Basic introduction Chinese name: sampling method mbth: sampling method main method 1: random sampling, stratified sampling main method 2: cluster sampling, systematic sampling classification: random sampling, non-random sampling Application fields: quality inspection random sampling, main methods, characteristics, stratified sampling, cluster sampling, systematic sampling, definition, steps and random sampling. Random sampling requires strict adherence to the principle of probability, and each sampling unit is selected. Random sampling is often used when the population is small, and its main feature is to extract from the population one by one. Random sampling can be divided into simple random sampling, systematic sampling, stratified sampling and cluster sampling. The main method is (1) lottery. Generally speaking, the lottery method is to number the N individuals in the group, write the numbers on the digital labels, put the digital labels into a container, and stir them evenly. One digital label is extracted from it every time, and the samples with the capacity of N are obtained continuously. The lottery method is simple and easy, and is suitable for the minority in the group. When there are a large number of individuals in the group, it is difficult to "evenly mix the group", which is probably due to the poor representativeness of the samples produced by lottery. (2) Random number method. In random sampling, another commonly used method is random number method, that is, random number table, random number dice or computer-generated random number are used for sampling. Features (1) Advantages: simple operation; (2) Disadvantages: The overall scale is too large to be realized. Stratified sampling definition Stratified sampling refers to the method of dividing the population into disjoint layers, then independently extracting a certain number of individuals from each layer according to a certain proportion, and combining the individuals extracted from each layer as samples. The smaller the intra-layer change, the better, and the greater the inter-layer change, the better. The method of grouping and extracting the number of individuals is stratified, and simple random sampling is carried out at each layer. There are generally three methods to extract the number of individuals from different groups: (1) equal number distribution method, that is, each layer is allocated the same number of individuals; (2) Equal ratio distribution method, that is, the ratio of the number of individuals extracted from each layer to the number of individuals in this group is the same; (3) Optimal allocation method, that is, the ratio of the number of samples extracted from each layer to the total number of samples is equal to the ratio of the variance of this layer to the sum of all kinds of variances. Advantages (1) reduce the sampling error, and increase the uniformity within the layer after stratification, thus reducing the variability of observation values and the sampling error of each layer. With the same sample content, the total standard error of stratified sampling is generally less than that of simple random sampling, systematic sampling and cluster sampling. (2) The sampling method is flexible, and different sampling methods can be adopted for different layers according to the specific conditions of each layer. For example, the prevalence of a disease among residents in a certain place can be divided into two levels: urban and rural. Urban population is concentrated. Systematic sampling method can be considered; The rural population is scattered, and the cluster sampling method can be used. (3) Different levels can be analyzed independently. The disadvantage of stratified sampling is that if the stratified variables are not selected properly, the intra-layer variation is large and the inter-layer mean value is similar, stratified sampling will lose its significance. Cluster sampling defines cluster sampling, also known as cluster sampling, which combines all the units in a group into several sets that do not cross and repeat each other, and is called a group; A sampling method in which samples are sampled in groups. When cluster sampling is applied, each cluster is required to have good representativeness, that is, the differences between units within the cluster are large and the differences between groups are small. Advantages and Disadvantages The advantage of cluster sampling is that it is easy to implement and saves money. The disadvantage of cluster sampling is that the sampling error caused by large differences between different groups is often greater than that caused by simple random sampling. The implementation steps are as follows: first, divide the crowd into group I, and then select several groups from group I clocks to investigate all individuals or units in these groups. The sampling process can be divided into the following steps: (1) determining the cluster label; (2) Divide the group into several non-overlapping parts, and each part is a group. (3) According to the sample size, determine the number of groups to be extracted. (4) A certain number of groups are extracted from the I group by simple random sampling or systematic sampling. For example, investigate the situation of middle school students suffering from myopia and make statistics in the last class; Conduct product inspection; All products produced by 1h are sampled and inspected every 8 hours, etc. The difference between cluster sampling and stratified sampling is similar in form, but quite different in fact. (1) stratified sampling requires large differences between layers, small differences between individuals or units within layers, small differences between groups and large differences between individuals or units within groups; (2) The sample of stratified sampling consists of several units or individuals extracted from each layer, while cluster sampling is either cluster sampling or cluster sampling is not. Systematic sampling definition Systematic sampling is also called mechanical sampling and equidistant sampling. When there are many individuals in the group, it is more troublesome to adopt simple random sampling. At this time, the population can be divided into several balanced parts, and then an individual can be extracted from each part according to predetermined rules to get the required samples. This kind of sampling is called systematic sampling. Steps Generally speaking, if you want to sample a population with a capacity of n, you can carry out systematic sampling according to the following steps: (1) Number the individuals of the population first. Sometimes you can directly use your own number, such as student number, admission ticket number, house number, etc. (2) Determine the segmentation interval and the number of segments, and when (sample size) is an integer, take; (3) determining the first number of individuals by simple random sampling in the first paragraph; (4) Sampling according to certain rules. Usually add the intervals to get the second individual number (), then add the third individual number, and so on until the whole sample is obtained.