Data frame containing the results of 16 trials comparing 8 treatments for moderate-to-severe plaque psoriasis from an HTA report Woolacott2006multinma, analysed in TSD2 TSD2multinma. Outcomes are success/failure to achieve 50%, 75%, or 90% reduction in symptoms on the Psoriasis Area and Severity Index (PASI) scale. Some studies report all three ordered outcomes, others only one or two. The latter are coded as missing values (see details).
Format
A data frame with 36 rows and 9 variables:
- studyn
numeric study ID
- studyc
study name
- year
year of publication
- trtn
numeric treatment code
- trtc
treatment name
- sample_size
sample size in each arm
- PASI50, PASI75, PASI90
ordered multinomial outcome counts (exclusive, see details)
Details
Outcome counts are "exclusive"; that is, for a study reporting all
outcomes, the counts represent the categories 50 < PASI < 75, 75 < PASI <
90, and 90 < PASI < 100, and are named by the lower end of the interval.
(As opposed to "inclusive" counts, which would represent the overlapping
categories PASI > 50, PASI > 70, and PASI > 90.) The count for the fourth
category (the lowest), 0 < PASI < 50, is equal to sample_size - PASI50 - PASI75 - PASI90.
Missing values are used where studies only report a subset of the outcomes. For a study reporting only two outcomes, say 50 and 75, the counts represent 50 < PASI < 75 and 75 < PASI < 100. For a study reporting only one outcome, say PASI 75, the count represents 75 < PASI < 100.