11.07.2015 Views

Verteporfin photodynamic therapy for neovascular age-related ...

Verteporfin photodynamic therapy for neovascular age-related ...

Verteporfin photodynamic therapy for neovascular age-related ...

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

DOI: 10.3310/hta16060Health Technology Assessment 2012; Vol. 16: No. 611710. Statistical issues10.1 Sample size considerationsThe study population size is the number of patients recruited during the study period.Uncertainties, e.g. about the proportion of ineligible patients identified, theproportions of eligible patients categorised as having different CNV sub-types, andthe precise ways in which control data will be modelled, make it difficult to provide aclear sample size calculation. However, <strong>for</strong> illustrative purposes, we have considereda simple comparison of a continuously scaled outcome, i.e. MDVA, between twosubgroups of patients with different types of CNV lesions [6]. The followingassumptions have been made <strong>for</strong> this illustration: (a) equal sample sizes <strong>for</strong> the twogroups, (b) analysis adjusted <strong>for</strong> baseline MDVA, (c) SD of changes in MDVA = 0.1logMAR, (d) 2-tailed significance level of 0.01, (e) power = 0.95. Such a comparisonwould require only about 50 subjects in each group to detect a difference of 0.1logMAR in the mean change between groups. Other outcomes may have a largerSD, and groups may not have equal sample sizes. A comparison <strong>for</strong> a continuouslyscaled outcome with SD=0.3, and two groups with sample sizes as unequal as 4:1,would require a total of about 1200 (960:240). These simple illustrations do not takeinto account the added strength from the longitudinal nature of the data, but also donot consider dependencies between patients treated by the same retinal teams.10.2 Descriptive statistical analysesMonthly reports will be generated <strong>for</strong> the Steering Committee <strong>for</strong> monitoringpurposes. Similar in<strong>for</strong>mation, tabulated by DP providing PDT, will be produced <strong>for</strong>commissioners and DPs. Each DP will receive patient specific in<strong>for</strong>mation <strong>for</strong> its ownservice.Details of the in<strong>for</strong>mation that will be provided in reports has not been finalised, andadditional in<strong>for</strong>mation may be added as the study progresses. However, the followingitems are illustrative of the in<strong>for</strong>mation that will be distributed:• number of subjects <strong>for</strong> whom data have been submitted and recruitment ratesover time;• number of subjects considered <strong>for</strong> PDT and treated, by CNV category;• demographic and baseline data;• details of treatments provided;© Queen’s Printer and Controller of HMSO 2012. This work was produced by Reeves et al. under the terms of a commissioning contract issued by theSecretary of State <strong>for</strong> Health.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!