Master of Science / Department of Statistics / Shie-Shien Yang / In fitting linear models, R[superscript]2 statistic has been wildly used as one of the measures to assess the goodness-of-fit and prediction power of the model. Unlike fixed linear models, at this time there is no single universally accepted measure for assessing goodness-of-fit and prediction power of a linear mixed model. In this report, we reviewed seven different approaches proposed to define a measure analogous to the usual R[superscript]2 statistic for assessing mixed models. One of seven statistics,Rc, has both conditional and marginal versions. Association mapping is an efficient way to link the genotype data with the phenotype diversity. When applying the R[superscript]2 statistic to the association mapping application, it can determine how well genetic polymorphisms, which are the explanatory variables in the mixed models, explain the phenotypic variation, which is the dependent variation. A linear mixed model method recently has been developed to control the spurious associations due to population structure and relative kinship among individuals of an association mapping. We assess seven definitions of R[superscript]2 statistic for the linear mixed model using data from two empirical association mapping samples: a sample with 277 diverse maize inbred lines and a global sample of 95 Arabidopsis thaliana accessions using the new method. R[superscript]2[subscript]LR statistic derived from the log-likelihood principle follows all the criterions of R[superscript]2 statistic and can be used to understand the overlap between population structure and relative kinship in controlling for sample relatedness. From our results,R[superscript]2[subscript]LR statistic is an appropriate R[superscript]2 statistic for comparing models with different fixed and random variables. Therefore, we recommend using RLR statistic for linear mixed models in association mapping.

This thesis was aimed to evaluate if sentiment related to stocks expressed on the subforum “Wallstreetbets” also reflects the traded volume in the stock market. For this purpose, a collection of comment data from posts filtered under the “Hot” section was issued between the 6th of April 2021 and the 20th of April 2021 on daily basis at 22.00 (GMT+2). The comments were preprocessed to filter out noise, and thereafter comments that contained mentions of stocks were analyzed using VADER, an algorithm for grading sentiment. In total sentiment regarding 13 different stocks were fitted into a mixed effect model with random slopes and intercepts. The results showed a positive correlation between sentiment expressed and the traded volume. This indicates that by studying the forum we can better understand how people invested in stocks make investment decisions, which potentially could lead to a competitive advantage over time.

Sufficient research exists indicating that the brain mechanisms involved with use of whole brain teaching (WBT) techniques will likely lead to improved academic achievement and that academic self-concept (ASC) is both a cause and consequence of academic achievement. However, it is not known if there is a relationship between WBT and ASC. Given the benefits derived from positive ASC, it becomes important to assess WBT as a predictor variable of positive ASC. The purpose of this quantitative study was to examine the relationship between different levels of exposure to WBT techniques and the mean difference in ASC, as measured by the general-school, mathematics, and reading subscores on the Self Description Questionnaire I, between treatment conditions. Self-concept theory as posited by Shavelson et al. and the Marsh/Shavelson revision, the skill development approach to self-concept enhancement, and the reciprocal effect model provide the theoretical foundations of this dissertation. A one-way multivariate analysis of variance (MANOVA) was used to determine if the mean ASC scores differed among 191 second and third grade students exposed to three levels of the WBT factor. Results of the three-group MANOVA failed to support use of WBT techniques to improve ASC. Reconfiguration of the quasi-independent variable into two groups revealed that general-school ASC scores were significantly lower in the group exposed to limited to no WBT techniques. Assessing students at risk for educational problems may reveal more convincing evidence for WBT as an effective ASC intervention. The implications for social change include encouraging WBT practitioners to make more empirically sound claims and decisions regarding their practice, thereby allowing students an educational experience grounded in scientific findings, rather than subjective assumptions.

No description available.

Economic sanctions are a tool of achieving peace and have become increasingly important in research lately, as it is a more current question than ever. With the Russian war on Ukraine, countries have been sending sanctions in the hopes of financially straining Russia. The purpose of the study is to investigate how sending sanctions to a main trading partner is associated with the economic development of the sender. The study was based on the gravity model as well as economic development determinants. We employed a panel data analysis regarding 19 countries. A Fixed Effect model was used in order to regress the relationship between sending sanctions and the economic development of the sanctioning states economy between the years 1990 and 2021. At a 5% significance level, we did not find any correlation between annual growth of Gross Domestic Product per capita and sanctioned years, however the findings showed that there was a statistically significant negative correlation between sending sanctions and the economic growth of the sender at a 10% significance level. Governmental institutions can use these findings to carefully consider sanction decisions and their potential impact on the economy in the future.

Spatiotemporal dynamics of resource availability can produce markedly different patterns of landscape utilization which necessitates studying habitat selection across biologically relevant extents. Feral pigs (Sus scrofa) are a prolifically expanding, generalist species and researchers have yet to understand fundamental drivers of space use in agricultural landscapes within the United States. To study multi-scale habitat selection patterns, I deployed 13 GPS collars on feral pigs within the Mississippi Alluvial Valley. I estimated resource selection using mixed-effects models to determine how feral pigs responded to changes in forage availability and incorporated those results with autocorrelated kernel density home range estimates. My results indicated season-specific habitat functional responses to changes in agricultural phenology and illustrated the interdependencies of landscape composition, hierarchical habitat selection, and habitat functional responses. These results indicate fundamental drivers of feral pig spatial distributions in an agricultural landscape which I used to predict habitat use to direct feral pig management.

No description available.

Greenhouse Gas emission increase is largely attributed to carbon dioxide emissions as the major gas causing climate change and atmospheric warming. According to Environmental Kuznets Curve Theory (EKC), the increase in economic growth is expected to reduce the environmental pollution from carbon dioxide emission caused at the beginning stages of economic growth. In this thesis, I examined the impact of economic growth on carbon dioxide emission. The key hypothesis tested in this study is the Environmental Kuznets Curve hypothesis. Data from 1967 to 2016 from over 15 countries in North and South America, published by the World Bank were used. Since EKC posits a non-linear relationship between economic growth (GDP/capita) and Carbon dioxide emission, I used a quadratic component in the regression model. I analyzed the data using the OLS regression as my baseline model. Each country is unique in many respects that are hard to capture by a set of variables in econometrics model. This poses a challenge to estimating an unbiased estimate. Using panel data model allowed controlling for time invariant unobserved country-specific factors that could bias the estimates. I estimated a fixed effect panel regression to examine the relationship between carbon dioxide emissions and economic growth is primarily measured with Gross Domestic Product (GDP) per capita. The results of the fixed effect panel regression showed that all variables are significant, except export and inflation which were not significant. OLS could not solve the issue of heterogeneity among the variables. Estimating country-specific fixed effects model eliminates unobserved heterogeneity across countries and, therefore provides relatively unbiased estimates compared to OLS estimates. The positive correlation between Total CO2 emissions, CO2 emissions from Solid, and CO2 emissions from gas and GDP per capita suggests that carbon dioxide emissions increase as GDP/ capita increases before the turning point. The negative correlation between Total CO2 emissions, CO2 emissions from Solid, and CO2 emissions from gas and GDP per capita squared suggests that there is a polynomial (quadratic) form which is like that of inverted U-shape of the EKC curve. The coefficient, although it is very small, suggests the impact of the negative relationship after the turning point at the vertex of EKC curve is fractional. As expected, the result indicates a higher population causes an increase in total CO2 emissions. The result from CO2 emissions from liquid shows a negative relationship between the dependent variable CO2 emissions from liquid and the independent variable GDP per capita at the highest level of significance. This result is different from that of total carbon dioxide emissions, CO2 emissions from Solid, and CO2 emissions from gas. Carbon emission from liquid looks different from carbon emissions from solid and gas. There are high and constant emission throughout all the years and in all countries used in the analysis. EKC hypothesis is proven to be true for total carbon dioxide emissions, carbon dioxide emission from solid and gas. The hypothesized correlation between GDPs per capita square and CO2 emissions is statistically supported for Total CO2 emission, CO2 emission from solid and CO2 emission from gas. CO2 emissions from Solid, and CO2 emissions from gas and GDP per capita squared suggest that there is a polynomial (quadratic) form which is like that of inverted U-shape of the EKC curve. This proves that EKC model is proven to be true for my data. Policies like population policies can help in increasing growth in GDP per capita and reducing growth in the amount of carbon dioxide emissions. Population policies could play a significant role aimed at mitigating and reducing climate change.

No description available.

No description available.