With probability samples the chance of each case being selected from the population is not known.

Multi-stage sampling have two or more successive stages using either probability, non-probability or both types of sample selection techniques.

Response is due to ineligibility to respond.

For all research questions where it would be impracticable for you to collect data from the entire population by questionnaires, you need to select a sample.

Census is not to collect and analyse data from every possible case or group member.

The larger the absolute size of the sample and, to a far lesser extent, the larger the relative proportion of the target population sampled, the greater the margin of error.

Non-probability sampling can be used generalise statistically about a target population.

Statisticians have also shown that a sample size of 10 or more will usually result in a sampling distribution for the mean that is very close to a normal distribution.  

The central limit theorem, occurs even if the population from which the sample is drawn is not normally distributed.

Probability samples have become far more prevalent with the rapid growth of online questionnaires.