Approaches to research
Observational Research
Also called “descriptive research”:
“Systematic observation involves watching people and carefully recording what they say or do”
(Cavanaugh & Blanchard-Fields, 2015, p. 18).
- Two commonly discussed types of observations research are “naturalistic observation” and “structured observations”
- naturalistic observations are conducted of people’s ongoing behavior in real life settings (e.g., malls, parks, lunchrooms), ethological research
- for example, we might record instances/percentages/whatever of students’ cell phone use in the hallways after class or on the ISU quad \ observing couples in a restaurant
- anthropology field studies
- structured observations are conducted in settings constructed by the researcher
- for example, a focus group provides structured observations of a groups’ opinions about a movie, a political candidate, or some other event
- a self-report inventory and opinion polling could be thought of as a structured observations
- archival research could also be thought of as a type of structured observation (gun purchases following high impact news event)
- Do we know what to look at? Can we identify clearly the phenomenon we are interested in?
- Observational research may be exploratory
- clinical evaluation and case studies
- focus groups and identifying the issues
- The quality of our observations and records?
- defining behavior objectively can be challenging
- suppose you are interested in conflict in intimate relationships: what count’s as “conflict”? Calm disagreements on which movie to see tonight? Unhappiness about sharing housekeeping duties? Shouting at each other about who to vote for in the upcoming election? Physical fighting (what about tickling?, what about unwanted tickling?)
- When to watch:
all at once: cross-sectional research: - longitudinal research looks at populations of different ages at a given point in time
- observations (date collection in some form) provide the basis for all empirical research. Any study is going to provide some type of observation. Doing this in a manner that gives us confidence in the meaning of the information we gather is what begin to identify the activity as research.
- Interpretation of observational/descriptive data
tabulations, graphs, percentages - measures of central tendency: mean, mode median
interpretations:
population statistics
sample statistics
- Interpretation of observational/descriptive data
- To generalize to a different (usually larger) group than the group we studied, several questions must be considered:
- How representative is our sample?
- How large is our sample (affects degree of error)?
Correlational Research
- identifying patterns and relationships: correlational research looks at the patterns that occur between naturally occurring events in life, what events seem to “go together” or “not go together”
- Correlational research takes some body of observations data and applies a technique to quantify the degree of association between two variables; we can specify the strength of the relationship between two variable; i.e., How much does know about one variable tell us about the second variable?
- Are variables associated?
- measuring the strength of an association
- correlations, negative and positive
- -1 -.5 0 +.5 +1
- Third body problems and the search for causes
- a particularly troubling case: one variable occurs before the other
- Post Hoc Ego Propter Hoc (after this, therefore because of this)
- maternal smoking during pregnancy and ADHD in children
Experimental Research (casual explanations, cause and effect)
- Experimental research seeks to answer questions about “cause”, how one event in the world affects other events in the world. We are often interest in experimental research because we until want to know how to achieve some desirable outcome in life.
- Variables: What are we interested in?
- Dependent variable: the qualities we are interested in understanding (effect)
- Independent variable: the qualities we manipulate to see what effect occurs with the dependent variable (cause)
- How can we know if the Independent Variable affects the Dependent Variable?
- nonexperimental designs: measure treat measure (ABA design)
- True experimental designs: ABAB, multiple baseline, group parametric designs
- Are our results reliable?
- reliable measures, results, findings are consistent, dependable, will be seen again if you look again, maybe “true” (whatever they mean)
- measure treat measure
- measure treat measure
- measure treat measure
- reliable measures, results, findings are consistent, dependable, will be seen again if you look again, maybe “true” (whatever they mean)
- Are our results valid?
- Are we drawing the correct conclusions about our date?
- Threats to validity:
- Internal validity: do our results demonstrate what we believe (wish) these results to demonstrate?
- External validity (generalizability): do our results apply to anyone beyond the group we worked with?
- Issues in internal validity: alternative explanations for our results
- the invisible sceptic in the back of the room (the purpose of experimental designs is to rule out alternative explanations for the findings (results) we observe
- common alternative possibilities:
- time/development (“maybe he/they grew out of it”)
- selection (“maybe there was something special/different about the person/people you looked at”)
- another factor (“maybe something else, that you didn’t consider/measure really caused the change”)
- Control Groups
- random assignment (and why selection studies are not experimental)
- measure1 treat measure1
- measure2 don’t treat measure2
- detection of differences
- real differences might be small (and likely to be missed)
- real differences (valid) may also be trivial (relatively unimportant in the real world)
- significance testing
- power
- measurement error
- quality of our measure
- sample size
- Issues in external validity
- sampling: Is the group we studied representative of the population we wish to draw conclusions about?
- confounding: “any situation in which one cannot determine which of two or more effects is responsible for the behaviors being observed” (Cavanaugh & Blanchard-Fields, 2015, p. 21)
- Are our results important?
- Effect size, mean difference (and standard of deviation), impact
Are our methods of research ethical?
- Ethics in research
- sources of ethical guidance in research:
- laws
- government regulations governing grant funding
- ethical standards of professional associations
- institutional policies
- conscience and personal morality
- What makes research ethical?
- Informed consent of participants
- voluntary
- freedom from coercion
- negative coercion (threat, bullying, intimidation)
- positive coercion (excessive positive rewards)
- freedom to withdraw
- informed
- risk:
- clear communication of risks
- procedures for identifying and dealing with untoward consequences
- purpose
- deception research
- debriefing responsibilities
- freedom to withdraw and consequences
- Quality of research
- unbiased, objective, clearly conceptualized
- makes a contribution to our shared knowledge and understanding
- potential benefits outweigh potential risks
- results communicated accurately and responsibly
- honesty in reporting results
- data/methods made available to others for replication
- issues of intellectual property, proprietary rights, copyrights, patients, and profit
- Who owns science? Who pays for science? Who show benefit from science?
- The authors of CITI (Collaborative Institutional Training Initiative) training feel that “bad” research (poorly designed) is unethical because it wastes resources
- Integrity of researcher
- public acknowledgement of potential conflicts of interest
- disclosure of financial entanglements
- source of funding
- accurate acknowledgment of contributions of others
- credit for contributions to the research: authorship
- credit for contributions to conceptualization: references
- plagiarism
- sources of ethical guidance in research:
A thought/suggestion this Wednesday: spend some time outside this week and weekend, preferably around things that are naturally green, brown, blue (grass, trees, bushes, grass, water). Is there someplace you could go where you would not see any immediate or prominent sign of human influence (trail, park, open field)? How does it affect you to spend time away from the activities of other people for a little while? How does this affect your motivation to study, to work, to pursue other interests? (nothing to write, no points, just something to consider). Have a good week. Turn in your question for ch. 2 on Monday. Dr. H