Implications of Small Samples for Generalization: Adjustments and Rules of Thumb

Tipton, Elizabeth; Hallberg, Kelly; Hedges, Larry V.; Chan, Wendy

doi:10.1177/0193841x16655665

Cited by 82 publications

(64 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…46,47 In addition, studies with a small sample size have a poor generalizability of their results. 48 Our results revealed that older adults were excluded mainly by the establishment of an arbitrary upper-age limit corroborating the results from previous studies. 17,49 Evidence indicates that exclusion of participants from RCTs based on age is either unjustified or poorly justified.…”

Section: Discussionsupporting

confidence: 92%

Exclusion of Older Adults from Ongoing Clinical Trials on Low Back Pain: A Review of the WHO Trial Registry Database

Nascimento

Ferreira

Poitras

et al. 2018

J American Geriatrics Society

View full text Add to dashboard Cite

Background/Objectives The burden of low back pain (LBP) is high, especially for older adults who experience a higher number of years living with a disability. However, this population is not being well represented in clinical trials (CTs). This study analyzed the International Clinical Trial Registry Platform (ICTRP) database from the World Health Organization to verify the future trend in the participation of older adults in registered CTs on LBP. Design We performed a cross‐sectional review of the ICTRP searching for prospective protocols planning interventions for LBP with registration dates from January 2015 through November 2018. From the protocols of the eligible studies, we extracted those planning to include older adults. Results A total of 167 protocols for CTs for LBP were planning to recruit participants older than 65 years. However, only five registries (2.99%; pooled sample = 169 participants) were designed to target participants specifically older than 65 years. The exclusion of older participants was not justified and imposed through an arbitrary upper‐age limit in 93.6% of the protocols. Most of the protocols are from single‐center studies, and a greater number are planned to be carried out in developed regions. Higher interest was in pharmacologic interventions, devices/technology, and physical rehabilitation. Conclusion Older adults with LBP will continue to be underinvestigated in CTs for LBP in the near future. In general, ongoing trials are small, planned in developed regions, and proposing pharmacologic interventions to deal with LBP. J Am Geriatr Soc 67:603–608, 2019.

show abstract

Section: Discussionsupporting

confidence: 92%

Exclusion of Older Adults from Ongoing Clinical Trials on Low Back Pain: A Review of the WHO Trial Registry Database

Nascimento

Ferreira

Poitras

et al. 2018

J American Geriatrics Society

View full text Add to dashboard Cite

show abstract

“…Conceptually, Tipton's β describes how close a sample is to approximating a random, probability sample from the underlying population of interest (Tipton ; Tipton et al. ).…”

Section: Methodsmentioning

confidence: 99%

“…Bhattacharyya's coefficient is an index that summarizes the similarity of two histograms and ranges from 0 to 1, with the following interpretation suggested by Tipton when applying the coefficient to propensity score distributions: b < 0.50 "low" generalizability of sample; 0.50 ≤ b < 0.80 "medium" generalizability of sample; 0.80 ≤ b < 0.90 "high" generalizability of sample; 0.90 ≤ b "very high" generalizability of sample. Conceptually, Tipton's b describes how close a sample is to approximating a random, probability sample from the underlying population of interest (Tipton 2014;Tipton et al 2016).…”

Section: Propensity Score Modelmentioning

confidence: 99%

Estimation of Population Average Treatment Effects in the FIRST Trial: Application of a Propensity Score‐Based Stratification Approach

Chung

Bilimoria

Stulberg

et al. 2017

Health Services Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…The issue of generalizability was first thoroughly investigated for clinical trials in Greenhouse et al 9 It was followed by other research, for example, for noninferiority trials in Zhang et al 10 and for survey studies in previous studies. [11][12][13][14] In this work, we target the causal inferences in observational studies where study subjects come from a retrospective convenience sampling (RCS).…”

Section: Population Average Treatment Effectmentioning

confidence: 99%

Generalizability of causal inference in observational studies under retrospective convenience sampling

Qin

2018

Statistics in Medicine

View full text Add to dashboard Cite

Many observational studies adopt what we call retrospective convenience sampling (RCS). With the sample size in each arm prespecified, RCS randomly selects subjects from the treatment-inclined subpopulation into the treatment arm and those from the control-inclined into the control arm. Samples in each arm are representative of the respective subpopulation, but the proportion of the 2 subpopulations is usually not preserved in the sample data. We show in this work that, under RCS, existing causal effect estimators actually estimate the treatment effect over the sample population instead of the underlying study population. We investigate how to correct existing methods for consistent estimation of the treatment effect over the underlying population. Although RCS is adopted in medical studies for ethical and cost-effective purposes, it also has a big advantage for statistical inference: When the tendency to receive treatment is low in a study population, treatment effect estimators under RCS, with proper correction, are more efficient than their parallels under random sampling. These properties are investigated both theoretically and through numerical demonstration.

show abstract

Implications of Small Samples for Generalization: Adjustments and Rules of Thumb

Cited by 82 publications

References 25 publications

Exclusion of Older Adults from Ongoing Clinical Trials on Low Back Pain: A Review of the WHO Trial Registry Database

Exclusion of Older Adults from Ongoing Clinical Trials on Low Back Pain: A Review of the WHO Trial Registry Database

Estimation of Population Average Treatment Effects in the FIRST Trial: Application of a Propensity Score‐Based Stratification Approach

Generalizability of causal inference in observational studies under retrospective convenience sampling

Contact Info

Product

Resources

About