Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
29 Cards in this Set
- Front
- Back
|
What is a descriptive study?
|
Describes an observation, idea for future studies
|
|
|
What is a case-control (or retrospective) study?
|
Looks back in time to detect causes or risk factors that may be suggested in a case-series
|
|
|
What is a follow-up (or cohort, logitudinal, prospective) study?
|
Follow a specific group over a period of time and collect data. The study observes and collects data without interfering.
|
|
|
What is a cross-sectional study?
|
Follow a large population at a defined time to measure the frequency of conditions and develop associations (survey). No time direction involved, present time only.
|
|
|
What is an Experimental Study?
|
Typical study we're involved with. Can be parallel, crossover, or sequential.
|
|
|
What is nominal data?
|
yes/no, all or nothing (data values fit in categories). There is no order (gender)
|
|
|
What is ordinal data?
|
ranked data (Likert scales, etc), there is an inherent order among categories but no consistent difference in magnitude change
|
|
|
What is interval or continuous data?
|
Data on a mathematical scale (blood pressure, SCr, visual analog scale, temperature). There is a consistent interval difference between values.
|
|
|
Prevalence=?
|
number of cases/number in group
|
|
|
Incidence=?
|
number of new cases/number in group during same timeframe
|
|
|
Odds Ratio=
|
AD / BC
|
|
|
Relative Risk=
|
(A/ A+B) / (C/C+D)
|
|
|
Relative Risk Reduction=
|
1-RR
|
|
|
Absolute Risk Reduction=
|
(A/ A+B) - (C/C+D)
|
|
|
Number Needed to Treat=
|
1/ARR
|
|
|
Calculation of SEM:
SEM= |
SD/square root of N
|
|
|
What are (2) appropriate tests for 2 sample, independent, parallel design study with NO confounders and NOMINAL data?
|
Chi square or Fisher's Exact
|
|
|
What are (2) appropriate tests for 2 sample, independent, parallel design study with NO confounders and ORDINAL data?
|
Wilcox Rank Sum or Mann Whitney U
|
|
|
What is an appropriate test for 2 sample, independent, parallel design study with NO confounders and CONTINUOUS data?
|
Student's T Test
|
|
|
What is an appropriate test for >2 samples, independent, parallel design study with OR without confounders?
|
ANOVA
|
|
|
regression analysis=
|
a PREDICTIVE model where associations are derived
|
|
|
correlation analysis=
|
explains how a variable changes in association with another variable and does not allow for prediction of one value based on the other
|
|
|
survival analysis=
|
helps to understand the probability of experiencing an outcome through a period of time
|
|
|
analysis of variance=
|
type of inferential statistical test and is not used to predict values of variables
|
|
|
type I error
|
The null hypothesis is rejected. By definition, it can only be considered if a statistical difference is found.
|
|
|
type II error=
|
occurs when a true null hypothesis is rejected. Should be considered when a result is not significant.
|
|
|
negative r2=
|
indicates an inverse correlation between variables
|
|
|
positive r2=
|
means that as one variable increases, so does the other
|
|
|
If an odds ratio data range includes 1, then...
|
There is no difference for comparison
|
