Recruitment & Sampling

• Populations and samples:

  • Population: Every person in the group of interest (target population)
  • Accessible population: Everyone in that group who you have access to
  • Sample: A subgroup of the population who you actually recruit
  • You will only ever have a sample. The goal is to make it as representative of the population as possible
• Inclusion/Exclusion criteria:

  • Starting off with a general population, your narrow it down by asking
  • What people do I have access to?
  • What’s my time period for recruitment?
  • then you narrow it down more via sampling methods to create your sample population
• Sampling Method:

  • Can introduce known and unknown biases through the methods used to recruit sample
  • Selection bias: The way you select people may mean your sample isn’t representative of your population
  • Example: Sampling obese people from people attending a weight loss clinic – obese people attending a weight loss clinic may be severely obese and/or they may be motivated to lose weight
  • Volunteer bias: People who volunteer to participate in research may be different to those who refuse
• Probability Sampling Methods - Simple random sampling:

  • Each member of the population has an equal chance of being selected (e.g. use a random numbers table)
  • Advantages:
  • Should result in a truly representative sample - bias minimised
  • Disadvantages:
  • Pragmatically difficult, particularly in large population
• Probability Sampling Methods - Systematic sampling:

  • Select every n th person in the accessible population
  • Advantages:
  • Can be more efficient than random sampling
  • Disadvantages:
  • The order of the list can introduce a systematic bias
• Probability Sampling Methods - Stratified sampling:

  • Sampling ensures a proportion of representation across specific characteristic
  • Advantages:
  • Ensures balance on characteristics that are known to be important
  • Disadvantages:
  • Getting info difficult, time consuming and sometimes arbitrary
• Non probability sampling methods:

  • Sampling Methods:
  • Convenience (incidental) sampling - take who you can get
  • Snowball sampling - get those you have to ask around (more common in qualitative research)
  • Purposive sampling - handpick those who meet your needs (more common in qualitative research)
  • Advantages:
  • easy and efficient
  • Disadvantages:
  • easily affected by bias - sample may not be representative
• Sample Size:

  • Larger samples more representative
  • Larger samples give more precision
  • For a survey you need enough people to be sure that your sample is representative
  • For an experiment you need enough to be sensitive to detect a change
  • The larger the true effect the easier it is to detect and so the smaller the required sample
• Types of Errors:

  • type 1 error:
  • false positive
  • detecting an effect that isnt actually there
  • failure to accept the null hypothesis
  • type 2 error:
  • false negative
  • failing to detect an effect that is actually there
  • wrongly accepting the null hypothesis
• Error Types:

  • Increased sample size = decreased variability = greater power to detect an effect if one exists
  • so increased sample size means theres less chance of a type 2 error, as a type 2 error occurs when you fail to detect an effect that is actually there
• Sample Size Calculation:

  • Finger in the air method common and profoundly dodgy
  • Better to perform a formal sample size calculation
  • But for this you need to establish some background data
  • The method varies depending on the study design
  • This will be discussed in more detail in the lecture on inferential statistics