Beruflich Dokumente
Kultur Dokumente
SESSION 06
RECAP
1. Problem definition
3. Research design
• Survey, Observations
• Scales
• Sampling
• Population
• Elements sharing common characteristics
• Census
• Complete enumeration of elements in the population
• Sample
• Sub-group of population selected for study
https://www.vectorstock.com/royalty-free-vector/research-process-sampling-from-a-target-population-vector-12456089
Parameter
Statistic
• Considerations - Census versus sample
• Budget
• Time
• Population size
• Variance
Element is the object about which or from which the information is desired -
the respondent.
Re-define population
• incidence rates
• completion rates
• resource constraints
5. Execute The Sampling Process
Sampling Techniques
Probability
Non-probability
Sampling Techniques
Sampling Techniques
• Usage
• Exploratory
• Qualitative research
Types of Non-probability Sampling
1. Convenience
2. Judgemental
3. Quota
4. Snowball
1. Convenience Sampling
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
3. Quota Sampling
1. Simple Random
2. Systematic
3. Stratified
4. Cluster
1. Simple Random Sampling
• Each element in the population has a known and equal probability
of selection
• How to do?
1. Sampling frame
3. Pick “randomly”
2. Systematic Sampling
• Select a random starting point and then picking every i th
element in succession
• Sampling interval (i) = Population size (N)/sample size (n)
• For example, there are 100,000 elements in the population and a sample
of 1,000 is desired. In this case the sampling interval, i, is 100.
• A random number between 1 and 100 is selected. If, for example, this
number is 23, the sample consists of elements 23, 123, 223, 323, 423, 523,
and so on.
3. Stratified Sampling
• A two-step process:
• Proportionate or disproportionate
Proportionate Sampling
Disproportionate Sampling
4. Cluster Sampling (1)
• Target population divided into mutually exclusive and collectively
exhaustive clusters
Cluster Sampling
2. Quantitative
• Formula
3. Adjustments
• Incidence rate
• Completion rate
It is desired to estimate the mean life time of a certain kind of vacuum cleaner.
Given that the population standard deviation is 320 days, how large a sample is
needed to be able to assert with a confidence level of 95% that the mean of the
sample will differ from the population mean by less than 45 days?
• A market researcher for consumer electronics company would like to study the
television viewing habits of the residents of a particular, small city. What sample
size is needed if he wishes to be 95% confident of being within +/- 0.035 of the
true proportion who watch the evening news on at least three weeknights if no
previous estimate is available?
Incidence Rate:
• Rate of occurrence
• Percentage of people eligible for participating in the study
• Incidence rate - x%,
• Sample size - 1/x % times - people should be approached to get a response
• As criteria gets complex, the number of contacts increases
Completion Rate:
2. Refusal
• Prior notification
• Incentives
• Follow-up
SPSS??