SAMPLING Flashcards
define sampling
selecting participants that allow us to make generalisable inferences
define population
A group of people about whom one would like to draw some meaningful conclusions
e.g.
Adolescents
People with schizophrenia
QUT Psychology undergraduates
define sample
a subset of that population that is actually included in the research study
e.g.
150 Year 10 students
30 outpatients
Everyone who attends wk3 lecture
define sampling frame
a list of people or elements of a population from which one might obtain a sample
e.g.
Electoral role
Telephone directory
Student enrolment list
define census
a list of ALL the people comprising a particular population
what does having a representative sample mean?
This simply means that you should select a sample whose typical characteristics are approximately the same as the typical characteristics of the population.
elements/means of measuring representativeness
sample statistic - a numeric characteristic of the sample (measured)
population parameter - numeric characteristic of the population (often unknown)
response rate - what proportion of people responded
sampling error - the difference between sample statistic and population parameter (depends on sample size)
what is sampling bias
something at impedes the representativeness of a sample
e.g. self-selection
what are the two types of sampling procedures
probability
- simple random
- systematic random
- stratified
- multicluster
non-probability
- convenience
- snowball
- purposive
define probability sampling
a way to ensure your sample is representative of the population based on characteristics deemed important to the study
what is the basic principle of probability sampling
a sample will be representative of the population if all members have an equal chance of being selected in the sample
allows researchers to calculate the relationship between the sample statistic and population parameter
what are the types of probability sampling
Simple random sample
Systematic random sample
Stratified random sampling
Multistage cluster sampling
define a simple random sample
each member has an equal and independent chance of being selected
whats the process of selection via a simple random sampling
> define the population
list all members
> assign numbers
- use a table of random numbers to select
- use ‘lottery’ method
- use a computer program to randomly select
define a systematic random sample
randomly select first person followed by every x^th person from the population is chosen
systematically choosing from the population by dividing the population size by the desired sample to determine the interval at which sample is selected
e.g. select a sample of 1000 from a list of 10,000»_space; select every 10th person form the list
what needs to be considered when using a systematic random sample
sampling bias
need to ensure list of elements/people is not arranged in a way that could lead to a biased sample (e.g. student list in GPA order)
what is stratified sampling
and
when is it used
sampling by dividing the population in to subpopulations (strata) and randomly sample from the strata
if you want to make sure the profile of the sample matches the profile of the population on some important characteristics (e.g. ethnic mix, gender)
why use stratified sampling?
can reduce sampling error by ensuring the ratios reflect the actual population (e.g. ratio of males to females(
to ensure that small subpopulations are included in the sample
what is multistage cluster sampling?
begin with a sample of groupings then sampling individuals from said groupings
> larger sample obtained first to identify members of a subsample
randomly choose from sample to participate in the study
wha is multistage cluster sampling good for?
identifying not readily identifiable sub groups
good but costly
pros and cons of probability sampling
PRO
- helps to overcome sampling bias»_space; representativeness
CON
choosing someone doesn’t mean they will take part
define probability sampling
not every member of the population has an equal chance of being part of the sample
when should Non-probability sampling be used
when there are no lists for the population of interest, no available (no sampling frame)
what are the types of non-population sampling
convenience
snowball
Quota
purposive
define convenience samples
selecting a sample from the available participants
e.g.
students enrolled in a particular course
people passing a particular location
pros and cons of convenience samples
PRO
easy and inexpensive
CON
no control over representativeness
define snowball sampling
collecting data with members of the population that can be located and then asking those members to provide information/contacts for other members of the population
when is snowball sampling used?
used mainly for hard to study populations
e.g.
homeless young people
illegal immigrants
what is a quota sample?
non probability sampling equivalent of stratified random sampling
want to reflect relative proportions of a population
without being able to sample randomly from each strata
define purposive/judgement sampling
selection with a clear purpose to the sampling strategy
e.g. selecting key informants, atypical cases, deviant cases or a diversity of cases
> if unable to sample all of a population, choose groups most likely to have a rich data source
when is purposive sampling used?
often used to
- select cases that might be especially informative
- select cases in a difficult to reach popluation
- select cases for in-depth investigation
what are the 5 rules of determining sample size?
- if population = <100, use entire population
- larger sample sizes make it easier to detect an effect or relationship in a population
- compare to other research studies in area through lit review
- use a power table for a rough estimate
use a sample size calculator
