@article{1481061,
      recid = {1481061},
      author = {Sorensen, Daniel.},
      title = {Statistical learning in genetics : an introduction using R  /},
      publisher = {Springer International Publishing AG,},
      address = {Cham :},
      pages = {1 online resource (xvi, 693 pages).},
      year = {2023},
      note = {Description based upon print version of record.},
      abstract = {This book provides an introduction to computer-based  methods for the analysis of genomic data. Breakthroughs in  molecular and computational biology have contributed to the  emergence of vast data sets, where millions of genetic  markers for each individual are coupled with medical  records, generating an unparalleled resource for linking  human genetic variation to human biology and disease.  Similar developments have taken place in animal and plant  breeding, where genetic marker information is combined with  production traits. An important task for the statistical  geneticist is to adapt, construct and implement models that  can extract information from these large-scale data. An  initial step is to understand the methodology that  underlies the probability models and to learn the modern  computer-intensive methods required for fitting these  models. The objective of this book, suitable for readers  who wish to develop analytic skills to perform genomic  research, is to provide guidance to take this first step.  This book is addressed to numerate biologists who typically  lack the formal mathematical background of the professional  statistician. For this reason, considerably more detail in  explanations and derivations is offered. It is written in a  concise style and examples are used profusely. A large  proportion of the examples involve programming with the  open-source package R. The R code needed to solve the  exercises is provided. The MarkDown interface allows the  students to implement the code on their own computer,  contributing to a better understanding of the underlying  theory. Part I presents methods of inference based on  likelihood and Bayesian methods, including computational  techniques for fitting likelihood and Bayesian models. Part  II discusses prediction for continuous and binary data  using both frequentist and Bayesian approaches. Some of the  models used for prediction are also used for gene  discovery. The challenge is to find promising genes without  incurring a large proportion of false positive results.  Therefore, Part II includes a detour on False Discovery  Rate assuming frequentist and Bayesian perspectives. The  last chapter of Part II provides an overview of a selected  number of non-parametric methods. Part III consists of  exercises and their solutions. Daniel Sorensen holds PhD  and DSc degrees from the University of Edinburgh and is an  elected Fellow of the American Statistical Association. He  was professor of Statistical Genetics at Aarhus University  where, at present, he is professor emeritus.},
      url = {http://library.usi.edu/record/1481061},
      doi = {https://doi.org/10.1007/978-3-031-35851-7},
}