Person:
Gruber, Susan

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Gruber

First Name

Susan

Name

Gruber, Susan
Author's Publications: search.filters.isAuthorOfPublication.b6a299fa-a14a-4f9a-b917-622604f29112

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Evaluating treatment effectiveness under model misspecification: A comparison of targeted maximum likelihood estimation with bias-corrected matching
    (SAGE Publications, 2014) Kreif, Noémi; Gruber, Susan; Radice, Rosalba; Grieve, Richard; Sekhon, Jasjeet S
    Statistical approaches for estimating treatment effectiveness commonly model the endpoint, or the propensity score, using parametric regressions such as generalised linear models. Misspecification of these models can lead to biased parameter estimates. We compare two approaches that combine the propensity score and the endpoint regression, and can make weaker modelling assumptions, by using machine learning approaches to estimate the regression function and the propensity score. Targeted maximum likelihood estimation is a double-robust method designed to reduce bias in the estimate of the parameter of interest. Bias-corrected matching reduces bias due to covariate imbalance between matched pairs by using regression predictions. We illustrate the methods in an evaluation of different types of hip prosthesis on the health-related quality of life of patients with osteoarthritis. We undertake a simulation study, grounded in the case study, to compare the relative bias, efficiency and confidence interval coverage of the methods. We consider data generating processes with non-linear functional form relationships, normal and non-normal endpoints. We find that across the circumstances considered, bias-corrected matching generally reported less bias, but higher variance than targeted maximum likelihood estimation. When either targeted maximum likelihood estimation or bias-corrected matching incorporated machine learning, bias was much reduced, compared to using misspecified parametric models.
  • Thumbnail Image
    Publication
    The Risk of Febrile Seizures Following Influenza and 13-Valent Pneumococcal Conjugate Vaccines
    (Oxford University Press, 2017) Baker, Meghan; Jankosky, Christopher; Yih, Katherine; Gruber, Susan; Li, Lingling; Cocoros, Noelle; Lipowicz, Hana; Coronel-Moreno, Claudia; Feibelmann, Sandra; Lin, Nancy; McMahill-Walraven, Cheryl; Menschik, David; Selvan, Mano; Selvam, Nandini; Tilney, Rong Chen; Zichittella, Lauren; Lee, Grace; Kawai, Alison Tse
    Abstract Background: Evidence on the risk of febrile seizures (FS) after vaccination with inactivated influenza vaccine (IIV) and 13-valent pneumococcal conjugate vaccine (PCV13) is mixed. Among children 6–23 months, we examined the risk of FS following IIV and PCV13 during the 2013–14 and 2014–15 influenza seasons, for which vaccine virus strains were the same. Methods: We used claims data from 4 large national insurers in the FDA-sponsored Sentinel Initiative, which was developed to monitor the safety of FDA-regulated medical products. With a self-controlled risk interval design, the risk of FS in 0–1 days following IIV and following PCV13 was compared with a comparison interval (14–20 days), adjusting for confounding by age, calendar time, and concomitant vaccination with the other vaccine. In exploratory analyses, we assessed whether the effect of IIV is modified by concomitant administration of PCV13. Results: During the study period, 355,486 children received IIV and 581,868 received PCV13. We observed an incidence rate ratio (IRR) of 1.12 (95% CI 0.80, 1.56) for the risk of FS following IIV after adjustment for age, calendar time and concomitant PCV13. PCV13 was associated with an increased risk of FS (IRR adjusted for age, calendar time and concomitant IIV, 1.80, 95% CI 1.29, 2.52). The attributable risk for PCV13 ranged from 0.33 to 5.16 per 100,000 doses. The age and calendar-time adjusted IRR comparing exposed time to unexposed time was greater for concomitant IIV and PCV13 (IRR 2.80, 95% CI 1.63, 4.83), as compared with that for PCV13 without concomitant IIV (IRR 1.54, 95% CI 1.04, 2.28). However, the formal test assessing for interaction between IIV and PCV13 was not statistically significant. Conclusion: We found an elevated risk of FS after PCV13 vaccine but not after IIV, when adjusting for concomitant administration of the other vaccine. We found some evidence to suggest that concomitant administration of IIV with PCV13 might interact to increase the risk beyond the independent effects of PCV13, but the study was not powered to assess this interaction. The risk of seizures associated with PCV13 is low compared with a child’s lifetime risk of FS. Findings should be interpreted in the context of the importance of preventing influenza and pneumococcal infections in young children. Disclosures L. Li, sanofi pasteur: The author is currently employed by Sanofi Genzyme, which shares the same parent company as sanofi pasteur, the manufacturer of the Flu vaccine. However, the work was done while this author was still employed by Harvard Pilgrim Health Care Institute., No financial benefit received