본문

서브메뉴

Assumption-Lean Approaches to Modern Statistical Inference
Assumption-Lean Approaches to Modern Statistical Inference
Assumption-Lean Approaches to Modern Statistical Inference

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103617
ISBN  
9798286453030
DDC  
310
저자명  
Hore, Rohan.
서명/저자  
Assumption-Lean Approaches to Modern Statistical Inference
발행사항  
[Sl] : The University of Chicago, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
286 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Foygel Barber, Rina.
학위논문주기  
Thesis (Ph.D.)--The University of Chicago, 2025.
초록/해제  
요약In the modern era of machine learning, where increasingly complex models drive decision-making, statistical inference becomes challenging. Assumption-lean inference minimizes reliance on distributional assumptions, ensuring robustness across diverse settings. This thesis explores two key aspects-predictive inference via conformal prediction and conditional independence testing-each providing practical, interpretable solutions to real-world challenges. The first part investigates distribution-free predictive inference. Conformal prediction (CP) constructs prediction intervals with distribution-free guarantees, but its validity relies on exchangeability and only ensures marginal coverage, leading to failures in non-i.i.d. settings, undercoverage for certain subpopulations, or discrepancies when test and training distributions differ. We address these limitations in two steps. First, in survival analysis, where right-censoring restricts observation of true survival times, we propose a novel lower prediction bound using a data-adaptive filter that excludes low censoring times, ensuring valid marginal coverage under mild conditions. Next, we tackle local coverage, aiming for prediction intervals that retain validity for each feature configuration. While exact local coverage is theoretically impossible, we introduce randomly-localized conformal prediction (RLCP), a framework that provides interpretable guarantees for relaxed notions of local validity, such as approximate coverage under smooth covariate shifts or within sufficiently large subpopulations. The second part develops assumption-lean tests for conditional independence. Given the inherent difficulties of testing conditional independence in a distribution-free manner, we propose a test for the conditional independence of X and Y given Z, under the assumption that X is stochastically increasing in Z. Our procedure, PairSwap-ICI, offers significant flexibility while ensuring finite-sample Type I error control and achieving high power against a broad range of alternatives that deviate sufficiently from the null.
일반주제명  
Statistics
일반주제명  
Applied mathematics
키워드  
Assumption-lean inference
키워드  
Conformal prediction
키워드  
Distribution-free inference
키워드  
Shape-constrained testing
기타저자  
The University of Chicago Statistics
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357917
■00520260202103617
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798286453030
■035    ▼a(MiAaPQ)AAI32044859
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aHore,  Rohan.▼0(orcid)0000-0001-7670-9700
■24510▼aAssumption-Lean  Approaches  to  Modern  Statistical  Inference
■260    ▼a[Sl]▼bThe  University  of  Chicago▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a286  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Foygel  Barber,  Rina.
■5021  ▼aThesis  (Ph.D.)--The  University  of  Chicago,  2025.
■520    ▼aIn  the  modern  era  of  machine  learning,  where  increasingly  complex  models  drive  decision-making,  statistical  inference  becomes  challenging.  Assumption-lean  inference  minimizes  reliance  on  distributional  assumptions,  ensuring  robustness  across  diverse  settings.  This  thesis  explores  two  key  aspects-predictive  inference  via  conformal  prediction  and  conditional  independence  testing-each  providing  practical,  interpretable  solutions  to  real-world  challenges.  The  first  part  investigates  distribution-free  predictive  inference.  Conformal  prediction  (CP)  constructs  prediction  intervals  with  distribution-free  guarantees,  but  its  validity  relies  on  exchangeability  and  only  ensures  marginal  coverage,  leading  to  failures  in  non-i.i.d.  settings,  undercoverage  for  certain  subpopulations,  or  discrepancies  when  test  and  training  distributions  differ.  We  address  these  limitations  in  two  steps.  First,  in  survival  analysis,  where  right-censoring  restricts  observation  of  true  survival  times,  we  propose  a  novel  lower  prediction  bound  using  a  data-adaptive  filter  that  excludes  low  censoring  times,  ensuring  valid  marginal  coverage  under  mild  conditions.  Next,  we  tackle  local  coverage,  aiming  for  prediction  intervals  that  retain  validity  for  each  feature  configuration.  While  exact  local  coverage  is  theoretically  impossible,  we  introduce  randomly-localized  conformal  prediction  (RLCP),  a  framework  that  provides  interpretable  guarantees  for  relaxed  notions  of  local  validity,  such  as  approximate  coverage  under  smooth  covariate  shifts  or  within  sufficiently  large  subpopulations.  The  second  part  develops  assumption-lean  tests  for  conditional  independence.  Given  the  inherent  difficulties  of  testing  conditional  independence  in  a  distribution-free  manner,  we  propose  a  test  for  the  conditional  independence  of  X  and  Y  given  Z,  under  the  assumption  that  X  is  stochastically  increasing  in  Z.  Our  procedure,  PairSwap-ICI,  offers  significant  flexibility  while  ensuring  finite-sample  Type  I  error  control  and  achieving  high  power  against  a  broad  range  of  alternatives  that  deviate  sufficiently  from  the  null.
■590    ▼aSchool  code:  0330.
■650  4▼aStatistics
■650  4▼aApplied  mathematics
■653    ▼aAssumption-lean  inference
■653    ▼aConformal  prediction
■653    ▼aDistribution-free  inference
■653    ▼aShape-constrained  testing
■690    ▼a0463
■690    ▼a0800
■690    ▼a0364
■71020▼aThe  University  of  Chicago▼bStatistics.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0330
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357917▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF17091 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.