| Question |
Answer |
| Positive predictive value |
TP/(TP + FP). Probability that person actually has the disease given a positive test result |
| Negative predictive value |
TN/(TN + FN) Probability that person actually is disease free given a negative test result. |
| What happens to PPV when there is a low incidence |
Low incidence --> low positive predictive value |
| Sensitivity |
TP/(TP + FN)Proportion of all people with disease who test positive. |
| Use a test with high sensitivity/specificity when there is low prevalence? |
High sensitivity` |
| Use a test with high specificity/sensitivity as a confirmatory tests after a poitive screen |
High specificity |
| Type I error = False positive/false negative? |
Type 1 error = false positive. Stating that there is an effect or difference when none exists. (to reject null and mistakenly accept the experimental) |
| Type II error = false positive/false negative? |
Type II error = false negative. Statin that there is not an effect or difference when one exists |
| Probability that there is a difference between two groups despite the study's failure to show the difference? |
Type II error |
| To mistakenly reject the null hypothesis? |
Type I error |
| To mistakenly fail to rejcet the null hypothesis? |
Type II Error |
| Stating that there is an effect or difference when none exists |
Type I error |
| Stating that there is not an effect or difference when one does exist |
Type II error |
| Probability of rejecting the null hypothesis when it is in fact false |
Power (1-beta) |
| Liklihood of finding a difference when there is one |
Power (1- beta) |
| Confidence interval that spans over 0. Is Ho rejected? |
not significant. Not rejected (no difference) |
| Confidence interval for odds ratio, relative risk includes 1. Ho rejected? |
Not significant. Not rejected |
| if CI between 2 groups overalps, then are these groups significantly different? |
Not significanly different |
| Measure teh extent to which the sample means devated from the true population mean |
SD/square root nSEM decreases as n increases (as you increase the number of people there will be less variability) |
| 1 standard devation = ___ %, 2 standard deviation ____%, 3 Standard deviation = ___% |
1 SD: 68 %, 2 SD = 95%, 3 SD = 97% |
| Relative risk |
Proportion of diseased in exposed/diseased in unexposed (a/a+b)/(c/(c+d)) |
| Odds ratio |
Odds of having disease in exposed vs. odds of having disease in unexposed (ad/bc) or (a/b)/(c/d) |
| Attributable risk |
Difference in risk between exposed and unexposed |
| Type of error: occurs when group being studied changes its behavior to meet expectations of researcher |
Hawthorne effect |
| Error: occurs when a researcher's belief in the efficacy of a treatment changes the outcome of that treatment |
Pygmalian effect |
BIOL3326 Forms
