Biostatistics Flashcards
continuous data
logical order with values that continuously increase (or decrease) by the same amount
-ratio data: 0 = none (age, height, weight)
-interval data: 0 does not equal none (temperature)
discrete data
data fits into a limited number of categories
-nominal data: arbitrary order (gender, ethnicity)
-ordinal data: ranked in logical order (NYHA functional class)
independent variables
changed by the researchers
-drugs, drug doses, placebos, patients
dependent variables
affected by the independent variables
-HF progression, HgbA1c, BO, cholesterol
null hypothesis
no statistical difference between groups
-what the researcher tries to disprove or reject
alpha level
-maximum permissibke error margin
-set at 5% 0.05
comparing P value to alpha
-if alpha is set at 0.05 and the p-value is less than 0.05 the null hypothesis is rejected (statistically significant)
-if p-value is greater than or equal to alpha the study has failed to reject the null hypothesis and the result is not statistically significant
confidence interval
CI = 1- alpha
Type 1 error: false positives
-conclusion was wrong and type 1 error was made
-alternative hypothesis was accepted and the null hypothesis was rejected in error
-alpha is 0.05 with p < 0.05 = statistically significant and the probability if type I error is < 5% –> 95% confident
Type 2 error: false negatives
when null hypothesis is accepted when it should have been rejected ‘
-set at 0.1 or 0.2
-risk incr if sample size is too small
study power
to avoid type 2 error
relative risk
risk in treatment group/risk in control group
-RR = 1 implies no difference in the risk of the outcome
-RR > 1 implies greater risk of the outcome in the treatment group
-RR < 1 implies lower risk of the outcome on the treatment group
Relative risk reduction
(% risk in control group - % risk in tx group) / % risk in the control group
or 1- RR
absolute risk reduction
% risk in control group - % risk in tx group
NNT/NNH
1 / (risk in control group - risk in tx group)
or
1/ ARR
HR
hazard rate in the tx group / hazard rate in the control group
OR / HR interpretation
= 1: event rate is the same
> 1: event rate in the tx group is higher
< 1: event rate in the treatment group is lower
Case control studies
retrospective comparisons of cases (patients with a disease) and controls (patients without a disease)
cohort studies
retrospective or prospective comparisons of patients with with an exposure to those without an exposure
randomized controlled trials
prospective comparison of patients who were randomly assign to groups
meta-analysis
analyzes the results of multiple studies