| Terms |
Definitions |
|
Replication
|
?
|
|
Reliability
|
?
|
|
Meta-analysis
|
?
|
|
Median Position
|
(n+1)/2
|
|
Stratified sampling
|
?
|
|
Demand characteristics
|
?
|
|
Naturalistic observation
|
?
|
|
Bar Chart
|
?
|
|
Control group
|
?
|
|
Laws
|
• More definitiveo Substantial evidenceo More “absolute” than a theoryo Theories explain laws• Exampleo Fechner’s law• As we experience more of a srimukys psychphysics• Law of closure
|
|
Null hypothesis prediction
|
?
|
|
Psychosocial effect
|
Experimenter bias--researcher's attitudes affect participant's behavior
|
|
Measurement error
|
any inaccuracy in measurement
|
|
response style
|
habitual way of responding
|
|
Variables
|
Characteristics or conditions that change or have different values for different individuals.
|
|
Negative Correlation
|
inverse relationship between facotrs
|
|
Time-sampling error
|
spurious changes in performance measured at different points.
|
|
matching
|
a procedure for creating equivalent groups in which participants are measured on some factor, expected to correlate with the dependent variable, groups are then formed by taking participants who score at the same level on the matching variable and randomly assigning them to groups
|
|
participants
|
how you got participants
number of participants
population drawn from
|
|
Observer drift
|
Observer changes criteria for recording behaviors over time
|
|
Experiment
|
The systematic manipulation of some environment in order to observe the effect of this manipulation on behavior; a particular comparison is produced
|
|
telephone survey
|
Participants are contacted by telephone and asked questions directly Can be done by a live researcher or by using Interactive Voice Response (IVR) technologyQuestions must be asked carefullyThe plethora of “junk calls” make participants suspicious
|
|
scatterplot
|
a graph depicting the relationship shown by a correlation
|
|
Converging Operations
|
many studies yielding the same outcome
|
|
Selection by maturation
|
refers to individual differences within various conditions that lead to changes over time (subgroups within various conditions that change at different rates)
|
|
event sampling
|
only certain behaviors occuring in predefined conditions are studied
|
|
experimental contamination
|
a situation that occurs when participants in one experimental condition are indirectly affected by the independent variable in another experimental condition because they interacted with participants in the other condition
|
|
experiments
|
casual conclusions can be drawn from this type of research
|
|
External validity
|
occurs when the causal relationship discovered can be generalized to other people, times and contexts. Correct sampling will allow generalization and hence give validity.
|
|
Reactivity
|
A possible reaction by participants in which they act unnaturally because they know they are being observed
|
|
Generalizability
|
"The issue of whether a particular experimental result will be obtained under different circumstances, such as with a different subject population or in a different experimental setting"
|
|
Methods of ealuating interrater reliability
|
Percent agreementCohen’s KappaPearson Product-Moment Correlation
|
|
2 types of order effect?
|
Fatigue & practice
|
|
ABA is a ___ design
|
within subjects design
|
|
Field Experiments
|
conducted out in the real world
|
|
Name the threat: in testing the effects of alcohol on performance, two groups are tested. One group receives drinks containing alcohol while the other does not. Both groups show a decrease in performance.
|
Placebo Effect
|
|
Coding guide
|
tells viewers what variables are and what they are represented by
|
|
dependent variable
|
thought to be the effect of something
|
|
Intercortile Range (IR)
|
Distance between datapoint 25% and 75%
|
|
sensitization effects
|
effects that may occur in a within-subjects experiment when participants become aware of the purpose of the experiment as they serve in more than one experimental condition; sensitization effects may lead researchers to conclude that participants' performance was due to the independent variable when it was actually caused by serving in multiple conditions of the experiment
|
|
interaction
|
the combined effect of two or more independent variables such that the effect of one independent variable differs across the levels of the other independent variable(s)
|
|
Post-hoc tests
|
inferential stats that are used after a significnt F-test to determine which means differ
|
|
HYPOTHETICAL CONSTRUCT
|
is an abstract concept used to relate and describe behaviors according to their underlying features.
EX: We describle ppls mental capacities using the construct of intelligence.
|
|
Ratio scale
|
true zero, can “do math” – weight, # of problems correct, kelvin
The highest form of scale in which there is a true zero and in which it is meaningful to consider multiplicative differences among attributes
|
|
Importance of debriefing
|
Make sure subjects understand what happened
Rectify negative feelings
Remove harmful after effects
Return subjects same psychological state
|
|
Frequency Method
|
Record the frequency of a behavior Usually within a time period
|
|
between groups
|
two or more groups are measured once
|
|
Main effect
|
When the effect of one independent variable is the same at all levels of another independent variable
|
|
factorial design
|
any experimental design with more than one independent variable
|
|
Participant Observation vs. Ethnographic Study
|
P: experimenter joins group, usually short termE: experimenter immersed in group for an extended period
|
|
convergent validity
|
scores on the measure are related to other measures of the same construct
|
|
repeated measures design
|
an experimental design in which each participant serves in more than one condition of the experiment; a within-subjects design
|
|
Null Hypothesis
|
hypothesis that the IV will not have an effect, equivalently the hypothesis that that means of various experimental conditions will not differ
|
|
Sampling frame
|
Subset of a population from which a sample is actually selected.
|
|
Difference threshold
|
The average point at which two stimuli are judged to be different (half of the interval of uncertainty)
|
|
predictor and criterion variables
|
Pred: intelligence CRIT: academic achievementPRED: attention CRIT: Recall PRED: stress Crit: Performance at workPRED: social support CRIT: Depression
|
|
multiple baseline across situations
|
initial baseline phases corresond to the same behavior in two separate situations
|
|
Complete Counterbalancing
|
the use of all possible orders of experimental conditions to counterbalance limitation effects
|
|
What are demand characteristics?
|
when participants pay attention to cues and info available in a situation ("demand" particular responses)
|
|
advantages of using repeated measures design in randomized experimenting
|
It requires fewer participants
It gives a more sensitive measure of the effects of a variable
|
|
Type II
|
type of error made when you fail to reject null when it is false
|
|
Type 2
|
occurs when we fail to reject a false hypo
|
|
internet research and ethical issues
|
Internet research has special ethical issuesHow do ethical guidelines developed for traditional research settings apply to Internet research?Many traditional ethical principles have direct applications to Internet researchThree areas where Internet research poses special problemsInformed consentPrivacy and confidentialityThe use of deception
|
|
converging operational definitions are not static, they are....
|
modified as we gather more data
|
|
The primary advantage of within-subjects designs over between-subjects designs is that within-subjects designsa. are unable to test for interactionsb. avoid, by definition, the problem of equivalent froupsc. avoid, by definition, the problem of sequ
|
b! avoid, by definition, the problem of equivalent groups
|
|
Scales of Measurement: Interval
|
A scale in which the unites of measurement between the numbers on the scale are all equal in size. EX. Temperature and many different Psych tests.
|
|
primacy and recency effect
|
if you give someone 20 words to remember, they are going to remember the first and last words.
|
|
What are the advantages of factorial designs?
|
1. economical (allow for testing multiple hypotheses with fewer particpants...efficient)2. interpretation (of several hypotheses, ability to talk about interaction, generalizeable)
|
|
correlational research: when is it used?
|
When gathering data in the early stages of researchWhen manipulating an independent variable is impossible or unethicalWhen you are relating two or more naturally occurring variables
|
|
What does the sums of squares withing-groups (SSwg) indicate?
|
total error variance of the data
|
|
why is AB an invalid way to evaluate therapy?
|
because changes occurring during treatment in the b phase may be cause by other factors that confounded with the factor of interest
|
|
Kohan's Kappa formulas
|
Pk = (Pc - Po)/ 1 - PcPo = (A1 + A2)/observation total Pc = ((C1 * R1) + (C2 * R2))/ total squared
|
|
Why are selection and additive effects with selection different from the other 6 threats to internal validity?
|
They are the only 2 that occur when a comparison group is added
|
