Browsing by Subject "Bayesian Inference"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Credible Subgroups: Identifying the Population that Benefits from Treatment
    (2017-05) Schnell, Patrick
    A single treatment may have a different effect on different patients. In particular, some patients may benefit from a given treatment while others do not. Often, some of the variation in effect among patients can often be explained by characteristics of those patients that are observable before treatment. Widespread acknowledgment of treatment effect variation due to observable patient characteristics has increased the health science community's interest in a broad field referred to as personalized or precision medicine. Among the aims of precision medicine are identifying the set of treatments that would benefit a given patient, and conversely, identifying the population of patients who would benefit from a given treatment. We treat the latter problem in the context of clinical trials run by treatment developers (e.g., pharmaceutical companies), with special attention paid to interactions between those developers and the relevant regulatory agencies (e.g., the US Food and Drug Administration). The primary difficulty in estimating the benefiting population in such settings is controlling the frequency with which at least one type of patient is incorrectly determined to benefit, and doing so in a way that does not render the approach excessively conservative. As a motivating application throughout this dissertation, we consider a battery of related clinical trials of treatments for Alzheimer's disease carried out by the pharmaceutical company AbbVie. These trials contain a small number of continuous and binary baseline patient characteristics that may influence the treatment effect. We apply standard and more novel regression models to the supplied data and develop methods of inference to accommodate the varied features of the datasets, such as nonlinear effects, multiple important endpoints, more than two treatments, and regions of the covariate space that are sparse in observations or lacking common support among treatment arms. We also discuss topics in practical implementation of these methods. Our approaches yield reliable and easily interpretable inferences regarding the population that benefits from treatment.
  • Thumbnail Image
    Item
    Microbial Husbandry: Nurturing Microbes to Capture Soil Ecosystem Services
    (2018-09) Ewing, Patrick
    Soil microbes drive many agroecosystem functions that dictate crop productivity, environmental outcomes, and management costs. Chapter 2 introduces microbial husbandry, a framework to manage soil microbes by creating soil conditions that allow critical taxa to thrive. Subsequent chapters apply microbial husbandry to nutrient cycling under maize (Zea mays L.) using a model system, ridge tillage and rye cover cropping (Secale cereale L.). We tested hypotheses with Bayesian structural equation modeling. In Chapter 3, arbuscular mycorrhizal fungi (AMF) insured against early season phosphorus (P) deficiency: AMF contributed to 40% higher maize P uptake in ridge till, at a 7% growth cost. Managers may increase P uptake by reducing physical disturbance to increase AMF abundance, and by increasing bulk density beyond levels in chisel plow. For Chapter 4, we wrote pyroots, a Python computer vision module, to measure roots and fungal hyphae in environmental samples cheaply and reproducibly (Appendix A; www.github.com/pme1123/pyroots). We also reported the first AMF hyphal length density values at 60 cm depth. Hyphal growth was independent of maize root growth, which suggests roots and hyphae can be managed independently. In Chapter 5, filamentous fungi acquired as much mineral nitrogen (N) as maize roots over five weeks after planting. While most root N uptake occurred in rows, fungal uptake occurred in both rows and inter-rows. Managers may encourage fungal N uptake without competing with crop needs by concentrating crop residue in the inter-rows. Overall, microbial husbandry helped us manage competing microbial functions simultaneously: nutrient provisioning in rows, and fertility building in inter-rows. Context-appropriate management tools can create soil conditions that enable microbes to perform these functions.