Study Guide Flashcards
Moderation
influences a situation either positively or negatively
Mediation
explains the relationship; critical for relationship
t-test
statistical test used to determine if there is a significant difference between the mean or average scores of two groups
Positive correlation
as one variable increases so does the other
Negative correlation
as one variable increases the other decreases
correlation coefficient
describes the direction (+ or -) and degree (strength) of relationship b/w 2 variables
Regressions
predicts the relationship b/w variables
between subjects design
different people test each condition so that each person is only exposed to a single user interface
within subjects design
a type of design in which all participants are exposed to every treatment of condition
matched pairs design
when you have different participants in 2 different conditions, but you match them according to certain variables, such as age, personality, gender and IQ
factorial design
design with more than one IV (2X2)
Univariate
analysis carried out on only one variable to summarize or describe the variable
Advantages of between-subjects design
good external validity, easier to set up; shorter sessions than within-subject designs
Disadvantages of between-subjects design
Costs more
Advantages of within-subjects design
Require fewer participants, cheaper, good internal validity
Disadvantages of within-subjects design
Order effect; fatigue; practice effect
Can you have validity without reliability?
No
Can you have reliability without validity?
Yes
When do you use a factorial design?
When you want to understand the effect of two or more independent variables upon a single DV
Nominal
Categories/names/labels/qualities; Ex- Type of car one drives
Ordinal
Data can be arranged in order; Ex- TV ratings
Interval
Temperature; year of birth
Ratio
Height/weight/age
Qualitative
Data consists of non-numerical values; Ex- college majors or hair color
Quantitative
Data consists of numerical values; Ex- Heights and body temperature
Basic research
builds on psychological knowledge
Applied research
Addresses social problems or issues
Variance
measure of how much values in a data set differ from the mean
Standard deviation
a measure of variation that indicates the typical distance b/w the scores of a distribution and the mean
Standard error
measures the accuracy with which a sample rep a population
Type 1 error
rejecting the null when it is true
Type 2 error
when you accept the null when you should reject it
Null hypothesis
statement that is the opposite of your hypothesis
fail to reject
when there is no real difference, the null is confirmed
Counterbalancing
used to deal with order effects when using a repeated measures design; does not eliminate them
Floor effect
Task is so difficult that hardly anyone performs well
Instrument decay
basic characteristic of the measuring instrumental change over time
Quasi-experimental design
address the need to study the effect of the IV settings in which central features of true experimental designs can’t be
Ceiling effect
IV appears to have an effect on the DV measure only b/c participants quickly reach max performance levels
