What is systematic sampling?

Systematic sampling is to arrange all the units in the population in a certain order, randomly select one unit as the initial unit within a specified range, and then determine other sample units according to pre-specified rules. First, randomly select a number R from 1 to K as the initial unit, and then take units such as r+k and r+2k. This method is simple to operate and can improve the accuracy of estimation.

According to the overall unit arrangement method, the unit arrangement of equidistant sampling can be divided into three categories: queuing according to relevant signs, queuing according to irrelevant signs and queuing according to natural state between queuing according to relevant signs and queuing according to irrelevant signs. According to the practice of realizing equidistant sampling, equidistant sampling can be divided into three types: linear equidistant sampling, symmetric equidistant sampling and cyclic equidistant sampling.

Extended data:

When using equidistant sampling, you must first sort the whole unit according to a symbol. There are two sorting methods.

1, sorted by irrelevant symbols, that is, the overall unit arrangement order has nothing to do with the symbols to be studied. If you investigate the income level of employees, you can sample the list of employees arranged by surname strokes; The quality inspection of industrial production can carry out equidistant sampling according to the time sequence of product production. It is generally believed that equidistant sampling in the queue of irrelevant symbols is a lottery method, and the random number table method is a better pure random sampling method, also known as disorderly system sampling.

2. According to the relevant signs, that is, the order of the whole unit arrangement is directly related to the signs to be studied. For example, in the sampling survey of agricultural output, samples can be taken from low to high or from high to low according to the estimated output of the current year or the average actual output over the years. This kind of equidistant sampling, also known as ordered system sampling, can make it possible for units with different mark values to be selected into the sample, thus improving the representativeness of the sample and reducing the sampling error.