# Sample Surveys 2022-08-28 >[!Quote] Probability methods guard against bias, because blind chance is impartial. >In [[self.stats/Statistics]] Investigators will make generalizations from the part to the whole. In more technical language, they make inferences from the sample to the population It is not feasable to study the entire population. This is, in fact, one of the reasons why Statistics exists in the first place. > A systematic tendency on the part of the sampling procedure to exclude one kind of person or another from the sample is called selection bias. > When a selection procedure is biased, taking a large sample does not help. This just repeats the basic mistake on a larger scale. When taking surveys, remember that there is a [[Non-Response Bias]], and so always make sure to take those into account. >Non-respondents can be very different from respondents. When there is a high non-response rate, look out for non-response bias. (Page 354) When you sample, it is important to make sure you have a **good** sample: >Some samples are really bad. To find out whether a sample is any good, ask how it was chosen. Was there selection bias? nonresponse bias? You may not be able to answer these questions just by looking at the data. (Page 354) >[!Summary] Summary Taken from [[Statistics (Freedman)]] >1. A sample is part of a population >2. A ***parameter*** is a numerical fact about a population. Usually a parameter cannot be determined exactly, but can only be estimated. > See [[Point Estimation]] >3. A statistic can be computed from a sample, and used to estimate a parameter. A statistic is what the investigator knows. A parameter is what the investigator wants to know. >4. When estimating a parameter, one major issue is accuracy: how close is the estimate going to be? >5. Some methods for choosing samples are likely to produce accurate estimates. Others are spoiled by selection bias or non-response bias. When thinking about a sample survey, ask yourself: > - What is the population? > - What is the parameter? > - How was the sample chosen? > - What was the response rate? >6. Large samples offer no protection against bias. >7. In quota sampling, the sample is hand picked by the interviewers to resemble population in some key ways. This method seems logical, but often gives bad results. The reason: unintentional bias on the part of the interviewers, when they choose subjects to interview. > This is also why you might find a lot of faulty results in qualitative User Researc >8. Probability methods for sampling use an objective change process to pick the sample, and leave no discretion to the interviewer. The hallmark of a probability method: the investigator can compute the change that any particular individuals in the population will be selected for the sample. Probability methods guard against bias, because blind chance is impartial. >9. One probability method is simple random sampling. This meanas drawing subjects at random without replacement. >10. Even when using probability methods, bias may come in. Then the estimate differs from the parameter, due to bias and chance error: > > estimate = parameter + bias + chance error > Chance error is also called *sampling error*, and bias is *non-sampling error* ## Sources - [[Statistics (Freedman)]]