In: Statistics and Probability
Why might it be important to put a lot of attention into how a sample is collected? How might a weak sample influence the inferences that can be made from data?
A lot of attention should be put into how a sample is collected because a sample has to reflect the representativeness of the population. It is not wise to conduct an experiment/survey using the entire population if the population is huge. In this case we infer about the population using a sample which acts as the representative of the population. A weak or biased sample might give wrong/biased conclusions about the population.
Below is the list of biases and their consequences that a sample can suffer from -
Undercoverage -
Occurs when some observations of the population are inadequately represented in the sample.
Nonresponse bias -
Occurs when individuals chosen for the sample are unwilling or unable to participate in the survey.
Voluntary response bias -
Occurs when sample members are self-selected volunteers. They might have more knowledge about the subject.
The above mentioned biases, when occur in sample, tend to deviate from conclusion about the population.
To overcome non representativeness of the sample. We should select a simple random sample. A simple random sample is the one in which -
1. The selection is based on chance and
2. Every element of the population has a probability of being selected