India - Annual Survey of Industries (Summary): 1990-91

Sampling Procedure

The sampling design followed in ASI 1990-91 is a circular systematic one. All the factories in the updated frame (universe) are divided into two sectors, viz., Census and Sample.

Census Sector: Census Sector is defined as follows:

a) All industrial units belonging to the 12 less industrially developed states/ UT's viz. Manipur, Meghalaya, Nagaland, Tripura, Sikkim and Andaman & Nicobar Islands etc.
b) For the rest of the states/ UT's., (i) units having 100 or more workers irrespective of their operation with or without power and all electricity undertakings and (ii) all factories covered under Joint Returns.
c) After excluding the Census Sector units as defined above, all units belonging to the strata (State by 4-digit of NIC-04) having less than or equal to 4 units are also considered as Census Sector units.

Remaining units, excluding those of Census Sector, called the sample sector, are covered on sampling basis through an efficient sampling design adopting State X 3 digit industry group as stratum so as to cover all the units in a span of three years. In any stratum, if the number of units was less than 20 , then the entire stratum was enumerated completely along with census factories. In any stratum if the units is between 21 and 60, a minimum sample of size 20 was selected by Circular Systematic Sampling. For all other units a uniform sampling fraction of 1/3 was adopted.

There was no deviation from sample design in ASI 1990-91

Please note that an inflation factor (Multiplier) WGT is available for each unit against records belonging for ASI Summary 1990-91 data. The multiplier is calculated for each stratum (i.e. State X NIC-04 (4 Digit) after adjusting for non-response cases.