Research Design Flashcards
Compare Qualitative and Quantitative research
Qualitative
- interview based
- Examines individuals
- In-depth
- Long-term
Quantitative
- Numbers
- Statistics
- Observations
- Standardized
- General statements
Qualitative Analysis
(1) The nonnumerical examination and interpretation of observations, for the purpose of discovering underlying meanings and patterns of relationships. This is most typical of field research and historical research. See Chapter 13. (2) A classy analysis.
- Describing attitudes, opinions, behavior, environment, values
- You can’t really standardize questions like that
- Important to explore all influential factors
- You don’t talk about the group or individuals, but the issues as the source of information
- Researchers do improvise if questions aren’t working
- Or when a subject talks about a topic in completely different terms, then rearrange your research accordingly
- You might recruit specific types of respondents
- You can’t make general statements based on qualitative research
Quantitative Analysis
(1) The numerical representation and manipulation of observations for the purpose of describing and explaining the phenomena that those observations reflect. See Chapter 14 especially, and also the remainder of Part 4.
(2) A BIG analysis.
- Research is really about the population
- Not about behavior
- So quantitative methodology would be better
- Usually a limited about of variables
- Derived from a theory; deductive
- Abstract from the complex, in-depth, rich description of individuals
- Income, gender, social class might matter but you wouldn’t ask if people had dogs/cats
- Sometimes perceived as flat or superficial
- Not about depth of information but about scope
- You must derive sample from general population; never representative
5 Main Differences between Qualitative and Quantitative
Areas of Difference:
- Problem formation
- Research design
- Data collection
- Data analysis
- conclusions/report writing
Qualitative vs Quantitative
Problem Formation
Qualitative
- Theory development; inductive
- Exploratory purpose
- Understand a problem; discover ideas
Quantitative
- Hypothesis and theory testing; deductive
- Description and understanding of relationship among variables
- Explain the problem; test hypotheses
Qualitative vs Quantitative
Research Design
Qualitative
- Research design modified as it is implemented
- Small sample
- Data saturation, sequential sampling
–First interview is new and exciting; second interviews you start to notice patterns; Third+ interview you can’t identify new reasons for voting
–May not be necessary to do extra interviews, but you could seek another subgroup or ask different questions
- Much more flexible in terms of changes mid-research
You can change order of questions or questions themselves
Quantitative
- Research design predetermined
- Large sample
- Sample size predetermined; driven by number you need for accuracy
- If you say you’ll interview 2,000, you have to interview 2,000
Qualitative vs Quantitative
Data Collection
Qualitative
- Asking primarily open-ended questions; unstructured
- Data: words, pictures, behavior
- Same questions not necessarily asked to all participants
- Data collectors may improvise
- Most important to remember the objective of the study; keep conversations on track
Quantitative
- Asking primarily closed-ended questions; structured
- Data: numbers
- Same questions asked to all participants
- Data collectors do not improvise
- Predefined order of questions
- Specific reasons for why you order questions that way
- Must observe and train interviewers to ask the same way
Qualitative vs Quantitative
Data Analysis
Qualitative
- Collect verbatim responses
- Limited statistical analysis
- Results cannot be generalized
- Focus on themes and meanings
- Validity based on credibility, richness, and authenticity
- Numbers aren’t important here; the attitude of the comments and results is most important
Quantitative
- Collect structured responses
- Basic to advanced multivariate statistical analysis
- Results are generalizable based on inferential statistical analyses
- Focus on trends, comparisons, predictions, explanations
- Validity based on controllability, generalizability, and replicability
Qualitative vs Quantitative
Conclusions & Report Writing
Qualitative
- Predicted on the assumption that each individual, culture, and setting is unique
- Idiographic statements
- Focuses on recognition of uniqueness
- Uses subjective experiences
- Based on study of uniqueness of individual
Quantitative
- Assume “law” or “trends” may be identified
- Nomothetic statements
- Attempts to generalize people
- Uses objective knowledge
- Based on numerical data or data that can be categorized
Units of Analysis (5)
- Individuals
- Groups (families, colleagues)
- Artifacts (photos, posts, books, articles)
- Geographical Units (states, countries, cities)
- Social Interactions (calls, texts, convos)
Cross-sectional studies
A study based on observations representing a single point in time. Contrasted with a longitudinal study. See Chapter 4.
- participants assessed a single time
- doesn’t work for cause & effect (need a pause)
- like a snapshot of a given moment
- associations, populations
Longitudinal studies
A study design involving the collection of data at different points in time, as contrasted with a cross-sectional study. See also Chapter 4 and cohort study, panel study, and trend study.
- expensive; often public or publicly funded
- comparing snapshots over time
Types of Long. Studies:
- Trend Studies
- Cohort Studies
- Panel Studies
Trend Studies
A type of longitudinal study in which a given characteristic of some population is monitored over time. An example would be the series of Gallup Polls showing the electorate’s preferences for political candidates over the course of a campaign, even though different samples were interviewed at each point. See Chapter 4 and cohort, longitudinal, and panel study.
- Focused on changes over time
- Marketing research - tracking brand awareness
- Based on different samples
- An increase in numbers might not actually represent an increase if you’re sampling different populations; could be sampling effect
- Be very cautious interpreting numbers;
- Political party preferences interpreted in this way
- Numbers are never 100% representative; always a bias; always an error
- You don’t have to track past respondents; easy in some ways
- Next year, use the same methodology with different samles
Cohort Studies
A study in which some specific subpopulation, or cohort, is studied over time, although data may be collected from different members in each set of observations. For example, a study of the occupational history of the class of 1970 in which questionnaires were sent every five years would be a cohort study. See Chapter 4 for more on this topic (if you want more). See also longitudinal study, panel study, and trend study.
- When you take a group of individuals experiencing the same event within their lives; a particular generation
- Ask generation throughout time
- To see how people/generations change throughout their lives
Panel Studies
A type of longitudinal study, in which data are collected from the same set of people (the sample or panel) at several points in time. See Chapter 4 and cohort, longitudinal, and trend study.
- To see real difference, you’d have to ask someone, conduct your campaign, and then ask the same person again
- You’d need to build a panel of people that you would ask before and after the campaign
- Much more difficult to plan, organize, and maintain
- You need people for baseline and again later
- High danger that the after panel will lose ability to represent the whole population
- The panel effect - Might feel foolish or stupid that they dont know during the time between; so they do research, but then they are no longer a representation of normal behavior
- You’re then, effectively doing a trend study because they’ll represent two different samples
