EDLD 6392 Advanced Topics in Statistical Reasoning Texas A&M University-KingsvilleResearch Designs by PurposeResearch Designs by SimilaritiesDescriptive Research DesignsDescriptive Research (Cont’d)Causal-Comparative ResearchCausal-Comparative (Cont’d)Quasi-Experimental ResearchQuasi-Experimental (Cont’d)Slide 10Slide 11Slide 12PowerPoint PresentationNon-experimental Research: Correlational DesignsCorrelation Research DesignScattergrams Representing Different Degrees and Directions of Correlation between Two VariablesSlide 17EDLD 6392Advanced Topics in Statistical ReasoningTexas A&M University-KingsvilleResearch Designs and Statistical Research Designs and Statistical ProceduresProceduresResearch Designs by PurposeEducational Research is conducted for four Educational Research is conducted for four primary purposes:primary purposes:1-Description1-Description2-Prediction2-Prediction3-Improvement3-Improvement4-Explanation4-ExplanationResearch Designs by SimilaritiesExperimental & Quasi-experimentalExperimental & Quasi-experimental-Involves Researcher Intervention-Involves Researcher InterventionNon-experimental Non-experimental - Examines phenomena as they exist- Examines phenomena as they existDescriptive, Causal-Comparative, and Descriptive, Causal-Comparative, and CorrelationalCorrelationalDescriptive Research DesignsThe PurposeThe PurposeThe description of natural or man-made The description of natural or man-made phenomena-their form, actions, changes over time, phenomena-their form, actions, changes over time, and similarities-with other phenomena, an effort and similarities-with other phenomena, an effort to describe. Involves making careful descriptions to describe. Involves making careful descriptions of educational phenomena, viewed as of educational phenomena, viewed as understandingunderstanding what people or things mean. what people or things mean.Studies primarily concerned with determining Studies primarily concerned with determining “what is.”“what is.”Descriptive Research (Cont’d)Types of MeasurementsTypes of Measurementsstandardized achievement scores, classroom standardized achievement scores, classroom observation instruments, attitude scales, observation instruments, attitude scales, questionnaires, and interviewsquestionnaires, and interviewsStatisticsStatistics Central Tendency (mean, median, mode)Central Tendency (mean, median, mode)Measures of Variability (SD, variance, range)Measures of Variability (SD, variance, range)Causal-Comparative ResearchThe PurposeThe PurposePurpose of explaining educational phenomena Purpose of explaining educational phenomena through the study of cause-and-effect relationships. through the study of cause-and-effect relationships. The presumed cause is called the The presumed cause is called the independent independent variablevariable and the presumed effect is called the and the presumed effect is called the dependent variabledependent variable. Designs where the researcher . Designs where the researcher does not manipulate the independent variable are does not manipulate the independent variable are called called ex post facto researchex post facto research..Causal-Comparative (Cont’d)Causal-Comparative research is also a type of Causal-Comparative research is also a type of non-experimental investigation in which non-experimental investigation in which researchers seek to identify cause-effect researchers seek to identify cause-effect relationships by forming groups of relationships by forming groups of individuals in whom the independent individuals in whom the independent variable is present or absent and than variable is present or absent and than determining whether the groups differ on determining whether the groups differ on the dependent variable.the dependent variable.Quasi-Experimental ResearchParametric TestsParametric TestsStatistical Analysis: The Statistical Analysis: The tt Test TestFor testing the significance of difference between For testing the significance of difference between two sample meanstwo sample meansBasic AssumptionsBasic Assumptions1-1-Scores form an interval or ratio scaleScores form an interval or ratio scale2-Scores are normally distributed2-Scores are normally distributed3-Score variances for the populations under study 3-Score variances for the populations under study are equal (SD=SD)are equal (SD=SD)Quasi-Experimental (Cont’d)Analysis of Variance (ANOVA)Analysis of Variance (ANOVA)Comparison of two or more group meansComparison of two or more group meansMultivariate Analysis of Variance (MANOVA)Multivariate Analysis of Variance (MANOVA)Statistical technique for determining whether groups differ on Statistical technique for determining whether groups differ on more than one dependent variablemore than one dependent variable..Basic AssumptionsBasic Assumptions1-1-Scores form an interval or ratio scaleScores form an interval or ratio scale2-Scores are normally distributed2-Scores are normally distributed3-Score variances for the populations under study are 3-Score variances for the populations under study are equal (SD=SD)equal (SD=SD)Quasi-Experimental (Cont’d)Nonparametric TestsNonparametric TestsNonparametric statistics tests statistical significance that Nonparametric statistics tests statistical significance that do not rely on any assumptions about shape or variance of do not rely on any assumptions about shape or variance of population scores.population scores.Used with measures that yield categorical or rank scores, Used with measures that yield categorical or rank scores, or do not have equal intervals. Nonparametric tests are or do not have equal intervals. Nonparametric tests are less powerful, they require larger samples to yield the less powerful, they require larger samples to yield the same level statistical significance.same level statistical significance.1-1-The Chi-Square TestThe Chi-Square Test = used to determine whether = used to determine whether research data in the form of frequency counts are research data in the form of frequency counts are distributed differently for different samples.distributed differently for different samples.Quasi-Experimental (Cont’d)Nonparametric Tests (Cont’d)Nonparametric Tests (Cont’d)2-2-The Mann-Whitney U test=used to determine whether the distributions of scores of two independent samples differ significantly from each other.3-The Wilcox signed rank test=used to determine whether