experimental psych exam 4

systematic between-groups variance

experimental variance, extraneous variance, deterministic

Nonsystematic within-groups variance

error variance, random

experimental variance

due to the independent variable

extraneous variance

due to the confounding variables

error variance

due to chance factors and individual differences, analyze the results of our study using the F-test(ANOVA), ratio of between groups variation to within groups variation

Maximizing experimental variance

real differences between the groups on the independent variable, manipulation check, multiple levels, increase differences between groups

controlling extraneous variance

groups as similar as possible at the start of the study, random assignment, select participants who are similar (limits external validity), build a confound into the study as another IV, the only difference is the independent variable manipulation

minimizing error variance

careful measurement, control over setting, reliable measures, special designs(ex. correlated group designs), within groups designs eliminates the typically largest source of error variance which is individual differences, control in research is control of variance

nonexperimental designs

do not include the critical controls of experimental designs, may still be used but caution is necessary, 4 designs( ex post facto design, single group posttest only design, single group pretest posttest design, pretest posttest natural control group design)

ex post facto design

a very weak design, what we do when we try to figure out after the fact what caused something to happen, not good science, does not control confounding variables

single group posttest only design

even with the manipulation virtually no control over confounding variables, we tend to use an implicit control group (What we think would have happened if there had been no manipulation)

single group pretest posttest design

the pretest documents that change occurred but factors other than the treatment could have accounted for the change, history, maturation, regression to the mean, etc.

pretest posttest natural control group design

like an experiment except that participants are not randomly assigned to the groups, a reasonably strong design except that it does not control for selection, selection could be a powerful confounding factor in many studies

experimental designs

meet all criteria for an experiment, provide more powerful tests of hypotheses, 3 designs(randomized posttest only control group design, randomized pretest posttest control group design, multilevel completely randomized between subjects designs)

randomized posttest only control group design

random assignment controls for selection, other confounding variables are controlled by comparing the treatment and no treatment groups, for example history and maturation should be the same in both groups

randomized pretest posttest control group design

adding a pretest allows us to quantify the amount of change following treatment, also allows us to verify that the groups were equal initially, a strong basic research design with excellent control over confounding

multilevel randomized between subjects design

may or may not include a pretest, multigroup extension of the basic experimental designs, controls virtually all sources of confounding variables

solomons four group design

a way to deal with a possible pretest manipulation, combines two basic experimental designs (randomized posttest only control group design, randomized pretest posttest control group design)

within subjects design

same participants in each group, all participants are exposed to all experimental conditions, need to control for sequence effects, the experience with one condition affecting performance in subsequent conditions, controlled by varying the order of presentation (counterbalancing)

matched groups design

uses matched random assignment

correlated groups designs

introduces a correlation between groups in the way groups are formed, more sensitive than independent groups designs

sequence effects sources

positive practice effects (PPE), negative practice effects (NPE), carryover effects

positive practice effects (PPE)

controls: control PPE with prior training

negative practice effects (NPE)

controls: control NPE with rest intervels

carryover effects

controls: control carryover effects by varying the order of conditions

within subjects strengths

more sensitive to small group differences, the variability due to individual differences is statistically eliminated, no group differences due to sampling error, selection cannot be present since groups are guarenteed to be equal, fewer participants are needed, each participant appears in each condition, instructions may take less time, participants were already instructed on the task in previous conditions

within subjects weaknesses

because participants experience all conditions they may figure out the hypothesis (potential subject effects), major issue is sequence effects, practice and carryover effects, controlled by varying the order of presentation(counterbalancing, random order of presentation, latin square design)

matched subjects designs

introduces correlation through matched random assignment, should match on relevant variables, variables that affect the dependent variable, variables that show considerable natural variation in the population sampled

matching participants

match participants in sets, set size is equal to the number of conditions, matching gets more difficult as: the number of matching variables increases, matching is done on the continuous variables, the number of conditions increase, once sets are matched randomly assign participants in the set to the conditions

strengths of matched subjects designs

increased sensitivity to group differences, no sequence effects

weaknesses of matched subjects designs

extra work of matching participants, participants without appropriate matches cannot be used in the study (attrition)

factorial designs

includes two or more independent variables, essentially two or more studies in one, by testing more than one independent variable at a time we can look at the interactive effects of independent variables, most independent variables in psychology interact with other independent variables

main effects

the effect of each of the independent variables on the dependent variable is the ___ of that variable

interactions

the combined effect of two or more independent variables on the dependent variable (ex. more than just a sum of the main effects) is an ____

we must always interpret when they are present

main effects in light of interaction effects

graphing factorial designs for two independent variables

select one independent variable and label the x axis with the levels of that variable, label the y axis with enough range to graph the mean scores of each cell, graph and label the means from the first level of the second independent variable and label that line, repeat that process for each level of the other independent variables labeling each line

evaluating main effects

looking at all the people tested under each level a factor A regardless of the level of factor B, doing the same for factor B

evaluating interactions

the interaction is best seen by graphing the results, the fact that the lines are not parallel suggests an interaction which is confirmed by the ANOVA

mixed designs

the independent variables do not have to be the same, ex. all within subjects or all between subjects, mixed in both senses as also possible

mixed (within subjects and between subjects)

the ANOVA must take this into account

mixed (manipulated and nonmanipulated)

will affect the interpretation

between groups variance is a function of

experimental effects and confounding variables

which of the following is not used in correlated groups designs?

random assignment to conditions

in a factorial design, the notion "2 x 3 x 2" tells us that the design has ___ independent variables

3

in experimental studies it is important to design experiments so that

experimental conditions are clearly different from each other

a serious weakness of the pretest posttest natural control group design is that

the two groups may be statistically different from each other at the start of the study

experimental variance (question)

is due to the effects of the independent variable

the systematic effects of uncontrolled confounding variables is termed

extraneous variance

F is a ratio of

between groups variation divided by within group variation

extraneous variation generally

reduced internal validity

the soloman four group design was developed in an attempt to

control possible interaction effects of the pretest and the manipulation

extraneous variance in a study

is unwanted

in choosing relevant variables for matching in a matched subjects design it is important to note that

available is relevant if it can have an effect on the dependent

an advantage of within subjects design is that

often there is a considerable savings of time since instructions do not have to be repeated

compared with within subjects design matched subjects designs

have no practice and carry over effects

which of the following is a potential confounding factor in within subjects design but not in a between subjects design?

sequence effects

matched subjects design (question)

are sensitive to small experimental differences just like within subjects design

in a repeated measures design the single largest contributing factor to error variance has been removed. what is that factor?

individual differences

which of the following statements is true?

any number of factors can be included but interpretation of interactions is more difficult as the number of factors increases

in a graph representing results in a factorial design, a line with a steep slope probably indicates

a main effect

what does an a x b interaction mean in a two way anova?

the effect of a was different depending on the level of b

factorial experiments (question)

include two or more independent variables

a 2 x 2 factorial design

results in a four-cell matrix

in graphing the results of a 2 x 2 factorial we can conclude that if the two lines are parallel then there is

no interaction between factor a and factor b

we have 2 factors in a study one is a between subjects factor and the other is a within subjects factor. The design is called a

mixed design

in a graph representing data from a factorial design parallel lines would indicate that

there is no interaction

factorial designs include (question)

two or more independent variables

By pretesting the two groups on the dependent variable in a randomized, pretest-posttest, control group design, we

test for initial equivalence on the dependent variable

in experiments we hope to find

between-groups variance

the two characteristics that distinguish experimental designs from nonexperimental designs are

control groups and randomization

in order to test the effects of the 1988 heat wave on worker productivity 48 machinists were randomly assigned to two groups of 24 machinists each. each group was tested at a different room temperature (cool and hot) using dependent measures of number of parts produced and accuracy. what type of design does this study represent?

a randomized posttest only control group design

the denominator of the f-test reflects

error variance

which of the following is an experimental design?

none of the others

the greater the extraneous and/or error variance

the more difficult it becomes to show the effects of experimental variance

which of the following does not increase error variance?

systematic effects of the independent variable

in within subjects designs each participant

serves as his or her own control

in a research study employing a within subjects design the researchers become concerned that the hypothesis might be discernible by participants because each participant sees all of the experimental conditions. in such a circumstance it would be best to use a

matched subjects design

the major disadvantage in using within subjects designs is the possible confounding factor of

sequence effects

the major advantage of within subjects designs over between subjects designs is

individual differences are eliminated

which of the following is not a characteristic of matched subjects designs?

each participant serves as his or her own control

by using a within subjects design we not only control but actually eliminate

the variance due to individual differences

in within subjects designs (question)

each participant serves as his or her own control

what are the two types of designs used to introduce the correlation in correlated groups designs?

within subjects designs and matched subjects designs

if two independent variables have an effect on each other in a factorial research design we are primarily concerned about their

interactive effect

in a 2 x 2 factorial design represented on a graph a main effect for factor b is indicated ( the x axis labeled with the levels of factor a) but no interaction is present. the graphed lines should be

parallel

what is usually the major contributor to error variance?

individual differences

a researcher can evaluate the effectiveness of the manipulations of the independent variable by including

a manipulation check

it is necessary to design and carry out experiments so that the experimental conditions

are clearly different from each other

A general but important rule in experimentation is that each study is designed so as to

maximize experimental variance, control extraneous variance and minimize error variance

in matched subjects designs the important variables to match on are

those related to performance on the dependent measures

the research design to use when strong carry over effects are thought to be likely is a

matched subjects design

negative practice effects (question)

decrease performance of participants

within subjects designs allow a researcher to test causal hypotheses with confidence and without

randomization

When we find an interaction and a main effect, all of the effects are interpreted in terms of the

interaction

what term refers to the situation in which two independent variables have an enhanced effect when they are in combination?

interaction

a four cell factorial matrix shows that the mean scores of all groups in all conditions are the same. this would indicate that there are

no main effects or interactions

research designs that include two or more independent variables are called

factorial designs

if two lines intersect on a graph of a 2 x 2 factorial we can conclude that

there is probably an interaction between a and b