Descriptive Methods & Ethical Research

Psych 231: Research Methods in Psychology

Correlational Methods

Measure two (or more) variables for each individual to see if the variables are related

Used for:– Predictions– Reliability and Validity– Evaluating theories

Problems: Can’t make casual claims

Causal claims

We’d like to say: – variable X causes variable Y

To be able to do this:– The causal variable must come first– There must be co-variation between the two

variables– Need to eliminate plausible alternative

explanations

Causal claims Directionality Problem:

– Airplanes and coffee spills

– Happy people sleep well• or is it that sleeping well when you’re happy?

Third variable problem:– Do Storks bring babies?

• A study reported a strong positive correlation between number of babies and stork sightings

Theory 1: Storks deliver babies

Theory 2: underlying third variable

The experimental method Manipulating and controlling variables in laboratory

experiments Must have a comparison

– At least two groups (often more) that get compared– One groups serves as a control for the other group

Variables– Independent variable - the variable that is manipulated – Dependent variable - the variable that is measured – Control variables - held constant for all participants in the

experiment

The experimental method

Advantages– Precise control possible– Precise measurement possible– Theory testing possible– Can make causal claims

The experimental method

Disadvantages– Artificial situations may restrict generalization to

“real world”– Complex behaviors may be difficult to measure

Ethical research

Two basic categories of ethical concerns:– need to consider the rights of our participants in

our research– need to behave ethically as scientists and

practitioners

Ethical research

Consider ethics at each step– What measurement techniques will be used– How are participants selected– What methods may be used on the participant

population– What design is appropriate– How are the data analyzed– How are the results reported

Using humans in research

For the most part the researcher has the power:

• you know what is going to be done to the participants

• participants may feel like they have to do it

APA’s code of ethics

Basic courtesy Institutional review board approval Informed consent

Informed consent

Information to allow a person to decide if they want to participate– Basic purpose of the study– Risks involved– Benefits involved– Rights to refuse or terminate participation

APA’s code of ethics

Basic courtesy Institutional review board approval Informed consent Avoiding deception

Using deception in research

Passive deception– Witholding information about the study

Active deception– Deliberately misleading participants

Using deception in research

Avoid it when possible When not possible – won’t work without it

– Make sure that you are up front with all possible risks

– Potential results must be worth it – Must debrief participants as soon as possible

(either right after participation or as soon as project is over)

Using deception in research

Alternatives to deception– Role-playing– Simulation studies– “honest” experiments

APA’s code of ethics

Basic courtesy Institutional review board approval Informed consent Avoiding deception Freedom from coercion Protection from harm

APA’s code of ethics (cont.)

Debriefing Confidentiality Costs vs. Benefits

Costs/Benefits analysis

Costs: all potential risks to the participants– Physical harm– Psychological harm– Loss of confidentiality

Benefits: the “good” outcomes– Direct benefits to participants– Benefits to knowledge base– Benefits to world at large

Ethical responsibility to science

Dirty tricks (this will get you thrown out) Questionable tricks (these are a little

fuzzier, but be wary) Neat tricks (accepted as okay, and

sometimes necessary)

Ethical responsibility to science

Fabrication of results Little or no attempt to minimize demand biases Reformulating your theory as you go Falsifying credentials Plagiarism Little or no attempt to minimize confounds Deliberately hiding (significant) errors in published

work Little or no attempt to minimize demand

characteristics

DT

DTDT

QT

QT

DT

QT

NT

Ethical responsibility to science

Throwing out data

Reorganizing order of report of experiments Violations of underlying statistical assumptions Strategic graphing of the data Duplicate publications (presented as new) Selective reporting of the results Leaving out some bad experiments (not bad results)

QT or DT depending on situation (reason for throwing out)??

QTQT

QT

NT

NT

DT

Using animals in research Why use animals in research?

– Same building blocks (e.g., nervous systems)– Control

• often we can’t control the relevant past experiences of our human subjects, but we can with animals

• easier to control certain experimental factors with animals

– Irreversible and/or harmful effects

Using animals in research

Why use animals in research (cont.)? – Some unique, special characteristics – Simpler systems– May allow you to focus on particular variables (IV’s

and DV’s), easier to do the experiment without a lot of complex interactions

Using animals in research But animals and humans are different

– Well, there are strong similarities• evolution - common ancestry - as a result,

things may work in similar ways– But, we do need to be aware that there are

differences, and always keep that critical eye, think of alternative explanations

Animal ethics: What rights do animals have? If animals are so similar to humans, then shouldn’t

they have similar rights that humans have? Isn’t it unethical to do things to them that we wouldn’t do to ourselves?

There is no simple answer, no clear right or wrong. Each individual must decide for themselves.

However, animal research has certainly helped our (humans) lives

Next time

Exam 1 is one week away. Review chapters 1,2,3,6, & 7