Scholarship & Research
Permanent URI for this communityhttps://scholarworks.montana.edu/handle/1/1
Browse
36 results
Search Results
Item Blood and black gold: natural resource extraction and violent crime on American Indian reservations(Montana State University - Bozeman, College of Agriculture, 2023) Sikoski, Laura Kate; Chairperson, Graduate Committee: Wendy A. StockUsing 2001 to 2016 precinct-level crime data, I examine the relationship between natural resource development in the Bakken oil fields and violent crime on American Indian reservations. While previous studies find positive effects of the Bakken oil boom on crime, the impacts of the oil boom on crime within reservations have never been evaluated. I find that the increase in crime caused by the Bakken oil boom was significantly more severe in reservations, driving the increase in regional crime found by other studies. These results suggest that community safety outcomes should be considered by federal, state, and tribal governments for future natural resource development on reservation.Item Intersectional identity: factors impacting student odds of first semester STEM major declaration(Montana State University - Bozeman, College of Education, Health & Human Development, 2023) Jacobs, Jonathan Daniel; Chairperson, Graduate Committee: Lauren DavisThough there is a large amount of literature on those who graduate from college with STEM degrees, there is a dearth of literature involving intersectional identity of college freshman who are considering entering STEM majors. This study seeks to begin the process of meeting the gaps in research. Data from the High School Longitudinal Study of 2009 (HSLS:2009) were analyzed using logistic regression; using listwise deletion, intersectional identities which impact odds of student declaring a STEM major were identified. Student race and ethnicity, student sex, student socio-economic status, teacher race and ethnicity, teacher sex, science utility, science interest, science self-efficacy, and science identity were the components of intersectional identity for this study. Student race, student socio-economic status, science self-efficacy, and science identity were statistically significant factors that increased student odds of entering college with as STEM degree (p<0.001). Students who were Asian had a statistically significant increase in odds over White students to enter college with a STEM degree. All other aspects of identity were not statistically significant. More research is needed in this field to gain a deeper understanding of how intersectional identity impacts a students' odds of declaring a STEM majors their first semester in college.Item Investigating newer statistics instructors' breakthroughs with and motivations for using active learning: a longitudinal case-study and a multi-phase approach towards nstrument development(Montana State University - Bozeman, College of Letters & Science, 2022) Meyer, Elijah Sterling; Co-Chairs, Graduate Committee: Stacey Hancock and Jennifer Green; This is a manuscript style paper that includes co-authored chapters.National recommendations call for a shift from using lecture-based approaches to using approaches that engage students in the learning process, primarily through active learning techniques. Despite these recommendations, the adoption of active learning techniques for newer statistics instructors remains limited. The goal of this research is to provide a more holistic understanding about statistics instruction, specifically as it relates to recommended active learning techniques and newer statistics instructors, including graduate student instructors (GSIs). In this research, I present two studies. In the first study, we investigated GSIs' breakthroughs in their knowledge about, emotions towards, and use of active learning over time by using a longitudinal collective case-study approach. Survey, interview, and observation data across four semesters revealed that the GSIs' breakthroughs in their use of active learning only occurred after their increased knowledge about active learning aligned with their emotions towards it. This study further revealed that the GSIs needed to feel confident in and be challenged by their course structure before implementing active learning techniques. The second study builds upon these findings by exploring statistics instructors' motivations or reasons for using active learning. Under the self-determination theory framework, we conducted a multi-phase study to develop an instrument that measures four different types of motivational constructs for using group work, a specific active learning approach. We constructed items using expert opinion and cognitive interviews, and then we conducted two pilot studies with newer statistics instructors. The resulting reliability and validity evidence suggest that this instrument may help support future studies' investigations of motivation, helping us to better understand newer statistics instructors' use of active learning. Together, these studies may help inform future recommendations on how to support newer statistics instructors' early adoption of such technique.Item Leveraging a global spring, 2-row barley population to accelerate the development of superior forage barley varieties for Montana growers(Montana State University - Bozeman, College of Agriculture, 2021) Hoogland, Traci Janelle; Chairperson, Graduate Committee: Jamie ShermanAs more people around the globe escape poverty, they are eating more meat and dairy products. To support this increased demand for animal products there is an urgent need to develop more sustainable high-quality forage and hay crops for the livestock production industry. Barley (Hordeum vulgare spp. vulgare L.) is considered one of the most drought tolerant of the annual cereals and spring barley has been shown to out yield established perennial forages under drought conditions in central Montana (Cash, Surber, & Wichman, 2006). To accelerate the development of superior forage barley varieties for Montana, the following goals were identified 1) Utilize a genome wide association analysis to find genetic regions related to key forage and agronomic traits, 2) Use statistical modeling to a) examine the relationship between difficult to measure forage traits such as quality and yield, and easy to measure agronomic traits such as flowering time and plant height, b) identify agronomic traits that can be used as proxies for yield and quality in the earliest stages of the breeding program when genetic and phenotypic variability are at their greatest. Through these techniques the importance of variation in timing of plant maturity was identified. Statistical modeling showed that variability in forage yield and quality was observed to be closely related to variability in the timing of heading and soft-dough dates. Plant height was also determined to be of importance especially for biomass yield. Through genome-wide association analysis, novel QTL were discovered in relation to all studied traits. QTL were detected on all seven chromosomes and the majority of forage trait QTL co-located with QTL related to the timing and progression of plant development and maturity. This appeared to indicate that in a population of global barley accessions, the loci with the greatest impact on forage traits may be those containing genes regulating plant development and senescence. This further strengthened the evidence from the modeling study that a relationship exists between the two trait categories: traits for measuring the timing of plant development and forage traits.Item Bayesian hierarchical latent variable models for ecological data types(Montana State University - Bozeman, College of Letters & Science, 2022) Stratton, Christian Alexander; Chairperson, Graduate Committee: Jennifer Green and Andrew Hoegh (co-chair); This is a manuscript style paper that includes co-authored chapters.Ecologists and environmental scientists employ increasingly complicated sampling designs to address research questions that can help explain the impacts of climate change, disease, and other emerging threats. To understand these impacts, statistical methodology must be developed to address the nuance of the sampling design and provide inferences about the quantities of interest; this methodology must also be accessible and easily implemented by scientists. Recently, hierarchical latent variable modeling has emerged as a comprehensive framework for modeling a variety of ecological data types. In this dissertation, we discuss hierarchical modeling of multi-scale occupancy data and multi-species abundance data. Within the multi-scale occupancy framework, we propose new methodology to improve computational performance of existing modeling approaches, resulting in a 98% decrease in computation time. This methodology is implemented in an R package developed to encourage community uptake of our method. Additionally, we propose a new modeling framework capable of simultaneous clustering and ordination of ecological abundance data that allows for estimation of the number of clusters present in the latent ordination space. This modeling framework is also extended to accommodate hierarchical sampling designs. The proposed modeling framework is applied to two data sets and code to fit our model is provided. The software and statistical methodology proposed in this dissertation illustrate the flexibility of hierarchical latent variable modeling to accommodate a variety of data types.Item Supporting data-intensive environmental science research: data science skills for scientific practitioners of statistics(Montana State University - Bozeman, College of Letters & Science, 2020) Theobold, Allison Shay; Chairperson, Graduate Committee: Stacey Hancock; Stacey Hancock was a co-author of the article, 'How environmental science graduate students acquire statistical computing skills' in the journal 'Statistics education research journal' which is contained within this dissertation.; Stacey Hancock and Sara Mannheimer were co-authors of the article, 'Designing data science workshops for data-intensive environmental science research' submitted to the journal 'Journal of statistics education ' which is contained within this dissertation.; Stacey Hancock was a co-author of the article, 'Data science skills in data-intensive environmental science research: the case of Alicia and Ellie' submitted to the journal 'Harvard data science review' which is contained within this dissertation.The importance of data science skills for modern environmental science research cannot be understated, but graduate students in these fields typically lack these integral skills. Yet, over the last 20 years statistics preparation in these fields has grown to be considered vital, and statistics coursework has been readily incorporated into graduate programs. As 'data science' is the study of extracting value from data, the field shares a great deal of conceptual overlap with the field of Statistics. Thus, many environmental science degree programs expect students to acquire these data science skills in an applied statistics course. A gap exists, however, between the data science skills required for students' participation in the entire data analysis cycle as applied to independent research, and those taught in statistics service courses. Over the last ten years, environmental science and statistics educators have outlined the shape of the data science skills specific to research in their respective disciplines. Disappointingly, however, both sides of these conversations have ignored the area at the intersection of these fields, specifically the data science skills necessary for environmental science practitioners of statistics. This research focuses on describing the nature of environmental science graduate students' need for data science skills when engaging in the data analysis cycle, through the voice of the students. In this work, we present three qualitative studies, each investigating a different aspect of this need. First, we present a study describing environmental science students' experiences acquiring the computing skills necessary to implement statistics in their research. In-depth interviews revealed three themes in these students' paths toward computational knowledge acquisition: use of peer support, seeking out a 'singular consultant,' and learning through independent research. Motivated by the need for extracurricular opportunities for acquiring data science skills, next we describe research investigating the design and implementation of a suite of data science workshops for environmental science graduate students. These workshops fill a critical hole in the environmental science and statistics curricula, providing students with the skills necessary to retrieve, view, wrangle, visualize, and analyze their data. Finally, we conclude with research that works toward identifying key data science skills necessary for environmental science graduate students as they engage in the data analysis cycle.Item The effects of red flag laws on firearm suicides and homicides(Montana State University - Bozeman, College of Agriculture, 2021) Harris, Mitchell John; Chairperson, Graduate Committee: Mark AndersonRisk-based firearm removal laws, commonly known as Red Flag laws have become increasingly popular among lawmakers attempting to reduce gun violence in America. Despite widespread public support, these laws have yet to be studied in economics. Using mortality data from the National Vital Statistics System, I find that Red Flag laws have a significant negative effect on firearm suicides and firearm homicides. Upon further analysis, I find that there is evidence of a pre-existing downward trend in both firearm suicides and firearm homicides. Red Flag laws do not cause changes in these mortality outcomes, rather there is an unobserved shock that decreases firearm suicides and homicides, while simultaneously affecting a state's propensity to adopt a Red Flag law. These results contradict existing non-economic literature, which suggests that Red Flag laws cause a large decrease in firearm suicides.Item Public revenue leakage from real estate non-disclosure laws(Montana State University - Bozeman, College of Agriculture, 2021) Bollum, Tanner; Chairperson, Graduate Committee: Daniel P. BigelowProperty tax is the single largest source of local own-source revenue. Due to lack of existing legal structure, county assessors are often left without access to market data. Prior to 2004, three states in the western portion of the United States had constitutions that lacked legislation regarding the disclosure of home sales. This is recognized in this research as non-disclosure laws (NDLs). New Mexico changed this legal structure in 2004 and mandated that county assessors receive all sales information in hopes that property assessments become more equitable. Using two-way fixed effects and a difference-in-differences design, I estimate the change in county level property tax revenue to be a 3.67 percent increase annually.Item Space-filling designs for mixture/process variable experiments(Montana State University - Bozeman, College of Letters & Science, 2021) Obiri, Moses Yeboah; Chairperson, Graduate Committee: John J. BorkowskiThe ultimate objective of this dissertation was to present a statistical methodology and an algorithm for generating uniform designs for the combined mixture/process variable experiment. There are many methods available for constructing uniform designs and four of such methods have been used in this study. These are the Good Lattice Point (GLP) method, the cyclotomic field (CF) method, the square root sequence (SRS) method, and the power-of-a-prime (PP) method. A new hybrid algorithm is presented for generating uniform designs for mixture/process variable experiments. The algorithm uses the G function introduced by Fang and Yang (2000), and adopted by Borkowski and Piepel (2009) to map q-1 points from q + k - 1 points generated in the hypercube to the simplex. Two new criteria based on the Euclidean Minimum Spanning Tree (EMST) which are more computationally efficient for assessing uniformity of mixture designs and mixture/process variable designs are presented. The two criteria were found to be interchangeable and the geometric mean of the edge lengths (GMST) criterion is preferred to the average and standard deviation of edge lengths (adMST, sdMST) criterion. The GMST criterion uses only one statistic to quantify the uniformity properties of mixture and mixture/process variable designs. Tables of good uniform designs are provided for mixture experiments in the full simplex (S q) for q = 3; 4; 5 and practical design sizes, 9 _ n _ 30, using the four number theoretic methods in this study. A conditional approach based on the GMST criterion for generating good uniform mixture/process variable designs is also introduced and tables of good uniform designs are given for the combined q-mixture and k process variable experiments for q = 3; 4; 5, k = 1; 2 and practical numbers of runs, 9 _ n _ 30. A new algorithm is provided to augment existing mixture design points with space-filling points including designs with existing clustered design points. In this algorithm, new design points are chosen from a candidate set of points such that the resulting augmented design has good space-filling properties. The SRS method is found to produce the best augmented space-filling mixture designs.Item Monothetic cluster analysis with extensions to circular and functional data(Montana State University - Bozeman, College of Letters & Science, 2019) Tran, Tan Vinh; Chairperson, Graduate Committee: Mark Greenwood; Mark C. Greenwood was a co-author of the article, 'Choosing the number of clusters in monothetic cluster analysis' submitted to the journal 'Electronic journal of applied statistical analysis' which is contained within this dissertation.; Mark C. Greenwood, John C. Priscu and Marie Sabacka were co-authors of the article, 'Visualization and monothetic clustering data with circular variables' submitted to the journal 'Journal of environmental statistics' which is contained within this dissertation.; Mark C. Greenwood was a co-author of the article, 'Clustering on functional data' submitted to the journal 'PeerJ - the journal of life and environmental sciences ' which is contained within this dissertation.; Mark C. Greenwood was a co-author of the article, 'Monothetic clustering and partitioning using local subregions: the R packages monoClust and PULS' submitted to the journal 'The journal of open source software' which is contained within this dissertation.Monothetic clustering is a divisive clustering method that uses a hierarchical, recursive partitioning of multivariate responses based on binary decision rules that are built from individual response variables. This clustering technique is helpful for applications where the rules of groupings of observations as well as predicting new subjects into clusters are both important. Based on the ideas of classification and regression trees, a monothetic clustering algorithm was implemented in R to allow further explorations and modifications. One of the common problems in performing clustering is deciding whether a cluster structure is present and, if it is, how many clusters are 'enough'. Some well-established techniques are reviewed as well as new methods based on cross-validation and permutation-based hypothesis tests at each split are suggested. Monothetic clustering is of interest to be applied in a variety of situations. This can include data sets with circular variables, where the variables' natures are not linear. A method for monothetic clustering and visualizations of clusters with circular variables was developed that could also be used in other classification and regression tree situations. Clustering is also interesting for data sets where the responses can be transformed into functional data, which has unique properties that need exploring. Partitioning Using Local Subregions (PULS), a clustering technique inspired by monothetic clustering to overcome some of its disadvantages in clustering functional data, is discussed. In this algorithm, clusters are formed based on aggregating the information from several variables or time intervals. In both monothetic clustering and PULS, it is possible to limit the set of feasible splitting variables to be able to create clusters for new observations without observing all variables or times to assign new observations to the clusters. R packages for these methods have been developed for others to use and test and support the proposed research, and a detailed vignette is provided for utilizing all the functions developed here.