Biostatistics Flashcards
The Sampling distribution of the mean
Sampling Distribution of the Mean: the distribution of sample means. The sampling distribution has key properties that allow us to make inferences about the population.
The standard deviation of the sampling distribution
The standard deviation of the sampling distribution (which we call Standard Error of the Mean, or Standard Error, or SE), is equal to: SD/√n. (where n=the number of observations in any given sample)
Standard deviation vs standard error of the mean
The standard deviation (SD) is based on measurements of individuals – it tells us how much variability can be expected among individuals in a population or sample.
The standard error of the mean (SE) is the standard deviation of the means in a sampling distribution – it gives us the precision to which our sample mean estimates the population mean. This precision increases (i.e., SE decreases) when we increase sample size.
Means testing summary table
Type I Error
Concluding that two populations are different (rejecting the null hypothesis), when they, in fact, are not different (that is, they are drawn from the same population).
Type II Error
not concluding a difference exists (not rejecting the null), when the samples, in fact, are drawn from significantly different populations
The Normal Distribution
If you want to use more than 2 samples, you must use . . .
. . . ANOVA
One sample t-test
Compares a sample mean to a known population mean or a pre-specified value
Two sample t-test
Compares two means (null: the samples are from a single population)
Chi-squared test
Seeks to determine whether an association exists between two categorical variables
For a two by two chi-square table, the critical value is ___ at an alpha level of 0.05.
For a two by two chi-square table, the critical value is 3.84 at an alpha level of 0.05.
The best way to decide whether a type II error exists is to ask two questions:
1) Is the observed effect clinically important?
2) To what extent does the confidence interval include clinically important effects?
The more important the observed effect and the more the confidence interval includes important effects, the more likely that a type II error exists.
Confidence intervals really are a measure of . . .
. . . how precise an estimated effect is
p and CI relationship
