Data Collection

Data Collection

1. Sampling Types

   • Simple Random Sampling
     • Random sampling is analogous to putting everyone's name into a hat and drawing out several names. Each element in the population has an equal change of occuring. Preferred but often difficult to do.
   • Stratified Random Sampling
     • Divides the population into groups known as strata. However, by characteristics, not geographically. i.e males vs females
   • Two-Stage Sampling
     • Used to cut costs, split into groups and take a sub-sample of that group. i.e split into suburbs and do just one block of that suburb
   • Cluster Sampling
     • Divide population into groups, usually geographically. Groups are called clusters or blocks. Similar to two-stage clustering where every element in the selected clusters are used.
   • Systematic Sampling
     • The list of elements is "counted off". That is, every kth element is taken. This is similar to lining everyone up and numbering off. Bad.
     • In systematic sampling, samples are selected systematically according to a pre-determined plan, such as grid sampling.
   • Random Sampling Within Segments
     • Similar to cluster or stratified with an arbitrary classification of segments
   • Convenience Sampling
     • Bad technique to use. In convenience samplng, readily available data is used. That is, the first people the surveyor runs into.

2. Sampling Methods

   • Haphazard Sampling
   • Purposeful Sampling
   • Subjective Sampling