final Flashcards
positive correlation
the relationship is such that a high score on one variable is associated with a high score on the second variable
-a low score relates to a low score
negative correlation
an inverse relationship
-high scores on one variable are associated with low scores on the second variable, and vice versa
assumption of linerarity
- the relationship between variable X and Y is linear - neither increasing nor decreasing (monotonic) (when the line “levels” out)
- violation of this would have the effect of reducing the size of the correlation
restricting the range
- limit the data in a population to some criterion (i.e., SAT scores 1200 and higher), or use a subset of data to determine whether two pieces of information are correlated, or connected. so…“SAT scores will produce higher college GPA”
- of one or both of the measured variables weakens the correlation
- not representational information/data
coefficient of determination
- a better interpretation of a correlation
- found by squaring the Pearson’s r – coefficient will always be a positive number, regardless if the correlation is positive or negative
- the portion of variability in one of the variables in the correlation that can be accounted for by variability in the second variable (i.e., SAT scores and the correlation to GPA)
regression analysis
- making predications on the basis of correlational research
- correlational research provides the foundation for using psychological tests to make predictions
- if you a statistically significant correlation exists between two variables, then knowing a score on one of the variables enables you to predict a score on the other
basic formula for regression lines
Y = a + bX
y: criterion variable; value you’re attempting to predict
a: y-intercept of the regression line
b: slope of the regression line
X: predictor variable; known value
directionality (correlations and causality)
-the casual relation could occur in either direction
A causing B or vice versa
-one cannot decide the direction of the causality
cross-lagged panel correlation technique
a type of correlational research designed to deal with the directionality problem
-if variables X and Y are measured at two different times and if X preceded Y, then X might be causing Y but Y cannot cause X
third-variable problem
if there is a strong correlation between X and Y, it is possible that X caused Y or Y caused X OR something else cause both X and Y
partial correlation
statistical procedure that allows you to remove the effects of the value of some know “third-variable” from the equation in order to see what correlation remains after that removal
Psychometric correlation use
- establish reliability of a test/measurement
- establish validity of a test/measure
Personality and Abnormal psychology correlation use
- trying to figure out if one attribute leads to another
- i.e., are attractive people happier or is it the happier you are, the more time you spend on appearance, or does an aspect of personality (i.e., extraversion) influence attractiveness, etc.
- e.g., Sleman: learned-helplessness
- attributional style questionnaire and Beck Depression Inventory
Results: severity of depression significantly correlated with pessimistic explanatory style
Nature-nurture correlation us
- heritability of IQ?
heritability of shyness?
bivariate analysis
a statistical analysis investigating the relationship between two variables
multivariate analysis
a statistical analysis investigating the relationships among more than two variables
i.e., multiple regression and factor analysis
factor analysis
type of statistical procedure that is conducted to identify clusters or groups of related items (called factors) on a test
basic research
goal is to increase our core knowledge about human behavior and mental processes in psychology
-usually takes place in a laboratory
applied research
designed primarily to increase our knowledge about a particular real-world problem with an eye toward directly solving it
-conducted in clinics, social service agencies, jails, gov’t agencies, and business settings
quasi-experimental designs
- used if subjects cannot be randomly assigned
- “quasi” means lack of control and therefore have a lower status of being “true”
- great value in applied research
non-equivalent control group
- two groups are compared
- no random assignment bc participants cannot or should not be separated (i.e., at a mental health institute, you can’t give one group therapy and not the other– that’s unethical but you can give them “new” therapy vs. “old”therapy)
- groups are not equal at the start of the study
Schematic:
O (obs) X (manipulated) O
O O
interrupted times series design
special type of time series where treatment/intervention occurred at a specific point and the series is broken up by the introduction of the intervention.
–If the treatment has a causal impact, the post- intervention series will have a different level or slope
O1 O2 O3 X O4 O5 O6
initial obs/manip / followup
allows for the analysis of trends in the data, both before and after the manipulation
archival research
a method in which existing records are examined to test a hypothesis
i.e., census data, gov’t files, diaries, medical records, etc.
ADV: used for gathering historical data, not hard to get, low reactivity
DISADV: access to private records may be more limited, make due with what is in the data, no control over the manner of data collection
formative evaluation
form of program evaluation that monitors the functioning of a program while it is operating to determining if it is functioning as planned