Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
29 Cards in this Set
- Front
- Back
Types of Experimental Studies |
Randomized Control Trial. Cluster-randomized trial. Quasi-experiment design. |
|
Randomized Control Trial |
Is a form of experimental study that is done with randomized subjects into the control and experimental group. Threats to validity include poor randomization, no blinding of subjects from investigators, poor follow up. |
|
Cluster Randomized trial |
Is a form of experimental study in which groups are randomized and not individuals into experimental and control groups. Threats to validity include poor randomization, no blinding, and analysis does not take into account clustering. |
|
Quasi-experimental Design |
When patients are no randomized, due to ethical reasons, data collected before and after intervention. Weakness include no randomization. Threats to validity include no adjustment for confounding factors. |
|
Observational Studies |
Cohort Study. Case-control study. Cross Sectional study. Case Series. |
|
Cohort Study |
Is study in which outcomes of groups using observed assignment. Detects associations, but not cause and effect. Threats to validy include bias in measurement of exposure and outcomes, and confounder not accounted for. |
|
Case-Control Study |
Compares exposures in patients with and with out the disease. Weakness include high risk for bias, and confounding. Threats to validity include selection bias, measurement bias. |
|
Cross-sectional Study |
Determines prevalence of disease. Threats to validity include selection bias, sample not representative. |
|
Internal Validity |
The extent to which study results are true and supported by the study. Effected by sampling, measurement and data anaylsis. |
|
External validity |
Is the degree to which the study is generalizable. |
|
Random Error |
The finding is due to chance. Can improve with increasing sample size or measurement precision. |
|
Systematic Error |
Due to bias. |
|
Prevalance |
Proportion of poplulation that has disease. (TP+FN)/(TP+FP+FN+TN) |
|
Sensitivity |
Is the ability to detect disease. TP/(TP+FN) |
|
Specificity |
Proportion of patients with out the disease who have a negative test. TN/(TN+FP) |
|
Positive Predictive Value |
Proportion of patients who have positive test with disease. Increases with increasing prevelance. TP/(TP+FP). |
|
Negative Predictive Vale |
Proportion of patients with negative result who do not have disease. Increases with lower prevalence. TN/(TN+FN) |
|
Positive Likelihood Ratio |
Is the ratio of the probability of a positive result in patients with the disease to the patients with out the disease. Sensitivity/(1-Specificity) |
|
Negative Likelihood Ratio |
Is the ratio of probability of those patients with a negative test with disease to patients who do have disease with negative result. (1-Sensitivity)/specificity |
|
Pretest Odds |
The odds patient has a disease prior to testing. Pretest probability/(1-pretest probability) |
|
Posttest Odds |
The odds patient has disease after test is performed. Pretest odds x LR (use LR+ if positive, LR- if negative) |
|
Pretest Probability |
Proportion of patients with diease before test is performed. Determined from population prevalance, clinical risk calculators, or clinical experience. |
|
Posttest Probability |
Proportion of patients with diease after a test is performed. Posttest odds/(1+posttest odds) |
|
Absolute Risk |
Is the risk of an event. Event/total patients in group. |
|
Relative Risk |
Is the ratio of the probability of an event in the exposure group over the control group. (event/exposed population)/(event/non exposed) |
|
Absolute Risk Reduction |
The difference between experimental group and control group. (event/exposed) - (event/nonexposed) |
|
Relative Risk Reduction |
ARR/(event/nonexposed) |
|
Number Needed to Treat |
= 1/ARR |
|
Number Neeed to Harm |
= 1/ARR |