A researcher divides his population into certain groups and fixes the size of the sample to be drawn from each group by his own choice. This is called

Fixing by his own choice how many to draw from each group makes this a quota sample.

A stratified random sample also divides into groups but then selects randomly, not by personal choice.

A cluster sample draws whole groups at random rather than a fixed number from each.

A simple random sample uses no grouping and gives each unit an equal chance.

Quota sampling is a non-probability method because the final units are picked at the researcher's discretion.

It resembles stratification in structure but lacks any random selection within the groups.