difference between population and sample
population is the total membership of a defined class of people, objects, or events while a sample is a SUBSET of cases selected from a population
why do we create samples?
we use samples to try to represent the whole population
different types of non-probability samples
- Convenience sample
- Volunteer sampling
- Purposive sampling
- Snowball sampling
convenience sample
only members of the population who are easily accessible are selected
Volunteer sampling
A sample of participants produced by a sampling technique that relies solely on inviting people to take part.
purposive sampling
a biased sampling technique in which only certain kinds of people are included in a sample
snowball sampling
recruitment of participants based on word of mouth or referrals from other participants
benefits of survey research
they're versatile, efficient and generalizable
Good survey questions
make questions/response choices clear, avoid making disagreements disagreeable, focus on one issue
quantitative and qualitative data
quantitive data is numerical while qualitative is usually structural
why might you use content analysis
content analysis may be used to easily interpret data or to interpret qualitative data into quantitative data
When personal contact will not work
Historical
Distance
Large scale collective behavior
deciding who to interview
...
why does direct observation have such high validity
direct observation is hands-on and also does not alter data
Why use focus groups?
interprets quantitative data, high external validity because it is a specific group and studied for a specific reason
how do we analyze most qualitative data
we want to know the meaning, context, and themes of the interview
why create case study
they are hypothesis building, answer why? questions, and they are multi-method
Present complex phenomena
What kind of information do you need for a case study and how would you organize it?
Structured Focused Comparison
Questions that travel
Equivalent measures
Choosing Cases
Independent Observation
natural experiment
An experiment in which nature, rather than an experimenter, manipulates an independent variable.
What aspects make experiments so powerful in terms of their ability to explain causal
inference?
...
Be sure to understand the validity and reliability issues with each method of data
collection we've discussed in this section of the class.
...
How do theory, hypotheses, and operationalization impact the choice of data collection
methods?
...
Probability Sample
a sample in which each member of the population has some known chance of being included
Radomization
a process of randomly assigning subjects to different treatment groups
Sampling Error
The amount different our sample is from the population as a whole
Cluster Sampling
the researcher divides the population into separate groups, called clusters. Then, a simple random sample of clusters is selected from the population.
Confidence Level
The different percentage points that the researcher is sure they are right, and then the remaining percentage point they are unsure of
Confidence Interval
the range of values within which a population parameter is estimated to lie
Margin of Error
The amount plus or minus that the results are off by. The larger the population, the smaller it is
Survey Instrument
a carefully structured or scripted set of questions that may be administered face to face, by telephone, by mail, by Internet, or by other means
Reactivity
occurs when people change their behavior in some way when they know another person is watching
Demographic Questions
questions that ask for basic information, such as age, gender, ethnicity, or income
Likert Scale
a numerical scale used to assess attitudes; includes a set of possible answers with labeled anchors on each extreme
Aggregate Data
Data that are collected on large populations of individuals and stored in databases.
Census
A complete enumeration of a population.
iterative process
Experimental process is done over and over again to improve results
Content Analysis
the systematic counting, assessing, and interpreting of the form and substance of communication
Episodic Record
Something that only occurs once or once in a long while
Running Record
Observer creates a sequential record of anything that happens during a specific period of time.
-Systematic
-Official
-Periodic
-Centralized
Substantive Content Analysis
Analysis focusing on the meaning of a communication. The recording process
Structural Content Analysis
Analysis focusing on the format of a communication. The interpreting process
intercoder reliability
in content analysis, the degree of agreement between or among independent coders. Sometimes multiple coders are used for the same research project
Like the example we did in class where we all had to choose and see if it matched
Going Native
When a researcher becomes part of a culture and loses the ability to observe clearly
Levels of Analysis
the differing complementary views, from biological to psychological to social-cultural, for analyzing any given phenomenon
Elite Interviewing
Collecting interview data from people who hold top positions of influence, often elected officials
interview protocol
The list of questions prepared for the interview that have been designed to ensure that the interview process is equally reliable and valid for all candidates.
participant observer
A group member who participates but also observes the group and adapts as necessary
comparative research
a methodology by which two or more entities (such as countries), which are similar in many dimensions but differ on one in question, are compared to learn about the dimension that differs between them
Ecological Fallacy
assumes that a generalized cultural value applies equally well to all members of the culture
Valid Casual Inference
...
Descriptive Statistics
numerical data used to measure and describe characteristics of groups. Includes measures of central tendency and measures of variation.
Inferential Statistics
numerical data that allow one to generalize- to infer from sample data the probability of something being true of a population
Taxonomy
distinguishes among categories of ideas concepts and variables. i.e. a table of contents
Typology
displays based on the cross-classification of two or more ideas, concepts, or variables
Experiment
Making observations in circumstances so arranged or interpreted that we can isolate the factors relevant to our particular inquiry
Why Experiments in Political Science
Best assessment of Causal Relationships
Enables complex phenomena to be decomposed
Accelerate interdisciplinary work
More likely to produce anomalous facts
Travels across levels of aggregation
threats to internal validity
Selection bias.
-Non-Randomization
-Differential attrition
Endogenous Change
-Testing
-Maturation
-Regression
Lack of appropriateness
Treatment misidentification
-Expectancy of Experimenters
-Placebo effect
-Hawthorne effect
Hawthorne effect
A change in a subject's behavior caused simply by the awareness of being studied
Threats of External Validity
Generalizability of sample
Results instability
Unique info from interviews
You are giving a person the ability to express the entirety of their opinion. You can't follow-up on surveys, etc.
Guided conversations
"unscheduled" or "semi Scheduled"- not following the order of your questions, but instead flowing with the convo
Hard t
Good Interview Questions
Are Direct
One at a time
Avoid asking why
Opening Questions
Probing
Threats to interview validity
Too narrow
Inaccurate
Rationalization
Lying
Sources of Aggregate Data
Public documents and official records
Private documents
Mass media
Physical culture and materials
Social science data archives
Disadvantages with Focus Groups
Subjective
Limited representativeness
Artificial setting
Groupthink
Method Effects
What is the difference between a classic experiment and a natural experiment?
A classic experiment is set up a person to be conducted, whereas a natural experiment is happening in nature and then recorded