Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
60 Cards in this Set
- Front
- Back
How many Americans are scientifically literate?
|
28%
|
|
How is scientific literacy developed?
|
-Learn about and conduct research
-Knowledge of the scientific process |
|
Epistemololgy
|
**The science of knowing
|
|
"Ways of Knowing"
|
-Tenacity: always been held as true (i.e. you eat turkey for Thanksgiving)
-Authority: someone who should know, said so (i.e. Mechanic examines your car) -Intuition: correct info will surface(reasoning) -Logic: common sense (rigorous logic) |
|
Problems with "ways of knowing"
|
-Filters in how we process info
---False premise; illogical reasoning ---Selective observation; expectations **Everday ways of knowing can even lead to conflicting ideas about "truth" |
|
The Scientific Method
|
-Combines "logic" with empiricism"
---Logic: constructing theories and hypotheses ---Empiricism: gathering data/observation |
|
How is "science" different from the "ways of knowing"
|
1. Scientific research is public
-is published; peer review -can be replicated 2. Science is empirical -multiple, planned, deliberate observations 3. Science is systematic and cumulative -systematic proceedures -new knowledge adds to or modifies old 4. Science is "objective" -explicit rules, standards, and procedures |
|
Who are "scientists"?
|
-They live in communities
-They are affected by society -They have a stake -Culture shapes how we think |
|
Goals of Scientific Research
|
-Exploration: the beginnings of a new area of study...
-Description: look for social regularities of aggregates -Explanation: develop understanding of WHY patterns exist (i.e. what causes what) -Prediciton: predict outcomes given certain factors |
|
The Research Process
|
1. Select topic
2. Focus question 3. Design study 4. Collect data 5. Analyze data 6. Interpret data 7. Inform others |
|
Theory
|
-An attempt to explain some aspect of social life
-Ideas about how/why evetns/ attitudes occur -Ex. Social Learning Theory |
|
Deduction
|
Starty with a theory, form a hypothesis, create observations, and then make an empirical generalization (general to specific)
|
|
Induction
|
Start with observations, make empirical generalizations, create theories, and then make an hypothesis (specific to general)
|
|
Qualities of a Good Theory
|
-Consistent with available information
-Helpful in predicting some outcome -Has heuristic value: generates reserach or more theory -Falsifiable: it is hypothetically possible for a test or observation to show that they thoery is wrong ---Falsifiable does not mean false ---It means that it must be possible to make an observation that owuld show the proposition to be false, even if that observation has not been made -Parsimonious: preference for the least complex explanation for an observation |
|
The Research Process
|
1. Find interesting and important concepts
2. Develop a research question or hypothesis 3. Determine appropriate research design 4. Observation: measure or manipulate variables 5. Analyze data and report findings |
|
Hypothesis
|
Specific testable prediction about the relationship between variables
|
|
Research Questions
|
Sometimes we ask a research question instead of stating a hypothesis:
-Reasons why: ---There is no theory or previous research to guide prediction ---Previous findings conflict/are inconclusive |
|
3 Common Methodologies used in Communication Research
|
1. Examine the content of a message
-Methodology: content analysis -Ex. Count the number of punches in Saturday morning cartoon shows 2. See if 2 phenomena are related to each other -Methodology: Survey -Ex. Is communication with the instructor, asking questions, attendance, etc. related to student's final course grade? 3. See if 1 phenomena cuases another -Methodology: Experiment -Ex. Does exposure to pornography cause increased acceptance of violence toward women? |
|
Conceptual Defintion
|
A working definition of what the concept means for purposes of investigation
|
|
Operational Definition
|
A definition of how exactly the concept will be measured in a study
|
|
Types of Validity
|
1. Face Validity
2. Content Validity 3. Criterion/Predictive Validity 4. Construct Validity |
|
Face Validity
|
The measure seems to look good on the face of it
-Ex. It makes logical sense |
|
Content Validity
|
The measure captures the full range meanings/ dimensions of the concept
-Ex. ALL aspects of it |
|
Criterion/Predictive Validity
|
The measure is shown to predict scores on some other relevant future measure
-Ex. SAT--> College GPA |
|
Construct Validity
|
The measure is shown to be related to other concepts that should be related (and not to ones that shouldn't)
-known-group method |
|
Reliability of Measurement
|
-Is your measurement consistent?
---Consistency between questions that are supposed to measure the same thing |
|
Inter-item Reliability
|
Administer questionnaire and look at internal consistency of multiple questions
-Inter-item reliability can be assessed by quantifying the internal consistency of answers across questions |
|
Relationship Between Validity and Reliability
|
-A measure must be reliable in order to be valid
-A measure does not need to be valid in order to be reliable |
|
Levels of Measurement
|
1. Nominal
2. Ordinal 3. Interval 4. Ratio |
|
Nominal Measurement
|
Variable is measure merely with different categories
-Categories must be mutually exclusive and exhaustive -Ex. Which political party do you identify with? (Democrat, Republican, Green, Other) -Ex. Did you watch TV yesterday? (yes, no) |
|
Ordinal Measurement
|
Variable is measured with rank-ordered categories
-Ex. Rank your major news source (2=Television, 1=Internet, 3=Newspaper, 4=Other) -Ex. How much TV did you watch yesterday? (1=none, 2=a little, 3=a lot) |
|
Interval Measurement
|
Variable is measured with successive points on a scale with equal intervals
-Ex. I watched a lot of TV yesterday (strongly disagree, 1, 2, 3, 4, 5, strongly agree) |
|
Ratio Measurement
|
Interval measurement wiht a true, meaningful zero point
-Ex. How much TV did you watch yesterday? (0hrs, 1hr, 2hrs, 3hrs, 4hrs, 5hrs....) |
|
What is Sampling?
|
Studying a portion of a population to make judgements about the entire population
-Sample= a subset of the population of interest |
|
Sampling Units
|
The things you are selecting for inclusion in your research
-Individuals -Groups (couples, companies, families, etc.) -Content (ads, tv shows, etc.) |
|
Generalizability
|
The extension of a research finding from the sample to the population
-Ability to generalize depends on how sample is selected |
|
Probability Samples
|
Intended to "represent" the population (generalizability)
|
|
Non-Probability Samples
|
Not intended to represent the population (not generalizing)
|
|
Non-Representative Sampling Techniques
|
1. Convenience Sample
2. Purposive Sample 3. Quota Sample 4. Snowball Sample |
|
Convenience Sample
|
-Select individuals that are available/handy
-Ex. students in class, people on High St., friends, volunteers, etc. |
|
Purposive Sample
|
-Select based on some purpose
-Select individuals for a special reason -Ex. parents of young children, individuals who use a wheelchair, etc. |
|
Quota Sample
|
-Pre-plan number of subjects in specified categories
-Ex. 100 men and 100 women -Ex. selecting individuals to match demographic proportion in the population |
|
Snowball Sample
|
-Select individuals who contact other similar individuals and so on....
-Useful when the desired sample characteristic is rare or difficult to identify/reach |
|
Probability Sampling
|
Sampling technique that uses random selection
|
|
Random Selection
|
Each element of the population has an equal probablity of being selected
-Random selection is based on probability theory -Reduces bias in the sample -Like flipping a coin, drawing from a hat, etc. |
|
Probability Sampling Techniques
|
1. Simple Random Sampling
2. Stratified Random Sampling 3. Multistage Cluster Sampling |
|
Simple Random Sampling
|
-Put all the names in a hat and draw
-First need a list of all the names -In practice, often use a computer or random numbers table instead of a "hat" -Ex. Phones: random-digit dialing |
|
Stratified Random Sampling
|
Sometimes you want to make sure to include specific kinds of diversity in your sample
-Determine proportion in the population -Divide population into subsets ("strata") -Select randomly from each strata so sample matches the population |
|
Stratified Random Sampling Continued
|
Why do this?
-Provides more control over final sample -Makes sure ou end up with proportional sample ---Useful when one group in a small minority of the population, but you want to make sure they end up in your sample proportionate numbers -Oversampling small groups improves intergroup comparisons |
|
Multistage Cluster Sampling
|
-First, randomly sample groups ("clusters")
-Then randomly sample elements within each cluster -Useful for populations not listed as individuals |
|
Multistage Cluster Sampling Example
|
-1st Stage: Random sample of universities
-2nd Stage: Random sample of clubs from those universities in the sample -3rd Stage: Random sample of members from the clubs in the sample |
|
Stratification vs. Clustering
|
Stratification:
-Divide population into groups different from each other (i.e. males vs. females) -Sample some people from every group -Less error compared to simple random sampling -More expensive to obtain stratification information before sampling |
|
Stratificiation vs. Clustering
|
Clustering:
-Divide population into comparable groups (i.e. schools, cities, etc.) -Select only some of the groups -More error compared to simple random sampling -Reduces costs to sample only some areas of the organization |
|
Sampling Error (Random Error)
|
-Sample data will be slightly different from population due to chance
-We can estimate the amount of sampling error statistically ("margin of error") -Sampling error is reduced by increasing the sample size |
|
Margin of Error (Confidence Interval)
|
An estimate of the range of values within which the true value is likely to fall among the population
-Conventionally, we use a 95% confidence interval ---plus or minus 3.5%= we are 95% confident that the true value (among the population) falls within 3.5 percentage points above or below the sample statistic |
|
The Relationship Between Sampling Error and the Margin of Error
|
As sample size increases, margin of error decreases (but never reaches zero)
-Diminishing returns as sample size increases |
|
Systematic Error
|
Error due to some systematic (non-random) factors
-Using non-representative sampling methods (i.e. convenience sample, snowball sample, etc.) -Could be caused by Non-response bias: a participants' refusal to particiapte |
|
Non-Response Bias
|
-You can randomly select people, but you cannt make these people participate
-Non-response destroys the generalizability of the sample ---You are generalizing to people who are willing to respond to surveys **Only a potentional problem if 50% of the sample refuses to participate. If 90% of the sample does not participate then there is a lot less of a problem, because there is a smaller percentage of non-response bias (10%). |
|
Non-Response Bias Example
|
The Presidential Election:
-How might responders and non-responders differ? ---Level of interest ---Tendency to be at home to answer the phone ---Many (younger) people have only a cell phone |
|
How to Interpret a Public Opinion Poll
|
1. Was the sample selected using one of the probability techniques?
2. What is the confidence level used in reporting the confidence level? 3. Are any breakout analyses reported? 4. Was there any bias in the questions posed to respondents? |