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;
65 Cards in this Set
- Front
- Back
Non-probability
|
samples are NOT selected using random sampling, reliance on available subjects, purposive or judgmental sampling
|
|
Probability
|
is based on random sampling
|
|
Purposive or judgmental sampling
|
Based on - researcher’s knowledge of the population, Purpose of study
|
|
Snowball sampling
|
Starts small, gets bigger, Initial sample leads to additional observations, Appropriate for difficult populations, Start with a small and accessible target population
|
|
Quota sampling
|
Matrix of important characteristics of a population, Determine the proportion of the population in each cell
|
|
Disadvantages of non-probability sampling
|
Sampling bias, Conscious or non-conscious, Lack of representativeness, Average of the sample DOES NOT closely approximate average of the population
|
|
Theoretical Population
|
what you really want, what your ideal population would be. Ex. one student from each school in each country
|
|
Accessible Population
|
what you actually got your hands on. Ex. a few students from each region
|
|
Parameter
|
summary description of a given variable in the population Ex. mean income of all families of UGA undergrads
|
|
Stratified sampling
|
Organize the population into homogenous subsets in order to select appropriate number of elements from each subset |
|
Multistage Cluster sampling
|
Large population makes an exhaustive list impossible or impractical. Ex. All church members in the US. |
|
Sampling Frame
|
list of all the elements (unit analysis) used to select your sample. If you do not have a sampling frame, you cannot do probability sampling. Ex. Poll UGA student body concerning changes to North Campus tailgating policy.
|
|
Sampling error
|
degree of disconnect between the statistic and parameter
|
|
Sampling design
|
refers to the rules and procedures by which the populations are included in the sample
|
|
Random
|
Everyone has a equal chance of being selected
|
|
Components of Classic Experimental design
|
Independent and dependent variable, random assignment, pre and post testing, experimental and control groups.
|
|
Independent variable
|
predicts outcomes put forth in hypothesis (cause)
|
|
Dependent variable
|
consequent variable (effect)
|
|
Experimental group
|
receives the stimulus (IV)
|
|
Control group
|
do not receive the stimulus, point of comparison
|
|
Random assignment
|
Eliminates the threat of selection bias, because the researcher uses probability sampling to determine who is in the experimental group and who is in the control group (the participants themselves DO NOT self-select exposure to the independent variable)In order to isolate the effect of the independent variable, we must randomly assign participants into each group
|
|
Manipulation Check
|
in experimentation, the researcher should check to determine whether the intended independent variable was manipulated appropriately
|
|
Internal validity
|
conclusions drawn from the experimental results may not accurately reflect what has gone on in the experiment itself
|
|
External validity
|
generalizability of experimental findings to the real world
|
|
Quantitative data analysis
|
Techniques researchers use to convert data to numerical form
|
|
Qualitative data
|
data whose form is textual, non numerical. Typically gathered by researchers who come from interpretivist or critical paradigms of knowing
|
|
Univariate
|
one variable
|
|
Bivariate
|
two variables simultaneously
|
|
Descriptive statistics
|
statistical computations describing the characteristics of a sample. Descriptive statistics merely summarize a set of sample observations.
|
|
Inferential statistics
|
the body of statistical computations relevant to making inferences from findings based on sample observations to some larger population
|
|
Alternative hypothesis (H1)
|
there is a relationship between variables
|
|
Null hypothesis (Ho)
|
There is no statistical relationship between variables
|
|
"Statistically significant"
|
If p < .05, “reject the null”
|
|
Components included in a full research article
|
Introduction, Lit Review, Hypotheses, Method Section, Results Section, Discussion Section, References, Appendix
|
|
Non-participant observation
|
the researcher watches the subjects of his or her study, with their knowledge, but without taking an active part in the situation under scrutiny
|
|
Participant observation
|
method employed in qualitative research to study communication phenomena in their natural settings. The researcher can adopt any of several roles in the field.
|
|
Characteristics of focus group research
|
Less control, Require skilled moderators, Can be difficult to analyze
|
|
Purposes of qualitative interviewing
|
Phenomena not directly observable, detailed cognitive processes, language use
|
|
Phenomenology
|
Approach researcher would take where focus in on participants’ personal experience, remove personal opinion and bias, no judgment
|
|
Interpretivism
|
Hold on to judgments and predictions as a researcher
|
|
Three forms of interview protocols
|
Structured (not qualitative), Semi-structured, Unstructured
|
|
Practices
|
socially recognized talk or action. Ex. delivering bad news, providing social support
|
|
Episodes
|
dramatic events. Ex. divorce, natural disasters
|
|
Encounters
|
people meeting and interacting. Ex. interviews, bus-stop conversation
|
|
Relationships
|
between people in social roles. Ex. mother-child, spousal communication
|
|
Focus of qualitative interviewing
|
Understanding meanings and rules for meaning making
|
|
Description of qualitative interviewing
|
Asking in a flexible and continuous manner, Primarily participant talking, Digging for detailed information.
|
|
Nominal
|
Most simplistic level, Nominal = Names, Categorical, Ex. Biological sex – Male and Female (Names, no Numbers), Religious affiliation, Political affiliation
|
|
Ordinal
|
Rank ORDER logically, Levels represent more or less of variable, Distance between levels doesn’t matter, Ex. Class Status, Level of education
|
|
Interval
|
Distance between attributes or levels must have meaning, Tells how much, Standardized intervals between each level, Specific number, Ex. Temperature (60 degrees is twice as warm as 30 degrees), IQ Scores
|
|
Ratio
|
Most sophisticated level, Distance between attributes or levels must have meaning, PLUS - Based on a true zero point, you can have a complete absence of the variable. In social science, we tend to view things as ration rather than interval
|
|
Continuous measure
|
increases steadily in tiny fractions, MEAN
|
|
Discrete (Categorical)
|
one category or another without middle steps, MODE
|
|
Continuous hypothesis
|
stating change along a continuum
|
|
Directional hypothesis
|
states the direction of the difference
|
|
Nondirectional hypothesis
|
states there will be a difference
|
|
Difference hypothesis
|
compare two attributes of the IV
|
|
Three criteria for causality
|
Time order (cause before effect, Correlation (have to be related), Non-spurious relationship (no outside factor)
|
|
Structured interview |
The same questions are asked in the same way, same order for all participants |
|
Semi-structured interview |
Researcher works with suggested questions whose wording and arrangement can vary from one participant to another |
|
Unstructured interview |
Researcher has few, if any, pre-fomulated questions |
|
The Complete-Partcipant role |
participants lack awareness of being observed |
|
Participant as observer |
the researcher participates in the activities of the group, with group members aware of researcher |
|
Observer as participant |
researcher has minimal involvement with group members and they are aware of the role |
|
Complete observer |
researcher observes the group with no participation, unaware of observation |