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;
17 Cards in this Set
- Front
- Back
|
What are the measures of central tendency?
What scale of measurement uses the central tendency? |
Mean: average
Median: # in the middle when values are ranked from low to high Mode: value that occurs most often Interval scale uses the measures of central tendency |
|
|
What is a type I error?
What is the probability if making a type I error? |
A type 1 error is rejection of the null hypothesis when it is true. i.e. there is no difference
Alpha is the probability of making a type 1 error, commonly set at 0.25 |
|
|
What is a type II error?
What is the probability of making a type II error? |
Type II is acceptance of the null hypothesis when it is in fact rejected.
Beta is the probability of a type II error, commonly set at 0.2 |
|
|
How is study power defined?
What are the 2 types of observational analytical studies? |
Power is defined as 1-beta
2 types of abservational analytical studies: 1. case - control 2. cohort |
|
|
Describe the relative risk
|
In a cohort study reletive risk compares the risk of developing the disease (outcome) in the exposure population vs. risk of developing disease (outcome) in unexposed population
|
|
|
The probability of an event occurring over time is graphed using _____
|
Kaplan-Meier survival curves
|
|
|
What is the difference between odds ratio and relative risk?
What test is used to compare Kaplan - Meier curves? |
Relative risk can only be used when the data are collected in a prospective manner.
Log-rank test |
|
|
What is incidence?
What is relative risk? |
Incidence - proportion of people that develop the disease during some fixed interval of time
Relative risk is the incidence of an outcome in the exposure population divided by the incidence of outcome in population not exposed |
|
|
Linear regression and Pearson's coefficient are used for which scale of measurement?
What is prevalence? |
Linear regression and Pearson's coefficient are used for interval scale of measurement
The proportion of people in a population who have the disease at one point in time |
|
|
Linear regression determines ______
What is used to measure correlation in linear regression? Which values are good? bad? |
the best fitting straight line
Pearson's correlation coefficient Pearson's measures from -1 to 1, the closer to one (- or +), the better |
|
|
Give examples of each tyoe of scale
|
Interval - weight, inches, cm (in a marathon, the distance from Mile 4 to mile 5 is the same as the disctance from mile 19 to mile 20)
Ordinal - pain scale (subjective), amt of pain perceived when increased from 9 to 10 is not the same (exact) as from 1 to 2 Nominal - ethnicity, eye color |
|
|
Which test is used to analyze paired, non-parametric data from 2 groups?
When is Kruskal - Wallis test used? |
Wilcoxan signed rank test:
1. dependent (paired) data 2. 2 groups 3. non-parametric Kruskal - Wallis 1. 3 or more groups 2. non-parametric |
|
|
The non-parametric tests are also used for ______ scale
Which tests are used to analyze nominal (categorical) data? How do you choose which one? |
The non-parametric tests are also used for ordinal scale
Chi-squared test and Fisher's exact test Sample size < 5 = Fisher's |
|
|
If comparing more than 2 groups with parametric features, what test should be used?
When 2 groups are parametric and independent, what test should be used? |
One-way analysis of variance (ANOVA)
t-test 1. parametric 2. 2 groups 3. independent |
|
|
Non-parametric comparison of 2 independent groups uses ______
|
Wilcoxan rank sum test or Mann - Whitney U test
1. 2 groups 2. independent 3. non-parametric |
|
|
When should a paired t-test be used?
Give examples |
1. 2 groups
2. parametric data 3. variables are dependent Measure data at different time points in the same patients Measure data before and after exposure in the same patients |
|
|
How is power increased?
In Gaussian (bell-shaped) distribution, what values are equal? |
Increase the sample size
The mean, median and mode are equal |
