Biostatistics Flashcards
Negative results RULE OUT a disease
Sensitivity
Positive test results RULE IN a disease
Specificity
What is the definition of PPV? NPV?
The probability that someone who has the disease tests positive. The probability that someone who does not have the disease tests negative
As prevalence increases, what happens to positive predictive value? What happens to negative predictive value?
Increases; Decreases
What is a type 1 error?
When you rejected the null hypothesis in error, and it really is true
What is a type 2 error?
When you are unable to prove the null hypothesis is not true by your study results
Calculation of sensitivity?
TP / (TP+FN)
Calculation of specificity?
TN / (TN+FP)
What is relative risk and how is it calculated?
The probability that a person exposed to a risk factor will have a certain outcome, compared to the probability a person NOT exposed to the risk factor will have the same outcome.
a / (a+b) divided by c/ (c+d)
How is relative risk interpreted?
1 means the outcome is more likely to occur in the experimental group compared to the control group
What studies are relative risk used in?
Randomized control trials and cohort studies
What type of study uses odds ratio?
Case-control study - Looks at a particular outcome and goes back in time to determine if a certain risk factor was present
What is odds ratio and how is it calculated?
Odds ratio is the probability of developing the disease when exposure is present compared with probability of developing the disease without exposure
What is standard error?
The accuracy with which a sample represents a population. The smaller the standard error, the more representative the sample will be of the overall population. The standard error is also inversely proportional to the sample size; the larger the sample size, the smaller the standard error because the statistic will approach the actual value.
What is the number needed to treat?
The average number of patients that need to be treated to prevent one additional bad outcome. The closest it approaches 1, the better. If negative number then it is the number needed to harm.