Metraipolis › archive › dc_8e8eb7550abe

Imputing Missing Data in Longitudinal Life-Logging Athlete Data — arXiv:2610.41226

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41226
License (as archived)
CC0-1.0
Archived
2026-11-03T05:39:57.738Z
SHA-256 of the archived text
ffc0c2ca7eda2703041e964730f238d1d08332c3036000eeb134cc99516395b4
Stable URL of this page
https://metraipolis.com/documento/dc_8e8eb7550abe

How to cite

Imputing Missing Data in Longitudinal Life-Logging Athlete Data — arXiv:2610.41226 — arXiv (en), https://arxiv.org/abs/2610.41226 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e8eb7550abe (Metraipolis archive dc_8e8eb7550abe, sha256 ffc0c2ca7eda2703041e964730f238d1d08332c3036000eeb134cc99516395b4)
BibTeX
@misc{dc8e8eb7550abe,
  title = {Imputing Missing Data in Longitudinal Life-Logging Athlete Data — arXiv:2610.41226},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41226},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e8eb7550abe; sha256 ffc0c2ca7eda2703041e964730f238d1d08332c3036000eeb134cc99516395b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41226. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term, diverse personal informatics data enables athletes to understand and act on their health and performance goals, whether assessing readiness right now, tracking how soreness relates to training load over time, or predicting how sleep affects next-day performance. However, the inherent missingness in longitudinal data, if handled inappropriately, can bias these analyses. To our knowledge, no prior work has systematically benchmarked classical and deep learning imputation methods on long-term self-tracking data from athlete populations. We evaluate six imputation methods across four missingness mechanisms at missingness rates spanning 10-80%. Using seven diverse long-term self-tracking datasets from 231 individuals, we assess both point accuracy and the preservation of temporal and multivariate structure. Our results show that no single method dominates across all conditions and reveal a critical trade-off: while PAIN is superior on point-wise accuracy, deep learning methods (BRITS, GRU-D, and GRIN) are better at preserving multivariate and temporal structure, particularly under higher missingness. Our findings offer a practical, goal-conditioned framework that guides researchers in selecting imputation strategies aligned with both the underlying missingness mechanism and the specific analytical goal of long-term self-tracking studies.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.41226 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T05:23:57.964Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).