1 Procedural Analysis or structured approach. 2 Sometimes known as Analytic Induction Used more commonly in evaluation and policy studies. Uses a set.

Slides:



Advertisements
Similar presentations
Andrea M. Landis, PhD, RN UW LEAH
Advertisements

Chapter 7 Flashcards. overall plan that describes all of the elements of a research or evaluation study, and ideally the plan allows the researcher or.
Asking Research Questions Deductive, Inductive, and non-theory driven research.
ORGANIZING AND PRESENTING QUALITATIVE DATA
Validity (cont.)/Control RMS – October 7. Validity Experimental validity – the soundness of the experimental design – Not the same as measurement validity.
Experimental and Quasi-Experimental Research
Increasing your confidence that you really found what you think you found. Reliability and Validity.
Copyright © Allyn & Bacon (2007) Hypothesis Testing, Validity, and Threats to Validity Graziano and Raulin Research Methods: Chapter 8 This multimedia.
Research designs and methods
The Scientific Method.
GROUP-LEVEL DESIGNS Chapter 9.
Experimental Research Designs
Correlation AND EXPERIMENTAL DESIGN
Slides to accompany Weathington, Cunningham & Pittenger (2010), Chapter 4: An Overview of Empirical Methods 1.
Analyzing Case Study Evidence
Standards for Qualitative Research in Education
Chapter 12 Quasi-Experimental, Correlational, and Naturalistic Observational 2012 Wadsworth, Cengage Learning.
Designing Case Studies
Validity Validity of measurement Validity of research
MSc Applied Psychology PYM403 Research Methods Validity and Reliability in Research.
Hypotheses & Research Design
Basic Research Methodologies
Basic Research Methodologies Psych 231: Research Methods in Psychology.
Designing Case Studies. Objectives After this session you will be able to: Describe the purpose of case studies. Plan a systematic approach to case study.
Experimental Design The Gold Standard?.
Introduction to Earth Science Doing Science.  Scientific method – a systemic approach to answering questions about the natural world  Sufficient observation.
Experimental and Quasi-Experimental Designs
Chapter 3 The Research Design. Research Design A research design is a plan of action for executing a research project, specifying The theory to be tested.
Quantitative Research Designs
Day 6: Non-Experimental & Experimental Design
Design Experimental Control. Experimental control allows causal inference (IV caused observed change in DV) Experiment has internal validity when it fulfills.
Web of Causation; Exposure and Disease Outcomes Thomas Songer, PhD Basic Epidemiology South Asian Cardiovascular Research Methodology Workshop.
Chapter 1: Research in the Behavioral Sciences History of Behavioral Research Aristotle and Buddha questioned human nature and why people behave in certain.
Big Idea 1: The Practice of Science Description A: Scientific inquiry is a multifaceted activity; the processes of science include the formulation of scientifically.
Debate: Reasoning. Claims & Evidence Review Claims are statements that serve to support your conclusion. Evidence is information discovered through.
Between groups designs (2) – outline 1.Block randomization 2.Natural groups designs 3.Subject loss 4.Some unsatisfactory alternatives to true experiments.
URBDP 591 I Lecture 3: Research Process Objectives What are the major steps in the research process? What is an operational definition of variables? What.
1 Copyright © 2011 by Saunders, an imprint of Elsevier Inc. Chapter 8 Clarifying Quantitative Research Designs.
METODE PENELITIAN AKUNTANSI. Tugas Tugas Telaah Tugas Riset.
11/8/2015 Nature of Science. 11/8/2015 Nature of Science 1. What is science? 2. What is an observation? 3. What is a fact? 4. Define theory. 5. Define.
1 The Theoretical Framework. A theoretical framework is similar to the frame of the house. Just as the foundation supports a house, a theoretical framework.
Quantitative Research SPED 500 Dr. Sandra Beyda Designs that maximize objectivity by using numbers, statistics, structure, and experimenter control Modes.
Scientific Methods and Terminology. Scientific methods are The most reliable means to ensure that experiments produce reliable information in response.
Introduction to Science.  Science: a system of knowledge based on facts or principles  Science is observing, studying, and experimenting to find the.
 Descriptive Methods ◦ Observation ◦ Survey Research  Experimental Methods ◦ Independent Groups Designs ◦ Repeated Measures Designs ◦ Complex Designs.
Experimental Research Methods in Language Learning Chapter 5 Validity in Experimental Research.
Chapter 8 – Lecture 6. Hypothesis Question Initial Idea (0ften Vague) Initial ObservationsSearch Existing Lit. Statement of the problem Operational definition.
PowerPoint presentation to accompany Research Design Explained 6th edition ; ©2007 Mark Mitchell & Janina Jolley Chapter 14 Single-n Designs and Quasi-Experiments.
Single-Subject and Correlational Research Bring Schraw et al.
Experimental and Ex Post Facto Designs
How to structure good history writing Always put an introduction which explains what you are going to talk about. Always put a conclusion which summarises.
2. Main Test Theories: The Classical Test Theory (CTT) Psychometrics. 2011/12. Group A (English)
EMR 6550: Experimental and Quasi- Experimental Designs Dr. Chris L. S. Coryn Kristin A. Hobson Fall 2013.
CJ490: Research Methods in Criminal Justice UNIT #4 SEMINAR Professor Jeffrey Hauck.
How Psychologists Do Research Chapter 2. How Psychologists Do Research What makes psychological research scientific? Research Methods Descriptive studies.
Can you hear me now? Keeping threats to validity from muffling assessment messages Maureen Donohue-Smith, Ph.D., RN Elmira College.
The Scientific Method. Scientifically Solving a Problem Observe Define a Problem Review the Literature Observe some More Develop a Theoretical Framework.
Chapter 12 Quantitative Questions and Procedures.
Experimental and Quasi-Experimental Research
Writing a sound proposal
Chapter 4: Inductive Arguments
Making Causal Inferences and Ruling out Rival Explanations
Single-Case Designs.
A 4 Step Process (Kind of…)
Chapter 11 EDPR 7521 Dr. Kakali Bhattacharya
ORGANIZING AND PRESENTING QUALITATIVE DATA
Chapter 8 VALIDITY AND RELIABILITY
Enhancing Causal Inference in Observational Studies
LEARNING OUTCOMES After studying this chapter, you should
Enhancing Causal Inference in Observational Studies
Presentation transcript:

1 Procedural Analysis or structured approach

2 Sometimes known as Analytic Induction Used more commonly in evaluation and policy studies. Uses a set of procedures as a way of establishing explanations and causal links The approach tends to assume that meanings are transparent, obvious and unambiguous, and instead concentrates on validating explanations.

3 References Robson, C. (1993) Real World Research (First Ed) Yin, R. (1994) Case Study Research: Design and Method Bryman,A (2008) Social Research Methods pp Gomm, R, Hammersley, M, & Foster P (eds) (2000) Case Study Method – See esp. chapter 8.

4 Reasons for structured approach Deficiencies in the analyst 1. Data overload (too much to remember, process etc.) 2. First Impressions (bias to first things read) 3. Information availability (easy information gets more attention) 4. Positive instances (stress what confirms ideas) 5. Internal consistency (discount the novel) 6. Uneven reliability (not all sources equally good)

5 Reasons for structured approach 2 7. Missing information (don’t try hard enough to fill gaps) 8. Revision of hypotheses (over- or under- react to new info) 9. Fictional base (compare with assumed average) 10. Confidence in judgement (too much when made) 11. Non-occurrence (seen as evidence for strong correlation) 12. Inconsistency (different interpretations of same data) All this means threats to: reliability and generalizability validity

6 Especially for validity History (background changes during study) Mortality (people dropping out unrepresentative) Maturation (people changed by the study) ambiguity about causal direction (unclear what causes what)

7 For generalizability Limited to: group studied setting it took place in time it happened particular constructs of the group

8 Pattern Matching Compare an empirical based pattern with a predicted one (and with several alternatives) Looking for causal connections If patterns coincide this strengthens internal validity.

9 1. Non-equivalent dependent variables as a pattern Like quasi-experimental designs: hypothesis testing Use where theory suggests multiple dependent variables or a variety of outcomes. If for each outcome, initially predicted outcomes are found and alternative are not found (i.e. no threats to validity found) then can infer causal influence.

10 e.g. Effects of decentralized approach to office automation from Yin Decentralization theory suggests 4 outcomes Employees create new applications Traditional supervisory links are threatened Organizational conflicts increase Productivity will increase If results in the case are as these 4 predictions then draw conclusions that it is decentralization that caused these effects.

11 Replication Literal replication = more cases of the same kind Theoretical replication = case where automation is centralized. Then there will be 4 different effects. Causal link is confirmed if this is what happened. BUT must be aware of threats to validity. Identify and eliminate all reasonable threats.

12 2. Rival Explanations Test contrasting theories i.e. we have several independent variables or starting circumstances. Examine cases for characteristics of the precursors to see which fits best.

13 Problems with pattern matching How do we know a pattern fits? Matter of judgement. Need to balance overly restrictive application of pattern matching with too loose a match. “eyeballing” the pattern is good enough.

14 Analytic Induction A.k.a. Explanation building i.e. build up and confirm a set of causal links between events, actions etc in the case.

15 Analytic Induction process

16

17 Problems Need constantly to entertain other plausible, rival explanations. = HARD WORK With each iteration, there may be a drift from the original question or lots of work to re- analyze data. Only establishes sufficient conditions (not necessary) No guide as to how many negative cases are needed for validity.

18 Time series Like time series in a quasi experiment.

19 Problem Changes may have no clear start or end point. Must compare 1. Theoretically significant trend predicted before research, 2. Rival trend predicted before research, 3. Any trend based on artefacts or threats to internal validity.

20 Chronologies Look for sequences and patterns of events. e.g. some events always happen before others, and the reverse is impossible some events always follow others, some events always follow others after the passage of time some time periods differ from other time periods in the type of events that occur.