Between Dec 19, 2024 and Jan 2, 2025, datasets can be submitted to DRUM but will not be processed until after the break. Staff will not be available to answer email during this period, and will not be able to provide DOIs until after Jan 2. If you are in need of a DOI during this period, consider Dryad or OpenICPSR. Submission responses to the UDC may also be delayed during this time.

Browsing by Subject "Bayesian hierarchical model"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Network-based mixture models for genomic data.
    (2009-06) Wei, Peng
    A common task in genomic studies is to identify genes satisfying certain conditions, such as differentially expressed genes between normal and tumor tissues or regulatory target genes of a transcription factor (TF). Standard approaches treat all the genes identically and independently a priori and ignore the fact that genes work coordinately in biological processes as dictated by gene networks, leading to inefficient analysis and reduced power. We propose incorporating gene network information as prior biological knowledge into statistical modeling of genomic data to maximize the power for biological discoveries. We propose a spatially correlated mixture model based on the use of latent Gaussian Markov random fields (GMRF) to smooth gene specific prior probabilities in a mixture model over a network, assuming that neighboring genes in a network are functionally more similar to each other. In addition, we propose a Bayesian implementation of a discrete Markov random field (DMRF)-based mixture model for incorporating gene network information, and compare its performance with that based on Gaussian Markov random fields. We also extend the network-based mixture models to ones that are able to integrate multiple gene networks and diverse types of genomic data, such as protein- DNA binding, gene expression and DNA sequence data, to accurately identify regulatory target genes of a TF. Applications to high-throughput microarray data, along with simulations, demonstrate the utility of the new methods and the statistical efficiency gains over other methods.
  • Thumbnail Image
    Item
    Statistical Analysis of Moose Habitat Behaviors Using Bayesian Hierarchical Model with Spatially Varying Coefficients
    (2017-06) Kroc, Matej
    In the past few years interest in statistical modeling has rapidly increased for scientists in many different fields. With new technologies and the ability to collect larger amounts of data they sought a tool which would help them to get a better understanding, and eventually, prediction of behavior of subjects in their range of study. For biologists and ecologists habitat data is necessary to develop effective conservation and management strategies, and help determine what is behind the change in the population of different species. Our research is focused on the moose habitat behavior statistics. Moose, Alces alces, are the largest of all deer species. Male moose are recognizable by their huge antlers, which can spread up to 6 feet wide. Because of their tall body, they prefer to browse higher shrubs and their typical habitat is a dense mixed boreal forest in North America, including the northern United States, Canada, Alaska, and in Scandinavia and Russia. Despite their large bodies, moose are good swimmers and are often seen in lakes and rivers feeding on aquatic plants both at and below the surface. One of the reasons why moose habitat behavior is the subject of study by many biologists is recent changes in population in North America. Since the 1990's, the moose population in northern Minnesota has decline significantly. Based on a moose population survey from 2017, the population in northeastern Minnesota has dropped from about 8; 000 moose to a stable population of just under 4; 000 moose over the last 4 years. Meanwhile, the northwestern Minnesotan population practically disappeared after declining from 4; 000 to fewer than 100. The reason behind this steep drop is unknown. Many scientists believe that it could be caused by climate change. Shorter winters and longer falls give more time for parasites, especially winter ticks, to find a host. For purposes of research, moose wore GPS collars, which allow biologists to track their location and collect essential data for future work. In some cases, moose received a tiny transmitter which monitored their heart rate and temperature and notified biologists when the moose died. This work intends to utilize the Bayesian hierarchic model with spatially varying coefficients to obtain better insights into moose habitat behavior in Northern Minnesota.