Experiments Explanatory research True experiments Experimental designs
Published byModified over 4 years ago
Presentation on theme: "Experiments Explanatory research True experiments Experimental designs"— Presentation transcript:
1 Experiments Explanatory research True experiments Experimental designs Quasi-experimental designsInternal validityExternal validityEthical issuesStrengths and weaknesses
2 Explanatory Research Purpose: to explain, to determine cause/effect What is explained?Variation in the dependent variableWhat can be studied in an experiment?Limited, narrow causal relationshipsVariables that can be studied in labTopics for which theory has been developed
3 True experiment includes Two groups (experimental and control)Random assignment to groupsVariation in independent variable (manipulated by researcher)Measurement of dependent variable
4 The groupsExperimental group – is exposed to independent variable (I.V.)Control group - is not exposed to I.V.I.V. is the only difference between the groupsAny differences in dependent variable (D.V.) must be due to I.V.
5 Assignment to groups Randomization Easy to carry out Can control for unmeasured or uncontrolled factorsMatchingSpecific characteristics matched in both groupsMay be very preciseRequires knowledge of relevant characteristicsMay not control for omitted factors
6 Pretesting Measures D.V. before experiment Establishes comparability of experimental and control groupsProvides baseline for comparison with posttestMay teach or “clue in” subjects (pretest effect)Costs extra
8 Experimental Designs Posttest-Only Effect of I.V. = (O1-O2) GroupsPretestI.V.Uncontrolled factorsPosttestChangeExper.N/AXO1ControlO2Effect of I.V. = (O1-O2)Eliminates effect of pretest
9 Experimental Designs Solomon four-group GroupsPretestI.V.Uncontrolled factorsPosttestChangeExper. 1O1XO3O3-O1Control 1O2O4O4-O2Exper. 2O5Control 2O6Effect of I.V. = (O3-O1) – (O4-O2) or (O5-O6)Effect of pretest = (O3-O5) or (O4-O6)
10 Quasi-Experimental Designs May be used when true experiment isn’t possibleUsually involve fewer controlsNo control groupApproximately equivalent control groupMay take place in the fieldMay be “ex post facto:” designed after the “treatment”
11 Internal Validity Source of Invalidity Solution History – outside eventsControl groupMaturation – changes in subjectsTesting – subject may learnInstrumentation - measurementStatistical regression - moderationSelection bias- groups not comparableRandomizationMortality – dropping outContamination (competition, demoralization)Treatment misidentification (experimenter expectations, placebo effect, Hawthorne effect)Randomization, double blind, process analysis
12 External Validity Generalization to “real world” Often a problem in experiments2 main issuesWould sample subjects behave same way outside lab?Cross-population generalizability: would findings hold for different groups, times, places?
13 Ethical IssuesDeception (misleading subjects about purpose of experiment)Selective distribution of benefits (also risks, harm)
14 Experiments’ Strengths and Weaknesses Isolation of cause/effectHigh internal validityEasy to replicateBest used for explanatory studies (testing of hypotheses)WeaknessesExternal validity may be low or undeterminedEthical issuesHigh cost per subject