Original article
Choice of Analytic Approach for Eye-Specific Outcomes: One Eye or Two?

https://doi.org/10.1016/j.ajo.2011.08.032Get rights and content

Purpose

To investigate the use of analytic approaches for eye-specific outcomes in ophthalmology publications.

Design

A review of analytic approaches used in original research articles published in ophthalmology journals.

Methods

All 161 research articles published in 5 ophthalmology journals in the first 2 months of 2008 were considered. Publications were categorized according to analytic approach: 1 eye selected, both eyes contribute, or per-individual outcome. Studies were considered suboptimal when criteria for eye selection were not provided or when measurements from both eyes were included without interocular correlation being considered. Visual impairment prevalence data were used to illustrate analytic approach choices.

Results

Measurements from both eyes were included in 38% of the 112 studies that used statistical inferential techniques. In 31 (74%), there was no mention of possible correlation. Only 7% used statistical methods appropriate for correlated outcomes. In 35 studies (31%), measurements from 1 eye were selected; 31% of these did not provide selection criteria. In 67%, only univariate tests were used. A review of 47 articles published in 2011 produced similar findings. Characteristics of studies were not found to differ according whether the studies were suboptimal. Using a test appropriate for correlated outcomes resulted in a P value 3.5 times that obtained ignoring the correlation.

Conclusions

Between-eye correlation seems not to be assessed commonly in ophthalmology publications, although its knowledge aids the choice of analytic approach when eye-specific variables are of interest. Statistical methods appropriate for correlated ocular outcome data are not being applied widely.

Section snippets

Selection and Categorization of Articles

An ophthalmologist (M.T.) selected 2 general and 3 subspecialty ophthalmology journals from the top 50% of the list of 45 ophthalmology journals on the ISI Web of Knowledge (ranked according to their 2007 impact factor). Both general and subspecialty ophthalmology journals were selected to reflect the broad spectrum and the distribution of analytic approaches in these published ophthalmologic articles. The journals selected were Acta Ophthalmologica, the American Journal of Ophthalmology, the

Review of Original Articles

In total, 161 original articles published in 2008 were reviewed. Of these, 31 articles were excluded from further analysis because no statistical inferential techniques were used (19.3%). One hundred eighteen (73.3%) of the remaining 130 articles that described the results of clinical or epidemiologic human investigations were considered further. The other 12 studies comprised 7 animal experiments, 3 laboratory studies, an article assessing the flow rate of vitreous cutters in different

Discussion

The findings of the present review indicate that interocular correlation is not assessed frequently or exploited in clinical ophthalmologic studies and that violation of the statistical assumption of independence remains fairly common practice. Although the issue of correlated data in ophthalmic research repeatedly has been raised in the literature, in the present study, it was found that interocular correlation was mentioned, assessed, or adjusted for in a small proportion of the articles in

References (39)

  • K. Sainani

    The importance of accounting for correlated observations

    PM R

    (2010)
  • K.K. Assil et al.

    Photopic pupillometry-guided laser in situ keratomileusis of hyperopic presbyopia

    J Cataract Refract Surg

    (2008)
  • N.S. Tang et al.

    Testing the equality of proportions for correlated otolaryngologic data

    Comput Stat Data Anal

    (2008)
  • B. Rosner

    Statistical methods in ophthalmology: an adjustment for the intraclass correlation between eyes

    Biometrics

    (1982)
  • B. Rosner et al.

    Incorporation of clustering effects for the Wilcoxon rank sum test: a large-sample approach

    Biometrics

    (2003)
  • P. Burton et al.

    Extending the simple linear regression model to account for correlated responses: an introduction to generalized estimating equations and multi-level modelling

    Stat Med

    (1998)
  • J. Katz et al.

    Appropriate statistical methods to account for similarities in binary outcomes between fellow eyes

    Invest Ophthalmol Vis Sci

    (1994)
  • D.E. Harle et al.

    Perimetry and migraine-deficits may not implicate glaucoma

    Graefes Arch Clin Exp Ophthalmol

    (2006)
  • Photocoagulation treatment of proliferative diabetic retinopathy: the second report from the Diabetic Retinopathy Study

    Arch Ophthalmol

    (1978)
  • H. Beckman et al.

    The Glaucoma Laser Trial: IAcute effects of argon laser trabeculectomy on intraocular pressure

    Arch Ophthalmol

    (1989)
  • E.G. Newcombe et al.

    Eyes or patients?Traps for the unwary in the statistical analysis of ophthalmological studies

    Br J Ophthalmol

    (1987)
  • I.E. Murdoch et al.

    People and eyes: statistical approaches in ophthalmology

    Br J Ophthalmol

    (1998)
  • H. Goldstein

    Multilevel Statistical Models

  • H. Brown et al.

    Applied Mixed Models in Medicine

  • M.K. Campbell et al.

    CONSORT statement: extension to cluster randomized trials

    Br Med J

    (2004)
  • A. Donner

    Statistical methods in ophthalmology: an adjusted chi-square approach

    Biometrics

    (1989)
  • R.J. Glynn et al.

    Comparison of alternative regression models for paired binary data

    Stat Med

    (1994)
  • R.J. Glynn et al.

    Accounting for the correlation between fellow eyes in regression analysis

    Arch Ophthalmol

    (1992)
  • R.J. Glynn et al.

    Methods to quantify the relation between disease progression in paired eyes

    Am J Epidemiol

    (2000)
  • Cited by (0)

    Supplemental Material available at AJO.com.

    View full text