Please enable JavaScript.

Coggle requires JavaScript to display documents.

Sampling: the process of selecting a subset (sample) from a larger group…

- - - - respondents are randomly chosen from a sampling frame
    - - every kth element is selected after a random start, where k = N/n
      - efficient & produces a sample that reflects the population structure based on the ordering criterion
    - - proportional (reflecting subgroup sizes)
      - non-proportional (oversampling smaller groups)
      - ensures representation of all subgroups
      - improves precision of estimates
    - - the variability of sample estimates in a cluster sample will generally be higher than that of a simple random sample
      - results are less generalisable to the population than those obtained from a simple random samples
    - - high/low profitability firms: based on gross margins, earnings per share or some other measure of profitability
      - helps analyze contrasting groups while controlling for confounding factors
  - - - quick & inexpensive but often biased & not representative of the broader population
      - best suited for pilot or exploratory studies
    - - useful for studying small or underrepresented groups, but not representative of the overall population
    - - opinions are more credible
      - findings are not generalisable to the overall population at large
    - - reaches hard-to-reach populations or when no sampling frame is available
- - - - sample mean (avg. of all observations in a sample)
      - standard deviation (variability or spread of observations in a sample)
  - - - ~ 68% within ±1 SE of mean
      - ~ 95% within ±2 SE of mean
      - ~ 99% within ±3 SE of mean