STATS 11- sampling

Question 1

The participants (or subjects)

Answer 1

• When deciding on WHO or WHAT is studied, a researcher needs to consider
• What is the population of interest
• What sample can be accessed
• Is the sample random
• Is the sample representative of the population

Question 2

Samples vs Population

Answer 2

• Most research involving people will obtain a sample and then try to generalise to the population
• The sample is just one part of a population because it may not be viable to study an entire population
• The sample wants to be representative of the whole population- so we can generalise the results to the population

Question 3

Populations

Answer 3

• Populations vary in size
• Vials of anti-biotics in the world (Purple)
  
  • All vials of antibiotics in the warehouse (Blue)
  • Vials in one container of 24 boxes (Yellow)
  • Vials in one box (Red)
• These are all populations

Question 4

Sample

Answer 4

• A sample is a selection or subset of individuals from the population
• Samples also vary in size
• If you take a sample of a thousand and a sample of a hundred
• The larger sample is more likely to be representative
• It is the relationship between the sample and the population that is most important (is the sample representative of the population)

Question 5

Why do we sample

Answer 5

• Time (Difficult to collect data from everyone quickly, though not impossible e.g. vote census)
• Money (expensive to collect data from everyone e.g. production costs, payment to participants
• Sufficiency (pattern of results don’t change much even if we have data from everyone)
• Access (not always possible to reach all members of a population
• Inclination (People don’t always want to participate in psychology studies)

Question 6

How do we sample

Answer 6

• Random sample
  
  • No pattern to selection
  • Usually quasi-random
  • e.g. enter all the names and numbers from the telephone directory into a computer database and ask the computer to randomly select participants
• Systematic
  
  • Draw from the population at fixed intervals
  • e.g. Every hundredth person listed in the phone book

Question 7

How do we sample 2

Answer 7

• Stratified sample
  
  • Specific groups appear in numbers proportional to their size in the population
  • e.g. A stratified sample of handedness would aim to have about 90% right to 10% left-handed participants to reflect the general population figures

Question 8

How do we sample 3

Answer 8

• Opportunity/convenience sample
  
  • people who are easily available
  • Often leads to a biased sample
  • e.g. all students in this lecture

Question 9

How do we sample 4

Answer 9

• Snowball sampling
  
  • recruit a small number of participants and then use those initial contacts to recruit further participant- hard to reach groups
  • Biases the sample (people tend to know like-minded people), but useful if you want to recruit very specific population
  • E.g. drug users might now other drug users

Question 10

Directed study

Answer 10

• How big should my sample size be
  
  • If the sample size is small: run the risk of accepting the null hypothesis when it should be rejected
• Can calculate the POWER (P) of a particular test- if certain parameters are known
• see statutes chapter 9 pg 51-6

Question 11

Think

Answer 11

• Identify two research articles in the field of interest to yourself
  
  • What is the population
  • What sampling method has been used (HAVE they used one)
• And then some revision
  
  • What experimental design has been used
  • What variables are there
  • What is the IV, how many levels does it have
  • What is the DV
• What statistical methods were used