Article

A primer on common statistical errors in clinical ophthalmology

Department of Ophthalmology, New York University School of Medicine, 462 First Avenue, New York, NY 10016, USA.
Documenta Ophthalmologica (Impact Factor: 1.63). 10/2010; 121(3):215-22. DOI: 10.1007/s10633-010-9249-7
Source: PubMed

ABSTRACT

Although biomedical statistics is part of any scientific curriculum, a review of the current scientific literature indicates that statistical data analysis is an area that frequently needs improvement. To address this, we here cover some of the most common problems in statistical analysis, with an emphasis on an intuitive, tutorial approach rather than a rigorous, proof-based one. The topics covered in this manuscript are whether to enter eyes or patients into the analysis, issues related to multiple testing, pitfalls surrounding the correlation coefficient (causation, insensitivity to patterns, range confounding, unsuitability for method comparisons), and when to use standard deviation (SD) versus standard error of the mean (SEM) "antennas" on graphs.

Download full-text

Full-text

Available from: Michael Bach
    • "According to the first approach, all eyes will be analyzed together without taking into consideration that there are partly correlated measurements, often with high correlation between eyes (Murdoch et al. 1998). Clearly, this is a statistically incorrect way, potentially gravely distorting results (Rosner 1982; Newcombe and Duff 1987; Altman and Bland 1997; Murdoch et al. 1998; Menz 2004; Holopigian and Bach 2010), and it is " so ingrained in statisticians that this is a bad idea that it never occurs to them that anyone would do it " (Bland and Altman 1994). Nevertheless, recent reviews of articles published in different ophthalmology and optometry journals revealed that considering correlation in ophthalmic and ocular outcome data is still not at all widespread today: Karakosta et al. reviewed ophthalmology articles and found that out of 42 articles using statistical inferential techniques and including measurements of both eyes, 31 did not mention possible correlation (Karakosta et al. 2012). "
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new method to make inference about an eye parameter based on data that contains measurements on both eyes for some subjects, and measurements on only one eye on the others. Subject effects are modeled as additive and random, and correlation between observations on the same subject are taken into account. We derive confidence intervals for the parameter of interest, using unbiased estimators of mean and variance, and yielding explicit formulas. The results are compared to approaches commonly used in the literature, using theoretical considerations and a simulation study. The method works well even for small to moderate sample sizes, for continuous and for discrete data, and it is applicable generally for the situation where data is collected partially in pairs and partially in singles, and inference is to be made about a common location parameter. The conclusions as to how one should best average correlated data may be surprising, and somewhat revising conventional wisdom.
    No preview · Article · May 2015 · Statistical Papers
  • Source

    Full-text · Article · Mar 2011 · Ophthalmic and Physiological Optics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In the decade and a half since Biswal's fortuitous discovery of spontaneous correlations in functional imaging data, the field of functional connectivity (FC) has seen exponential growth resulting in the identification of widely-replicated intrinsic networks and the innovation of novel analytic methods with the promise of diagnostic application. As such a young field undergoing rapid change, we have yet to converge upon a desired and needed set of standards. In this issue, Habeck and Moeller begin a dialogue for developing best practices by providing four criticisms with respect to FC estimation methods, interpretation of FC networks, assessment of FC network features in classifying sub-populations, and network visualization. Here, we respond to Habeck and Moeller and provide our own perspective on the concerns raised in the hope that the neuroimaging field will benefit from this discussion.
    Full-text · Article · Jun 2011 · Brain Connectivity
Show more