Sampling is the process of….
selecting participants for a study
*sampling is key. Bad sampling can break a study
Sampling began in the…. with…
1800s with political polling and marketing
Researchers want to ensure that their samples are …..
good representations of the populations they want to study
The goal of research is to….
generalize from the sample to the entire population
What is the difference between the target and the accessible population
Target - group defined by the researcher’s specific interests
Accessible - the people the researcher can realistically involve in the study
How well one can generalize the results from a given sample to the population depends on…..
Therefore, the researcher must determine….
- the samples representativeness
- how well the sample represents the target population
Describe selection bias
Participants or subjects are selected in a manner that increases
the probability of obtaining a biased sample.
- not always conscious - might be ignorance or subconscious bias
Accuracy of a sample improves rapidly as….
the sample size increases
Outline 3 requirements for Probability sampling
*The exact size of the population must
be known, and it must be possible to list all the individuals.
* Each individual in the population must have a specified probability of selection.
* The selection process must be
unbiased; must be a random process
In non-prob sampling, the odds of selecting a particular individual are…
unknown
A good way of telling is a sample is representative of a population is if the sample is….
normally distributed
*why psych often avoids dichotomous formats
The basic principle of probability sampling is that:
A sample will be representative if
all members of the population have an equal chance of being selected
*only needs to be representative in characteristics relevant to the study
List the 5 types of probability sampling and their weaknesses
- Simple random - fair and unbiased, but no guarantee that the sample is representative
- Systematic - selections not random or independent
- Stratified random - each subgroup has representation, but overall sample may not represent the population
- Proportionate stratified - solves weakness of stratified, but some strata may have limited representation in the sample
- Cluster - selections not random or independent
- can use a combined sampling strategy
What the 4 types of non-prob sampling
Convenience sampling
Quota sampling
Purposive/Judgemental sampling
Snowball sampling
Outline convenience sampling
- indis selected from those who are available and willing
- easy but a weak form of sampling as it is likely biased
Outline snowball sampling
- used in exploratory research when participants are hard to find
- mostly vulnerable groups
- data collected from a few memebers of pop, found through referrals
Outline purposive/judgmental sampling
- select participants on the basis of knowledge
- done for a particular subset of a population
Outline quota sampling
- Subgroups identified to be included; quotas established for individuals to be selected through convenience from each subgroup
- researcher is able to control the composition of a convenience sample
- addresses issue of representativeness (though sample is therefore probably biased)
Give 2 ethical principles in selecting participants
- select in a non-discriminatory manner (which probability sampling is ideal)
- use data from all participants selected
One issue with research at large is that…
there is a strong bias towards publishing data from WEIRD populations - due to habitual dependence on convenience sampling
