Table 2.
Number (%) of respondents rating each competency as 1 or 2 (1 was fundamental, 3 was neutral, and 5 was specialized)
| Rank | Competency | Percent fundamental | 95% exact confidence interval |
|---|---|---|---|
| 1* | Assess sources of bias and variation in published studies and threats to study validity (bias) including problems with sampling, recruitment, randomization, and comparability of study groups | 94.6 | 88.7, 98.0% |
| 2 | Recognize limitation in statistical competency and realize when it would be best to involve a professional statistician | 92.9 | 86.4, 96.9% |
| 2* | Identify the strengths and limitations of study designs for addressing a clinical or translational research question | 92.9 | 86.4, 96.9% |
| 4 | Communicate research findings for scientific and lay audiences | 89.3 | 82.0, 94.3% |
| 5* | Understand the basic principles and practical importance of probability, random variation, commonly used statistical probability distributions, hypothesis testing, type I and type II errors, and confidence limits | 87.4 | 79.7, 92.9% |
| 6 | Understand the value of data quality and data management | 87.3 | 79.6, 92.9% |
| 7 | Understand the reasons for performing research that is reproducible from data collection through publication of results | 85.6 | 77.6, 91.5% |
| 8 | Understand appropriate methods for data presentation, especially effective statistical graphs and tables | 82.9 | 74.6, 89.4% |
| 8 | Distinguish between variable types (eg, continuous, binary, categorical) and understand the implications for selection of appropriate statistical methods | 82.9 | 74.6, 89.4% |
| 8* | Understand the potential misinterpretation of results in the presence of multiple comparisons | 82.9 | 74.6, 89.4% |
| 11 | Evaluate size of the effect with a measure of precision | 82.1 | 73.8, 88.7% |
| 12* | Understand issues relating to generalizability of a study, including sampling methods and the amount and type of missing data | 80.9 | 72.3, 87.8% |
| 13 | Evaluate the impact of statistics on ethical research (eg, an inadequate power calculation may mean it is unethical to ask subjects to consent to a study) and of ethics on statistical practice | 79.5 | 70.8, 86.5% |
| 14 | Compute descriptive and simple inferential statistics appropriate for the data and research question | 76.8 | 67.9, 84.2% |
| 15 | Understand the components of sample size, power, and precision | 71.4 | 62.1, 79.6% |
| 16* | Understand the need to address loss to follow-up | 68.8 | 59.2, 77.3% |
| 17* | Understand the concepts and bias implications of reliability and validity of study measurements and evaluate the reliability and validity of measures | 66.7 | 57.1, 75.3% |
| 18 | Evaluate potential violations of the assumptions behind common statistical methods | 65.2 | 55.6, 73.9% |
| 19 | Identify when clustered, matched, paired, or longitudinal statistical methods must be used | 64.9 | 55.2, 73.7% |
| 20† , * | Understand the concepts of sensitivity, specificity, positive and negative predictive values, and receiver operating characteristic curves | 59.1 | 49.3, 68.4% |
| 21† | Understand the purpose of data and safety monitoring plans | 49.5 | 39.9, 59.2% |
| 22† | Identify appropriate methods to address potential confounding and effect modification | 47.7 | 38.1, 57.5% |
| 23† , * | Understand the purpose of meta-analysis and its place in the hierarchy of evidence | 34.2 | 25.5, 43.8% |
| 24† | Understand the uses, importance, and limitations of early stopping rules in clinical trials | 18.0 | 11.4, 26.4% |
*
Competencies required in order to evaluate ‘design-specific susceptibility to error,’ needed for literacy regarding evidence within the Scientifically Informed Medical Practice and Learning Model.
†
These competencies can be considered important for training but are not fundamental for all learners according to this survey.