2360 FINAL

chapters 8-13

what are the three things needed to establish cause and effect relations?

covariation, temporal precedence and eliminating extraneous variables

experimental designs have the ability to identify...

cause and effect relations between variables

covariation

when changes in one variable are associated with changes in another variable; part of determining causality -- 2 variable must vary or change together in a systematic way

covariation tells us two variables relate to each other

cannot establish causation

temporal precedence

when changes in the suspected cause (treatment) occur before changes in the effect (outcome)

without temporal precedence you cannot determine...

which variable is the cause and which is the effect

correlational designs can establish covariation, but cannot establish ___ ___

temporal precedencee

experimental designs can establish ____ _____

temporal precedence

extraneous variable

any factor separate from the independent variable that could account for variations in the dependent variablei

internal validity

degree to which you can rule out other possible causal explanations for an association between the independent and dependent variable

mundane realism

how closely our study parallels to the real worldtw

two group design or simple experiment

experimental design that compares two groups or conditions and is the most simple way to establish cause and effect

the _____ group gets the key treatment, while the ____ group does not

experimental, control

experimental control

the ability to keep everything between groups the same except for the one element you want to test

the goal of experimental control is to..

have only one element vary between groups - the factor the researcher wants to test

all or nothing comparison

comparison where one group gets all and other gets nothing (treatment)

problems with all or nothing comparisons

quality of the manipulation

can lead to many differences between groups

how to create quality groups?

be sure to have a high degree of experimental controla

little more versus a little less approach

experimental group gets a little bit more of the treatment - control group gets a little less

experimental hypothesis

make a clear and specific prediction of how the independent variable will influence the dependent variable

directional hypothesis

predict the direction of the difference between groups -- specify which group would have higher (or lower) scores on the DV

where do researchers store observations and data?

researchers keep a log or field notes to use as data

if the results of your t-test for independent means are statistically significant, what does that mean?

the difference between the two experimental groups was the product of legitimate variable manipulation and not happenstance

often in experiments with study groups ____ is lost because people start acting like or sharing opinions similar to other people in their assigned study group

independence

if you are interested in determining whether fatigue causes a negative mood state you would need to conduct an...

experiment

experimental realism

when someone becomes so involved in the study that they are influenced by ito

the ____ ____ is manipulated in an experiment

independent variable

multigroup design

experimental design with 3 or more groups -- when we have more than 2 possibilities to test

allows us to have multiple levels of the IV

within-subjects design

all subjects participate in both levels of the independent variable

3 types of within-subjects designs

pretest-posttest, longitudinal design, repeated measures design

factorial design

a design in which all levels of each independent variable are combined with all levels of the other independent variables

allows investigation of the separate main effects and interactions of two or more independent variables

mixed design

includes within and between subjects in the same design

programs evaluation

involves using scientific method to assess whether an organized activity is achieving its intended objectives

in two group designs, it is important to minimize interactions between participants to maintain independence

true

random assignment

any method of placing participants in groups that is nonsystematic and unbiased, and ensures each participant has an equal chance of being in any group

matched pair design

makes sure both groups have participants who are similar, or matched, on important trait -- then randomly assign one to experimental group and other to control group

between subjects design

expose participants to only one of two groups - one condition of an experimentre

researcher notes

keep track of anything out of the ordinary that happens during the study

manipulation check

measure that helps determine whether the manipulation effectively changed or varied the independent variable across groups

should find a difference between groups to be certain we adequately manipulated our independent variablea

a t-test for independent means (independent samples t-test) should be used when comparing the means of ____ groups.

two

If you want to compare more than two groups, or do multiple pairwise comparisons, what tests should you use?

ANOVA or post-hoc test

control group

a comparison group; the participants in a study that receive no intervention

experimental group

the group that gets the treatment

independence

the assumption that each participant represents a unique and individual data point

effect size

a statistical measure of the magnitude of the difference between the groups

null hypothesis

the hypothesis of no difference; usually the hypothesis the researcher is trying to statistically reject

what is the major benefit of experimental designs?

ability to establish cause and effect relationships

what is the difference between a directional and non directional hypothesis?

directional states the direction of outcome, non directional states a correlation

t test for independent means

a statistical test comparing the groups' means to see if the groups differ to a degree that could not have just happened accidentally or by chance; also known as an independent samples t-test