Chapter 2: How Psychologists Do Research

Psychology as a SCIENCE

• Empiricism:

  • The view that science should ONLY rely on observation, experimentation, and measurement!

  • We follow the scientific method!

    1. carefully planned, systematic steps

    2. be objective — avoid bias

    3. replication

• Aim is to avoid confirmation bias.

1. Formulate a theory.

   • You develop a scientific explanation about a phenomenon. A literature review of existing studies informs your theory. In this example, your theory is that a major cause of car crashes is distracted driving.

2. Developpe a testable hypothesis.

   • You create a specific, testable hypothesis related to the theory. In this example, a good testable prediction is that “Using a cell phone will interfere with driving because it is distracting.”

3. Test with a research method.

   • You test your hypothesis by selecting the most appropriate research method. You then collect data to evaluate your hypothesis. For example, in an experiment you might have some participants talk on a handheld or hands-free cell phone in a driving simulator while other participants do not talk on a cell phone.

4. Analyze the data.

   • You analyze the data using appropriate statistical techniques and draw conclusions. If the data do not support your hypothesis, you either discard the theory or revise it (and make plans to test the revision).

5. Share the results and conduct more research.

   • You submit results to research journals and present them at conferences to share them with the scientific community. Then you continue the process by refining your theory, making further predictions, and testing hypotheses.

Operational Definitions of Variables

• Objective and Systematic Research:

  • Must create operational definitions to qualify (describe) and quantify (measure) variables so they can be understood objectively.

    • Defined in clear, measurable ways.

    • Must be created for both the independent and dependent variables.

Scientific Research

• Skepticism and Critical Thinking:

  • “Show me”

  • Examine the validity of a claim.

• Principle of Falsifiability:

  • Scientists must state and idea in such way that it can be refuted, or disproved by counterevidence!

  • For a theory to be a good theory, it has to be falsifiable.

• Scientists must be willing to tell others:

  • Where they got their ideas.

  • How those ideas were tested.

  • What the results were.

• This is important so that:

  • Studies can be replicated.

  • Finding can be verified independently.

Types of research methods

• Descriptive methods: Describe what is occuring.

  • Observational studies: allow researcher to watch what participants do in a natural environment or a laboratory.

  • Self-reports: use surveys, question-naires, or interviews to gather information directly from participants.

  • Case studies: allow in-depth investigation of one or a few people or an organization.

• Correlational methods: Test the relationship between variables.

• Experimental methods: Investigate what causes an outcome.

Research Methods

• Research Method: Descriptive

  • Basic Purpose: To observe and record behavior.

    • How Conducted: Do case studies, surveys, or naturalistic observations.

      • What Is Manipulated: Nothing

        • Weaknesses: No control of variables; single cases may be misleading.

• Research Method: Correlational

  • Basic Purpose: To detect naturally occurring relationship; to assess how well one variable predicts another.

    • How Conducted: Compute statistical association, sometimes among survey responses.

      • What Is Manipulated: Nothing

        • Weaknesses: Does not specify cause and effect.

• Research Method: Experimental

  • Basic Purpose: To explore cause and effect.

    • How Conducted: Manipulate one or more factors; use random assignment

      • What Is Manipulated: The independent variable(s)

        • Weaknesses: Sometimes not feasible; results may not generalize to other contexts; not ethical to manipulate certain variables.

Case Studies

• Among the oldest research methods!

• A technique that studies one person or animal in depth (over a an extended period of time) to reveal underlying behavioral principles.

• Strength:

  • Allows us to study rare psychological phenomenon.

  • Provides a lot of data.

• Weakness:

  • It can lead to misleading and wrong conclusions when overgeneralized.

Observational Studies

• Recording behavior in a naturally situation without trying control the situation.

  • Example:

    • Jane Goodall - Studied chimpanzees in the jungle.

  • Strength

    • Valuable in early stage of research.

  • Weakness

    • Experimenter does not have control.

    • One cannot draw cause the effect conclusions!

    • Observer Bias

Psychological Tests

• Standardized:

  • Uniform procedures are in place for giving and scoring the test.

• Norms:

  • Established standards of performance.

  • Allows researchers to determine scores that are considered to be high, low, or average.

Evaluating Measures

• Reliability:

  • How consistent are the test results - “test-retest reliability”

  • When a questionnaire yields similar scores from one session to another.

• Validity:

  • Does it measure what it claims it measures?

  • Example - Scientists want to be positive that their depression questionnaire is actually measuring depression and NOT anxiety.

• For a test to be valid it must be reliable!

• BUT a reliable test can still be completely invalid!!!!!

Surveys

• Questionnaires and interviews that gather information by asking people directly about their experiences, attitudes, or opinions.

  • Strength:

    • Used to gather data from a large number of people.

    • Easy to administer, cost-efficient, and relatively fast way to collect data.

• Weakness:

  • Self-Report Bias - Info is not recalled accurately. Avoid revealing negative information about self.

  • Social Desirability Effect - Try to appear as though you match what you believe are the views of the researcher or the majority group.

  • Wording Effects - When the wording used in a survey affects the results.

    • Example:

      • “Government censorship”

        • 27% of Americans approved

      • “More restrictions on what is shown on television”

        • 66% approved the second statement.

Cross-Cultural Studies

• Must consider:

  • Methods and sampling - Must consider how one language translates into another. Must make sure their samples are similar in all important ways (example - education) otherwise something can be incorrectly viewed as a cultural difference.

  • Stereotyping - Avoid oversimplifying. Try to understand average cultural differences without saying everyone is Cultural A is ______.

  • Avoid treating culture as a thing - When it is a collection of belief’s and traditions. Researchers not only find differences in traits and behaviors across cultures but try to determine the underlying mechanisms for them.

Correlation

• When one trait or behavior accompanies another, we say the two correlate.

• Correlation Coefficient:

  • Is a statistical measure of the relationship between two variables.

Scatterplots

• Strong Positive Correlation

  

• Scatterplot:

  • Is a graph comprised of points that are generated by values of two variables.

  • The slope of the points depicts the direction.

  • The amount of scatter depicts the strength of the relationship.

• A positive correlation: as one variable increases so does the other OR as one decreases so does the other.

  • Variable 1 = amount of time playing violent video games.

  • Variable 2 = number of aggressive acts.

• Strong Negative Correlation

  

• No relationship (0,00)

  

• A negative correlation: as one variable goes increases, the other decreases:

  • Variable 1 = depression scores.

  • Variable 2 = self-esteem scores

Correlation Does Not Mean Causation

• Point!!!!

  • If two variables are related, that does not mean that once caused another!

Third Variable Problem

Illusory Correlation

• Definition:

  • The perception of a relationship between two variables where none exists.

  • Examples:

    • The belief that sugar is associated with children being hyper.

    • The belief that going outside in the cold with your hair wet is associated with sickness.

    • The belief that vaccines increase likelihood of autism.

Correlations

• Do not forget that correlation ® can only exist between:

  • 0→1

Scatterplots

• Positive Correlation: both variables go _____?

  • The same direction

• Scatterplot:

  • The SLOPE of the points depicts the ______?

    • How steep

  • The amount of SCATTER depicts the _____ of the relationship.

    • direction

  

• In a negative correlation, as one variable INCREASES, the other variable _______?

  • Decreases.

Experimental Methods Cause and Effect

• Experimental Methods:

  • A research method the tests causal hypotheses by manipulating independent variables (x) and measuring the effects on dependent variables (y).

• Manipulate factors:

  • Experimenter manipulates the independent variable.

• Random Assignment:

  • Participants are assigned at random to the control group or the experimental group.

• Independent Variable: X

  • Is a factor that is manipulated by the experimenter.

  • The effect of the independent variable is the focus of the study (use of cell phone when driving).

• Dependent Variable: Y

  • Is the outcome response that is measured.

  • Is a factor that may change in response to an independent variable.

  • In psychology, it is usually a behavior or a mental process, such as number of car accidents or test scores.

Groups in an Experiment

• Control Group:

  • A comparison group of participants who receive no intervention.

• Experimental Group:

  • One or more treatment groups that receive the intervention of the independent variable being investigated.

Random Assignment

• Random Assignment:

  • Every member of the sample has an equal chance of being placed in a control group of an experimental group.

  • Minimizes pre-existing difference between the conditions.

  • Researchers can be certain the conditions are otherwise equal (age, attitudes, driving experience).

  

Problems

• Confounds:

  • Any difference between the experimental and control groups, as a result of something other than the independent variable.

  • Example of issue:

    • You are studying cell phone use and car accidents.

    • Experimental group (uses cell phone) has many 80 year old participants.

    • Control group (doesn’t use cell phone) has primarily 20 year old participants.

    • Problem?

      • THIS WILL ALTER YOUR DATA and cause you to misinterpret your findings!

Evaluating Therapies

• Placebo Effect:

  • Any effect on behavior caused by the administration of a substance or condition, which is assumed to be an active active agent.

  • Just believing you are getting a treatment can relieve your symptoms (e.g. depression).

• Double-blind Procedure:

  • In evaluating drug therapies, patients and experimenters should remain unaware of which patients had the REAL treatment and which patients had the PLACEBO treatment.

Random Sample

• Random Sampling:

  • Is a method that ensures every member of a larger population has an equal chance of being selected for the study.

  • Problem if not used:

    • Biased results

Population:

• This is the group you want to know about.

Random sample:

• At the start of a study, participants may be selected at random from the population. Each person in the population has an equal chance of being selected.

Random assignment:

• Participants are then assigned at random to the control group or the experimental group. Each person has an equal chance of being assigned to either group.

Institutional Review Boards

• Institutional Review Boards (IRBs):

  • Committee that reviews proposed research to ensure that it meets the accepted standards of science and provides for the physical and emotional well-being of research participants.

• For Research to be Ethical:

  1. Privacy and Confidentiality: Researchers must respect participants’ privacy and keep all data records completely confidential.

  2. Informed consent: People must be told what their participation will involve (risks and benefits).

  3. Protection from Harm: Researchers cannot ask participants to endure unreasonable pain or discomfort.

  4. Deception: Knowing a study’s specific goals can sometimes alter participants’ behavior.

  5. Debriefing: After the study is completed, participants must be told the purpose of the study.