Quantitative methodology part one.compressed
2 likes182 views
The document discusses the application of quantitative research methodologies in postgraduate education, focusing on key concepts like philosophical paradigms, research designs, and various quantitative research methods. It outlines characteristics of quantitative research, including the positivist paradigm, and details different experimental and quasi-experimental designs that can be utilized to establish relationships or effects within research studies. Additionally, it emphasizes how the research question dictates the appropriate methodological approach and highlights the importance of rigorous data analysis.
Quantitative methodology part one.compressed
- 2. You can use all the quantitative data you can get, but you still have to distrust it and use your own intelligence and judgment. Alvin Toffler
- 3. Our Focus for Today 1. Some important concepts to keep in mind 2. Quantitative research: Characteristics and when to use it 3. Types of quantitative research methods 4. Exercises to practice
- 4. Four Main Concepts Philosophical Paradigms Research Paradigms Research Designs Research Methods General to Specific
- 5. What Is a Philosophical Paradigm? It is a basic image of what is reality (ontology), how we know something (epistemology), and how we should find out knowledge (methodology)
- 6. Taken from Weaver, K. & Olson, J.K. (2006, p.465) What Is a Research Paradigm? A pattern of beliefs and practices that regulates inquiry within a discipline by providing lenses, frames, and processes through which investigation is accomplished
- 7. Adapted from Wiersma, W. & Jurs, S.G. (2009) What Is a Research Design? A plan or strategy for conducting a research study. It includes decisions on what, who, when, where, how, means, analyses, etc. It should respond to the nature of the research question
- 8. Adapted from Wiersma, W. & Jurs, S.G. (2009) What Is a Research Method? A set of techniques or strategies to gather and analyze data that responds to the chosen research design
- 9. How Do These Concepts Apply to Quantitative Research?
- 10. The Philosophical Paradigm • Ontological assumptions (view of the world): • There is one defined reality • It is fixed, measurable, and observable • Epistemological assumptions (how knowledge is created): • Knowledge is objective and quantifiable • Research should test and expand theory • Methodological assumption (what should be done to get knowledge): • Use objective measurement and analysis to get valid knowledge
- 11. The Research Paradigm Positivist Paradigm There is one objective reality Quantitative research paradigm
- 12. Adapted from Wiersma and Jurs (2009) The Research Design • Top-down logic (deductive) • Looks for relationships, facts, and causes • Theory-based • Focused on individual variables • Context-free (generalizations) • Researcher has a neutral role • Statistical analysis
- 13. The Research Method • Experimental • Quasi-experimental • Pre-experimental
- 14. When to Choose Quantitative Research If you are interested in: • Determining relationships, effects, and/or causes • Testing theories, models, approaches (even if that is not an explicit goal of the study, but theoretical principles are important in one way or another)
- 15. Types of Quantitative Research Methods
- 16. • Experimental: High degree of control. Random selection or assignment • Quasi-experimental: Minor level of control because random selection or assignment is not possible. Statistics is used to improve the control of variables • Non-experimental: Little or no control
- 17. Experimental Methods • Posttest-only control group • Pretest- posttest control group • Solomon four groups • Factorial
- 18. • Description: Two or more groups are compared using posttest and random assignment of subjects and treatment to control prior differences. One group does not receive treatment • Diagram: RG1 X1 O1 R = Randomization X = Treatment O = Posttest RGn Xn On n= number of experimental treatments used RGn+1 __ On+1 Control group (no treatment) • Use: When it is necessary to establish if a variable has effect or not and pretest is not acceptable or possible. • Common statistical tests: t-test and analysis of covariance if subject variables are involved Posttest-Only Control Group Design
- 19. • Description: Two or more groups are compared using a pretest to measure the dependent variable before the treatment is administered. Such measurement is used as statistical control in the analysis and random assignment of subjects assure equivalence of the groups. One group does not receive treatment • Diagram: RG1 O1 X1 O2 R = Randomization X = Treatment O = test RGn O2n-1 Xn O2n n= number of experimental treatments used RGn+1 O2n+1 __ O(2n+1) Control group (no treatment) • Use: When it is necessary to establish if a variable has effect or not • Threats to validity: Interaction effect of testing (threat to external validity) • Common statistical test: Analysis of covariance Pretest-Posttest Control Group Design
- 20. • Description: To address the reactive effect of testing and interaction of testing and treatment, two control groups are added to the pretest-posttest control group design; one without taking pretest and another one without pretest and treatment • Diagram: RG1 O1 X O2 RG2 O3 - O4 R = Randomization O = Test X = Treatment RG3 - X O5 RG4 - - O6 • Use: When resources and time are available to deal with the complexity of four research groups • Threats to validity: None by itself • Common statistical tests: 2X2 ANOVA (disregarding pretests), ANOVA plus 2X2 factorial design, or meta-analysis Solomon Four Groups Design
- 21. • Description: The different levels of two or more independent variables (factors) are considered to establish not only their effects on the dependent variable but also the ones caused by the interaction among them. Theoretically, the number of independent variables and their levels may be as needed. For example, a 2 X 3 X 5 means one variable with 2 levels, another with 3, and the last one with 5 • Diagram: (Notation of a 2 X 2 factorial design) R X11 O R X12 O R X21 O R X22 O R = Randomization X11 = Factor 1, level 1 X12 = Factor 1, level 2 X21 = Factor 2, level 1 X22 = Factor 2, level 2 O = Measurement • Use: When measuring the interaction among variables is needed • Threats to validity: None by itself • Common statistical test: Factorial ANOVA, MANOVA, MANCOVA, multiple regression analysis Factorial Design Drug Therapy Placebo Drug A Psycho- therapy None Control Drug A Method A Method A Combined
- 22. Quasi-Experimental Designs • Nonequivalent posttest-only control group • Nonequivalent pretest- posttest control group • Counterbalanced • Time series
- 23. • Description: Two or more groups are compared using only posttest. There is not random assignment of subjects since they are already in groups • Diagram: G1 X O1 X = Treatment O2 = Posttest n = number of treatments used Gn Xn On Gn+1 ___ On+1 • Threats to validity: Selection, statistical regression, and reactive effect of testing • Use: Only if some antecedent data establish extent of similarity between groups Nonequivalent Posttest-Only Control Group Design
- 24. • Description: Two or more groups are compared using pretest and posttest. Pretest scores are used for statistical control or for generating gain scores. There is not random assignment of subjects since they are already in groups • Diagram: G1 O1 X1 O2 O= Test X = Treatment n= number of treatments used Gn O2n-1 Xn O2n Gn+1 O2n+1 __ O2n+2 • Threats to validity: Selection, statistical regression, and reactive effect of testing • Common statistical tests: Covariance and multiple regression Nonequivalent Pretest –Posttest Control Group Design
- 25. • Description: The order in which treatments are administrated is changed during the study so as to test every subject for all the considered conditions and control order effects in repeated measures • Basic Diagram : G1 XA XB O G2 XB XA O X = Treatment G = Group O = Measurement • Threats to validity: Multiple treatment interference • Common statistical test: ANOVA Counterbalanced Design
- 26. • Description: The dependent variable is measured several times before applying a treatment and then a new series of measurement is performed • Diagram : O1 O2 … X Oi… On X = Treatment O = Measurement • Threats to validity: History and reactive effect of testing • Statistical tests: They depend on the specific type of time series designed Time Series Design
- 27. Taken from The bmj (2017) Some Statistical Tests
- 28. Pre-Experimental Designs These designs will be explained in the second session of the webinars devoted to quantitative research
- 29. Exercises
- 30. Establish what research design is appropriate for this study… •Problem: A researcher has three different groups of employees (engineers, administrators, sales personal) which are not performing at the expected level. Data shows three different levels of current performance: high, average, and low. •Purpose: To determine the effects of different types of feedback on employees’ performance •Research Question: What is the effect of different types of feedback over the performance of employees? • Values of the independent variable: positive, negative, no feedback
- 31. Establish what research design is appropriate for this study… •Problem: Faculty morale is low at a university according to the results of a questionnaire applied. •Purpose: To establish the effect of sensitivity training on faculty morale •Research Question: What is the effect of sensitivity training workshops on faculty morale? • Values of the independent variable: treatment, no treatment
- 32. Establish what research design is appropriate for this study… •Problem: A new calculus program has been suggested to improve students performance •Purpose: To establish the effect of the suggested program on students’ calculus scores •Research Question: What is the effect of the suggested calculus program on students’ scores? • Values of the independent variable: treatment, no treatment
- 33. Now do the same with your own study… •Problem: • Research Question: • Research Design: •Research Method:
- 34. Advanced Ideas for Today: Your research question determines the method you should use to gather data Quantitative research asks for data that generate valid and objective answers
- 35. Now you know 1. The paradigms behind quantitative research 2. The experimental and quasi- experimental methods you can use to answer your research question(s)
- 36. References Thebmj (2017). Study design and choosing a statistical test. BMJ Publishing Group Ltd. Retrieved from http://www.bmj.com/about-bmj/resources- readers/publications/statistics-square-one/13-study- design-and-choosing-statisti Weaver, K. & Olson, J. K. (2006). Understanding paradigms used for nursing research. Journal of Advanced Nursing, 53(4), 459-469. doi: 10.1111/j.1365-2648.2006.03740.x Wiersma, W. & Jurs, S.G. (2009). Research methods in education: An introduction (9th ed.). Boston, MA: Allyn and Bacon
- 37. What’s Up at MN & DN this summer? 1. VERY IMPORTANT – backwards map your summer work 2. 30 day writing challenge, 30 day work-life balance challenge, and 365s - keep you in touch with your work 3. Group work – RLC writing OR Lingerers
- 38. Avoid this one 1. VERY IMPORTANT – backwards map your summer work 2. 30 day writing challenge, 30 day work-life balance challenge, and 365s - keep you in touch with your work 3. Group work – RLC writing OR Lingerers