-
Independent Variable
Stimulus, research manipulated, causes the Dependent Variable
-
Dependent Variable
Effect, not researcher manipulated, caused by another variable.
-
Pretesting
Measurement of DV among subjects prior to experiment
-
Posttesting
Remeasuring of DV after being exposed to IV, after the experiment
-
Experimental Group
Group that will receive experimental stimulus
-
Control Group
Group that will not receive experimental stimulus
-
Randomization
Assigning subjects to experimental and control groups randomly
-
Matching
Pairs of subjects are matched on their similarities on one or more variables, and one member of the pair is assigned to experimental group and to the control group
-
One Shot Case Study
- Researcher measures a single group of subjects on a dependent variable following the administration of an experimental stimulus
- Ex: Show video to one group and give questionnaire.
-
One Group Pretest-Posttest Desgin
Researcher adds a pretest for the experimental group but lacks a control group.
-
Static Group Comparison
- Researcher does not add pretest to the experimental or control group.
- Has control and experimental group.
-
Sources of Internal Invalidity
Possibility that the conclusions drawn from experimental results may not accurately reflect what went on in the experiment itself.
-
SOII: History
historical events may occur that will confound the results.
-
SOII: Maturation
people grow and change which can affect the results.
-
SOII: Testing
testing and retesting influences peoples behavior.
-
SOII: Instrumentation
different measures of the DV in pretest and posttest can affect the results.
-
SOII: Statistical Regression
danger that change occurs by virtue of evolution than by the effects of the stimulus.
-
SOII: Selection Biases
Comparisons dont have meanings unless the groups are comparable.
-
SOII: Experimental Morality
subjects may drop out of experiment before its completed.
-
SOII: Casual Time Order
ambiguity about the time order of the experimental stimulus.
-
SOII: Diffusion or imitation of treatments
subjects may share information with each other.
-
SOII: Compensation
pressure to offer some form of compensation to the control group.
-
SOII: Compensatory Rivalry
subjects deprived of the stimulus might work harder.
-
SOII: Demoralization
subjects deprived of the stimulus might just give up.
-
Sources of External Validity
Possibility that the conclusions drawn from experimental results may not reflect what went on in the experiment itself
-
Solomon-four-group-design
Four groups of subjects, assigned randomly from a pool
-
Questionnaire
- Instrument specifically designed to elicit information that will be useful for analysis.
- Questions: respondents chooses one answer from a set of responses.
- Statements: respondent agrees or disagrees. Close ended.
-
Respondent
A person who provides data for analysis by responding to the survey questionnaire
-
Questions and Statements
Questionnaires provide a method of collecting data by 1) asking people questions and 2) asking people to agree or disagree with statements
-
Open-ended Questions
Questions for which the respondent is asked to provide his/her own answers
-
Close ended Questions
Questions in which the respondent is asked to select an answer from among a list provided by the researcher
-
Guidelines for asking questions
- Choose Appropriate Question Forms
- Make Items Clear
- Avoid Double-Barreled Questions
- Respondents Must Be Competent to Answer
- Respondents Must Be Willing to Answer
- Questions Should be Relevant
- Short
- Items Are Best
- Avoid Negative Items
- Avoid Biased Items and Terms
-
General Questionnaire Format
Questionnaires should be spread out and uncluttered
-
Formats for Respondents
check boxes adequately spaced out
-
Contingency Questions
survey question intended for only some respondents, determined by their responses to some other question
-
Matrix Questions
Efficient format for presenting a set of closed-ended questionnaire items that have the same response category
-
Ordering Items in a Questionnaire
Order of questionnaire items can affect responses
-
Questionnaire Instructions
Every questionnaire should have clear instructions and introductory comments where appropriate
-
Pretesting the Questionnaire
Questionnaires should be pretested before being administered to the study sample
-
Self-Administered Survey
- respondents are asked to complete the questionnaire themselves
- Mail Distribution : great for taboo topics, poor return rate, can send follow ups.
- In-Person: ideal method. Highest respoense rate, researcher has greatest control, grat for taboo topics.
-
Survey Interviews
- ask questions orally
- Face-to-Face: higher rsponse rate, completion rate 80-85%, presence of
- interview increases the number of I dont knows.
- Telephone Survey Interviews: cheaper than face to face, RDD elimintes
- potential dialing, greater control over data.
- Appearance and Demeanor: researcher must remain neutral in appearance and actions.
- Familiarity: researcher must be familiar with questionnaire.
- Exact Wording of question.
- Recording Responses: record responses accurately.
- Probing: can use probes to elicit response.
-
Online Surveys
- Involves the use of the Internet and the world, wide, well suited for taboo topics.
- Must be used with caution, respondents may not represent intended population.
-
Unobstrusive Research
Method of studying social behavior without affecting it
-
Content Analysis
- Study of recorded human communication
- Well suited to answer what, to whom, why, how, with what effect?
- ex: books, magazines, poems, songs, letters, etc.
-
Analysis of Existing Statistics
- Using data analyses that others have already done
- Existing data supplemental source of data.
- Existing statistics can provide a historical or conceptual context within which to locate original study
-
Comparative and Historical Research
- Examination of societies over time and in comparison with one another.
- Using historical methods by sociologists, political scientists, and other social scientists to examine societies over time and in comparison with one another
- Appropriate topics: Social Class, Capitalism, Religion, Revolution
-
Coding
Process of transforming raw data into a standardized form.
-
Coding: Manifest Content
visible, surface content
-
Latent Content
Underlying meaning of communications
-
Needs Assessment Studies
Studies that aim to determine the existence and extent of problems
-
Cost-benefit Studies
Studies that aim to determine whether the results of a program justify its expense
-
Monitoring Studies
Studies that provide a steady flow of information about something of interest
-
Program Evaluation
The determination of whether a social intervention is producing the intended result
-
EMIC
Researcher has an insider’s perspective because they are entering a familiar setting.
-
ETIC
- Researcher has an outsider’s perspective because they are entering an unfamiliar setting.
- Nothing taken for granted, harder for researcher to access
-
Key Informant
- Important relationships that are developed before or while in the field
- helps the researcher gain access to information, people, and situations that they wouldn’t be able to get access to.
-
Quasi-Experimental Design
Nonrigorous inquires somewhat resembling controlled experiments but lacking key elements such as pre- and posttesting and/or control group
-
Time-series Designs
Design that involves measurements made over some period
-
Nonequivalent Control Groups
Control group that is similar to the experimental group but is not created by the random assignment of subjects
-
Multiple Time-series Designs
Improved version of the nonequivalent control group design
-
Qualitative Data Analysis
- Nonumerical examination and interpretation of observations involves discovering meanings and pattersn of relationships most typical in field research and historical research.
- Purpose of discovering underlying meanings and patterns of relationships
-
Linking theory and analysis
- Search for explanatory patterns
- “plausible relationships proposed among the concepts and sets of concepts”
- - Strauss and corbin
-
Discovering Patterns
seek to discover patters such as changes over time or possible causal links among variables.
-
Six different ways of looking for patterns in a particular research topic
- Frequencies: how often does it occur?
- Magnitudes: examine the degree at which it happens
- Structures: what types?
- Processes: is there any order?
- Causes: what could have caused it?
- Consequences: how does it affect?
-
Cross-Case Analysis
- Analysis involving an examination of more than one case
- Two strategies: Variable oriented and case oriented.
-
Variable-oriented analysis
- Analysis that describes and/or explains a particular variable
- Aim to achieve a partial, overalla explanation usign relatively few varibles.
- Similar to the idea of a nomothetic explanation.
- Ex: predict the decision to attend college. Variables: gender, parental expectations, school performance, peer support.
-
Case-oriented Analysis
- Analysis that aims to understand a particular case or several cases by looking closely at the details of each
- most extensiece and pursue in greater depth
- similar to the idea of idiographic explanation
- Ex: political pollster who attempts to explain voting intentions on the basis of 2 or 3 variables. Variables: political party, sociodemographics, gender, education.
-
Grounded Theory Method
- Theories are generated solely from an examination of data rather than being derived deductively
- begins with observations rather than hypotheses
- seeks to discover patterns and develop theories from the gorund up and inductive approach to research.
-
Constant Comparative Method
Observations are compared with one another and with the evolving inductive theory
-
Coding
- Classifying or categorizing individual pieces of data
- -key to the process of discovering patterns among the data.
-
Coding Units
Must identify a standardized unit of analysis prior to coding
-
Coding as a Physical Act
The act of actual coding. May be done manually or on the computer.
-
Open coding
initial classification and labeling of concepts
-
Axial coding
identify the core concepts
-
Selective coding
identify the central concept that organizes the other concepts that have been identified
-
Memoing
Writing memos or notes to yourself and others involved in the project.
-
Concept mapping
- graphic display of concepts and their interrelations
- -can be on a single sheet of paper, on a blackboard, computer, pages etc.
-
Quantitative Analysis
- Numerical representation and manipulation of observations for the purpose of describing and explaining the phenomena
- To conduct quantitative analysis:
- Researcher must engage in a coding process after the data has been collected
- Generate codes from your data
- Search for explanatory patterns
-
Univariate Analysis
Analysis of a single variable, for the purposes of descriptions
-
Frequency Distribution
Description of the number of times the various attributes of a variable are observed in a sample
-
Bivariate Analysis
- Analysis of two variables simultaneously
- Determining relationships between variables themselves
- Purpose is usually explanatory
- Example: Religious attendance Reported by Men and Women in 2004 (i.e. gender and religious attendance)
-
Multivariate Analysis
- Analysis of more than two variables simultaneously
- Used to understand the relationship between two variables more fully
- Example: Religious Service attendance, gender, and age (i.e. gender, religious attendance, AND age)
-
Mean
- Dividing the sum of the values by the total number of cases
- Example: Age Number
-
Mode
Most frequently occurring attribute
-
Median
The middle attribute in the ranked distribution of observed attributes
-
Dispersion
distribution of values around some central value, such as an average
-
Range
- distance separating the highest from the lowest value
- Example: Indicate that the age range is from 13 to 19
-
Standard Deviation
- measure of dispersion around the mean
- Note: The smaller the deviation, the more tightly the values are clustered around the mean
- Low-standard Deviation: tightly clustered values
- High-standard Deviation: spread out values
-
Continuous Variable
- variable whose attributes form a steady progression
- Example: age or income: steadily increases with each increment of time
-
Discrete Variable
- variable whose attributes are separate from one another
- Example: gender or religious affiliation: jumps from category to category without intervening steps
-
Statistical Analysis
- Applied branch of mathematics especially appropriate for a variety of research analyses
- Two types: Descriptive and Inferential Statistics
-
Descriptive Statistics
- Statistical computations describing either the characteristics of a sample or the relationship among variables in a sample
- Used to summarize data
- Sometimes used to summarize the distribution of attributes on a single variable and sometimes used to summarize the associations between variables
-
Data Reduction
- Reduction of data from unmanageable details to manageable summaries
- Mean
- Mode
- Median
- Dispersion
- Standard Deviation
-
Measure of Association
- Descriptive statistics summarizing the relationship between variables
- Proportionate Reduction of Error (PRE) :Logical model for assessing the strength of a relationship by asking howmuch knowing values one variable would reduce our errors in guessing values on the other
-
Regression Analysis
- Method of data analysis in which the relationships among variables are represented in the form of an equation
- General formula for describing the association between two variables
- Y = f(X)
- “Y is the function of X”
- “X causes Y”
- “The value of X determines the value of Y”
- Can be used
- to predict the values of a dependent variable on the basis of
- values of one or more independent variable
-
Linear regression analysis
A perfect linear association between two variables
-
Multiple regression analysis
Impact of two or more Independent Variable on a single Dependent Variable
-
Partial regression analysis
Effects of one or more variables are held constant
-
curvilinear regression analysis
Curved geometric lines instead of straight lines
-
Inferential Statistics
- The body of statistical computations relevant to making inferences from findings based on sample observations to some larger population
- Used to estimate generalizability of findings arrived at through the analysis of a sample to the larger population from which the sample has been selected
- Some estimate a single-variable characteristic of the population
- Some estimate the relationship between variables in a population
-
Statistical Significance
estimate the relationships between variables in the population
-
Tests of Statistical Significance
class of statistical computations that indicate the likelihood that the relationship observed between variables in a sample can be attributed to the sampling error only
-
Sampling error
degree of error to the expected for a given sample design
-
Variables
Set of attributes.
-
Attributes
- Characteristics that describe an object, attributes are categories that make up the variables.
- *social research involves the study of variables and their relationships.
- * relationship between attributes and variables form the heart of description and explanation in science.
-
Idiographic Reasoning
Identifying all the reasons for a single outcome.
-
Nomothetic Reasoning
Identifying some of the reasons for a class of situations.
-
Induction
Expands from specific to general.
-
Deduction
Reduces from the general to the specific.
-
Qualitative Data
- Rich detail, non-numerical data, in depth details of the human experience.
- Field research and interviews.
-
Quantitative Data
Numerical data, superficial description. Survey and experiments.
|
|