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;
22 Cards in this Set
- Front
- Back
|
Descriptive Studies
|
o condensing findings into one study
• Easy to do (questionnaires) • Have their place in research, beneficial for identifying right now or current problems. They are involved in thought and not just easier to do. |
|
|
Longitudinal studies
|
Measure how things change over time. 4 Types:
Trend, Cohort, Panel, Cross Sectional |
|
|
Trend Study
|
many samples are taken from one population changing at different time periods.
Participants change each time the trend is measured (no set timeframe) |
|
|
Cohort Study
|
Many samples from an unchanging population.
Example: people who attended nasp 2011 (set list) |
|
|
Panel Study
|
we take one sample from one clearly defined population and then we measure it across time.
Same sample every time we measure |
|
|
Cross Sectional
|
Many samples from many different populations all at once.
Snapshot in time ex: survey of all grades at once or a survey of how long members have been a part of NASP. |
|
|
Causal Comparative Studies
|
Does not involve manipulation of an independent variable, so it's not a true experiment.
Simply comparing two groups (men vs. women) Idea is to focus on the characteristic on which they are different. (Comparing Gender w/IQ). Finding a characteristic between the two groups that causes the difference. Gives us food for thought & helps us identify nuisance variables that the two groups have in common |
|
|
Matching
|
Pair people up in some way to have the same characteristics based on match-ability to rule out extraneous variables.
|
|
|
Correlational Studies
|
Tells us the strength and the direction of the linear relationship between 2 variables – it is also unitless. Pure measure of strength and relation
• Can range from -1 to +1 - rρ (correlation coefficient in a sample (r) or population ρ) • -1 = perfect negative linear relationship (as one goes up the other goes down) • +1 = perfect positive linear relationship (as one goes up the other goes up) • 0 = perfectly balanced = no linear relationship between the two variables • Sign (+,-) tells us the direction of the relationship • Strength is determined by the numerical value. Closer the number is to 1 the stronger the relationship, closer to 0 is a weaker. • A restriction in range will decrease the size of the correlation coefficient and strength in correlation (number will get closer to 0) • When you compute a correlation coefficient it does not matter what you label “x” and what you label “y”. It just says that they are (un)related linearly. |
|
|
Percentage of variability (variance)
|
When you square the correlation coefficient you get the percentage of variability (variance) of one variable accounted for by its linear relationship with the other variable
|
|
|
The Crudd factor
|
everything correlates to everything else, but is there anything meaningful to it? Probably not.
|
|
|
The Shotgun approach
|
having a big correlation matrix, correlating everything and seeing what comes up. Not the best approach. All you have really found is type one error.
|
|
|
Prediction
|
Stems from industrial organizational psychology. How to select from a pool of applicants for some position.
|
|
|
X axis = prediction
|
(interview, gre, grades) given to see if they will meet y.
|
|
|
Y axis = criterion
|
expected success in the program
|
|
|
Xc
|
Predictor cut score (if u score above this you get the job/get into the program)
|
|
|
Yc
|
criterion cut score (above is succeeded, below has failed)
|
|
|
Base Rate
|
Proportion of the TOTAL population that would SUCCEED if we ADMITTED EVERYONE
BR = A+D/N |
|
|
Selection Ratio
|
Proportion of population who GET IN to the program or get the job.
SelR = A+B/N |
|
|
Success Ratio
|
Proportion of those who get in to the program that are also successful.
SuccR = A/A+B |
|
|
Increasing predictor cut score (Xc)
|
Base Rate does not change
Selection Ratio decreases Success Ratio increases |
|
|
Increasing criterion cut score (Yc)
|
Base rate decreases
Selection Ratio does not change Success Ratio decreases |
