2,324 research outputs found
High-dimensional inference and confidence sets of models
No full textIn high-dimensional regression problems, a key aim is to identify a sparse model that fits
the data well. This may be used to form accurate predictions or to gain subject-matter
understanding. When strong dependence is present among covariates, it is common for
many models to fit the data equally well. Whilst it is sufficient to report a single model for
prediction, when the goal is to gain subject-matter understanding, Cox & Battey (2017)
argue that a confidence set of models – a set consisting of all models of appropriate fit
– should be reported and propose a method to achieve this aim. This thesis provides a
theoretical elucidation of this approach, and based on the results, explores further ideas
in high-dimensional data analysis.Open Acces
HCmodelSets: An R package for specifying sets of well-fitting models in high dimensions
No full textIn the context of regression with a large number of explanatory variables, Cox and Battey(2017) emphasize that if there are alternative reasonable explanations of the data that are statisticallyindistinguishable, one should aim to specify as many of these explanations as is feasible. The standardpractice, by contrast, is to report a single model effective for prediction. The present paper illustratesthe R implementation of the new ideas in the packageHCmodelSets, using simple reproducibleexamples and real data. Results of some simulation experiments are also reported
HCmodelSets: An R Package for Specifying Sets of Well-fitting Models in High Dimensions
No full textIn the context of regression with a large number of explanatory variables, Cox and Battey (2017) emphasize that if there are alternative reasonable explanations of the data that are statistically indistinguishable, one should aim to specify as many of these explanations as is feasible. The standard practice, by contrast, is to report a single effective model for prediction. This paper illustrates the R implementation of the new ideas in the package HCmodelSets, using simple reproducible examples and real data. Results of some simulation experiments are also reported
Heather Battey's contribution to the Discussion of 'Assumption-lean inference for generalised linear model parameters' by Vansteelandt and Dukes
No full textA topologically valid construction of depth for functional data
No full textNumerous problems remain in the construction of statistical depth for functional data. Issues stem largely from the absence of a well-conceived notion of symmetry. The present paper proposes a topologically valid notion of symmetry for distributions on functional metric spaces and a corresponding notion of depth. The latter is shown to satisfy the axiomatic definition of functional depth introduced by Nieto-Reyes and Battey (2016).The work was supported by a UK Engineering and Physical Sciences Research Council research fellowship (to HSB) and a Spanish Ministerio de Ciencia, Innovación y Universidades grant MTM2017-86061-C2-2-P (to AN-R)
The Times, They Are Changing
No full textIn 2015, Rutgers became only the second accredited law school in the United States to select the open-source ILS, Koha. The merger of two unique catalogs at Rutgers Law School has presented unique challenges with respect to migration mapping, data recall for large records, and relevancy ranking, all of which affect search results and usability of the OPAC. System migrations always result in some data being lost or incorrectly transferred. The hope is to minimize just how much data is compromised while fixing errors that might not have come to light but for the migration.Peer reviewe
Heather McHugh, 4th Annual ODU Literary Festival
No full textThe author of Dangers, published in 1978 in Houghton Mifflin\u27s New Poetry Series, and A World of Difference, also a Houghton Mifflin publication (1981), Heather McHugh is a rare poet, known for her formal elegance, her piercing wit, and her supple use of rhyme and rhythm. The Denver Quarterly remarked on her interest in seeing doubly and double-talking and praised her passionate intelligence and affection for the tongue\u27s intimate intricacies. McHugh\u27s Thursday evening reading will conclude the 1981 Literary Festival. McHugh grew up in Williamsburg and now teaches at the State University of New York at Binghamton. She is a member of the board of directors of the Associated Writing Programs
Ep. #121 - Heather Paxson
No full textThis recording and transcript form part of a collection of podcasts conducted by the Cultures of Energy at Rice University. Cultures of Energy brings writers, artists and scholars together to talk, think and feel their way into the Anthropocene. We cover serious issues like climate change, species extinction and energy transition. But we also try to confront seemingly huge and insurmountable problems with insight, creativity and laughter.Dominic and Cymene plug Cultures of Energy 7—this year’s energy humanities symposium at Rice which begins today, details at culturesofenergy.org—and then they turn to cheese, why it’s funny, how it can be applied to cats, “cheddaring,” and much more. Is there an anthropologist who knows more about cheese than anyone? Yes of course there is, it’s MIT’s Heather Paxson, author of the award-winning The Life of Cheese: Crafting Food and Value in America (U California Press, 2012). She joins us (14:59) to talk about her research on the microbiopolitics of food and naturally we begin with what’s in her fridge. Heather tells us about her investigation of artisanal cheesemaking and what it tells us about the shift from Pasteurian to Post-Pasteurian regimes of microbiopower. We hear about goat ladies as revolutionaries, the truth about vegan cheese, and debate whether artisanal foodmaking is an elite project. Heather discusses the search for moral meaning in everyday life as a throughline in her work and we turn to her latest research on food safety inspections, the porosity of food borders and the synecdochic reasoning of the state when it comes to managing food flows. We close by discussing the impact of feminist analytics of labor in her research. What is “beef candy China”? Listen on and you might just find out
Cox reduction and confidence sets of models: a theoretical elucidation
No full textFor sparse high-dimensional regression problems, Cox and Battey [2, 14] emphasised the need for confidence sets of models: an enumeration of those small sets of variables that fit the data equivalently well in a suitable statistical sense. This is to be contrasted with the single model returned by penalised regression procedures, effective for prediction but potentially misleading for subject-matter understanding. The proposed construction of such sets relied on preliminary reduction of the full set of variables. While various possibilities could be considered for this, [14] proposed a succession of regression fits based on incomplete block designs. The purpose of the present paper is to provide insight on both aspects of [14]. For an unspecified reduction strategy, we begin by characterising models that are likely to be retained in the model confidence set, emphasising geometric aspects. We then evaluate possible reduction schemes based on penalised regression or marginal screening, before theoretically elucidating the reduction of [14]. We identify features of the covariate matrix that may reduce its efficacy, and indicate improvements to the original proposal. An advantage of the approach is its ability to reveal its own stability or fragility for the data at hand
HERStory Makers 2023: Heather Mcclelland
No full textHeather Mcclelland is a chartered psychologist and researcher at the University of Glasgow studying mental health. She took part in HERStory Makers 2023.What is HERStory Makers?HERStory Makers is a social media competition for female-identifying early career researchers to share their research, their career journeys, and to inspire the next generation. Winners are selected by public vote. HERStory Makers is also part of EXPLORATHON, Scotland's contribution to European Researchers' Night.In 2022-23, EXPLORATHON was supported by the Engineering & Physical Sciences Research Council [grant number EP/X020762/1].Author contributions to contentHeather Mcclelland conceived, planned, and recorded the video content. Kirsty Ross edited the video content to insert HERStory Maker credits, add subtitles, and ensured the video length was below Twitter/X limit of 2 mins and 20 secs.</p
- …
