Dataset Information

Falsification Testing of Instrumental Variables Methods for Comparative Effectiveness Research.

ABSTRACT: To demonstrate how falsification tests can be used to evaluate instrumental variables methods applicable to a wide variety of comparative effectiveness research questions.Brief conceptual review of instrumental variables and falsification testing principles and techniques accompanied by an empirical application. Sample STATA code related to the empirical application is provided in the Appendix.Comparative long-term risks of sulfonylureas and thiazolidinediones for management of type 2 diabetes. Outcomes include mortality and hospitalization for an ambulatory care-sensitive condition. Prescribing pattern variations are used as instrumental variables.Falsification testing is an easily computed and powerful way to evaluate the validity of the key assumption underlying instrumental variables analysis. If falsification tests are used, instrumental variables techniques can help answer a multitude of important clinical questions.

SUBMITTER: Pizer SD

PROVIDER: S-EPMC4799892 | biostudies-other | 2016 Apr

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Falsification Testing of Instrumental Variables Methods for Comparative Effectiveness Research.

Pizer Steven D SD

Health services research 20150821 2

<h4>Objectives</h4>To demonstrate how falsification tests can be used to evaluate instrumental variables methods applicable to a wide variety of comparative effectiveness research questions.<h4>Study design</h4>Brief conceptual review of instrumental variables and falsification testing principles and techniques accompanied by an empirical application. Sample STATA code related to the empirical application is provided in the Appendix.<h4>Empirical application</h4>Comparative long-term risks of su ...[more]

PMID: 26293167

Similar Datasets

Project description:BackgroundWe used various methods for identifying and prioritizing patient-centered outcomes (PCOs) for comparative effectiveness research (CER).MethodsWe considered potential PCOs ("benefits" and "harms") related to (1) gabapentin for neuropathic pain and (2) quetiapine for bipolar depression. Part 1 (April 2014 to March 2015): we searched for PCO research and core outcome sets (COSs). We conducted electronic searches of bibliographic databases and key websites and examined FDA prescribing information and reports of clinical trials and systematic reviews. We asked patient and clinician co-investigators to identify PCOs. Part 2 (not part of our original study protocol): in 2015, we surveyed members of The TMJ Association, Ltd., a patient group associated with temporomandibular disorders (4130 invitations sent). Participants prioritized (1) the importance of six potential benefits and (2) 21 potential harms selected by the investigators in part 1, using stated preference methods. We calculated descriptive statistics.ResultsIn part 1, we identified a COS for pain, the Initiative on Methods, Measurement, and Pain Assessment in Clinical Trials (IMMPACT) recommendations. The COS identified several important benefits, but it lacked specific recommendations about which potential harms to include in CER. We did not identify a COS for bipolar depression. Research reports, prescribing information, and patient co-investigators helped identify but not prioritize outcomes. We abandoned our electronic search for PCO research because we found it would be resource-intensive and yield few relevant reports. In part 2, surveying patients was useful for prioritizing PCOs. Members of The TMJ Association, Ltd., completed the survey (N =?746) and successfully prioritized both benefits and harms. Participants did not identify many benefits other than those we identified in part 1; several participants identified additional harms.ConclusionsThese exploratory results could inform future research about identifying and prioritizing PCOs. We found that stakeholder co-investigators and research reports contributed to identifying PCOs; surveying a patient group contributed to prioritizing PCOs. Prioritizing potential harms was particularly challenging because there are many more potential harms than potential benefits. Methods for identifying and prioritizing potential benefits for CER might not be appropriate for harms. Further research is needed to determine the generalizability of these results.

Dataset Information

Falsification Testing of Instrumental Variables Methods for Comparative Effectiveness Research.

Publications

Falsification Testing of Instrumental Variables Methods for Comparative Effectiveness Research.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets