学前教育研究方法chapter-9--Quasi-experimental-research.ppt

Chapter 9.Quasi-experimental researchQuasi-experimental research involves the use of intact groups of subjects in an experimental rather than assigning subjects at random to experimental treatments.1Random assignment attains equivalence of the group within the limits of random fluctuation.When conducting education research,there are many situations in which random assignment of subjects is not an option.A true experimental design can be fashioned in those instances by randomly assigning classrooms to treatments.In most cases though,when the researcher does not have the power to randomly assign subjects to groups,there will be some factors on which the intact groups differ that make them nonequivalent.21.Posttest-only,nonequivalent control group designThe posttest-only nonequivalent control group design contains as many groups as there are experimental treatments,plus a control group.Intact groups are used,and subjects are measured only once,after the experimental treatments bave been applied.G1 X-O1 G2 -O23 G1 X1-O1 G2 X2-O2 Gk Xk-Ok Gk+1 -Ok+142.Pretest-posttest,nonequivalent control group design is similar to the posttest-only nonequivalent control group design,except that the subjects are also pretested.In its general form,if there are k experimental treatments,it can be diagrammed as follows.G1 O1-X1-O2 G2 O3 -O453.Time series designsTime series designs as quasi-experimental designs involve repeated measurement of one or more intact groups,with an experimental treatment inserted between two of the measurements of at least one group.G O1-O2-O3-X-O4-O5 6Multiple-group time series designG1 O1-O2-O3-X1-O4-O5G2 O6-O7-O8-O9-O1074.Single-subject designsSingle-subject designs commonly involve repeated measurements,and they use the single-variable rule-changing only one variable at a time.8Single subject design are characterized by what is sometimes called the single-variable rule.This means that only one variable,the treatment,is changed during the period in which the experimental treatment is applied.The period during which the traditional treatment of normal condition is in effect is called the baseline.9A-B Designbaseline condition(A)Experimental treatment(B)O1-Ok Ok+1-O2k X TA TB10A-B-A DesignThe A-B-A design extends the A-B design so that another period of the baseline condition is included following the period of experimental treatment.11