Sampling: Estimating the Frequency of Behaviours and Beliefs

Population

the entire set of people or products in which you are interested in 

Sample

A smaller set, taken from that population 

Census

A set of observations that contains all members of the population of interest.

External validity is concerned whether the sample used on the study is adequate to represent the WHAT

External validity is concerned whether the sample used on the study is adequate to represent the UNSTUDIED POPULATION

Just because a sample comes from a population does not mean it WHAT to that population

Just because a sample comes from a population does not mean it GENERALIZES to that population

Samples can either be

1. WHAT

2. WHAT

Samples can either be

1. Biased

2. Representatives

Biased sample or unrepresentative sample

some members of the population of interest have much higher probability than other members of being included in the sample 

Unbiased sample or representative sample

all member of the population have an equal and known change of being included in the sample 

Only WHAT samples allow us to make inferences about the population of interests

Only UNBIASED samples allow us to make inferences about the population of interests

A sample can be bias in two ways

1. WHAT

2. WHAT

A sample can be bias in two ways

1. Sampling those who are easy to contact

2. Sampling only those who volunteer

Convenience sampling

using a sample of people who are easy to contact and readily available to participate 

This can reduce WHAT when the same group of people participate in all studies 

This can reduce GENERALIZATION when the same group of people participate in all studies 

Biased sample may occur when the people the researcher can contact are WHAT from population to which they want to WHAT

Biased sample may occur when the people the researcher can contact are DIFFERENT from population to which they want to GENERALIZE

Self-selection

when a sample is known to contain only people who volunteer to participate

Probability sampling or random sampling

Every member of the population of interest has an equal and known chance of being selected for the sample, regardless of whether they are convenient or motivated to volunteer 

Nonprobability sampling

Involve nonrandom sampling and can result in biased samples

The most basic form of probability sampling is WHAT

The most basic form of probability sampling is SIMPLE RANDOM SAMPLING

Simple random sampling

sample is chosen completely at random from the population of interest

Systematic sampling

A probability sampling technique in which the researcher uses a randomly chosen number N, and counts off every Nth member of a population to achieve a sample

Cluster sampling

clusters of participants within the population of interest are selected at random, followed by data collection from all individuals in each cluster.

Multistage sampling

Using two random samples are selected: first a random sample of clusters and then a random sample of people within those clusters

Stratified random sampling

the researcher purposefully selects particular demographic categories or strata and then randomly selects individuals within each of the categories, proportionate to their assumed membership in the population 

Stratified random sampling differs from cluster in two ways:

• first strata are WHAT categories (such as ethnic or religious groups) whereas clusters are more WHAT.

• Second the final sample sizes of the strata reflects their WHAT in the population, whereas clusters are not selected with WHAT in mind 

Stratified random sampling differs from cluster in two ways:

• first strata are MEANINGFUL categories (such as ethnic or religious groups) whereas clusters are more ARBITRARY.

• Second the final sample sizes of the strata reflects their PROPORTIONS in the population, whereas clusters are not selected with PROPORTIONS in mind 

Oversampling

Researcher intentionally overrepresents one or more groups 

Weighting

Adjust the data so responses from members of underrepresented categories count more and overrepresented members count less

Random

occurring without any order or pattern 

Random sampling (probabilistic sampling)

researchers create a sample using some random method

Random sampling enhances WHAT validity

Random sampling enhances EXTERNAL validity

Random assignment

used only in experimental designs (used when researchers want to place participants into two different groups) 

Random assignment enhances WHAT validity by helping ensure that the comparison group and the treatment group start out with the same kinds of people 

Random assignment enhances INTERNAL validity by helping ensure that the comparison group and the treatment group start out with the same kinds of people 

WHAT sampling is the most common sampling technique

CONVENIENCE sampling is the most common sampling technique

Purposive sampling

A biased sampling technique in which only certain kinds of people are included in a sample.

Snowball sampling

participants are asked to recommend a few acquaintances for the study 

Quota sampling

A biased sampling technique in which a researcher identifies subsets of the population of interest, sets a target number for each category in the sample, and nonrandomly selects individuals within each category until the quotas are filled

In a frequency claim, WHAT validity is a priority

In a frequency claim, EXTERNAL validity is a priority

For most variables when researchers are striving to generalize from a sample to a population the WHAT of the sample is in fact much less important than WHAT that sample was selected 

For most variables when researchers are striving to generalize from a sample to a population the SIZE of the sample is in fact much less important than HOW that sample was selected 

Only a sample of WHAT-WHAT people are needed 

Only a sample of 1000-2000 people are needed 

The WHAT the sample size the WHAT the margin of error that is the more accurately the sample’s results estimate the views of the population but once you reach 1000 people it takes many more people to gain just a little more WHAT 

The LARGER the sample size the SMALLER the margin of error that is the more accurately the sample’s results estimate the views of the population but once you reach 1000 people it takes many more people to gain just a little more ACCURACY 

Sample size is a WHAT validity issue not an WHAT validity issue 

Sample size is a STATISTICAL validity issue not an EXTERNAL validity issue 

Internet panel method

invites respondents based on randomly selected postal addresses and provides Internet access and tablets to members of the sample who need it