Experimental psych test 3

Quasi experimental design
Click the card to flip 👆
1 / 49
Terms in this set (49)
Quasi experimental design
research studies in which participants are selected for different conditions from preexisting groups; this may also entail self selection into groups. participants not randomly assigned to the experimental and control groups. does not permit the researcher to control the assignment of participants to conditions or groups. characterized by lower levels of control over the who what when where and how of the study
nonequivalent control group design
research designs have both experimental and control groups but participants aren't randomly awssigned to these groups. most common type of quasi experimental design
problems with nonequivalent control group design
how to compare the results between groups when they aren't equivalent to begin with. they may or may not be interpretable, depends on whether the pattern of results obtained can be accounted for by possible differences between the groups of by something else in the study
improve interpret ability of nonequivalent control group designs
matching, identifying/building extraneous variables into design or study as moderator variables, pretesting
delayed control group design
nonequivalent control group design in which the tesdting of one group is deferred, the two groups are tested sequentially with an appreciable time interval between them
interrupted time series design
no control group, these designs allow the same group to be compared over time by considering the trend of the data before and after the treatment
multiple time series design
variation nof interrupted time series design - not really a design without a control group - a time series design in which a control group and experimental group are included to rule out as a rival hypothesis
observational research designs
research methodologies in which the researcher observes, records, and quqantifies ongoing behavior. can be experimental or nonexperimental. the manner in which data is collected is the defining characteristic of observational designs/research - data collection procedure forefits some degree of control
issues with observational designs
sampling of observations - must be randomized or nonsystematic. the observer as a test - must beet all psychometric requirements of a good test - reliable. valid. standardized. objective - when more than 1 observer, observer charastics - experimenter effects - become a possible extraneous variable and must be controlled. - train raters to standardize, build into design as moderator variable, select for good observers
levels of observation
naturalistic/complete observation, observer-participant, participant-observer, complete participant
naturalistic/complete observationresearch conducted in such a way that the participants' behavior is disturbed as little as possible by the observation process - observing people in the mall or deer from standobserver participantobservations are made that there isn't any intraction, but participants are aware of observer's presenceparticipant observerresearcher's participant in naturally occuring groups and recorded their behavior - end of world cultcomplete participantobservations made within observer's own group. observer completelypotential observation problemsintrusiveness, reactivity, issues of privacycorrelational designsresearch designs where we measure two or more variables and attempt to determine the degree of relationship between themcorrelational designs characterized byno manipulation, low control, no causal inferencestypes of correleational designspredictive, concurrent, postdictivepredictive correlational designIV data collected before DV data with/appreciable time interval between the twoconcurrent correlational designIV and DV data collected at about the same time without any appreciable time interval between the 2postdictiveDV has been occurring in the past before IV was collectedproblems with postdictive designsselective sampling, instances where occurrence of DV could/may influence one's standing on IV, archival data - no control over how data collected - unknown qualityarchival researchrefers to research conducted using data that the researcher had no part in collectingarchival datathose that exist in public record or archives. researcher simply examines/selects data for analysisarchival research limitationsmost archival data collected for unscientific reasons by people who aren't researchers, so may not be very useful,may be incomplete, may be subject to bias, insurance records/police records. archival research is carried out after the fact, ruling out other hypothesis for particular observed correlations may be difficult. reliance on post hoc explanations elevates susceptibility to alternate explanations.Cross sectional designThese are research designs in which different cohorts or individuals are tested at a given point in time. Cross sectional designs are between subject designs. Primary advantage is that they're very economicalLongitudinal designsResearch design in which a cohort is selected and studied over a relatively long period of time with repeated measures. Same group/sample of individuals is studied over time. Can be between subjects or independent group designs. This would be the case if in studying s given cohort at each individual time of measure my we selected s different sample of the same cohort. This is still longitudinal bc were studying the same cohort and its between subject at each time of measure rn we are selecting a different sample but from the same cohort.Advantages of longitudinal designStrength in allowing us to assess the change in variables or constructs over time. Generally stronger than cross sectional designs bc temporal sequencing of the IV and DV is more establishedMeta analysisDescribed as a set of statistical methods for quantitatively aggregating results of several primary studies to arrive at an overall summary statement or conclusion about the relationship between specified variables.Calculating the effect size statisticD or r in meta analysis. Cumulating the effects across studies requires that outcomes from all studies be converted to a common metric. The d statistic provides a measure of the strength of a treatment or IVThe d statisticEffect size statistic. Standardized difference between two means. Represents the observed difference between the experimental and control groups in SD units. Positive d value indicates that the experimental group performed better than the control group on the DV. Negative d value indicates that the control group performed better than the experimental group on the DV. A 0 d value indicates that there's no difference between the groups. D= M(e)-M(c)/S(w)Advantages of meta analysisControls for sampling error by assigning more weight to studies with larger samples and obtains more stable effect size estimates. Focuses on the magnitude of effects instead of the statistical significance of effects- significance tests have been critiqued blas bring major stumbling block to scientific progress in psych. Uses a common metric to aggregate effect sizes across studies. A meta analysis summarizes the IV/DV effects across multiple studies to reach s population level overall conclusion about specified effects. Ability to summarize large volumes of literature. Can be used to resolve conflicts between two or more bodies of literature by comparing effect sizes between them. Ability to investigate relationships not investigated in original primary studies. Investigate and find trends too subtle to identify with narrative reviews. More standardized and relatively more objectiveDisadvantages of meta analysisGarbage in garbage out. Apples and oranges comparisons. Number of primary studies available. Selection of primary studies for inclusion file drawer problems. Judgment calls.EthicsTruth in reporting - accurate reporting or research and plagiarism. Treatment of research participants. Internal vs external controls and checksEthicalPiece of behavioral research is ethical when the benefits and relevance of research balance costs in time and risks of harm to participants when their interest and well being are respected and they're property informed about nature of research and voluntary nature of their participantCase studyCase studies include observation and archival methodologies and involve a situation that presents itself for investigation. Many case studies result from problems that present themselves to researchers as opportunities that must be grasped quickly or lostPrinciple characteristics of case studiesExamine individual instances of some phenomenon or an individual method or treatmentHaphazard samplesPopulation subgroup for whose section the researcher uses hit o kiss methods. Almost worthlessPurposive samplesNo random sample that is chosen for some characteristic that it possesses. Constitute a population. Error in judgment by researcher in selecting the sample may influence results.Convenience samplesNo random sample that's chosen for practical reasons. Selects a desirable group but may not come close to sampling all of the populationProbability samplingRandom samplingSystematic samolesProbability sample but not random sample. Involves selecting elements from an ordered sampling frameSimple random samplesGroup chosen from an entire population such that every member of the population has an equal and independent chance of being selected in a single samoleStratified random samplesRandom sample in which two or more sub samples are represented according to some predetermined proportion generally in the same proportion as they exist in the populationCluster samplingGroup selected by using clusters or groupings from a large populationMultistage samplingA firm of cluster sampling in which clusters are further broken down by taking samples from each sampleAnimal rightsThe notion that animals have the same sort of rights as people including legal rights. Not generally acceptedAnimal welfareGenerally accepted term for concerns about the care and use of animals. Humane treatment of animalsresponse rateIn survey research, the percentage of individuals in the sample who return the completed survey