1998
DOI: 10.1136/bjo.82.8.971
|View full text |Cite
|
Sign up to set email alerts
|

People and eyes: statistical approaches in ophthalmology

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

3
219
0
8

Year Published

1999
1999
2021
2021

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 277 publications
(230 citation statements)
references
References 16 publications
3
219
0
8
Order By: Relevance
“…Our interest was in examining the relation between pulsatile ocular blood flow and the degree of diabetic retinopathy in an eye. Therefore, if the extent of pathology differed, we used each eye of a patient in an appropriate grouping and the average of two eyes if the ocular condition was the same in both eyes, providing an optimal use of the available data (Murdoch et al 1998). Excluded from the study were patients with ocular disease other than diabetes and those with a refractive error ±4 diopters.…”
Section: Methodsmentioning
confidence: 99%
“…Our interest was in examining the relation between pulsatile ocular blood flow and the degree of diabetic retinopathy in an eye. Therefore, if the extent of pathology differed, we used each eye of a patient in an appropriate grouping and the average of two eyes if the ocular condition was the same in both eyes, providing an optimal use of the available data (Murdoch et al 1998). Excluded from the study were patients with ocular disease other than diabetes and those with a refractive error ±4 diopters.…”
Section: Methodsmentioning
confidence: 99%
“…20,21 Moreover, the inclusion of bilateral data from thirteen patients necessitated a statistical correction for potential inter-eye correlation within a subject. 22,23 To account for variable follow-up time and inter-eye correlation, an exact logistic regression analysis was performed. Using this method, a correction for bilateral cases was applied by explicitly identifying these cases and setting the case number as a conditional variable during the entire regression analysis.…”
Section: Quantitative Analysis and Statisticsmentioning
confidence: 99%
“…VF data were treated as dependent variables and FD-OCT measurements as independent variables in all regressions. To evaluate the dependence between variables from a same patient and to provide valid statistical inferences, intraclass correlation coefficient (ICC) was performed (16) . Values of ICC lower than 0.3 were considered as a weak association (17) .…”
Section: Methodsmentioning
confidence: 99%