Please enable JavaScript.

Coggle requires JavaScript to display documents.

Chapter Eight: Sampling - Coggle Diagram

- - - - population:
        all people or items with the characteristics that one wishes to study
        
        unit of analysis:
        person, group, organization, country, object, etc. that you wish to draw inferences about
      - Step Two:
        Choose a Sampling Frame
        
        sampling frame:
        an accessible section of the target population from where a sample can be drawn
        
        ex: list with contact information
        
        Step Three:
        Choosing a Sample from the Sampling Frame
        
        Use a well-defined sampling technique.
        Sampling techniques are grouped into two categories: probability (random) sampling and non-probability sampling
        
        Probability Sampling:
        technique in which every unit in the population has a chance of being selected
        
        simple random sampling:
        all possible subsets of a population (sampling frame) are given equal probability of being selected
        
        systematic sampling:
        sampling frame is ordered according to criteria and elements selected at regular interval through that ordered list
        
        stratified sampling:
        sampling frame is divided into homogenous and non-overlapping subgroups, and a simple random sample is drawn from each
        
        cluster sampling:
        divide the population into clusters, randomly sample a few clusters, and measure all unites within that cluster
        
        usually divided along geographical boundaries
        
        matched-pairs sampling:
        compare two subgroups within one population based on specific criterion
        
        multi-stage sampling:
        combine multiple of the single-stage techniques
        
        Non-Probability Sampling:
        some units of the population have zero chance of selection or probability of selection cannot be accurately determined
        
        convenience sampling:
        aka accidental or opportunity sampling;
        a sample is drawn from the part of the population that is readily available or convenient
        
        limits generalizability
        
        quota sampling:
        the population is segmented into mutually exclusive subgroups, then a non-random set of observations is chosen from each subgroup to meet a quota
        
        proportional quota sampling:
        proportion of respondents in each subgroup should match that of the population
        
        non-proportional quota sampling:
        less restrictive; you do not have to achieve a proportional representation, but maybe meet a minimum size in each subgroup
        
        expert sampling:
        respondents are chosen in a non-random way based on their expertise on what is being studied
        
        snowball sampling:
        start by identifying a few respondents that match inclusion criteria and then ask them to recommend others
  - - - responses from different respondents can be graphed into a frequency distribution, based on their frequency of occurrences
        
        For a large number of responses in a sample, this tends to look like a bell curve called a normal distribution
        
        can be used to estimated overall characteristics of the entire sample:
        sample statistics
        
        Entire populations cannot be sampled, so population characteristics, called population parameters, are unknown
        
        statistic: value estimated from observed data
        
        sampling error:
        difference between sample statistics and population parameters
        
        IF a sample is truly representative of the population, estimated sample statistics should be identical to the theoretical population parameters
        
        sampling distribution:
        compare sampling statistics across samples from same population; zero variability indicates representativeness
        
        1 more item...