PURPOSE OF CAUSAL – COMPARATIVE RESEARCH To determine cause of differences thatalready existed between or among groupsthen attempts to determine the reason, or theresults, of the differences Used when independent variables cannotor should not be examined using controlledexperiments A common design in educational researchstudies
CAUSAL - COMPARATIVE & CORRELATIONAL RESEARCH Lack of manipulation Requires caution interpreting results causation is difficult to infer Both can support subsequent experimental research
CAUSAL - COMPARATIVE VERSUS CORRELATIONAL RESEARCH CAUSAL – COMPARATIVE CORRELATIONAL does not to understand cause Attempts attempt to understand and effect effect cause and investigates at least independent investigates two or more one variable variables two or more groups, comparing one groupof subjects a score on these groups / requires each variable for each subject use compare averages or analyzes tablesusing scatterplots crossbreak data when analyzing data or correlational coefficients and/
CAUSAL - COMPARATIVE & EXPERIMENTAL RESEARCH requires at least one categorical variable (group membership) both compare performances (average scores) to determine relationships compares separate groups of subjects
CAUSAL - COMPARATIVE VERSUS EXPERIMENTAL RESEARCH EXPERIMENTAL CAUSAL - COMPARATIVE causalcomparisons group group comparisons individuals already in groups Individuals randomly assigned to before research begins treatment groups independent not manipulated variable manipulated by the researcher cannot should not is not
NON – MANIPULATED VARIABLES Age Sex Ethnicity Learning Style Socioeconomic Status Parental Educational Level Family Environment Preschool Attendance Type of School
INSTRUMENTATIONAny of these devices can be used: Achievement Tests Questionnaires Interview Schedules Attitudinal Measures Observational Devices
DESIGN Select two groups that differ on some independent variable I. One group possesses some characteristics that the other does not II. Each group possesses the characteristic but in differing amounts
ONE GROUPPOSSESSES SOME CHARACTERISTICS THAT THE OTHER DOES NOT INDEPENDENT DEPENDENT GROUP VARIABLE VARIABLE C O I (Group possesses (Measurement) Characteristic) -C O II (Group does (Measurement) not possess characteristic)
EACH GROUP POSSESSES THECHARACTERISTIC BUT IN DIFFERING AMOUNTS INDEPENDENT DEPENDENT GROUP VARIABLE VARIABLE C1 O I (Group possesses (Measurement) characteristic 1) C2 O II (Group possesses (Measurement) characteristic 2 )
THREATS TO INTERNAL VALIDITY IN CAUSAL COMPARATIVE RESEARCHWEAKNESSES: Lack of randomization Inability to manipulate an independent variable
WAYS OF CONTROLLING EXTRANEOUS VARIABLESMatching of SubjectsFinding or Creating Homogeneous SubgroupsStatistical Matching
OTHER THREATSLoss of SubjectsLocationInstrumentation
THREATS UNDER INSTRUMENTATIONInstrument DecayData Collector CharacteristicsData Collector Bias
EVALUATING THREATS TO INTERNAL VALIDITY• Step 1: ask: What specific factors either are known to affect or may logically be expected to affect the variable on which groups are being compared?• Step 2: ask: What is the likelihood of the comparison groups differing on each factor?• Step 3: Evaluate the threats on the basis of how likely they are to have an effect.
SUBJECT CHARACTERISTICSSocioeconomic Level of the FamilyGenderEthnicityMarketable Job Skills
DATA ANALYSYS IN CAUSAL COMPARATIVE STUDIES•The first step in a data analysis of a causal-comparative study is to construct frequencypolygons.•Means and standard deviations are usuallycalculated if the variables involved arequantitative.•The most commonly used test in this study is at-test for differences between studies.•Analysis of covariance is particularly useful inthis study.•The results of causal-comparative studiesshould always be interpreted with caution,because they do not prove cause and effect.
ASSOCIATIONS BETWEEN CATEGORICAL VARIABLESGrade level and gender of teachers (hypothetical data) GRADE LEVEL MALES FEMALES TOTAL Elementary 40 70 110 Junior High 50 40 90 Senior High 80 60 140 TOTAL 170 170 340
Such data can be used for purposes of prediction and with caution in the search for cause and effect. Knowing that a person is a teacher and male, for example, we can predict with some degree of confidence that he teaches either junior or senior high school, since 76% of males who are teachers do so. 40/170 is the probability of error in this table. In this example, the probability that gender is a major cause of teaching level seems quite remote. Further, prediction from cross break tables is much less precise than the scatter plots.
ANALYSIS OF COVARIANCE Is used to adjust initial group differences on variables used in causal-comparative and experimental research studies. Analysis of covariance adjusts scores on a dependent variable for initial differences on some other variable related to performance on the dependent. Suppose we were doing a study to compare two methods, X and Y, of teaching fifth graders to solve math problems. Covariate analysis statistically adjusts the scores of method Y to remove the initial advantage so that the results at the end of the study can be fairly compared as if the two groups started equally.
DATA ANALYSIS AND INTERPRETATION Analysis of data involves a variety of descriptive and inferential statistics. The most commonly used descriptive statistics are (a) the mean, which indicates the average performance of a group on some measure of a variable, and (b) the standard deviation, which indicates how spread out a set of scores is around the mean, that is, whether the scores are relatively homogeneous or heterogeneous around the mean.
The most commonly used inferential statistics are: (a) the t test, used to determine whether the means of two groups are statistically different from one another; (b) analysis of variance, used to determine if there is significant difference among the means of three or more groups; and (c) chi square, used to compare group frequencies, or to see if an event occurs more frequently in one group than another.
LACK OF RANDOMIZATION Lack of randomization, manipulation, and control factors make it difficult to establish cause-effect relationships with any degree of confidence. However, reversed causality is more plausible and should be investigated. It is equally plausible that achievement affects self-concept, as it is that self-concept affects achievement.
The way to determine the correct order of causality-which variable caused which- is to determine which one occurred first. The possibility of a third, common explanation in causal-comparative research is plausible in many situations. One way to control for a potential common cause is to equate groups on that variable. To investigate or control for alternative hypotheses , the researcher must be aware of them and must present evidence that they are not in fact the true explanation for the behavioral differences being investigated.