Statistics – Sampling:
Data sampling is a statistical technique used to select, manipulate and analyze a subset of data points to identify patterns and trends in the larger data set being examined. Data scientists, predictive modelers and data analysts often work with a small, manageable amount of data about a statistical population to build and run analytical models more quickly and accurately.
Sampling is particularly useful with data sets that are too large to efficiently analyze.For example, in big data analytics applications or surveys,identifying and analyzing a representative sample is more efficient and cost-effective than surveying the entire population.
The size of the required data sample and the possibility of introducing a sampling error are important.A small sample may sometimes reveal the most important information about a data set. Using a larger sample increases the likelihood of accurately representing the data as a whole, even though the increased size of the sample may impede ease of manipulation and interpretation.
Data sampling can be accomplished using probability or nonprobability methods.
Probability Samplinguses randomization to select sample membersin the data set to ensure that there is no correlation between points.
Non-probability samplinguses non-random techniques (i.e. the judgment of the researcher). It can be difficult to calculate the odds of any particular item, person or thing being included in your sample.
Probability data sampling methods include:
Simple random sampling is used to randomly select data from the whole population using a software.
Stratified sampling:Subsets of the data sets or population are grouped based on a common factor, and samples are randomly collected from each subgroup.
Cluster sampling: The larger data set is divided into subsets (clusters) based on a specific factor, then a random sampling of clusters is analyzed.
Multistage sampling: A complicated form of cluster sampling, this method also involves dividing the larger population into a number of clusters. Second-stage clusters are further broken out based on a secondary factor, and those clusters are then sampled and analyzed and the process continues.
Systematic sampling: A sample is created by setting an interval at which point to extract data from the larger population. For example, selecting every 10th row in a spreadsheet of 20 items to create a sample size of 2 rows to analyze.
Nonprobability data sampling methods include:
Convenience sampling: Data is collected from a convenient group (easily accessible, available).
Consecutive sampling: Until the predetermined sample size is met, data is collected from every subject that meets the criteria.
Purposive or judgmental sampling: Selecting the data to sample based on predefined criteria.
Quota sampling: A selection ensuring equal representation within the sample for all subgroups in the data set or population.
Errors happen when you take a sample from the population rather than using the entire population. Sample error is the difference between the statistic you measure and the parameter you would find for the entire population.
If you were to survey the entire population, there would be no error. Sample error can only be reduced, since it is considered to be an acceptable tradeoff to avoid measuring the entire population.When the sample size gets larger, the margin of error becomes smaller. But, there is a notable exception: if you use cluster sampling, this may increase the error because of the similarities between cluster members.