Table 2

Serious errors and omissions occurring in papers submitted to OEM

  Authors unclear of type of epidemiological study
  Adequacy of sample size not considered
  Bias in selection of subjects
  Data collection problems and missing data not adequately reported
  Non-respondents not investigated
  Sample selection and exclusions inadequately justified
  Parametric tests carried out on obviously skewed data
  Use of multiple paired tests
  Inappropriate analysis of repeated measures or longitudinal data
  Incorrect analysis of matched case-control studies
  Modelling incorrect—for example, inadequate adjustment for confounders, interaction terms  not included, only significant variables from preliminary analyses included
  Inadequate description of the methodology and statistical procedures
  Inappropriate summary statistics for non-normal data
  No presentation of risk estimates—for example, odds ratios—and confidence intervals
  Potential bias due to sample selection, no or poor response, missing values, exclusions
  Lack of statistical power not considered
  No allowance made for multiple testing
  Misunderstanding and misinterpretation of results from models