Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapter 19: Population and Sampling Procedure - Coggle Diagram
Chapter 19: Population and Sampling Procedure
Population
Definition: Including all people or items with the characteristic one wish to understand
As there is rarely enough time or money to gather information from everyone or everything in population, the goal becomes finding a representative sample (subset) of that population.
Sometimes we need to sample over time, space, or some combination of these dimensions
the population from which the sample is drawn may not be the same as the population about which we actually want the information
Sampling Procedures:
Define the population
Identify the sampling frame
Select a sampling procedure
Define the sample size
Select the sample units
Collect data from the sampled
Sampling Techniques:
Non-probability
Sampling
a) Does not involve random selection
b) May or may not represent the whole population
c) For qualitative , pilot or exploratory study, randomization is impossible like when the population is almost limitless
d) When the research does not aim to generate results that will be used for creating generalisations pertaining to the entire population.
e) When there are limited budget, time and workforce
Convenience Sampling (accidental or haphazard)
a) Most common
b) Samples selected because they are accessable to researcher
c) Easiest, cheapest, and least time consuming
Disadvantage : no evidence that they are representative of populations
Purposive Sampling
a. sample respondents with a purpose in mind
b. would have 1 or more specific predefined groups we are seeking
c. very useful for when you need to reach a targeted sample quickly and where sampling for proportionality is not the primary concern
d. can get opinions of your target population but also likely to overweight subgroups in your population that are more readily accessible
Judgmental Sampling
a. commonly known as purposive sampling
b. subjects are chosen to be part of the sample with specific purpose in mind, researcher believes that some subjects are fit for the research compared to others
Expert Sampling
a. Assembling of a sample of respondents with known or demonstrable experience or expertise in some area
2 reasons you might do expert sampling:
1) best way to elicit views of respondents who have specific expertise
2) to provide evidence for the validity of another sampling approach you have chosen
Advantage:
-you have some acknowledged experts to back you
Disadvantage:
-even the experts can be and often are, wrong
Quota Sampling
a. researcher ensures equal or proportionate representation of subjects depending on which trait is considered as basis of the quota.
2 types:
1) Proportional- represent major characterisitcs of the population by sampling a proportional amount of each.
2) Non-proportional
Heterogeneity Sampling (sampling for diversity)
When we want to include all opinions or views, and we are not corncerned about representing these views proportionately
Snowball Sampling
a. Done when there is a very small population size
b. Researchers ask the initial subject to identify another potential subject who also meet the criteria of the research
c. Useful when you are trying to reach populations that are inaccessible or hard to find
d. Downside: hardly representative of the population
Probability
Sampling
a. Different members of population have an equal chance of selection
b. Allows researchers to draw some general conclusions beyond the people included in the study
c. Eliminate researcher's bias
d. Avoid sampling error
e. More accurate and rigorous
Simple Random Sampling
a. All such subsets of the frame are given an equal chance of probability of being included
b. Minimises bias and simplifies analysis of results
c. Disadvantages:
i) Complete frame or a list of all units in the whole population is needed
ii) Costs of obtaining the sample can be high if the units are geographically widely scattered
iii) the standard errors of estimators can be high
iv) Simple random sampling can be vulnerable to sampling error
v) Cumbersome and tedious
To conduct a random sampling, consider the following questions:
What is the basic unit to be examined?
How should the target population be delineated?
What variables or parameters are of interest?
How should the sample be drawn?
How many units should be included?
Stratified Random Sampling
a. Involves dividing the population into subgroups based on variables known about those subgroups, and then taking a simple random sample of each subgroup
b. Tricky for the uninitiated
c. Benefits:
i) enable researchers to draw inferences about the specific subgroups
ii) Lead to more efficient statistical estimates
iii) more convenient
iv) can be applied to different strata
d. Drawbacks:
i. increase cost and complexity of sample selection
ii. when examining multiple criteria, stratifying variables may be related to some, but not others, further complicating the design and potentially reducing the utility of the strata
iii. can potentially require a larger sample than would other methods
Systematic Sampling
a. Random sampling with a system
b. From the sampling frame, a starting point is chosen at random, and thereafter at regular intervals
c. Common form is an equal-probability method, in which every kth element in the frame is selected, where k, the sampling interval is calculated as,
k=N/n , where n is the sample size, N is the population size
d. More efficient
Cluster Sampling
a.Population is divided into mutually exhaustive subsets
b. A random sample of the subsets is selected, if the researcher examines all units in the selected clusters, the procedure is called
one-stage cluster sampling
, if a sample of units is selected probabilistically from the selected subsets, the procedure is known as
two-stage cluster sampling
c. Follow these steps:
Divide the population into clusters
Randomly sample clusters
Measure all units within sample clusters
d. Advantage:
i) Do not need a complete frame of secondary sampling units
ii) Geographical concentration of the units to be studied
e. Draw back:
if there is a large variation between clusters in the variables to be examined the method may yield poor decision
Multi-Stage Sampling
a. Combination of sampling methods
b. Able to achieve a rich variety of probabilistic sampling methods that can be used in a wide range of social research contexts
Sample size in Quantitative Research
3 factors/variables , one must know about a given study, each with a certain numerical value:
Significance level
Power
Effect size
Techniques/ ways in determining the minimum sample size:
a. use specific formulas
b. opinion of statistical and testing experts
c. use of calculation using computer -assisted technology
d. based on the type data collection used
Appropriate sample size is required for validity
Rules of thumb to determine sample size:
Sample sizes larger than 30 and less than 500 are appropriate for most research
For samples to be broken into sub-samples, a minimum sample size of 30 for each category is necessary
In multivariate research, the sample size should be several times (preferably 10 times or more) as large as the number of variables in the study
For simple experimental research with tight experimental controls, samples can be as small as 10 to 20 in size
Sample size in Qualitative Research
The minimum number of informant for this study is 1 (who is special, authoritive, and has the best of knowledge related to the matter)
Consideration/ influences on how many interviews a researcher may conduct:
The type of sampling techniques that are employed
Resourcing of the study, can place limitation on what sampling is feasible
Sampling continues until researcher senses they has reached saturation
Interview structure and content
Heterogeneity of the group
The number of interview done alreeady
Interview's complexity
researcher's experience
Number of researchers
The more interviews, the more defensible the researcher believes the research will be