survey sampling 5.pptVIP

population;population;Chapter5. Cluster sampling;5.1 Nature of Clusters ;An example ;A cluster sample could be taken by identifying the different classes in Zhe Jiang Gong Shang university as clusters. A sample of these classes (clusters) would then be chosen at random, so all students in thoseclasses selected would be included in the sample. ;5.1.2 Characteristics of cluster sampling; Disadvantages 1. Imprecise if clusters homogeneous and therefore sample variation greater than population variation (large design effect).;cluster sampling;5.1.3 Principle of One-stage cluster sampling ;Zhe jiang;5.1.4 the nature of clusters What makes a desirable cluster depends on the survey’s situation and resources. ; The number of elements in a cluster is called the size of the cluster. ; Cluster elements;mean per element of population; packs elements;5.2.2 Random Choice of Clusters;5.2.3 Estimator for population mean and population variance;(2)Assume that the clusters are selected with srs, the variance of the mean: ;……;(3)A more convenient computation: The form is the variance between the cluster totals . ;5.2.4 the estimators for population total;Example1 Objective:To find out the mean earnings of chartered accountants in a state. A=1000 (chartered accountancy firms), a=10 (the clusters interviewed) , supposing that the number of accountants in each firm is the same , that is 10 , some information is listed in the table:;;Another way :; Example2 (p153) A newspaper has 39800 subscribers served by carrier routes. There is a card for each subscriber ; in the file the cards of each subscriber in geographical order , and neighboring routes follow each other . The number of cards per carrier varies between 50 and 200. the chief purpose of the survey is to find out how many of the subscribers own their homes .An interview survey of about 400 subscribers is wanted , in clusters of 10 subscribers each. These save