
3 necessary conditions for causation
 A precedes B
 A and B must covary (B must occur when A does)
 A must be the most plausible cause for B with other potential causes ruled out

Why conduct a nonexperimental study?
Some variables cannot be experimentally manipulated (ex: gender, love/hate); Some processes take too long to study experimentally; CAN be used as a means of suggesting, clarifying, refining, or extending experimental research findings

It is not possible to make determinations of causation with a correlational study because of _______ and ______
third variable problem; directionality problem

This is the correlation between X and Y, with Z held constant
partial correlation

a variable that accounts for the relationship between 2 other variables
mediator variable

variable that specifies when effects will hold
moderator variable

Comparisons of two or more groups that are differentiated on a preexisting variable/grouping; the variable is measured, not manipulated
quasiexperimental research

examples of quasiexperimental research
 Sex differences in abilities
 Differences among psychiatric populations
 Different cognitive skills of children in various age groups
 Change in attitude towards research methods before and after the course

Measuring attributes over time can also be ________ IF there is not a random assignment to conditions OR a control group for comparison
quasiexperimental

QuasiExperimental research may be subject to
selection bias

weakness of nonexperimental study
inability to establish causation

Pros of correlational research
Allows us to study the relationship between two or more variables; quantifies the strength of the relationship between two or more variables; it can be used to predict values for one variable from values for other variables (regression analysis)

Magnitude and Sign of r
 Small: r = .20.29
 Medium: r = .30.49
 Large: r = .501.0

simultaneously analyzing multiple variables
multivariate analysis

in regression analysis, the _____ is the known variable; The ______ is the predicted variable
predictor; criterion

Regression analysis can be extended to ________ (using several predictors for one criterion)
multiple regression

Quasiexperiments may look a lot like an experiment, but it lacks ___________
random assignment

In quasiexperiments we use a nonmanipulated independent variable, or...
classification variable

a research design where patterns of scores over time are compared before a treatment is implemented and after a treatment is implemented
time series design

If I measure your attitudes about research methods before we begin the class, and then again after class,
then the change in attitude (better or worse) could be because of the class or some other events that occurred during the between the tests
pretestposttest design

during time series design, treatment is an independent event that researchers have no control over
interruped time series design

during time series design, treatment is implemented by the
researcher (i.e., examining a new therapy technique).
noninterruped time series design

advantages to singlesubject designs:
ability to focus on individual performance; don't leave individuals untreated in control groups; allow flexibility in design

major disadvantages to singlesubject designs
some effects are small and can't really be seen in one subject; sometimes you can't try out different variables on the same subject and you must use betweensubject designs.

commonly used singlesubject designs
Time Series; Interrupted Time Series; Multiple Time Series; “AB” Designs

a statistical technique that allows you to combine effect sizes or significance testings from many different studies
metaanalysis

Committee that reviews proposals of intended research and evaluates if the research is ethical and if the rights of the participants are being protected
Institutional Review Board (IRB)

written or verbal acknowledgment that subjects know
what they are getting into and that they have these rights
informed consent

by commission, when a research deliberately misleads the participant (provides false information, or uses a confederate)
active deception

by omission, when a researcher withholds information about the nature of a study from the participants (not fully
explaining the purpose of the study when it starts)
passive deception

describing the nature of the research after participation
debriefing

a strategy for selecting study participants in which each and every person has an equal and independent chance of being selected
random sampling

the most straightforward of the random sampling strategies. We use this strategy when we believe that the population is relatively homogeneous for the characteristic of interest
simple random sampling

take every nth person from the sampling frame; not a random sampling strategy
systematic sampling

treats the population as though it were two or more separate populations and then randomly samples within each
stratified random sampling

begin by stratifying the population into relevant subgroups and then random sampling within each subgroup. The number of participants that we recruit from each subgroup is equal to their proportion in the population.
proportionate sampling

useful when it would be impossible or impractical to identify every person in the sample; ex: Rather than randomly sample 10% of students from each class, which would be a difficult task, randomly sampling every student in 10% of the classes would be easier
cluster sampling

Ex: To obtain a representative national sample, researchers may select zip codes at random from each state. Within these zip codes, streets are randomly selected. Within each street, addresses are randomly selected
multistage sampling

uses a "manonthestreet" technique to recruit those who wander by or selects a sampling frame that does not accurately reflect the population
haphazard sampling

targets a particular group of people
purposive sampling

selects a particular group of people but it does not come close to sampling all of a population
convenience sampling

A key aspect of experiments that allows test of causal relationships is the manipulation of the ________
independent variable

Another key feature of experiments is the control of factors that could affect the results but are not part of the independent variable(s) manipulated. These extraneous factors are called _________
confounding variables

If confounding variables are not ______, the causal relationship between the independent and dependent variables will be unclear
controlled

If an EV affects the groups in an experiment differentially, we do not know whether the IV or EV is resulting in the differences in the DV. In this case, we say that the results of the experiment are:
confounded

an error in data collection based on poor measuring
instruments or human error
measurement error

Extent to which items on a test, inventory, questionnaire, adequately measure the construct they are supposed to measure
content validity

degree to which a test or other measure assesses the underlying theoretical construct it is supposed to
measure
construct validity

Two major types of validity
test and experimental

Extent to which a measure correlates with other indicators of a construct
convergent validity

Extent to which a measure does not correlate with other measures that do not measure the construct of interest
discriminant validity

Are the statistical tests accurate and appropriate? The degree to which conclusions reached about relationships between variables are justified
[statistical] conclusion validity

Do the results apply to the broader population of people and situations? Generalization.
external validity

Was the independent variable the sole cause of the change in the dependent variable? Have we ruled out all possible sources of confounding?
internal validity

incorrectly rejecting null hypothesis
type I error

incorrectly failing to reject the null hypothesis
type II error

The tendency by participants to act differently than normal because they know they are being studied
Hawthorne effect

The tendency by participants to respond to what they think the experimenter wants (or demands) from them
demand characteristics

The tendency to feel inadequate or to experience unease when being observed
evaluation apprehension

Treatment effects that are due to participants’ expectations that the treatment will work
placebo effects

Any factor that creates groups that are not equal at the start of the study; threat to validity
selection

Changes due to normal growth or predictable changes; threat to validity
maturation

Loss of participants during a study. The participants who drop out may be different from those who continue; threat to validity
attrition

Changes due to an event that occurs during the study, which might have affected the results; threat to validity
history

Changes in participants’ behavior in one condition because of information they obtained about the procedures in other conditions; threat to validity
diffusion of treatment

Any change in the calibration of the measuring instrument (especially human measuring instruments) over the course of the study; threat to validity
instrumentation

Effects on performance in one condition due to experience with previous conditions; These are
of concern whenever a participant is tested more than once under different conditions; threat to validity
order of sequence effects

Changes due to the effects of previous testing; threat to validity
testing

Participants selected because of extreme scores will on average be less extreme on a retest; very common in psyc research; threat to validity
regression to the mean/statistical regression

Any preconceived idea by the researcher about how the experiment should turn out can influence the results. (not deliberate – e.g. scientific fraud)
experimenter bias

both the participant and the experimenter are unaware of the condition the participant is assigned to
doubleblind

about assignment to the condition
random assignment

randomly select individuals from the population for your study
random selection

One way to control extraneous factors is through ______ to the various levels of the IVs
Random assignment

Two or more independent variables makes it a ______
factorial design

Why is random assignment used?
To equate the differences we might see among individuals; to control extraneous factors

The most effective way to minimize many of the threats to validity is to have a _______ and ________
control group; random assignment

Way to minimize observer effect (experimenter bias):
use a blind procedure

Ways to minimize participant effects (Hawthorne, demand characteristics, evaluation app, placebo):
Observe participants unobtrusively, make responses anonymous, us deception, ask participants abt their perceptions of the purpose of the exp

Way to minimize diffusion of treatment threat:
blind procedure, use of deception

Way to minimize selection threat:
random selection & random assignment

Ways to minimize history and maturation threat:
Use of a control group, possibly shorter duration of experiment

Ways to minimize testing, order effects:
using research design without a pretest; use of unobtrusive measures; counterbalancing; using different equivalent pretest/posttest

Way to minimize instrumentation threat:
careful specification and control of the measurement procedures; standardized instruments;

Ways to minimize statistical regression threat:
use of control group; avoid use of extreme scorers

Ways to minimize attrition threat:
Use of a large group, or followup with a portion of those who leave study

test the individual under only one treatment or research condition (sometimes referred to as independent groups)
betweensubjects design

test the same person under two or more research conditions (sometimes referred to as repeated measures)
withinsubjects design

test used when comparing 2 means
 between: t test
 within: repeated measures t test

test used when comparing more than 2 means
 between: oneway ANOVA
 within: repeated measures ANOVA

test used when comparing more than 4 means across at least 2 factors
mixed: factorial ANOVA

