Asking Research Questions Deductive, Inductive, and non-theory driven research
Independent Variable (IV)-variable that the research intentionally manipulates in order to observe its effect on the DV. • Dependent Variable (DV)- measure of behavior used by the researcher t0 assess the effects (if any) of the IV. • (example: Effects of Caffeine on Fine Motor Skills)
Internal Validity- the degree to which differences in performance (the dependent variable) can be attributed unambiguously to an effect of the independent variable. (aka confounds or “threats to internal validity”) • External Validity- the extent to which the results of a particular research study can be generalized to different populations, settings, and conditions.
Deduction (to deduce) - to derive as a conclusion from something known or assumed (to go from a general statement or theory to specific predictions/observations) • Induction- to assert or establish on the basis of observation of particular (specific) facts (to go from specific observations to more general theory or statement)
Theory-an explanation, usually in general terms. • Hypothesis/hypotheses- a specific, testable statement, often a prediction about what you expect to happen in your study. • A theory explains events in general terms, while a hypothesis makes a specific statement about a specified set of circumstances.
Example: Theory/hypothesis • “Theory”: Caffeine will negatively affect a person’s ability to perform fine motor skills. • “Hypothesis”: People will produce more errors on a mirror drawing task as the number of cups of coffee they drink increases.
You use deductionwhen you derive a specific hypothesis from a more general theory. • You use inductionwhen you take a set of specific findings and produce a more general explanation (a “theory”).
Theory Driven Research: Deductive & Inductive ResearchProgramsPage 19 of Course Packet
Theories serve two purposes in research: • They guide scientific research by suggesting research hypotheses. (Deductive Research) • They organize empirical knowledge. (Inductive Research) These two purposes lead to two different types of research (deductive and inductive), both driven by theories.
In Deductive research, the research uses already established theories to deduce a specific and testable hypothesis of the form “I expect this will happen if……” (Deductive hypothesis)
In Inductive research, the research gathers many specific findings (usually though performing multiple studies) and then uses these specific findings to create a more general explanation (a theory). • The hypothesis is of the form: “I wonder what will happen if….” (Inductive hypothesis)
The Cyclical Nature of Theory Driven ResearchPage 20 of Course Packet
Step1: Finding an interesting topic • Intro Psych text • Talk to others doing research in area of interest • Take a course, attend seminars or lectures • Do a literature search and read/explore what is known about the topic.
Graham Wallas (1858-1932)1926 The Art of Thought Four stages of the scientific process: • Preparation • Incubation • Illumination • Verification Stages 1-3 would all be part of the Step 1 in the process of theory-driven research.
Step 2: Developing a Testable Hypothesis (review) Hypotheses can be of two sorts: Deductive and Inductive • Deductive Hypotheses are the way in which theories guide research (Form: “I expect this will happen if…”) • while Inductive Hypotheses are the way in which theories organize empirical knowledge (Form: “I wonder what will happen if…”)
A hypothesis cannot contain vague concepts such as “mentally disturbed” or “intelligence”. (need operational definitions) • A hypothesis cannot be circular. • A hypothesis is untestable if it appeals to ideas or forces that are not recognized by science (unobservable forces)
Step 3: Selecting a design and evaluating ethics • Different designs map onto the different goals of a piece of research. (description, prediction, etc.). Pick a design that fits your goal. • Identify a target population and a sampling technique. • Perform a formal evaluation for ethical issues via review boards (IRB or IACUC). Must be done before ANY data are gathered, even “pilot” data!
Step 4: Implement study in a way that achieves unambiguous results • Avoid “threats to internal validity”. • Control some variables and yet strive for high “external validity”.
Step 5:Collect and Summarize Data Use descriptive statistics to summarize and understand data. • Measures of Central Tendency: mean, median, mode. • Measures of variability: range, variance, standard deviation.
Step 6: Draw conclusions using Inferential Statistics Null Hypothesis Significance Testing (NHST) • Parametric statistics such as Student’s t-test or Analysis of Variance (ANOVA) • Non-parametric statistics such as Chi-square or Mann-Whitney U test
Step 7: Reject, Modify, Support Based on your findings, you can choose one of three options: • Reject your hypothesis showing a lack of support for your original theory or idea. • Modify your original theory or idea based on your findings. • Support your original theory or idea based on your findings.
Example Step 1: topic- “Stress causes illness” (general statement) Step 2: Specific hypothesis- (thru operational definition)- “I expect I will see an increase in visits to UHS during exam week.” (Deductive hypothesis) Step 3-6: ethics approval, design choice, summarize/analyze results. Find increase in viral illnesses during exam week. Step 7: Modify- Stress increases Viral illness
Non-theory driven researchB.F. Skinner, Radical Behaviorism • When you run into something interesting, drop everything and study it. • Some ways of doing research are easier than others • Apparatuses sometimes breakdown • Theories are not necessary and can get in the way of good research. Seek only to describe the functional relationships between/amongst variables
Description: events and their relationships are defined classified, cataloged. • Examples: DSM-IV TR 2000(diagnostic statistical manual of mental disorders, IV ed. TR 2000) • Pace of Life Study (Levine 1990)
2) Prediction (correlation): occurs when measures vary together (co-vary) in a consistent way. • Examples: GRE scores/undergraduate GPA as predictors of success in a graduate school environment. • Ambady & Rosenthal (1993)
3) Explanation: (causal inference) requires three conditions: • co-variation of events-when one changes, the other changes in a consistent way. • time-order relationship- one event always precedes the other. Antecedent-consequent. • elimination of plausible alternative causes- eliminate all “threats to internal validity” “True Experimental Design”
4) Application: research designed to solve a problem, applied research Quasi-experimental and Applied Behavior Analysis