Skip to main content

Table 3 Quality of reporting

From: Self-controlled designs in pharmacoepidemiology involving electronic healthcare databases: a systematic review

Required items to be reported in the

Method section

 Assumptions for the use of a self-controlled design (whether the setting is valid for the design implementation, with regard to major assumptions)

53 (50)

 Case and control period definition (including number and duration) for case-crossover studies

50/53 (94)

 Risk and control period definition (including number and duration) for self-controlled case-series

49/55 (89)

 Sensitivity analyses conducted (varying periods duration)

54 (50)

 Statistical model

99 (93)

With the appropriate model a

99/99 (100)

 Effect estimator

107 (100)

 Sample size or power calculation

13 (12)

Result section

 Appropriate effect estimator with a measure of variability

102 (95)

 Person-time in the different periods (for self-controlled case series)

18/55 (33)

Estimate displayed

 Unadjusted effect estimators

36 (34)

 Adjusted effect estimators

38 (36)

 Both unadjusted and adjusted effect estimators

33 (31)

  1. Data are reported as n (%)
  2. aConditional logistic regression or conditional Poisson regression model for case-crossover studies, conditional Poisson regression model, Cox’s stratified proportional hazards model or conditional logistic regression model for self-controlled case series