psy 240 exam 3

quasi-experiment

special efforts to limit the effects of extraneous variables so that the results may be interpreted meaningfully, if not always causally. it is designed when random assignment cannot be used

preexperimental design

weak internal validity but can still be of value when they are the only option. has few or no controls, and numerous extraneous variables

one-shot study

a preexperimental design where a single group is observed on a single occasion after experiencing some event

pretest/posttest

a preexperimental design where one group of participants is tested at pretest and posttest

pretest-posttest nonequivalent control group design

two comparable but not randomly assigned groups of participants are tested before and after treatment

time-series design

one group is tested several times before and several times after treatment

multiple time-series

two nonequivalent groups are tested several times before and several times after treatment

causation in quasi-experiments

can provide as much useful information as those of experiments and may be interpreted with nearly as much confidence

selection bias

when there are differences between the comparison groups within a study. controlled by time-series designs

interaction of selection

when extraneous variables affect one group, but not the other. controlled by time-series designs

history effects

when something occurs during the study that affects the results. can be controlled through time series and multiple time series designs

maturation effect

when someone changes as they progress. can be controlled through nonequivalent control group or multiple time-series designs

testing effects

when there are different results each time a test is done. controlled by nonequivalent control group and multiple time-series designs

subject attrition

when participants leave throughout the study. no control, researcher must watch for this confound

factorial designs

testing effects of more than one independent variable simultaneously

factors

independent variables and subject variables

main effect

each factor has an effect on the dependent measure. one of these per each IV measure

interaction effect

if one factor affects each other factor

marginal means

the means for each level of the independent variables, collapsed across the other independent variable

ANOVA

factorial designs are most commonly analyzed using this statistical procedure. tells the researcher which main effects and/or interaction effects are statistically significant

levels

the different categories or values of a factor that are being manipulated or measured in a study or experiment

correlation

used to provide info about the relationship and predict future scores

regression

a statistical technique used to predict the relationship between the outcome (dependent variable) and one or more independent variables

multiple correlation

examines the relationship between one dependent variable and two or more independent variables, indicating how well the independent variables collectively predict the dependent variable

multiple regression

a statistical method used to examine the relationship between a dependent variable and multiple independent variables. determines how each IV contributes to the outcome while controlling for other factors

pilot study

a smaller version of the study conducted to refine the research design, methods, and procedures

cell mean

mean of a particular combination of levels of the variables that divide the groups

mixed design

a factorial design where one factor is a between-groups factor and one is a within-subjects factor

higher-order factorial designs

a factorial design used when there are 3 or more independent variables.

well-designed factorial designs

clearly defined variables and hypotheses, random assignment & counterbalancing, controlling extraneous variables, good sample size, and conducting a pilot study

observational research

used for starting research on a new topic, making careful observations, taking studies into the field, sometimes the best way to answer a research question

field experiments

controlled experiments involving random assignment and the manipulation of an independent variable conducted in a natural setting

observational studies

investigations involving no manipulation of an independent variable. suggests relationships among variables but casual conclusions cannot be drawn

naturalistic observation

researchers unobtrusively observe behavior in their natural setting; the investigator does nothing to interfere with the participants’ behavior

desensitization

the researcher gradually moves closer to the participants until they can sit near or even among them; often used in animal studies

habituation

The researcher appears in the setting numerous times until their presence no longer affects the participants’ behavior. can be used for animal or human observations

reactivity

the behavior changes because of the presence of the observer

participant observation

the researcher is an active participant in the situation. the researcher can be a disguised participant or an undisguised participant

undisguised participant studies

the other participants are aware that the researcher is observing their behavior. commonly used among anthropologists

disguised participant studies

the other participants do not know that the researcher is observing their behavior.

hawthorne effect

the effect of the observer on the behavior of the subjects

observer bias

a person’s conscious or unconscious preferences can affect their perception of a situation

ecological validity

the results can be readily generalized to real life. greater for field experiments than laboratory experiments

interobserver reliability

the degree to which a measurement procedure yields consistent results when used by different observers

reliability

the consistency with which a measurement technique yields the same results

narrative records

a way to collect observational data: running records of behavior in a given situation. can be very complete or rather sketchy. can be done with audio/video recording or by handwriting notes. can be code later on and organized to generate/test hypotheses. Must make notes unobtrusive to be effective

checklist

a way to collect observational data: can be used to guide observations. can also save time by allowing the record-making procedure to be efficiently organized

static checklist

a way to collect observational data: used to record characteristics that will not change during the course of the observations. may include characteristics about the setting, weather, and how many people are present. each category must have its own operational definition

action checklist

a way to collect observational data: used to record the presence or absence of specific behaviors and characteristics over time. could be used to record the types of play behavior a child demonstrates on the plaground. can provide info simply about frequency of different categories of behaviior, or it can provide info about the order of behaviors and their duration

behavior sampling

a researcher observes subsets of a participant’s behavior at different times and/or in different situations

time sampling

the times at which observations will be made are chosen in an effort to obtain a representative sample of behaviors

random time sampling

each interval of time is equally likely to be chosen

systematic time sampling

occurs when time intervals for observation are chosen purposefully

situation sampling

observations are made in different settings and circumstances. this can greatly enhance the generalizability of an observational study

systematic event sampling

events are chosen in a purposeful manner

random event sampling

events are chosen in a manner so that each event is equally likely to be chosen, perhaps by using a random numbers table to determine events

reactive measures

assessments where participants alter their behavior because they know they are being observed, leading to potential bias

laboratory experiments

controlled studies conducted in a structured setting where researchers manipulate independent variables and measure their effects on dependent variables while minimizing external influences

advantages of observational researcher

captures natural behavior in real settings, avoids self-report biases, useful for studying behaviors unethical to manipulate

agreement

calculated by # of agreements divided by # of opportunities to agree, all multiplied by 100. above 80% is considered good

participant effects

effect on participants will be noticeable in smaller groups, greatest effect on those is closer to research. needs operational definitions to be minimized

disadvantages of observational studies

most are correlational, reactive measure, reactivity, expectancy effects, influence of observer on behavior