Flashcards
Empirical Research
Cards in this deck (12)
- 1four Ps of quantitative researcha) Paradigm: assumptions about epistemology. Reliable: consistent/Valid: accurate/Falsifiable: can your study be proven wrong, null is possible to measure/Useful: knowledge and problem solving
b) Purpose: description, explanation. Classify objects/variables and identify universal/generalizable laws or rules. Create an accurate representation of reality by focusing on the measurable dimensions of reality. Description, correlation, cause!
c) Process: BASIC steps of doing that method. 4 steps: preparation, engagement, reflection and analysis, expression.
d) Product: Data that results and documents such as executive summaries, research reports (specifics of expression step of process) - 2What is reliability? What is validity? Why are different types of reliability and validity important?a) Reliability: the extent to which the measurement yields data which are consistent, stable and dependable.
b) Validity: a measure of whether a test measures what it is supposed to - 3What are the four levels of measurement? Be able to give communication research-related examples of each.a) Nominal: yes/no, male/female, no rank level or order, categories/
b) Ordinal: ranking (what did you prefer most, what was the first second third for you, ranking RELATIVE TO OTHER ITEMS ON LIST/
c) Interval and Ration levels: "Great divide" from discrete categorical data to continuous data. RATE instead of RANK, equal distance scale, we can't measure zero usefulness in any meaningful way. - 4What are the two basic questions we ask when analyzing data?is it valid and is it reliable?
- 5Explain each of the following: Central Tendency, Dispersion, Difference, and Association/Correlation.a) Central Tendency: mean, median, mode. They describe the central features of a data set rather than its extreme or outlying values/
b) Dispersion: the range and variability of scores/
c) Difference: disparity/variance/
d) Association/Correlation: a statistical procedure for measuring the strength of association between two or more variables. More generally, the degree to which variables are related. - 6What is the basic test/measure for each of the above? (How do we measure dispersion? How do we test for difference?). When do we use a T-test and when do we use Chi-square, etc.a) Central Tendency: mean, median, mode. They describe the central features of a data set rather than its extreme or outlying values/
b) Dispersion: the range and variability of scores/
c) Difference: disparity/variance/
d) Association/Correlation: a statistical procedure for measuring the strength of association between two or more variables. More generally, the degree to which - 7What are the basic criteria for effective survey questions? What are the more common errors researchers make when constructing survey questions?a) Central Tendency: find the mean, median and mode/
b) Dispersion: find the minimum, maximum, range, interquartile range, variance and standard deviation/
c) Difference: t Test: compares the mean scores of two groups on the same variable to determine the probability that the groups are different. ANOVA: used to compare more than two groups (F=Variance between groups/Variance within groups)/
d) Correlation: provides a measure of strength of relationships between variables (scatterplot)/
e) Chi-Square Test: a statistical test for determining whether two groups differ significantly in their distribution of scores on the same variable (Male/Female and their Political Affiliation) - 8What are the basic types of scales? (Likert, Guttman, etc.) Be able to identify them when you see them.a) Likert Scale: strong agree to strongly disagree
b) Semantic-Differential Scale: pairs opposite ideas toward a concept or an object and invites the respondent to decide where between the two opposites their opinion lies
c) Guttmann- - 9identify the strengths and weaknesses of surveys and experiments.a) Surveys:
b) Strengths: Respondents can answer large numbers of questions rapidly/large numbers of people can be surveyed rapidly/with appropriate sampling and the assumption of normally distributed attributes in the sampled population, you can make generalizations with a known level of confidence from your sample to a wider population.
c) Weaknesses: The "why" question isn't answered/Most survey designs do not allow us to assess causal relationships/Increasing unwillingness of consumers to participate in surveys.
d) Experiments:
e) Strengths: Potential to identify variables that have significant causal relationships, to assess the direction of causality, and to identify variables that have no significant effect on other variables.
f) Weaknesses: Artificiality of the experimental conditions, experimental conditions are not the same as the real world - 10Define with example the types of samples discussed in your text. Why is response rate important?a) Nonprobability Sampling:
i) Convenience sampling: based on the convenience to the researcher (Ex: an instructor requests your consent)
ii) Purposive/Judgmental Sampling: based on the idea that a specific person or media content will meet specific criteria the researcher may have (Ex: seeking out students that exemplify a specific problem, ADD)
iii) Quota Sampling: attempts to replicate in a sample the features that the researcher thinks are important in the population (interviewing both on campus and off campus students
iv) Network/Snowball Sampling: a form of volunteer sampling that occurs when you rely on members of a network to introduce you to other members of the network
v) Volunteer Sampling
b) Probability Sampling:
i) Random Sampling: throwing dice, drawing names out of a hat
ii) Stratified Random Sampling: sampling in which randomly selected units from small or minority populations are forced into the sample to ensure that they are represented in the proportion to their presence in the population
iii) Systematic Sampling: sampling every nth person on the list
iv) Mult - 11What are the steps to a classic experiment?Ask a question/Do secondary research/Construct a hypothesis/Test your hypothesis by doing an experiment/Analyze your data and draw a conclusion/Communicate your results
- 12What are the three criteria for causation?Causal Relationship: a relationship between variables in which changes in one variable demonstrably result in changes in another. /"A" must precede "B" in time/"A" and "B" must vary together(covariance)/"B" must demonstrably be caused by "A" and not by something else.
Information
- Description
- Communication Studies Flashcards on Empirical Research, created by Tyler Gonzales on 12/12/2018.
- Created by
- Tyler Gonzales
- Views
- 0
- Rating