BIOSTATS Flashcards
Type 2 error
Said no difference when there was a difference
False-negative
Increase power and duration to prevent
Type 1 error
Said there was a difference and there wasn’t
False positive
Power
Power equals one minus b
Nominal data
Yes or no
Ordinal data
Ranking
Interval data
Temperature is an example no real zero
Ratio data
Has a real zero examples are height weight time and length
Statistical test used for nominal data
Chi-square or Fisher exact test
Statistical test used for ordinal data
Wilcoxon rank sum test or mann Whitney u test
Ratio and interval data statistical test
Students t-test and anova
Relative risk or risk ratio
Risk in treatment group divided by risk in control group
If equal to one no difference
If less than one less likely to occur in treatment group
If greater than one the event is more likely to occur in the treatment group
Relative risk reduction
Percent risk in control group minus percent risk in treatment group divided by percent risk in control group
Or 1-rr
Absolute risk reduction
% risk in control group -% in treatment group
Number needed to treat
1/ARR