Experimental Psychology (L7-L9)

• Hypothesis


  A statement about a predicted relationship between at least two variables
• Hypothesis


  • Represents the end of the long process of thinking about a research idea
  • Predicts the effects of specific antecedent conditions on some behavior that is to be measured
• Experimental hypothesis


  A tentative explanation of an event or a behavior. It is a statement that predicts the effect of an independent variable on a dependent variable.
• Experimental hypothesis


  • Cognitive behavior therapy (CBT) produces less relapse than antidepressants
• Nonexperimental hypothesis


  Predicts how variables (events, traits, or behaviors) might be correlated, but not causally related
• Nonexperimental hypothesis


  • Red-haired patients receive less relief from pain medication than blonde patients
• Characteristics of an experimental hypothesis

  • Synthetic statements
  • Testable statements
  • Falsifiable statements
  • Parsimonious statements
  • Fruitful statements
• Synthetic statements


  Can either be true or false. Expressing the potential relationship between the antecedents and the behaviors to be measured.
• Synthetic statements


  • If you eat an increasing number of apples every week, then you will lessen your chance in consulting a doctor.
  • If employees will get longer vacation days, then rates of resignation among employees will be lessened.
  • I am on a diet or I am not on a diet.
  • You have a neighbor and you do not have a neighbor.
• Testable statements


  Means for manipulating antecedent conditions and measuring the resulting behavior must exist. Without testability, we cannot evaluate the validity of a hypothesis.
• Testable statements


  • If touch-me-not plant folds when being touched, then it has feelings.
  • If a company has great compensation benefits, then it will attract many applicants.
• Falsifiable statements


  Statements of research hypotheses must be falsifiable (disprovable) by the research findings.
• Falsifiable statements


  • If you listen intently to this discussion, then you will know how to construct a good and proper hypothesis
• Parsimonious statements


  Parsimony means that the simplest explanation is preferred.
• Fruitful statements


  A hypothesis is fruitful when we can think of new studies that will become important if the hypothesis is supported.
• Models in formulating hypothesis


  • Inductive model (specific to general principles)
  • Deductive model (from general principle to make predictions about specific instances)
• Where to begin in formulating hypothesis

  • Prior research
  • Observation
  • Real-world problem
• Prior research


  • Identifies questions that have not been conclusively answered or addressed at all
  • Suggests new hypotheses
  • Identifies additional variables that could mediate an effect
  • Identifies problems other researchers have experienced
  • Helps avoid duplication of prior research when replication is not intended
• Observation


  Forming hypotheses about the kinds of antecedent conditions that affect people's behavior comes naturally
• Real-world problem


  Try to figure out what causes it. An added benefit is that once the cause can be determined, a solution often suggests itself.
• Finding Inspiration for Research Question

  1. Informal Observations

  2. Practical Problems

  3. Previous Research
• Empirically Testable Research Question


  Questions expressed in terms of a single variable or relationship between variables
• Generating Empirically Testable Research Questions


  1. Look at the Discussion Section

  2. Generate your own research questions
• Generating Empirically Testable Research Questions


  1. What are some possible causes of the behavior or characteristic?

  2. What are some possible effects of the behavior or characteristic?

  3. What types of people might exhibit more or less of the behavior or characteristic?

  4. What types of situations might elicit more or less of the behavior or characteristic?
• Generating Empirically Testable Research Questions


  1. Are there other ways to operationally define the variables?

  2. Are there types of people for whom the statistical relationship might be stronger or weaker?

  3. Are there situations in which the statistical relationship might be stronger or weaker—including situations with practical importance?
• Evaluating Research Questions


  • Interestingness: Its answer is in doubt, The answer fills the gap in the research literature, The answer has an important practical implications
• Evaluating Research Questions


  • Feasibility: Time, money, equipment and materials, Technical knowledge and skill, Access to research participants
• Research does not have to be complicated or difficult to produce interesting and important results
• It is generally good practice to use methods that have already been used successfully by other researchers
• Variables


  Anything that can change or be changed. Potential relationship between the two variables.
• Independent variable (IV)


  The variable (antecedent condition) an experimenter intentionally manipulates
• Independent variables


  • Lighting (bright or dim)
  • Noise levels (loud or soft)
  • Difficulty (easy or hard)
• Levels of an independent variable

  The values of the IV created by the experimenter
• An experiment requires at least two levels of the independent variable
• Levels of independent variable


  • blue
  • yellow
  • pink
  • purple
• Dependent variable


  The outcome measure the experimenter uses to assess the change in behavior produced by the independent variable
• The dependent variable depends on the value of the independent variable
• Independent variables


  • Treatments
  • Manipulations
  • Interventions
  • Conditions
• Dependent variables


  • Measures
  • Effects
  • Outcomes
  • Results
• Extraneous variables


  Factors that are not the focus of the experiment but can influence the findings