Lab Quiz Flashcards
What is a Retrospective Study?
retrospective studies can take advantage of a larger sample size by looking at data that has already been collected
What is a Prospective study?
prospective studies incorporate better controls over conditions, producing greater validity, predictive power, and cost
Single Blind vs Double blind study
In a single-blind study, only the participants are blinded (i.e don’t know which group they are in). In a double-blind study, both participants and experimenters are blinded
What is the null hypothesis
predicts a condition or treatment will have no effect, or there will be no difference between treatments.
what is the alternative hypothesis?
there will be a measurable effect as a result of tx
do you ever prove a hypothesis is true?
No - you can only accept or reject the null hypothesis
define Independent Variable
“treatment variable” is the one
controlled by the researcher; i.e. treatment(s) you are applying, groups you are testing. Categorical, or continuous numerical.
define Dependent Variable
“response variable” is the
condition that changes in response to the independent
variable; what you are actually measuring.
define Controlled Variables
Variables that need to be held
constant to isolate the effects of the experimental treatment (tying to avoid a “confounding effect”).
ex: temperature held constant
What things need to be considered when designing an experiment?
Population of interest, levels of tx, control tx, # of replications, and potential sources of error
What is the Nuremberg Code?
The Nuremberg Code (1946) is the most important ethical standard in medical research. Has 10 elements including consent, experiments for the greater good of society, etc.
How to calculate a test statistic?
(difference between groups)/(difference within groups)
define p value
p is defined as the probability of getting the test statistic you did, or one more extreme, given the null hypothesis is true.
How do you determine significance of a test statistic?
Compare p to ⍺ to determine significance
If p > ⍺, we fail to reject the null hypothesis
tx has no effect
When do you reject the null hypothesis?
If p < ⍺, we reject the null hypothesis and conclude that there is a
significant difference between the groups
When do you fail to reject the null hypothesis?
If p > ⍺, we fail to reject the null hypothesis
When do you use a t-test?
A t-test can only be used when comparing the means of two groups - often used in hypothesis testing to determine whether a process or treatment actually has an effect on the population of interest, or whether two groups are different from one another.