Quiz 3 Flashcards
(31 cards)
What is reliability?
Consistency of a measurement or test
Four types of reliability
Test, retest reliability
Inter rater reliability
Parallel forms, reliability
Internal consistency
Test, retest reliability (how it is calculated and determined)
Administer the same test to same group at two different times
Calculate the correlation efficient (Pearsons r) between the two sets of scores
Inter rater reliability (how it is determined and calculated)
Have multiple rater/observers score or categorize the same set of data
Uses Cohen’s kappa for categorical, fleiss’ kappa four more than two Raters, , ICC for continuous data
Parallel forms, reliability ( how it is determined and calculated)
Develop two equivalent versions of a test,
give both versions to the same group
Compute the correlation between the two sets of scores
Internal consistency(how it is determined and calculated)
Look at how well the items within the list are related
Use cronbachs alpha in split half reliability
Higher alpha (>0.7) means better consistency
Independent variable
A variable you change or control (the cause)
Dependent variable
The variable you measure or observe (the effect)
Validity
How well a test measures what it is supposed to measure
Three types of validity
Content validity
Construct validity
Criterion related validity
How content validity is determined and calculated
Not usually statistical, based on expert judgment, sometimes a content validity ratio is calculated using expert ratings
How construct validity is determining calculated
Uses factor analysis and checks correlations
How criterion related validity is determined in calculated
Correlation coefficients (pearsons r) between the test and an external criterion
Predictive and concurrent
Example of when something can be reliable, but not valid
Survey is designed to measure math ability, but only includes basic math questions
Reliable because everybody gets a similar score each time
Not valid because it doesn’t truly measure math ability
What is a hypothesis?
An educated guess
Role of hypothesis
To reflect the general problem statement or question that is driving research
Define sampling error
A measure of how well a sample represents the population
General goal of hypothesis testing
To rule out simply error as a plausible explanation for the results of research study
Define hypothesis testing
Technique to help determine whether a specific treatment has an effect on the individuals in a population
When is hypothesis test used?(3)
Sample is selected from the population
Treatment is administered to the sample
After treatment, the individuals in sample are measured
Types of hypothesis
Research hypothesis
Null hypothesis
Null hypothesis
Statements that contain two or more things that are equal(unrelated) to one another(no difference)
Refers to populations and are written in Greek symbols
Research hypothesis
Statement that there is a relationship between two variables
Statement of inequality
Refers to samples and are written in Roman symbols
Two types of research hypothesis
Directional and non-directional