USA EIP Final Exam Review 2022 with
complete solution
Internal Validity - the control of extraneous factors
- has the least amount of bias and error
- everything is accounted for
External Validity - Refers to how applicable or generalizable the results are to a certain
population
- population= stroke pt's, PT, OT, etc.
T/F: the more internally valid a study, the least externally valid it is - True
Threats to Validity - Attrition/Mortality - Subjects leave the study before finishing
- this can increase bias by skewing results
Threats to Validity - Subject Selection/Assignment - Sample size must be a valid
representation of a population in order to generalize results
Threats to Validity - Other Forms of Bias - - Competition
- The Hawthorn Effect: when someone acts differently b/c they're being watched
- Researcher Influence
- Binding
Statistics/Data Analysis - - Statistics give researchers a tool in which to explain,
describe and predict future results
- The type of statistical test depends on the type and amount of data collected
Commonly Used Descriptive Statistics - 1. T-Test
2. ANOVA
3. Regression
T-Test - Compares a mean value to either a theoretical mean or another mean
ANOVA (Analysis of Variance) - Compares groups to each other
- it is trying to see how far the data skews away from the mean
- used with more than 2 groups
, Regression - Measures how the independent variable effects the dependent variable at
several points
Statistical Significance - A statistical statement of how likely it is that an obtained result
occurred by chance
"P-Value"
Confidence Interval - A range of values so defined that there is a specified probability
that the value of a parameter lies within it.
Independent Variable - The variable that is CHANGED or controlled in a scientific
experiment to test the effects on the dependent variable
Dependent Variable - The variable being tested and measured in an experiment; the
RESPONSE is being measured
Experimental Method Discussion - 1. Participants
2. Materials
3. Procedures
4. Measures
Quasi-Experiment: - When participants are not randomly assigned to groups
Threats to Internal Validity - 1. History
2. Maturation
3. Regression
4. Selection
5. Mortality
6. Diffusion of Treatment
7. Compensatory or Rivalry
8. Testing
9. Intrumentation
Threats to External Validity - 1. Interaction of Selection and Treatment
2. Interaction of Setting and Treatment
3. Interaction of History and Treatment
What makes up a good question? - 1. Background --> overview/broad
2. Foreground --> specific
3. Equipoise --> equal view about a topic; minimized bias
4. Directional or Non-Directional --> deals with hypothesis but ends up being biased
(directional); depends on how it is worded
What does PICO stand for? - P- Patient Population
complete solution
Internal Validity - the control of extraneous factors
- has the least amount of bias and error
- everything is accounted for
External Validity - Refers to how applicable or generalizable the results are to a certain
population
- population= stroke pt's, PT, OT, etc.
T/F: the more internally valid a study, the least externally valid it is - True
Threats to Validity - Attrition/Mortality - Subjects leave the study before finishing
- this can increase bias by skewing results
Threats to Validity - Subject Selection/Assignment - Sample size must be a valid
representation of a population in order to generalize results
Threats to Validity - Other Forms of Bias - - Competition
- The Hawthorn Effect: when someone acts differently b/c they're being watched
- Researcher Influence
- Binding
Statistics/Data Analysis - - Statistics give researchers a tool in which to explain,
describe and predict future results
- The type of statistical test depends on the type and amount of data collected
Commonly Used Descriptive Statistics - 1. T-Test
2. ANOVA
3. Regression
T-Test - Compares a mean value to either a theoretical mean or another mean
ANOVA (Analysis of Variance) - Compares groups to each other
- it is trying to see how far the data skews away from the mean
- used with more than 2 groups
, Regression - Measures how the independent variable effects the dependent variable at
several points
Statistical Significance - A statistical statement of how likely it is that an obtained result
occurred by chance
"P-Value"
Confidence Interval - A range of values so defined that there is a specified probability
that the value of a parameter lies within it.
Independent Variable - The variable that is CHANGED or controlled in a scientific
experiment to test the effects on the dependent variable
Dependent Variable - The variable being tested and measured in an experiment; the
RESPONSE is being measured
Experimental Method Discussion - 1. Participants
2. Materials
3. Procedures
4. Measures
Quasi-Experiment: - When participants are not randomly assigned to groups
Threats to Internal Validity - 1. History
2. Maturation
3. Regression
4. Selection
5. Mortality
6. Diffusion of Treatment
7. Compensatory or Rivalry
8. Testing
9. Intrumentation
Threats to External Validity - 1. Interaction of Selection and Treatment
2. Interaction of Setting and Treatment
3. Interaction of History and Treatment
What makes up a good question? - 1. Background --> overview/broad
2. Foreground --> specific
3. Equipoise --> equal view about a topic; minimized bias
4. Directional or Non-Directional --> deals with hypothesis but ends up being biased
(directional); depends on how it is worded
What does PICO stand for? - P- Patient Population
