When an ad is placed in a newspaper asking readers to take a survey, it is an example of a non-probability sample. This is because not all readers of the newspaper have an equal chance of being selected to participate in the survey. Some readers may not see the ad, others may not be interested in participating, and still others may not meet the criteria specified in the ad. Therefore, the sample of participants is not representative of the entire population of newspaper readers, and it is not possible to calculate the margin of error or the level of confidence for the results. Non-probability sampling is less reliable than probability sampling but it is often used when the researcher wants to reach a specific group of people or when a probability sample is too expensive or not feasible.