Methodology | Pakistan Bureau of Statistics

1.1 Background

Pakistan Bureau of Statistics has been carrying out Labour Force Survey (LFS) since 1963. The questionnaire and methodology of the survey have been undergoing pertinent improvements through the forum of “Panel on Labour Statistics” comprising all important stakeholders to keep current with best practices. The questionnaire was revised in 1990 to include probing questions on marginal economic activities, likely to be carried out mostly by women and tend to go unrecorded with conventional questions. The questionnaire was further improved in 1995 to reckon with the size and composition of migration and informal sector. The scope of the survey was extended in 2001-02 to take the stock of occupational safety and health of employed persons. The questionnaire was further articulated for undertaking 1st quarterly LFS 2005-06. This practice has since been continuing. Last meeting of the Panel was held to review the questionnaire and methodology of the LFS 2020-21 and included disability module and labour underutilization questions.

This report presents annual results of LFS 2020-21. The survey’s sample size comprises of 99,904 households divided up into four distinct quarterly representatives at National level with urban rural breakdown.

1.2 Objectives

The major aim of the survey is to collect a set of comprehensive statistics on the various dimensions of country’s civilian labour force as a means to pave the way for skill development, planning, employment generation, assessing the role and importance of the informal sector and, sizing up the volume, characteristics and contours of employment. The broad objectives of the survey are as follows:

To collect data on the socio-demographic characteristics of the total population i.e. age, sex, marital status, level of education, current enrolment and migration etc;
To acquire current information on the dimensions of national labour force; i.e. number of persons employed, unemployed, and underemployed or out of labour market;
To gather descriptive facts on the engagement in major occupational trades and the nature of work undertaken by the institutions/organizations;
To profile statistics on employment status of the individuals, i.e. whether they are employers, own account workers, contributing family workers or paid employees (regular/casual);
To classify non-agricultural enterprises employing household member(s) as formal and informal;
To quantify the hours worked at main/subsidiary occupations;
To provide data on wages and mode of payment for paid employees;
To make an assessment of occupational health and safety of employed persons by causes, type of treatment, conditions that caused the accident/injury and time of recovery; and
To collect data on the characteristics of unemployed persons i.e. age, sex, level of education, previous experience if any, occupation, industry, employment status related to previous job, waiting time invested in the quest for work, their availability for work and expectations for future employment.

1.3 Field Operation

PBS is the national statistical organization responsible for collection, processing, compilation and dissemination of statistics. It has 34 Regional/Field Offices located all over Pakistan. These offices are equipped and manned with regular and trained field staff for the collection of data from the field.

In order to evolve dynamics of field enumeration in line with the survey’s objectives, training is imparted to the concerned staff on interviewing techniques and other procedure to be used in the enumeration. For quality control, supervisors from Regional/Field Offices and headquarter, make frequent field visits to keep the collection process on track.

1.4 Reference Period

Reference period is past week i.e. seven days before the date of enumeration.

1.5 Data Processing and Editing

Soon after data collection, the supervisors edit, check and clean the filled-in questionnaires manually for consistency and completeness and refer back to field where necessary. Editing and coding is carried out by Regional/Field offices, while checking is done at headquarter by the subject matter section. Computer edit checks are applied to get even with errors identified at the stage of data entry. The relevant numerical techniques are used to eliminate erroneous data resulting from mistakes made during coding. The survey records are further edited and rectified through a series of computer processing stages.

1.6 Sampling Plan

Universe: The universe for Labour Force Survey consists of all urban and rural areas of the four provinces of Pakistan and Islamabad excluding military restricted areas. The population of excluded areas constitutes about 1% of the total population.

1.7 Sample Design

A stratified two-stage sample design is adopted for the survey.

1.8 Sampling Frame

Pakistan Bureau of Statistics (PBS) has developed its own sampling frame for both urban and rural domains. Each city/town is divided into enumeration blocks. Each enumeration block is comprised of 200 to 250 households on the average with well-defined boundaries and maps. The frame used in this survey was the most recent frame which is updated through Population and Housing Census 2017.

1.9 Stratification Plan

1.9.1 Rural Domain: Each administrative district in the Punjab, Sindh and Khyber Pakhtunkhawa (KP) is considered an independent stratum whereas in Balochistan, each administrative division constitutes a stratum.

1.9.2 Urban Domain: All administrative divisions in the four provinces, constitutes separate stratum.

1.9.3 Selection of primary sampling units (PSUs)
Enumeration blocks in both Urban and Rural domains are taken as Primary Sampling Units (PSUs). Sample PSUs from each ultimate stratum/sub-stratum are selected with probability proportional to size (PPS) method of sampling scheme. In both Urban and Rural domains, the number of households in an enumeration blocks considered as measure of size.

1.9.4 Selection of secondary sampling units (SSUs)
The listed households of sample PSUs are taken as Secondary Sampling Units (SSUs). A specified number of households i.e. 12 from each urban sample PSU and 16 from rural sample PSU are selected with equal probability using systematic sampling technique with a random start.

1.10 Sample Size and Its Allocation

A sample of 99,904 households is considered appropriate to provide reliable estimates of key labour force characteristics at National/Provincial level with Urban and Rural breakup. The entire sample of households (SSUs) is drawn from 6808 Primary Sampling Units (PSUs) out of which 4552 are rural and 2256 are urban. The overall sample has been distributed evenly over four quarters independently. The distribution of sample PSUs and SSUs in the urban and rural domains of the four provinces is as under: -

Table 1.1 Distribution of Sample Size by Province

Province/Area	Sample Enumeration Blocks (PSUs)			Sample Households (SSUs)
Province/Area	Rural	Urban	Total	Rural	Urban	Total
Khyber Pakhtunkhawa	976	180	1156	15616	2160	17776
Punjab	2004	936	2940	32064	11232	43296
Sindh	872	948	1820	13952	11376	25328
Balochistan	700	192	892	11200	2304	13504
Pakistan	4552	2256	6808	72832	27072	99904

1.11 Method of Data Collection

Data are collected by direct interview method. Generally, the head of household is chosen to provide information about all members of the household. In case of his/her non-availability at the time of interview, some other informed member of the household down the line is interviewed. The total sample for the year is evenly distributed for enumeration on quarterly basis to offset the effect of seasonal variations. The information collected however relates to the week preceding the date of enumeration.

1.12 Coverage

The survey covers all urban and rural areas of the four provinces of Pakistan and Islamabad and military restricted areas. The population of excluded areas constitutes about 2% of the total population.

All sample enumeration blocks in urban areas and mouzas/dehs/villages in rural areas were enumerated except 3462 households which were not covered due to non-contact or refusal cases in urban and rural areas. However, the number of sample households (96,442) enumerated as compared to total sample size (99,904) is high as response rate is (96.53%). Province-wise detail of dropped sample areas (PSUs) are shown as under:

Table 1.2 Detail of Dropped Enumeration Blocks/ Households

Province/Area	Sample Enumeration Blocks (PSUs)			Sample Households (SSUs)
Province/Area	Rural	Urban	Total	Rural	Urban	Total
Khyber Pakhtunkhawa	14	2	16	424	90	514
Punjab	-	-	-	362	390	752
Sindh	-	-	-	137	700	837
Balochistan	32	5	37	1120	239	1359
Pakistan	46	7	53	2043	1419	3462