| reference and index test | a diagnostic test that is being evaluated against another test, for reference |
| screening tests | a test to detect a potential disease in someone that does not have symptoms |
| reliability (of a study/measure) | the degree to which the result of a study/measurement can be depended on to be accurate, quality of being trustworthy |
| accuracy | the degree to which the results of a study/measurement come close to the correct value |
| reproductibility | the ability of something to be replicated/copied, the extent to which consistent results are obtained when an experiment is repeated |
| precision | condition of being exact and accurate |
| validity (of study/measure) | the extent to which a concept is accurately measured in a quantitative study, the quality of being factually sound |
| sensitivity | the true positive rate; it measures the proportion of positives that are correctly identified. e.g. diseased people who are actually identified as diseased |
| specificity | the true negative rate; it measures the proportion of the negatives that are correctly identified. e.g. non-diseased people that are actually identified as healthy |
| gold standard method | a method that has been tested repeatedly and has a reputation of being a reliable method in the field |
| variation/variability | change or difference in condition, e.g. when we measure something over and over again and get different results. lack of consistency |
| coefficient of variation | ratio of the standard deviation to the mean. the higher the coefficient variation, the greater the level of dispersion around the mean, so the greater the variation. |
| bias | inclination towards a certain group. research bias -> when the researcher skews the study outcome to a specific result |
| 95% confidence intervals | a statistical estimate. when you take 100 samples and compute a confidence interval on them, approximately 95 of them will contain the true (mean) value.
a range in which the mean is located |
| daily repeat analysis | an analysis that is done every day to see what changes |
| median difference | the middle value when you put all the data from smallest to largest. the median difference is the difference between the medians of two groups (?) |
| median | the middle value when you put all the data from smallest to largest, the number for which half the observations are smaller and half are larger |
| interquartile range (IQR) | the difference between the upper and lower quartiles, this is the middle 50% of the data |
| reference change value (RCV) | it defines the minimal significant difference between two measurements at different time points |
