Chapter Two: The Research Enterprise in Psychology

1
Chapter Two The Research Enterprise in Psychology

• Goals of the Scientific Enterprise
• Skepticism (testing claims before accepting
  them as fact) and humility (the willingness
  to reject you ideas when confronted with
  contradictory facts is the foundation in which
  the scientific method is founded.
• Critical thinking. Thinking that does not
  blindly accept arguments and conclusions.
  Rather, it examines assumptions, discerns
  hidden values, evaluates evidence, and assesses
  conclusions.
• Hindsight Bias.  The tendency to believe,
  after learning an outcome, that one would
  have foreseen it.
• Overconfidence. The tendency to be more
  confident than correct - to overestimate the
  accuracy of one's beliefs and judgments.

2
Goals of the Scientific Enterprise

• Measurement and Description.
• The goal of psychology is to develop
  measurement techniques that make it possible to
  describe behavior clearly and precisely.
• Theory. An explanation using an integrated set of
  principles that organizes and predicts
  observations.
• Hypothesis. A testable prediction relationship
  between two or more variables. A variable are any
  measurable thing that can be observed or
  measured.
• Operational definitions. A statement of the
  procedures (operations) used to define research
  variables.
• Selecting a Research Method and Research Design.
  The researcher must select a strategy that
  appears to be the most practical and appropriate.

3
Goals of the Scientific Enterprise - cont

• Steps in a Scientific Investigation
• Data Collection. Data collection strategies for
  making empirical observations and measurements.
• Data Analysis and Conclusions.
• Replication. Repeating the essence of a research
  study, usually with different subjects in
  different situations, to see whether the basic
  finding generalizes to other subjects and
  circumstances.
• Advantages of the Scientific Approach
• 1. Clarity and precision
• 2. Intolerance of error.
• Research methods consists of different approaches
  to the observations, measurement, manipulation,
  and control of variables in empirical studies.

4
The Scientific Method

• Experimental and control conditions
• 1. Experimental condition - the condition or
  group in which subjects receive some amount of
  the independent variable.
• 2. Control condition - the condition or group in
  which subjects do not receive any amount of the
  independent variable.
• a.    Subjects are treated the same in all other
  respect and are similar to experimental
  condition subjects.
• b.    Random assignment balances individual
  differences among subjects between the two
  groups.         
• c.    A fake treatment or placebo controls for
  the expectation of control condition subjects.
          
• d.    Independent variable. The experimental
  factor that is manipulated the variable whose
  effect is being studies.        

5
Experimental and control conditions - cont

• e. Dependent variable. The behavior or mental
  process that is being measured the variable
  that may change in response to manipulations of
  the independent variable.
• 3. Experimenter effects. 1.    To control the
  effects of the expectations of subjects and
  experimenters.       a.    Single-blind
  studies - subjects don't know whether they are
  in the experimental or control group.
         b.    Double-blind studies - neither
  experimenter nor subjects know which subjects
  are in which group.
• 2. Limitations of experimental research
        1.    The setting is artificial and
  subject's behavior may differ from real life.
        2.    Subject's behavior may be a reaction
  to the experimenter.

6
Case Study

• 1.    General characteristics    a.  Detailed
  descriptions of particular individuals.     b. 
  Based on careful observations or psychological
  tests.       
• 2.    Advantages    a.    Produce detailed
  pictures of individuals.    b.    Can illustrate
  psychological principles well.    c.    Help
  avoid practical or ethical difficulties.
• 3.    Disadvantages    a.    Rely on memories,
  that can be inaccurate    b.    Difficult to
  interpret.    c.    Cannot use to generalize
  about human behavior.    d.    They are not
  tests of hypotheses.

7
Surveys

• 1.    Gather information by asking people
  directly.
• 2.    Potential problems with surveys.       
  a. Random sampling. Subjects should, but do not
  always, represent the larger population
  being described.               
• b. Volunteer bias - volunteers differs from
  non-volunteers.
• c.  Subjects may lie, forget or remember
  incorrectly.
• d.  Potential biases or ambiguities in wording
  of questions.               
• e. False consensus effect. The tendency to
  overestimate the extent to which other share
  our beliefs and behaviors.

8
Correlation Studies

• Correlation is a way of measuring the strength of
  linear relationship between two variables.
• A.    Purpose and Definitions. 1. The purpose
  - to determine whether two or more phenomena
  are related, and if so, how strongly. 2.   
  Definition - numerical measure of the strength
  of the relationship.            3.   
  Variable - anything that can be measured, rated,
  or scored.
• B.    Characteristics of correlation         
  1.    Direction of a relationship between
  variables.                 a.  Positive
  correlation - high values of one variable are
  associated with high values of the other
  low values of one variable are associated with
  low values of the other.                
  b.  Negative correlation - high values of one
  variable are associated with low values of the
  other.                 c.   Uncorrelated - no
  relationship between two variables.        

9
Correlation Studies - cont

• 2. Strength of relationship between the two
  variables expressed as correlation.
• a.  Correlation coefficient - statistic used to
  express a relationship.  
• b.    Possible range of correlation coefficient
  is -1 to 1.        (1)   -1 indicates a strong
  negative relationship.        (2)   1 indicates
  a strong positive relationship.        (3)   
  Zero indicates no relationship.        (4)   
  The closer to either 1 or -1, the stronger
  the relationship.        (5)    The closer to
  0, the weaker the relationship.
•   Benefits and limitations of correlations.
            1.    Benefit - allows one to predict
  from one variable to another.           2.   
  Limitation - cannot show causation.

10
Correlation Studies - cont

• Example 1 Correlation coefficient Scatterplot
  and the correlation coefficient
• Example 2 Correlation coefficients
  explanationCorrelation coefficients measure the
  degrees of association between two sets of data
  and have values which range between -1.0 and
  1.0. A correlation coefficient of -1.0 indicates
  a perfectly negative relationship between two
  sets of data a zero correlation coefficient
  indicates purely random behavior (i.e., no
  association at all) and a 1.0 correlation
  coefficient indicates a perfectly positive
  relationship between the two sets of data. The
  higher the correlation coefficient (i.e., closer
  to 1.0), the more closely one data set mirrors
  another.

11
Correlation Studies - cont

• Positive correlation.If the correlation
  coefficient is positive, then there is a positive
  linear relationship between the two variables.
  The larger the value, the stronger the
  relationship. The range that the correlation
  coefficient can have is between 0 and 1, where 1
  implies perfect positive linear association, and
  close to zero implies very poor or no linear
  relationship.
• Negative correlation.
• If the correlation coefficient is negative, then
  there is a negative linear relationship between
  the two variables. The larger the absolute value,
  the stronger the relationship. The range that the
  correlation coefficient can have is between 0 and
  -1, where -1 implies perfect negative linear
  association, and close to zero implies very poor
  or no linear relationship.

12
Correlation Studies - cont

• Zero correlation.
• A correlation coefficient of zero, or very close
  to zero implies no or very little linear
  association.
• Observational Studies
• 1.    General characteristics a.   
  Researchers observe behavior without interfering.
  b.    Involve many subjects.
• c.    Involve counting, rating or measuring
  specific behaviors.              (1)
  Systematic measuring reduces errors and
  biases.                   (2) Cross-checking by
  more than one rater occurs.            d.   
  Cannot explain behavior.  

13
Observational Studies.

• 2.    Types of observational studies.     a.   
  Naturalistic observation.          
  (1)  Describes behavior in the natural
  environment.           (2)  Can be used to
  describe animals or humans.    
• b.    Laboratory observation             
  (1) Subjects observed in the laboratory.
               (2)  Observation might cause
  subjects to alter behavior.

14

15
Statistical Reasoning

• Measures of Central Tendency
• Mode. The most frequently occurring score in a
  distribution
• Mean. The arithmetic average of a distribution,
  obtained by adding the scores and then dividing
  by the number of scores.
• Median. The middle score in a distribution half
  the scores are above it and half are below it.
• Range. The difference between the highest and
  lowest scores in a distribution.
• Standard deviation. A computed measure of how
  much scores vary around the mean score.
• Statistical significance. A statistical
  criterion for rejecting the assumption of no
  difference in a particular study.

16
ETHICAL ISSUES

• A.    American Psychological Association's
  ethical guidelines        1.    Dignity and
  welfare of subjects must be respected.       
  2.    Human subjects must voluntarily consent to
  participate.        3.    Subjects must know
  enough to make intelligent decision or
  informed consent.        4.    Subjects must be
  free to withdraw from a study at any time.
         5.    Methods must follow governmental or
  institutional regulations.
                 See The Tuskegee Syphilis Study
• B.    Two controversial issues         1.    Use
  of deception.                a.    Misleading
  subjects so the results are not affected.
                 b.    New guidelines govern use
  of deception.
•        2.    Use of animals               a.   
  Many purposes for conducting research using
  animals.               b.    Opposition has
  resulted in improved treatment and
                       regulations.