GOALS OF THE SCIENTIFIC ENTERPRISE
• There are 3 interrelated goals• 1: Measurement and description—how do we
measure the phenomenon• 2: Understanding and prediction—hypothesis,
variables (measurable conditions—controlled or observed)• 3: Application and control—theories (bring
understanding from description and generates new predictions)
STEPS IN A SCIENTIFIC INVESTIGATION
• 1: Formulate a testable hypothesis—variables must be defined• Operational definition describes actions or
operations that will be used to measure or control a variable
STEPS
• 2: Select research method and design the study• Depends on nature of the question• Experiments, case studies, surveys, naturalistic
observation, etc…
STEPS
• 4: Analyze data and draw conclusions• Statistics are used to analyze and determine the
validity of the hypotheses
STEPS
• 5: Report the findings• Findings usually submitted to a journal: periodical
that publishes technical and scholarly material
ADVANTAGES OF THE SCIENTIFIC APPROACH
• 1: It is clear and precise• 2: Intolerant of error---findings are reviewed by
other skeptical researchers
EXPERIMENT
• Def: a research method where a variable is manipulated under carefully controlled conditions and observes changes in that variable
INDEPENDENT AND DEPENDENT VARIABLES
• Ind. Variable: one that is changed to see its impact on another variable (controlled or manipulated)• Dep. Variable: one that is affected by
manipulation of the ind. variable
EXPERIMENTAL AND CONTROL GROUPS
--Experimental Group: subjects who receive special treatment in regard to the ind. variable--Control Group: do not receive special treatment--Both groups must be similar, except in treatment
EXTRANEOUS VARIABLES
• Def: any variables other than ind. variable that seem to influence the dep. variable in a specific study• Even if groups are alike there are smaller
differences that could affect outcome
EXTRANEOUS VARIABLES
• Confounding of variables: when 2 variables are linked together in a way that makes it difficult to sort out their specific traits• Makes it difficult to see which variable is affecting
the outcome
HOW TO PREVENT EXTRANEOUS VARIABLES
• Random assignment: when subjects have an equal chance of being assigned to any group or condition in the study
VARIATIONS IN DESIGNING EXPERIMENTS
• Sometimes it is good to use only one group• Instead you create control conditions and
experimental conditions
VARIATIONS CONTINUED
• Manipulate more than one ind. variable in a single experiment• Allows researchers to see if two variables interact
VARIATIONS CONTINUED
• Use more than one dependent variable in a single study• Helps form a more complete picture
ADVANTAGES OF EXPERIMENTAL RESEARCH
• Allows conclusions about cause and effect relationships btwn variables• Creates precise control• Helps avoid extraneous variables
DISADVANTAGES OF EXPERIMENTAL RESEARCH
• Experiments are artificial• Experimental method can not be used in some
instances (ethics)• Sometimes it is hard to manipulate variables
PERMITS RESEARCHERS TO DESCRIBE PATTERNS OF BEHAVIOR AND DISCOVER LINKS BETWEEN VARIABLES
DESCRIPTIVE/ CORRELATIONAL
NATURALISTIC OBSERVATION
• Def: researcher observes w/o interfering directly• Strength: experiments are less artificial• Weakness: hard to remain unobtrusive
CASE STUDIES
• Def: in-depth investigation of an individual subject• Includes: interviews, observation, testing• Good w/psych disorders• Problem: highly subjective
SURVEYS
• Def: use of questionnaires or interviews to gather info. about specific aspects of a subject’s behavior• Use to gather info. hard to observe• Easy to gather from a large sample
ADVANTAGES OF DESCRIPTIVE/CORRELATIONAL
RESEARCH• Broadens scope of what can be studied• Covers some of what can’t w/experimental
research• Cannot control events• Cannot demonstrate that 2 variables are casually
related
STATISTICS: USE OF MATHEMATICS TO ORGANIZE, SUMMARIZE, AND INTERPRET NUMERICAL DATA
STATISTICS AND RESEARCH
DESCRIPTIVE STATISTICS
• Used to organize and summarize data• Include measure of central tendency, measures of
variability, and the coefficient of correlation
CENTRAL TENDENCY
• 3 measures:1: Median: score that falls in the center of the
distribution of scores2: Mean: avg. of scores (most useful)3: Mode: most frequent score
VARIABILITY
• Def: how much the scores in a distribution vary from each other and from the mean• Standard of deviation: an index of the amount of
variability in a set of data• Large variability = large standard of deviation• Small variability = small s.o.d.
CORRELATION
• Def: when 2 variables are related to each other• Correlation coefficient: numerical index of the
degree of relationship btwn 2 variables—indicates direction of correlation and the strength of the relationship
POSITIVE/NEGATIVE CORRELATION
• Positive(+): variables co-vary in the same direction (Ex.: increased study time = increased test score)• Negative(-): variables co-vary in opposite
direction (Ex.: increased absences = decreased test scores)
STRENGTH OF CORRELATION
• Size of coefficient indicates strength• Coefficient varies btwn 0 and +1.00 (pos.); 0 and
-1.00 (neg)• Closer to zero, the weaker the relationship
INFERENTIAL STATISTICS
• Def: used to interpret data and draw conclusions• Did chance play a factor?• Statistical significance: exists when the
probability that the observed findings are due to chance is very low (5 chances in 100)
META-ANALYSIS
• Def: combines statistical results of many studies of the same question, giving an estimate of the size and consistency of a variable’s effect• Allows to test the generalizability of findings
across people, places, and times and variations in procedure in a precise and objective way
SAMPLING
• Sample: collection of subjects being observed in a study• Population: group from which the sample is taken
SAMPLING BIAS
• Def: exists when a sample is not representative of the population from which it was drawn
PLACEBO EFFECT
• Def: occurs when participant’s expectations lead them to experience some change even though they receive empty, fake, or ineffectual treatment
DISTORTIONS IN SELF-REPORT DATA
• Questionnaires, inventories, interviews have flaws• Social desirability bias: tendency to give socially
approved answers to questions about oneself
DISTORTIONS
• Response set: tendency to respond to questions in a particular way that is unrelated to the content of the questions
EXPERIMENTER BIAS
• Def: when researcher’s expectations about the outcome of a study influence the results obtained
DOUBLE-BLIND PROCEDURE
• Def: research strategy in which neither subjects nor experimenters know which subjects are in the experimental or control groups
QUESTION OF DECEPTION
• Deceiving in order to observe specific situations• Proponents: “white lies”, not harmful to
participants, benefits worth it• Critics: it is lying, may diminish trust, may
produce distress in subjects