What are the different drug metabolizing enzymes and what do they metabolize?
2D6=codeine, debrisoquin, fluoxetine; 2C9=s-warfarin, phenytoin,hexobarbital,ibuprofen; 2C19=clopidogrel in, omeprazole, diazepam, propanolol; 3A4=steroids, Ca channel blockers, benzos, amiodarone, erythromycin, clopidogrel out; 1A2=tylenol,caffeine,theophylline, warfarin; 2A6=zidovudine, warfarin; 2E1=tylenol
What value shows the variability of the sample mean from the true population mean?
Standard Error of the Mean = (standard deviation)/sqrt(sample size). Its like the standard deviation for populations.
What value shows the variability of the individual observations?
Researchers plan to estimate the mean LDL cholesterol by selecting a sample from the entire U.S. population. What will the precision of the estimate depend on?
Standard error of the mean. i.e. standard deviation in the population, sample size and variance in the population.
This sets limits which include the population mean for 95% of all samples.
In a study, a p value of .00001 tells you that your results are very unlikely if:
There really is no difference between the two groups. Your results are very likely if there is truly a difference between the two groups.
Incorrectly concluding a difference exists when in fact there is no difference.
Type I error
Failing to conclude a difference exists when a difference in fact does exist.
Type II error
The probability of making a type I error.
Significance level (alpha)
The probability of not making a type II error.
Power = 1 - false negative rate
Numerical data that can only take on integer values.
Numerical data that can take on any value.
Non-numeric data with hierarchy of values
Non-numeric data with no level of order
This graphical depiction shows the interquartile range
Probability of + test/Probability of - test
You want to minimize missing cases.
Sensitivity. Low false negative rate.
You want to minimize unnecessary grief.
Specificity. Low false positive rate.