Using the 2000-01 Survey Data

This page lays out some key concepts and some recommended reading to hopefully help the newest user get started with the 2000-01 Survey data.  

Know the Components of the Survey

The 2000-01 survey has three components: community, household and migrant follow-up.   Each component has at least one questionnaire, one codebook and one data file associated with it:  (a) The community component has one questionnaire, one codebook and one data file.  (b) The household component has three questionnaires - old households, new households and moved households - two codebooks (an old & new household codebook and a moved household codebook) and several data files.  (c) The migrant follow-up component has two questionnaires - rural to urban and rural to rural - one codebook and several data files.


Study the Fieldwork Documentation

In addition to the questionnaires and codebooks for each of the three components, we highly recommend reviewing the field manuals before even attempting to use any part of the survey data.   In fact, it may be more beneficial to study the field manuals first before looking over the questionnaires and codebooks.   Each component has its own field manual, although there is some overlap across field manuals:

• Community

The community field manual contains descriptions and interviewer instructions for each of the questions asked in the community questionnaire.  There are additional concepts and fieldwork descriptions in the household survey field manual.

• Household

The household survey field manual contains an overview of the project, definitions and key concepts, general procedures used in the fieldwork and then question by question descriptions and instructions over all of the forms.  

• Migrant Follow-Up

The migrant follow-up field manuals - one for rural to urban migrants and one for the rural to rural migrants - contain an overview of the project, definitions and key concepts, general procedures used in the fieldwork and then question by question descriptions and instructions over all of the forms.  

Using the Codebooks           

In the front of each codebook, there are two sections that should be helpful in using the codebook and the data files:

• Codebook Conventions    
  

This section describes the different conventions used in the codebook including data file pointers,  the column format, the variable names, missing and not applicable values and standard vs restricted-use shading.

• Identifier Variables

This section describes the identifier variables used across all survey years and all survey components.  This identifier section is critical for understanding and using the data.

Understand the Data Files

• Data Format

All data files are in SAS xport transport format.  This means that when you reference the data file with a libname statement in your SAS program that you must specify the xport engine and the entire path name for the data file. For example:

libname in1 xport '/this/is/the/directory/filename.01';

• Data Structure and Specifications

Please refer to the 2000 survey data files chart to learn about the data structure and the specifications for each of the data files.  Specifications on each data file includes:  the corresponding survey forms with brief descriptions; the SAS data set name; the number of observations and variables; the unit/level of analysis (1 obs=); the identifier sets; how the data file is currently sorted; and the SAS pathname.