TRAINING KEY 45: Intra-class correlation for systematic sampling

Practical Methods for Design and Analysis of Complex Surveys.
Risto Lehtonen and Erkki Pahkinen

TRAINING KEY 45: Intra-class correlation for systematic sampling



INTRODUCTION

In this Training Key we use the Province'91 data set as the frame population in calculating the intra-class correlation coefficient under systematic sampling. The total of the study variable UE91 (number of unemployed in the province) is to be estimated. In Part A, the book example will be worked out. The effect of different sorting orders of the population on the intra-class correlation will be examined in Part B. Part C provides an option for interactive analysis.



A) INTRA-CLASS CORRELATION FOR SYSTEMATIC SAMPLING IN THE PROVINCE'91 POPULATION

We calculate the intra-class correlation coefficient for systematic sampling involving four separate systematic samples of eight elements (see book example 2.4 on page 45). Further instructions will be given once you start.
 

 


B) INTRA-CLASS CORRELATION FOR SYSTEMATIC SAMPLING WHEN VARYING THE SORTING ORDER

We examine the effect of the sorting order of the Province'91 population on intra-class correlation. It will be shown that the sorting order matters: the value of the intra-class correlation coefficient varies much depending on the sorting order. Further instructions will be given once you start.
 

 


C) INTERACTIVE SAS USE

Please download the SAS code for your own further training. Instructions are given in the SAS code once you download. NOTE! You need to have access to SAS in your computer.
 

Key45a.sas

Key45b.sas