---
OA_place: repository
OA_type: green
_id: '20303'
abstract:
- lang: eng
  text: Observational genome-wide association studies are now widely used for causal
    inference in genetic epidemiology. To maintain privacy, such data is often only
    publicly available as summary statistics, and often studies for the endogenous
    covariates and the outcome are available separately. This has necessitated methods
    tailored to two-sample summary statistics. Current state-of-the-art methods modify
    linear instrumental variable (IV) regression---with genetic variants as instruments---to
    account for unmeasured confounding. However, since the endogenous covariates can
    be high dimensional, standard IV assumptions are generally insufficient to identify
    all causal effects simultaneously. We ensure identifiability by assuming the causal
    effects are sparse and propose a sparse causal effect two-sample IV estimator,
    spaceTSIV, adapting the spaceIV estimator by Pfister and Peters (2022) for two-sample
    summary statistics. We provide two methods, based on L0- and L1-penalization,
    respectively. We prove identifiability of the sparse causal effects in the two-sample
    setting and consistency of spaceTSIV. The performance of spaceTSIV is compared
    with existing two-sample IV methods in simulations. Finally, we showcase our methods
    using real proteomic and gene-expression data for drug-target discovery.
acknowledgement: "The authors would like to thank Stephen Burgess and Ashish Patel
  for helpful discussions at\r\nthe start of this research project, and Anton Rask
  Lundborg for helpful discussions on the\r\nuniform asymptotic results. This work
  was partially completed during SH’s research visit at\r\nNovo Nordisk. The authors
  would like to thank Jesper Ferkinghoff-Borg, Kang Li and Lewis\r\nMarsh for facilitating
  this visit and for discussing necessary concepts and tools in statistical\r\ngenetics
  at an early stage. SH and NP are supported by a research grant (0069071) from Novo\r\nNordisk
  Fonden. JB is funded at the University of Exeter by research grant MR/X011372/1."
alternative_title:
- PMLR
article_processing_charge: No
arxiv: 1
author:
- first_name: Shimeng
  full_name: Huang, Shimeng
  id: 989c2a06-fb4e-11ef-a992-ab766442255b
  last_name: Huang
  orcid: 0000-0001-6919-821X
- first_name: Niklas
  full_name: Pfister, Niklas
  last_name: Pfister
- first_name: Jack
  full_name: Bowden, Jack
  last_name: Bowden
citation:
  ama: 'Huang S, Pfister N, Bowden J. Sparse causal effect estimation using two-sample
    summary statistics in the presence of unmeasured confounding. In: <i>The 28th
    International Conference on Artificial Intelligence and Statistics</i>. Vol 258.
    ML Research Press; 2025:3394-3402.'
  apa: 'Huang, S., Pfister, N., &#38; Bowden, J. (2025). Sparse causal effect estimation
    using two-sample summary statistics in the presence of unmeasured confounding.
    In <i>The 28th International Conference on Artificial Intelligence and Statistics</i>
    (Vol. 258, pp. 3394–3402). Mai Khao, Thailand: ML Research Press.'
  chicago: Huang, Shimeng, Niklas Pfister, and Jack Bowden. “Sparse Causal Effect
    Estimation Using Two-Sample Summary Statistics in the Presence of Unmeasured Confounding.”
    In <i>The 28th International Conference on Artificial Intelligence and Statistics</i>,
    258:3394–3402. ML Research Press, 2025.
  ieee: S. Huang, N. Pfister, and J. Bowden, “Sparse causal effect estimation using
    two-sample summary statistics in the presence of unmeasured confounding,” in <i>The
    28th International Conference on Artificial Intelligence and Statistics</i>, Mai
    Khao, Thailand, 2025, vol. 258, pp. 3394–3402.
  ista: 'Huang S, Pfister N, Bowden J. 2025. Sparse causal effect estimation using
    two-sample summary statistics in the presence of unmeasured confounding. The 28th
    International Conference on Artificial Intelligence and Statistics. AISTATS: Conference
    on Artificial Intelligence and Statistics, PMLR, vol. 258, 3394–3402.'
  mla: Huang, Shimeng, et al. “Sparse Causal Effect Estimation Using Two-Sample Summary
    Statistics in the Presence of Unmeasured Confounding.” <i>The 28th International
    Conference on Artificial Intelligence and Statistics</i>, vol. 258, ML Research
    Press, 2025, pp. 3394–402.
  short: S. Huang, N. Pfister, J. Bowden, in:, The 28th International Conference on
    Artificial Intelligence and Statistics, ML Research Press, 2025, pp. 3394–3402.
conference:
  end_date: 2025-05-05
  location: Mai Khao, Thailand
  name: 'AISTATS: Conference on Artificial Intelligence and Statistics'
  start_date: 2025-05-03
date_created: 2025-09-07T22:01:35Z
date_published: 2025-05-01T00:00:00Z
date_updated: 2025-09-09T07:47:13Z
day: '01'
department:
- _id: FrLo
external_id:
  arxiv:
  - '2410.12300'
intvolume: '       258'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.2410.12300
month: '05'
oa: 1
oa_version: Preprint
page: 3394-3402
publication: The 28th International Conference on Artificial Intelligence and Statistics
publication_identifier:
  eissn:
  - 2640-3498
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
scopus_import: '1'
status: public
title: Sparse causal effect estimation using two-sample summary statistics in the
  presence of unmeasured confounding
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 258
year: '2025'
...
