Internal
Links

Top

  An Introduction to   Methods: How the Social Sciences are Done
External
Links
Blank
See Also:  An Overview of Methods
Link
Blank
The Deductive method of analysis begins w/ theory 
     & builds a question ( Hypothesis ) based on that theory
The hypothesis is tested using some form of the experimental 
    method to test some part of the theory
Blank
Blank
The Induction method of analysis begins w/
      gathering generalizations from data
Theory is then created to explain the generalizations
Blank
Blank
Research can be used to test a theory or generate a theory,
     but research cannot "find out the truth"
Blank
Blank
Theory:  A set of interrelated statements about reality, 
       usually involving one or more cause-effect relationships
Blank
Blank
      Theories are made up of verifiable statements about reality that, 
      with the right information, can be tested
Blank
Blank
      Theory refers to a set of interrelated statements about reality, 
      usually involving one or more major cause-effect relationships. 
      Ideally these statements can be tested through research
Blank
Blank
Law:  Theory or part of a theory that is well established and therefore has greater acceptance by scientific community
Blank
Blank
Hypothesis:  a research question, that  always takes the form of a statement
      It must be able to be disproved
Blank
Blank
       A Hypothesis is a testable statement
Blank
Blank
       When social scientists use research for theory testing, they usually make use of a hypothesis
Blank
Blank
Correlation:  A relationship by which two or more variables change together
Blank
 Blank
Concept:   An abstract idea that represents some element of the world
Blank
Blank
Variable: a concept that can take on different values or that has two or more categories 
      from case to case
Blank
Blank
Independent Variables influence or cause the dependent variable.
Sometimes called the predictor variable.
Independent Variable:  the variable that the researcher thinks is the cause.
Blank
Blank
Dependent Variables should be the effect in the cause-effect relationship.
Its value depends on the value of the independent variable. 
Blank
Blank
Positive correlation:  both variables change in the same direction
Blank
Blank
Negative correlation:   variables change in opposite directions
Blank
Blank
Control Variable:  a variable that is held constant 
     in order to observe the effect on two or more other variable
Blank
Blank
Spurious Correlation:  An apparent, although false, relationship 
      btwn two or more variables caused by some other variable(s)
Blank
Blank
Measurement
Blank
Blank
1.  Operational Definition:  Precise statement of the measuring of a variable 
     or of the categories of a variable for purpose of measurement
Blank
Blank
2.  Reliability:  the consistency of the measurement
Blank
Blank
3.  Validity:  measuring the concept you intend to measure
Blank
Blank
4.  Constructs  Created by researchers when they are attempting to measure abstract concepts such as intelligence
Blank
Blank
Reactivity:  tendency of people being studied to react to the researcher or to the fact that they are being studied
Blank
Blank
Hawthorne effect: a form of reactivity where people being studied attempt to please the researcher
Blank
Blank
Placebo effect:  form of reactivity:  people as a result of being studied, when in fact nothing has changed
Blank
Blank
Objectivity:  a state of complete personal neutrality in conducting research
Blank
Blank
Bias:  non-objectivity in research; personal involvement in conducting research (whether intentional or unintentional)
Blank
Blank
The Survey:  Most widely used method in sociology
Blank
Blank
Kinds of Surveys
   - questionnaire
   - telephone interview
   - personal interview
Blank
Blank
Fixed-response questions are like multiple-choice exam questions.
Blank
Blank
Likert Scale
Give a clear range of choices on a 5 or 7 pt scale

                          Neutral /
Strongly Agree   Agree    No Opinion    Disagree     Strongly Disagree
     ______          _____        _____         _____             ______
 

Blank
Blank
Open ended questions:  respondent states or writes an answer to the question in their own words.  (Similar to an interview)
Blank
Blank
There are FOUR types of questions typically used in surveys & interviews
     - Background  (demographics)
     - Activities 
     - Knowledge
     - Sentiments (opinions, values, attitudes, feelings, etc.)
Blank
Blank
Nature of questions:
Use short statements
Begin w/ 'easy' questions
Near the end: 'hard' questions
End w/ open ended questions
Blank
Blank
Sampling:  the random selection from a general population to establish a 
Sample Group, which represents the entire population
Blank
Blank
In-Class Project:  Surveying
Blank
Blank
Experiments:  carried out in a situation that is under some control of the researcher, such as a lab or classroom
Blank
Blank
Experimental Process:
Sample to determine the
Control & experimental groups
Pre-test
Experimental manipulation
Post-test
Debriefing
Analysis
Blank
Blank
Experimental Group:  goes through an experience or manipulation
Blank
Blank
Control Group: does not experience a manipulation of an independent variable & receives the pre-test & post-test
Blank
Blank
Lab Experiments:  done in setting w/ almost total control by researcher
Blank
Blank
Field Experiments
 a.  Natural Experiments
 b.  Social Experiments
Blank
Blank
Natural Experiments
Give pre & post tests around a natural event.
Or you could tabulate data before & after a natural event
Blank
Blank
Social Experiments
Give pre & post tests around a social policy 
Blank
Blank
Interviews:  oral surveys
Strength of interview over survey is that researcher can follow leads to unplanned questions
Structured interviews:  questions are pre-planned
Unstructured interviews:  unplanned questions that follow the flow of the conversation
Blank
Blank
Field Observation
Obtrusive:  Seen, recognized as a researcher:  open
Unobtrusive:  hidden or not recognized as a researcher:  secret
Participant observation:  during research, participate in the activities of the subjects
Non-participatory observation:  do not participate, remain separated, aloof
Blank
Blank
Content analysis:  Analysis of narrative data
from open ended surveys, interviews, books, press, media, etc.) that looks for regularity 
Blank
Blank
Statistical Analysis
Analysis of existing data (census, govt records, etc.) 
or data you have collected (surveys, experiments, interviews, etc.) 
to determine correlations
Blank
Blank
Multivariate Analysis:  sorting out many factors to determine most important factors
Blank
The End