Lecture 4 - Data Collection Methods & Data Sampling

Question 1

Quantative Data Collection Methods

Answer 1

• Data Collection Methods:
  1. Surveys
  2. Survey Experiments
  3. Documents & Records – ‘’Archival Data’’ (Large-n data sets)

Question 2

Survey Experiments

Quantative Data Collection Method

Answer 2

• In a survey experiment, a researcher randomly assigns participants to at least two experimental conditions (vignettes).
• Aims to identify if there is a relationship between the manipulated variables.

Question 3

Qualitative Data Collection Methods

Answer 3

• Data Collection Methods:
  1. Interviews ⟶ Structured / Semi-structured / Unstructured
  2. Focus groups
  3. Participant observations / Ethnographic Research
  4. Documents & Records – ‘’Archival Data’’

Question 4

Interviews

Qualitative Data Collection Method

Answer 4

In-depth analysis of individual perspectives

Question 5

Focus Groups

Qualitative Data Collection Method

Answer 5

Identifying group norms and discovering variety within a group / observe group interaction

Question 6

Participant observation & Ethnographic Research

Qualitative Data Collection Method

Answer 6

• Research directly observe actors in their “natural environment”.
• Overt and covert participation observation
• Ethnography attempts “to attain as holistic a picture as possible of a particular [small] society, group, institution, or situation. The emphasis in ethnographic research is on documenting or portraying the everyday experiences of individuals by observing and interviewing them and relevant others.” (Frankel & Wallen, 2006)
• Ethnographic Methods: Participant observation, Interviews, Focus groups, document analysis

Question 7

Sample

Answer 7

Units of observation

Question 8

Sampling Strategy

Answer 8

How do you access the participants / data?

Question 9

Study Population / Sampling Frame

Answer 9

Who / What do you have access to?

Question 10

Theoretical Population

Answer 10

Who / What do you want to study?

Question 11

Cross-sectional

Answer 11

Observations at one point in time

Question 12

Longitudinal

Answer 12

• Repeated observations of the same variables (e.g. people) over long periods of time
  1. Panel: Observe the exact sample of people over time
  2. Cohort: Observe people who shared an experience over time
  3. Trend: Observe different people over time

Question 13

Probability Sampling

Answer 13

• The general rule in quantitative research is that you are often interested in being able to make generalizations.
• Aims to ensure that each individual / unit of observation in the population has an equal chance of being included in the study.

Question 14

Simple Random Sample

Type of Probability Sampling

Answer 14

People are chosen at random

Question 15

Systematic Sample

Type of Probability Sampling

Answer 15

Every nth person is chosen

Question 16

Stratified Sample

Type of Probability Sampling

Answer 16

1. Population is divided into sub-groups (stratums)
2. Random sample is selected from each sub-group

Question 17

Clustered Sample

Type of Probability Sampling

Answer 17

1. Divide population into clusters (groups) based on physical / geographic proximity
2. Randomly choose one cluster to study

Question 18

Multi-stage Cluster Sampling

Type of Probability Sampling

Answer 18

Sampling is done in various stages, but only the sample of the last unit is studied (e.g. Gemeente selecteren ⟶ dan dorpen selecteren in die gemeente ⟶ dan huishoudens uit die dorpen selecteren)

Question 19

Sampling Error

Answer 19

The error that arises in a data collection process as a result of taking a sample from a population rather than using the whole population. It is the deviation between sample parameter and population parameter (e.g. mean).

Question 20

Confidence Interval

Answer 20

Probability that sample accurately reflects the population (Standard CI = 95%).

Question 21

Margin of Error

Answer 21

Range by which the population parameter may deviate from the sample parameter. E.g. measuring heights of students:
- Average = 175cm
- Margin of Errors = ±6.2cm
- We are 95% confident that true height of ALL students is likely to be between 168.8cm and 181.2cm

Question 22

Non-probablity Sampling

Answer 22

• Does not aim to ensure that each individual/unit of observation in the population has an equal chance of being included in the study.
• The general rule in qualitative research is that you continue to sample until you are not getting any new information or are no longer gaining new insights.

Question 23

Convenience Sample

Type of Non-probability Sampling

Answer 23

Made up of individuals who volunteer and are available. Made up of data sources easily available (e.g. top 10 results on Google).

Question 24

Quota Sample

Type of Non-probability Sampling

Answer 24

Research determines what kind of characteristics are wanted in the sample. Minimum of two groups for comparison (e.g. Do women use different weapons from men?)

Question 25

**Purposive Sample** | Type of Non-probability Sampling

Answer 25

Researcher decides who should be included. Specific individuals are targeted (not volunteers).

Question 26

**Snowball Sample** | Type of Non-probability Sampling

Answer 26

Used when researching difficult populations. Respondents help you find new respondents.