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;
142 Cards in this Set
- Front
- Back
- 3rd side (hint)
Intuition
|
personal judgement or a single story about one's personal experience
-tells us about the world |
finding an explanation for our own behaviors or the behaviors of others
|
|
ex. conclusion that when you adopt a child, you conceive one shortly after
|
intuition
|
problem: we may draw conclusions about cause and effect-illusory corrleation
|
|
authority
|
we are more likely to believe a speaker sho is prestigious, trustworthy, and respectable
|
ex. aristotle
|
|
use of objective observations to answer question about the nature of a behavior
|
empiricism
|
-knowledge is based on observations
-data are collected |
|
to conclude a causation:
|
-covariation of cause and affect
-temporal precedence -elimination of plausible alternative explanations |
|
|
covariation of cause and effect
|
cause is present, effect occurs
when cause is NOT present, effect DOES NOT occur |
|
|
temporal precedence
|
a temporal order of events in which the cause COMES BEFORE the effect
|
1. cause=tv viewing
2. effect=aggression |
|
elimination of alternative explanations
|
-nothing other than a causal variable could be responsible for this observed effect
|
ex. children who watch a lot of TV are left alone more than those who don't.
|
|
Basic research
|
-tries to answer fundamental questions about the nature of a behavior
-theoritical issues concerning phenomena |
ex. russian memories are recalled more often when speaking russian. english memories in english
|
|
what are the personality charactieristics for this job?
|
Basic research
|
|
|
applied research
|
conducted to address the issues in which there are practical problems and potential solutions
|
violence and sex impair memory for TV ads.
|
|
measure personality and use to determine best personalities for the job and hire accordingly
|
applied research
|
|
|
skeptical attitude
|
ideas must be evaluated on the basis of careful logic and results from scientific investigation.
|
|
|
type of idea or questions
-makes a statement about something that may be true |
hypothesis
|
|
|
when is a hypothesis not testable?
|
when the hypothesis is circular
concepts are poorly defined -involves non scientific ideas or forces |
MUST be observable
not "the devil made me do it" |
|
a systematic body of ideas about a particular topic or phenomenon
|
theories
|
|
|
what do theories do?
|
ORGANIZE and EXPLAIN a variety of specific facts or descriptions of behaviors
-these facts are NOT meaningful by themselves |
|
|
what else do theories do?
|
generate new knowledge by focusing our thinking so that we notice new aspects of behavior
|
NOT the same as hypothesis
-grounded on actual data from prior research MUST be falsifiable |
|
Parts of a scientific manuscript
|
Abstract
intro method results discussion |
|
|
ethical research (milgram's obedience study)
|
participants met another "participant"-Mr. Wallace who was hooked up to electric shocks
-shocked him |
showed the human inability to resist authority
|
|
belmont report
|
set of guidelines for the TREATMENT OF PARTICIPANTS
|
|
|
beneficence (from belmont report)
|
Maximum results,
minimum risks |
|
|
benefits from beneficence
|
education
treatment for condition satisfaction with contributing to research money |
|
|
risks from beneficence
|
physical harm
psychological stress debriefing loss of privacy and confidentiality -naturalistic observation and privacy issues |
|
|
autonomy (belmont report)
|
decision whether or not to participate
-INFORMED CONSENT FORM-can quit at any time..etc. |
|
|
justice (from belmont report)
|
selection of participants
make sure to choose a variety of participants equally exposed to drugs |
|
|
IRB
|
Needs to have IRB
-at least 5 people, 1 from outside institution -NOT peer review process -submit application to IRB for review and approval |
|
|
debriefing (from belmont report)
|
researcher reveals full nature of experiment
makes sure not distress was experienced |
|
|
operational definition of a variable
|
in terms of the operations of techniques that a researcher uses to MEASURE/MANIPULATE
|
ex: anxiety:
self report questionnaire number of foot taps amount of sweat |
|
nonexperimental method
|
observe or measure variables of interest
behavior is observed as it NATURALLY HAPPENS |
CORRELATIONAL method
cannot determine direction of cause and effect |
|
experimental method
|
directly manipulating and CONTROLLING variable
MANIPULATE 1 variable and measure another |
researcher manipulates the IV and controls all other variables either by RANDOMIZATION or by DIRECT EXPERIMENTAL CONTROL
|
|
Variable that is MANIPULATED to observe its effect on the dependent variable
|
IV
|
|
|
Variable that is the subject's response to, and dependent on the level of the independent variable
|
DV
|
|
|
a relationship in which INCREASES in the values of the first variable are accompanied by both increases and decreases in the values of the 2nd variable
|
curvilinear relationship
|
|
|
diagional lines-show relationship between variables-like correlation (pos and neg)
|
linear relationship
|
|
|
flat line
|
no relationship
|
|
|
degree to which a measurement device accurately measures the theoretical construct it is designed to measure
|
construct validity
|
|
|
certainty with which results of an experiment can be attributed to the manipulation of the IV rather than to some other confounding variable
|
internal validity
|
|
|
different measures of the SAME CONSTRUCT give the SAME RESULT
|
convergent validity
|
if life satisfaction and pos. affect are not related-not correlated
|
|
measure of the 2 constructs that are not related so they allow us to discriminate between the 2 constructs
|
discriminant validity
|
|
|
subjects behavior changes because of the awareness of the observer
|
reactivity-like cameraman following around
|
to minimize this, allow subject to get used to observer
-conceal observer |
|
true score
|
real score on the variable
|
|
|
measurement error
|
an unreliable measure of intelligence contains considerable measurement error and does not provide an accurate indiciation of an individuals true intelligence
|
-little measurement error=reliable
-yield identical (or close) intelligence score EACH TIME |
|
pearson product moment correlation coefficient
|
r=-1 to 1
the closer r is to 1 or -1=stronger |
|
|
measuring same individuals at 2 points in time
|
test-retest reliability
|
|
|
measures what it is supposed to measure
|
face validity
|
|
|
reliability coefficient determined by the correlation between scores on half of the items on a measure with scores on the other half
|
split-half reliability
|
|
|
an indicator of reliability that examines the agreement of observations made by 2 or more raters
|
interrater reliability
|
|
|
measurement scale with categoreis with NO numeric scales
ex. males/females introverts/extroverts |
nominal
|
|
|
measurement scale with rank ordering/numeric values limited
ex. 2, 3, 5 star restaurants -intervals between variables NOT known |
ordinal
|
|
|
measurement scale with numeric properities that are literal
-assume equal interval between values ex. inteligence/aptitude test score/temp no true 0 |
interval
|
|
|
measurement scale where zero indicates absence of variable measured
does have absolute 0 ex. reaction time/weight/age |
ratio measurement scale
|
can form ratios (someone weighs 2x as much as another person)
|
|
does not test hypothesis framed before study
-qualitative in nature but can be quantative also |
naturalistic obeservation
|
|
|
observation that is only interested in a few specific behaviors-
-much less global than naturalistic -in defined settings |
systematic observation
|
reactivity is a problem here
|
|
uses previous information to answer questions
|
archival research
|
statistical records
survey archives written records (content analysis) |
|
statistical records
|
public records
ex. baseball records |
|
|
survey archives
|
consisting of data from surveys that are stored in computers and available
-cheap/free and are about NATURAL samples |
|
|
written records
|
diaries and letters
|
|
|
content analysis
|
systematic analysis of these existing documents (of statistical records, survey archives)
|
|
|
answering in a socially desirable way
"faking good" |
response set
|
a pattern of individual response to questions on a self report measure that is not related to the content of the questions
|
|
larger sample size = raises or lowers the size of CI?
|
LARGER sample size REDUCES the size of CI
|
|
|
confidence interval
|
an interval of values within which there is a given level of confidence (ex 95%) where the population lies
|
|
|
probability sampling
|
each member of the population has an specific probability of being chosen
|
used when it is important to accurately describe the population
|
|
non probability sampling
|
we don't know the probability of any particular member of the population being chosen
|
this affects ability to generalize
ex. asking psych students to knock on doors in dorm buildings |
|
ex. a computer program randomly chooses 100 students from a list of all 10000 college students
|
simple random sampling (prob)
|
|
|
ex. the names of all 10000 college students are sorted by major and a computer randomly chooses 50 students from each major
|
stratified random sampling (prob)
|
|
|
ex. 200 clusters of psych majors are identified at schools all over the US. out of these 200 clusters, 10 clusters are chosen randomly and every psych major in each cluster is sampled
|
cluster sampling (prob)
|
|
|
ex. ask students around you at lunch or in class to participate
|
haphazard (convenience) sampling (nonprob)
|
|
|
ex. in an otherwise haphazard sample, select indiviuals who meet a criterion (age of a group)
|
purposive sampling (nonprob)
|
|
|
ex. collect specific proportions of data representative of percentages of groups within population, then use haphazard techniques
|
quota sampling (nonprob)
|
|
|
sampling frame
|
the actual population of individuals (or clusters) from which a random sample will be drawn.
|
rarely will this coincide with population of interest-some biases will be introduced
|
|
response rate
|
the percentage of people in the sample who actually competed the survey. 100 out of 200 people mail back, response rate=50%
|
|
|
when researchers are able to manipulate a variable by presenting written, verbal, or visual material to the participants
|
straightforward manipulation
|
|
|
when a confederate is used
or stimulating a situation like in the real world |
staged manipulation
|
|
|
ceiling effect
|
failure of a measure to detect a difference because it was too EASY
|
|
|
floor effect
|
failure of a measure to detect a difference because it was too DIFFICULT
|
|
|
demand characteristics
|
cues that inform the subject how they are supposed to behave
any feature of the experiment that informs the participants the purpose of the study |
|
|
experimenter bias (expectancy effects)
|
any influence (intentional/unintentional) that the experimenter exerts on subjects to confirm the hypothesis under investigation
|
|
|
manipulation check
|
a measure used to determine whether the manipulation of the IV has had its INTENDED EFFECT on a subject
|
|
|
confounding variable
|
a variable that is not controlled in a research investigation
|
|
|
internal validity
|
certainty with which results of an experiment can be attributed to the manipulation of the IV rather than some other confounding variable
|
|
|
what type of design (a true experimental design) where the DV is measured only ONCE, after the manipulation of the IV
|
posttest-only design
|
|
|
what type of design is an experiment in which DIFFERENT SUBJECTS are assigned to EACH GROUP?
|
independent groups design
|
also called between-subjects design
|
|
what type of design is an experiment where the same subjects are assigned to each group?
|
repeated measures design
|
also called within-subjects design
|
|
what is an order effect?
|
the order of presenting the treatments affects the DV.
ex. greater recall in a certain condition could be because of the order of the conditions |
repeated measures
|
|
what is a practice effect? (order effect)
|
an improvement in performance as a result of repeated practice with a task
|
repeated measures
|
|
what is a fatigue effect? (order effect)
|
when performance gets worse because the participant gets tired/bored/distracted
|
repeated measures
|
|
what is a contrast effect? (order effect)
|
when the response of the 2nd condition in the experiment is altered because the 2 conditions are contrasted to one another
|
repeated measures
|
|
how would you solve order effects?
|
counterbalancing
|
|
|
what is counterbalancing?
|
using all possible orders of presenting the conditions in the experiment
|
|
|
what is a matched pairs design?
|
RANDOMLY assigning participants to groups.
goal is to first match people on a participant CHARACTERISTIC. |
matching variable will either be DV or something closely related to DV
|
|
cross-sectional method
|
randomly selecting participants from different AGE GROUPS.
different participants make up different age groups |
adv: fast
disadv: generation (cohort) effects |
|
longitudinal method
|
single group of participants is followed over time and tested repeatedly
|
disadv: may not apply to other generations
mortality (attrition) improved performance reactivity adv: allow you to see the development of behaviors. |
|
Using more than 2 levels of an IV
|
the results of an experiment with only 2 GROUPS (2 levels of an IV) will always appear to be LINEAR
|
using MORE than 2 levels of the IV reveals a CURVELINEAR or nomonotonic relationship
|
|
complex design
|
2 OR MORE IVs are manipulated SIMULTANEOUSLY in a single experiment
|
|
|
complex design=factorial design
|
can determine each IV alone (main effects) and the effect of the IVs in the combination (interaction effects)
|
1 2
3 4 |
|
what is an interaction?
|
when the effects of 1 variable depend on the level of another variable
|
you can't discuss the effect of 1 IV without considering the effect of the other IV
parallel lines generally indicate LACK of interaction |
|
what is the main effect?
|
the DIRECT EFFECT of an IV on a DV
|
|
|
what is a quasi experimental design?
|
NOT a true experiment
approximates the control features of true experiments to infer that a given treatment DID have its intended effect |
addresses the need to study the effect of an independent variable in settings in which the control features of true experimental designs cannot be achieved.
|
|
internal validity
|
are the conclusions telling us the truth?
|
|
|
problems with one group pretest-posttest design
HISTORY |
can be caused by any confounding event that OCCURS AT THE SAME TIME as the experimental manipulation
|
threat to internal validity
|
|
problems with one group pretest-posttest design
MATURATION |
any changes that occur systematically over time.
ex. problem in smoking reduction if more people become concerned about their heatlh |
threat to internal validity
|
|
problems with one group pretest-posttest design
TESTING |
taking any pretest changes the participants behavior.
|
threat to internal validity
|
|
problems with one group pretest-posttest design
INSTRUMENT DECAY |
people may get tired of recording the number of cigarettes smoked per day-leads to an apparent reduction in cigarette smoking when is not really true.
|
threat to internal validity
|
|
problems with one group pretest-posttest design
REGRESSION TOWARD THE MEAN |
when participants are selected because they score extremely high or low on some variable and when tested their scores are more likely to go in the direction of the mean.
|
threat to internal validity
|
|
problems with nonequivalent control group design
SEECTION |
when participants who form the 2 groups in the experiment are chosen from existing natural groups.
|
threat to internal validity
|
|
interrupted time series design
|
the effectiveness of the treatment is determined by measuring both before and after treatment
|
the treatment is NOT introduced at random points in time.
|
|
control series design
|
interrupted time series design with a CONTROL GROUP
|
|
|
what is a quasi experimental design?
|
NOT a true experiment
approximates the control features of true experiments to infer that a given treatment DID have its intended effect |
addresses the need to study the effect of an independent variable in settings in which the control features of true experimental designs cannot be achieved.
|
|
internal validity
|
are the conclusions telling us the truth?
|
|
|
problems with one group pretest-posttest design
HISTORY |
can be caused by any confounding event that OCCURS AT THE SAME TIME as the experimental manipulation
|
threat to internal validity
|
|
problems with one group pretest-posttest design
MATURATION |
any changes that occur systematically over time.
ex. problem in smoking reduction if more people become concerned about their heatlh |
threat to internal validity
|
|
problems with one group pretest-posttest design
TESTING |
taking any pretest changes the participants behavior.
|
threat to internal validity
|
|
problems with one group pretest-posttest design
INSTRUMENT DECAY |
people may get tired of recording the number of cigarettes smoked per day-leads to an apparent reduction in cigarette smoking when is not really true.
|
threat to internal validity
|
|
problems with one group pretest-posttest design
REGRESSION TOWARD THE MEAN |
when participants are selected because they score extremely high or low on some variable and when tested their scores are more likely to go in the direction of the mean.
|
threat to internal validity
|
|
problems with nonequivalent control group design
SEECTION |
when participants who form the 2 groups in the experiment are chosen from existing natural groups.
|
threat to internal validity
|
|
interrupted time series design
|
the effectiveness of the treatment is determined by measuring both before and after treatment
|
the treatment is NOT introduced at random points in time.
|
|
control series design
|
interrupted time series design with a CONTROL GROUP
|
|
|
single-subject experimental design
|
NOT case studies
traditionally used in studies of reinforcement and behavior modification |
|
|
reversal design: ABA/ABAB
|
A=baseline
B=treatment |
|
|
multiple baseline design
|
measure baseline in several situations (ex. aggressive behavior at home/school/daycare)
introduce treatment at different times in different situations |
|
|
a measure of variability of scores about a mean.
the mean of a sum of squared deviations of scores from the group means |
variance
|
S^2
|
|
the average deviation of scores from the mean (square root of variance)
|
standard deviation
|
S
|
|
regression equation
|
a mathematical equation that allows prediction of one behavior when the score of another variable is known
|
y=a+bx
|
|
null hypothesis
|
assuming that there is no difference between the populations from which the samples were drawn
reject null if p<.05 |
ex. the drug will have no effect
|
|
alternative/research hypothesis
|
there is a difference between the populations
|
ex. the drug had an effect
|
|
t-test
|
tests the significance of the DIFFERENCE BETWEEN MEANS
|
independent groups
repeated measures |
|
one-tailed test
|
group 1> or < than group 2
you hypothesize that group 1 LESS THAN OR GREATER THAN group 2 |
|
|
two-tailed test
|
you DO NOT SPECIFY a predicted direction of difference
say group 1 WILL DIFFER from group 2 |
|
|
ANOVA (f-test)
|
used to determine whether 2 or more means are significantly different.
|
F=ratio of systematic variance to error variance
|
|
two-tailed
|
h0: mean ofexperimental pop=control pop
hA: mean of experimental pop NOT=to control pop |
|
|
one-tailed
|
h0: mean of experimental pop is less than OR EQUAL to control pop
hA: mean of experimental pop is greater than control pop |
|
|
if p<.05
|
conclude that sample means are significantly different
|
IV had an effect
|
|
if p>.05
|
conclude that the sample means are not significantly different
|
IV did not have an effect
|
|
type 1 error
|
when the null hypothesis is TRUE but you REJECT it.
IV had no effect but you conclude IV had an effect |
False alarm
ALPHA |
|
type 2 error
|
IV had an effect but you conclude that it did not
null is FALSE but you DO NOT REJECT it |
Miss
BETA |
|
prob of correctly deciding null is false
|
1-B
|
POWER
|
|
a limitation on generalization is an...?
|
interaction
|
ex. 2 different subject groups of the population would BEHAVE DIFFERENTLY
|
|
best evidence for external validity is ?
|
REPLICATION with different populations/situations/times
|
|
|
exact replication
|
allows you to relate your results to previous results
to confirm a surprising or unexpected result |
extraordinary claims require extraordinary proof
|
|
conceptual replication
|
replication of the conceptual relationship between variables using DIFFERENT PROCEDURES and DIFFERENT PARTICIPANTS
|
measuring DV in operationally different ways.
|
|
meta-analysis
|
a set of statistical procedures for COMBINING THE RESULTS OF A NUMBER OF STUDIES in order to provide a GENERAL ASSESSMENT of the relationship between variables
|
|