Skip to main content

Table 4 Predicted probabilities for any exploration of subgroup analysis and for reporting subgroup analysis using appropriate methods

From: No improvement in the reporting of clinical trial subgroup effects in high-impact general medical journals

Condition

Predicted probability (any subgroup analysis)

Predicted probability (subgroup analysis using appropriate methods)

Journal of publication

  

 British Medical Journal

0.55 (0.41, 0.69)

0.52 (0.33, 0.71)

 Annals

0.57 (0.42, 0.73)

0.84 (0.63, 1.05)

 Journal of the American Medical Association

0.60 (0.49, 0.70)

0.70 (0.55, 0.86)

 Lancet

0.60 (0.53, 0.68)

0.76 (0.67, 0.85)

 New England Journal of Medicine

0.66 (0.59, 0.73)

0.67 (0.59, 0.75)

Year of publication

  

 2007

0.61 (0.54, 0.69)

0.77 (0.68, 0.87)

 2010

0.57 (0.50, 0.64)

0.71 (0.61, 0.80)

 2013–2014

0.66 (0.59, 0.72)

0.65 (0.57, 0.73)

Biostatistician as coauthor

  

 No biostatistician as coauthor

0.61 (0.55, 0.68)

0.65 (0.56, 0.74)

 Biostatistician as coauthor

0.61 (0.56, 0.70)

0.73 (0.67, 0.80)

Medical condition under study

  

 Obstetrics/gynecological

0.43 (0.25, 0.61)

0.71 (0.42, 1.00)

 Cardiovascular

0.61 (0.52, 0.70)

0.85 (0.75, 0.95)

Infectious disease

0.57 (0.46, 0.69)

0.58 (0.44, 0.73)

 Cancer

0.68 (0.57, 0.78)

0.56 (0.41, 0.70)

 Psychiatry/neurology

0.64 (0.51, 0.77)

0.54 (0.32, 0.76)

 Autoimmune, including DM

0.69 (0.57, 0.82)

0.67 (0.46, 0.87)

 Pulmonary/critical care

0.50 (0.32, 0.68)

0.83 (0.64, 1.00)

 Other chronic disease

0.75 (0.65, 0.85)

0.79 (0.64, 0.95)

 Other, uncategorized

0.48 (0.33, 0.64)

0.89 (0.68, 1.00)

First author’s region

  

 Other

0.56 (0.44, 0.69)

0.63 (0.48, 0.78)

 North America

0.63 (0.57, 0.69)

0.70 (0.61, 0.79)

 Europe

0.62 (0.55, 0.68)

0.73 (0.65, 0.81)

Funding

  

 No industry funding

0.56 (0.51, 0.62)

0.78 (0.71, 0.85)

 Industry funding

0.69 (0.62, 0.75)

0.62 (0.54, 0.69)

Significance of the primary outcome

  

 Not significant

0.68 (0.62, 0.75)

0.75 (0.66, 0.84)

 Significant

0.58 (0.52, 0.63)

0.67 (0.61, 0.74)

Sample size

  

 Quintile 1

0.28 (0.17, 0.38)

0.51 (0.27, 0.75)

 Quintile 2

0.54 (0.44, 0.63)

0.70 (0.56, 0.84)

 Quintile 3

0.67 (0.57, 0.77)

0.70 (0.58, 0.81)

 Quintile 4

0.72 (0.63, 0.82)

0.75 (0.66, 0.84)

 Quintile 5

0.85 (0.78, 0.93)

0.72 (0.62, 0.82)

  1. Predicted probabilities were calculated using the marginal standardization method; DM Diabetes Mellitus