Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Hierarchical time-oriented approaches to missing data inference.

K M Albridge1, J Standish, J F Fries

  • 1Department of Medicine, Stanford University School of Medicine, California 94305.

Computers and Biomedical Research, an International Journal
|August 1, 1988
PubMed
Summary

Accurate clinical data inference is crucial. This study found that tailored, time-oriented strategies, like interpolation, provide more precise missing data estimations than standard methods.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Disability outcomes and dose escalation with etanercept, adalimumab, and infliximab in rheumatoid arthritis patients: a US-based retrospective comparative effectiveness study.

Current medical research and opinion·2012
Same author

Oral sucrose for procedural pain in infants.

Lancet (London, England)·2011
Same author

Lymphoma and luekemia in rheumatoid arthritis: are they associated with azathioprine, cyclophosphamide, or methotrexate?

Journal of clinical rheumatology : practical reports on rheumatic & musculoskeletal diseases·2008
Same author

More on scleroderma renal crisis.

Journal of clinical rheumatology : practical reports on rheumatic & musculoskeletal diseases·2008
Same author

The epidemiology of NSAID gastropathy: the ARAMIS experience.

Journal of clinical rheumatology : practical reports on rheumatic & musculoskeletal diseases·2008
Same author

Evaluation of a preliminary physical function item bank supported the expected advantages of the Patient-Reported Outcomes Measurement Information System (PROMIS).

Journal of clinical epidemiology·2007

Area of Science:

  • Biostatistics
  • Clinical Informatics
  • Data Science

Background:

  • Clinical data are frequently incomplete in practice.
  • Physicians and researchers must infer missing information for accurate analysis.
  • Various imputation strategies exist, ranging from simple to complex.

Purpose of the Study:

  • To analyze and compare different imputation strategies for missing clinical data.
  • To identify the most accurate methods for inferring missing values in time-oriented datasets.
  • To evaluate the impact of data characteristics and missingness patterns on imputation accuracy.

Main Methods:

  • Analysis of imputation strategies using a time-oriented data bank of patients with systemic lupus erythematosus.
  • Evaluation of nine distinct inference strategies: interpolation, extrapolation, nearest value, previous value, patient-specific mean/regression, disease-specific mean, normal values, and regression of correlated variables.

Related Experiment Videos

  • Development and application of a hierarchical, stepwise approach incorporating ranked strategies tailored to variable characteristics.

    • Main Results:

    • Interpolation emerged as the most effective single imputation technique for the studied dataset.
    • Time-oriented strategies (e.g., interpolation) significantly outperformed non-time-oriented methods (e.g., disease-specific mean).
    • Hierarchical, time-oriented imputation approaches yielded inferences with significantly smaller mean differences from actual values compared to typical statistical package strategies.

    Conclusions:

    • Tailoring imputation strategies to individual variable characteristics and incorporating time-oriented methods are key to accurate missing data inference.
    • A hierarchical, stepwise approach to imputation, considering the nonrandomness of missing data, improves precision.
    • The proposed methods offer superior accuracy for handling incomplete clinical data compared to conventional statistical approaches.