prediction model performances. The ultimate goal of this study was to assess what SNP-SNP combinations amongst these known pigmentation genes should be included as an additional variable in future prediction models and how much they can potentially enhance overall pigmentation prediction model performance. The second part of the project involved the analyses of several differentially expressed candidate genes between different hair color follicles of the same individual using quantitative Real Time PCR. We looked at 26 different genes identified through a concurrent non-human primate study being performed in the laboratory. The purpose of this study was to gain more insight on the level of differentially expressed mRNA between different hair color follicles within the same human individual. Data generated from this part of the project will act as a pilot study or ‘proof of principle’ on the mRNA expression of several pigmentation associated genes on individual beard hair of varying phenotypic colors. This analysis gives a first glimpse at expression levels that remain constant or differentiate between hairs of the same individual, therefore limiting the contribution of individual variation.

This dissertation proposes the development of a new quantile-based generalized logistic distribution GLDQB, by using the quantile function of the generalized logistic distribution (GLO) as the basic building block. This four-parameter distribution is highly flexible with respect to distributional shape in that it explains extensive levels of skewness and kurtosis through the inclusion of two shape parameters. The parameter space as well as the distributional shape properties are discussed at length. The distribution is characterized through its -moments and an estimation algorithm is presented for estimating the distribution’s parameters with method of -moments estimation. This new distribution is then used to fit and approximate the probability of a data set. / Dissertation (MSc)--University of Pretoria, 2014. / Statistics / MSc / Unrestricted

No description available.

In this research, the fire effects on structural and compositional change, and advance regeneration of oak forests in the Ozarks of Missouri were investigated by combining the statistic methods of MANONA, survival analysis, CART analysis, and logistic analysis. Results indicated that fire treatments significantly reduced the midsotry and understory basal area and stem density. However, fire effects on overstory tree survival differentiated among size classes. A new morphological variable, ratio of the total height to the square of basal diameter, was found to be statistically significantly related to the tree mortality rate for most of the species. The developed logistic regression models for selected species using the morphological variable well simulated the impact of initial stem size of advance regeneration on mortality for most of the species. The resultant logistic regression models could be a potential tool to compare and quantify species response to fires on a comparable basis.

No description available.

Evaluating the effectiveness of an intervention can pose challenges if there is not an adequate control group. The effects of the intervention can be distorted by observable differences in the characteristics of the control and treatment groups. Propensity score matching can be used to confirm the outcomes of an intervention are due to the treatment and not other characteristics that may also explain the intervention effects. Propensity score matching is an advanced statistical technique that uses background information on the characteristics of the study population to establish matched pairs of treated participants and controls. This technique improves the quality of control groups and allowing for a better evaluation of the true effects of an intervention. The purpose of this study was to implement this technique to derive county-level matches across the southeastern United States for existing counties within a single state where future statewide initiatives are planned. Statistical analysis was performed using SAS 9.4 (Cary, NC, USA). A select set of key county-level socio-demographic measures theoretically relevant for deriving appropriate matches was examined. These include the proportion of African Americans in population, population density, and proportion of the female population below poverty level. To derive the propensity-matched counties, a logistic regression model with the state of primary interest as the outcome was conducted. The baseline covariates of interest were included in the model and used to predict the probability of a county being in the state of primary interest; this acts as the propensity score used to derive matched controls. A caliper of 0.2 was used to ensure the ratio of the variance of the linear propensity score in the control group to the variance of the linear propensity score in the treatment group is close to 1. The balance of covariates before and after the propensity score matching were assessed to determine if significant differences in each respective covariate persisted after the propensity score matching. Before matching, a significant difference was found in the proportion of African Americans in control group (21.08%, n=3,450) and treatment group (36.95%, n=230) using the t-test (P<0.0001). The percent of females below poverty level showed significant difference between control and treatment group (P=0.0264). The t-test of population density also showed significant differences between the groups (P=0.0424). After matching, the mean differences for the treated-control groups were all zero for these three covariates and the characteristics were no longer showing any significant differences between the two groups. This study found that the use of propensity score matching methods improved the accuracy of matched controls. Ensuring that the control and treatment counties have statistically similar characteristics is important for improving the rigor of future studies examining county-level outcomes. Propensity score matching does not account for unobserved differences between the treatment and control groups that may affect the observed outcomes; however, it does ensure that the observable characteristics between the groups are statistically similar.This method reduces the threat to internal validity that observable characteristics pose on interventions by matching for these potentially confounding characteristics.

This research explored variables that influence community college student degree aspirations and students purpose for enrolling and pursuing specific degree types. The study was conducted using secondary data for students pursuing Associate in Arts, Associate in Science, and Bachelor of Applied Science degrees at a single community college. A logistic regression test was used to test graduate and baccalaureate degree aspirations of the entire sample of students and separately by degree type. Significant predictors of degree aspirations included age, gender, credits enrolled in, participation in student groups, academic course planning, receipt of scholarship, and college GPA. In general, community college students had high degree aspirations. Younger students tended to be on the collegiate transfer track and older students tended to want to pursue baccalaureate degrees locally. In addition to having high degree aspirations, a large proportion of students attended the college for occupational purposes and created intermediate and long-term goals related to their academic aspirations. The findings of the research confirm findings of previous studies on college student degree aspirations, and add to the understanding of variables contribute to students' educational goals. Recommendations for practice and future research are presented.

Traffic safety and mobility of roadway work zones have been considered to be one of the major concerns in highway traffic safety and operations in Florida. In intent to expose Florida's work zones crash characteristics, the Florida Traffic Crash Records Database for years 2002, 2003 and 2004 were explored. Statistical models were estimated and Florida's work zone crash traits for single vehicle crashes and two-vehicle crashes were drawn. For the single-vehicle crashes, trucks were found more likely to be involved in single vehicle crashes in freeway work zones compared to freeways without work zones. Straight level roadways are significantly affected by the presence of work zones. The lighting condition is also one of the risk factors associated with work zone single-vehicle crashes. In fact, at work areas with poor or no lighting during dark conditions, motor vehicles are more prone for crashes compared to non-work zone locations with poor or no lighting during dark. The weather condition is positively associated with single-vehicle work zone crashes. Results showed that during rainy weather, drivers are less likely to be involved in work zone crashes compared to the same weather conditions in non-work zone locations. This fact may be due to the vigilant driving pattern during rain at work zones. For the two-vehicle work zone crashes, results showed that drivers younger than 25 years of age and drivers older than 75 years old have the highest risk to be the at-fault driver in a work zone crash. Male drivers have significantly higher risk than female drivers to be the at-fault driver. The model conspicuously shows that drivers under the influence of narcotics/alcohol are more likely to cause crashes (i.e. at-fault driver) at work zones. Road geometry and the lighting condition were significant risk factors associated with two-vehicle work zone crashes. Freeways straight segments are more susceptible to crashes in work zone areas. Poor lighting or no lighting at all during dark can lead to significantly higher crash hazard at work zones. Foggy weather causes a significant mount in work zone crash risk compared to non-work zone locations. In addition to that, work zones located in rural areas have higher crash potential than work zones located in urban areas. After examining the current Florida work zone Maintenance of Traffic (MOT) plans, known as the Motorist Awareness System (MAS), it was realized that this system is static hence does not react to changing traffic conditions. An ITS-based dynamic lane management system, known as dynamic lane merging system, was explored to supplement the existing MAS plans. Two forms of dynamic lane management were recognized as dynamic lane merging namely the early merge and the late merge. These two systems were designed to advise drivers on definite merging locations. Previously deployed dynamic lane merging systems comprise several Portable Changeable Message Signs (PCMS) and traffic sensors. The addition of multiple PCMSs to the current MAS plans may encumber the latter and usually requires relatively extensive equipment installation and relocation which could be inefficient for short term movable work zones. Therefore, two Simplified Dynamic Lane Merging Systems (SDLMS) were designed, deployed, and tested on Florida's short term movables work zones. The first SDLMS was a simplified dynamic early merge system (early SDLMS) and the second SDLMS was a simplified dynamic late merge system (late SDLMS). Both SDLMS consisted of supplementing the MAS plans used in Florida work zones with an ITS-based lane management system. From the two-to-one work zone configuration (first site), it was noted that the ratio of the work zone throughput at the onset of congestion over the demand volume was significantly the highest for the early SDLMS compared to the MAS and late SDLMS. Travel time through the work was the lowest for the early SDLMS, followed by the late SDLMS, and then MAS. However, the differences in mean travel times were not statistically significant. It was also concluded that the early SDLMS resulted in higher early merging compared to the MAS and that the late SDLMS in higher late merging compared to the MAS. The first site was used as a pilot for testing the system since data collection was limited to two days for each MOT type. Hence, operational measures of effectiveness (MOEs) could not be evaluated under different demand volumes. It should also be noted that the RTMS was not available during the MAS data collection which disabled us from collecting speed data. From the three-to-two work zone configuration site, data was collected extensively relative to the first site. The RTMS was available for all three MOT types tested which enabled the collection of the speed data that are used as a safety surrogate measure. The mean speed fluctuation in the closed lane was the highest under the MAS system for all demand volumes and in all three lanes. Comparing the dynamic early merge and the dynamic late merge mean speed fluctuations in the closed lane and the middle lane, results showed that the mean speed fluctuation for the early merge are lower than those of the late merge under all demand volumes. However, the difference in the mean speed fluctuation is only statistically significant under demand volume ranging between 1 and 500 veh/hr. As for the shoulder lane, it was noted that the speed mean speed fluctuation is significantly the lowest for demand volumes ranging between 1500 veh/hr and 2000 veh/hr under the late SDLMS compared to the early SDLMS and the MAS. The ratio of the throughput over demand volume was taken as the operational MOE. Results showed that the Dynamic early merge performs significantly better than the regular MAS under demand volume ranging between 500 veh/hr and 2000 veh/hr. Results also showed that the dynamic late merge perform better than the MAS under volumes ranging between 1500 veh/hr and 2000 veh/hr and significantly poorer than the MAS under low volumes. Therefore, the late SDLMS is not recommended for implementation under low volumes. Results also showed that the late SDLMS performs better than the early SDLMS under higher volume (ranging between 1500 veh/hr to 2000 veh/hr). A simulated work zone with a two-to-one lane closure configuration was coded in VISSIM and operational and safety MOEs under MAS, early SDLMS, and late SDLMS were compared under different drivers' adherence rate to the merging instructions, truck percentage in the traffic composition, and traffic demand volumes. Results indicated that throughputs are higher in general under the early SDLMS, travel times are lower under the early SDLMS. However, overall, the early SDLMS resulted in the highest speed variance among MOT types. The MAS resulted in the lowest speed variances overall.