Note on Sample Design and Estimation Procedure

1.0 Objective of the survey: There are primarily two objectives of PLFS. The first is to measure
the dynamics in labour force participation and employment status in the short time interval of
three months for the urban areas only in the Current Weekly Status (CWS). Thus, in every quarter,
PLFS will bring out the level and change estimates of the key labour force indicators in CWS viz.
Worker Population Ratio (WPR), Labour Force Participation Rate (LFPR), Unemployment Rate
(UR). Secondly, for both rural and urban areas, level estimates of all important parameters in both
usual status and CWS will be brought out annually.

1.1 Outline of the Survey Programme

1.1.1 Geographical coverage of the survey: The survey covers the whole of the Indian Union
except the villages in Andaman and Nicobar Islands which remain extremely difficult to access
throughout the year.

1.2 Schedules of enquiry: Following schedules are canvassed:

Schedule 0.0PL : List of households

Schedule 10.4 : Employment and Unemployment (First Visit)
Schedule 10.4 : Employment and Unemployment (Revisit)

1.3 Sample Design

1.3.1 Rotational scheme for pilot survey:
A rotational panel sampling design has been used in urban areas. The rotational scheme is of two
years duration to accommodate the changes in the urban frame in the intracensal period; in the
sense that the sampling frames for both rural and urban areas will remain unchanged for every
two-year duration. In this rotational panel scheme each selected household in urban areas will be
visited four times – one with first visit schedule and other three with revisit schedule. The
estimates can be given for successive quarters without any break in the series (starting from the
fifth quarter), ensuring a 75% matching between consecutive quarters. The proposed design aims
at generating quarterly estimates of level and change parameters of some important labour force
indicators (LFPR, WPR & UR) based on CWS data in urban areas and annual estimates of level
parameters based on usual status for both rural and urban areas in the line of employment &
unemployment survey of NSS quinquennial round.

1.3.2 Rotational panel design for urban areas

i. The initial rotational panel is for two years, where only 25% FSUs of urban annual
allocation will be covered in the first quarter (Panel P 11 ) with detail listing and canvassing of
visit 1 schedule in the selected households; where P ij indicates the panel belonging to jth
quarter of the ith two-year period of rotation.
 Periodic Labour Force Survey

ii. Another 25% FSUs will be covered in the second quarter (Panel P 12 ) for taking up visit 1
schedule and revisit schedule will be canvassed in the selected households of Panel P 11 .
iii. A new panel P 13 of 25% FSUs will be surveyed in third quarter with visit 1 schedule and
revisit schedules will be canvassed in the households of panels P 11 & P 12 .
iv. In the fourth quarter, households of panels P 11 , P 12 & P 13 will be surveyed with revisit
schedule and a new panel P 14 with 25% FSUs for visit 1 schedule.
v. In the subsequent quarters of second year 75% FSUs (3 panels - P 12 , P 13 & P 14 ) will be
common and an earlier panel (P 11 ) will be replaced by a new panel (P 15 ) for canvassing visit
1 schedule. This will continue till 8th quarter.
vi. All the FSUs of the panels P 11 , P 12 , ...., P 18 (each of which is with 25% of FSUs) will be
selected before commencement of survey in the first quarter.
vii. At the end of the second year of each two-year duration, updated frame will be used for both
rural and urban areas.
viii. FSUs of another set of panels P 21 , P 22 , ..., P 28 selected from the updated frame will be made
ready before commencement of first quarter of third year (first quarter of the second two-
year duration). These panels P 21 to P 28 will take care of the changes in the urban frame
during the intracensal period.
ix. In the ninth quarter (first quarter of the second two-year duration), panel P 21 selected from
the updated frame will be introduced and the panels P 16 , P 17 and P 18 of the old frame will be
surveyed.
x. This scheme will continue for another 2 years with the introduction of panels P 22 to P 28 each
in one quarter for the subsequent 7 quarters till the end of the fourth year (second year of the
two-year period).
xi. This scheme of rotation of panels will enable generation of estimates of change parameters
with 75% matching and 25% of unmatched samples from fifth quarter onwards.
xii. One of the main advantages of this plan of rotation is that there will not be any break in the
series of estimates of the change parameters starting from 5th quarter.
xiii. Since major changes in the rural-urban frame occurs in the Census years (say for the year
2023-24), provision is to be made to generate estimates without break in the series of
estimates considering panels from pre and post-census frames.

1.3.3 Rural samples

For rural areas, samples for all the 8 quarters have been selected before commencement of survey
for each two-year period, while the frame remains same for this duration. In each quarter, only
25% FSUs of annual allocation (as is done in each sub-round of NSS rounds) are being covered in
rural areas so that independent estimates can be generated for each quarter. For this purpose,
quarterly allocation is multiple of 2 for drawing interpenetrating sub-samples.

There will not be any revisit in the rural samples.

2
Note on sample design and estimation procedure
 Periodic Labour Force Survey

1.3.4 The following table gives the rotational panel schemes in tabular format:

panels from updated frame

panels for the first 2 year period
for the next 2 year period
During the four quarters During the four quarters of During the four quarters of
of the first year the second year the third year
Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4
P 11 * P 11 P 11 P 11 P 15 * P 15 P 15 P 15 P 21 * P 21 P 21 P 21
P 12 P 12 P 12 P 16 P 16 P 16 P 22 P 22
Urban P 12 * P 16 * P 22 *
Panel P 13 P 13 P 13 P 17 P 17 P 17 P 23
P 13 * P 17 * P 23 *
P 14 P 14 P 14 P 18 P 18 P 18
P 14 * P 18 * P 24 *
Fresh rural samples in
Rural R 11 * R 12 * R 13 * R 14 * R 15 * R 16 * R 17 * R 18 * third year from the updated
frame
*Visit 1 schedule will be canvassed
R ij * indicates samples to be covered in rural areas in jth quarter of ith two-year period

1.3.5 It is seen from the above table that one panel of urban sample FSUs will be in the sample for
4 quarters and the selected households in an FSU will be surveyed for the successive periods
during which the FSU remains in the sample. Selected households will be visited 4 times for
canvassing the detailed schedule of enquiry of the PLFS (Schedule 10.4: Employment and
Unemployment). These visits are termed as first visit and revisit. For this, two formats of the
detailed schedule of enquiry have been devised viz., Schedule 10.4: Employment and
Unemployment (First Visit) and Schedule 10.4: Employment and Unemployment (Revisit).

To implement the rotational scheme in urban areas, when a panel appears for the first time in any
quarter with 25% of annual allocation, listing and selection of households will be done in all the
selected FSUs in that panel. The first visit schedule will be canvassed in the selected households.
The selected FSUs/households will be revisited in the subsequent three quarters as the panel will
remain in the sample for four quarters. During the revisit, listing and selection of households
will not be done afresh. Only the households selected during first visit will be revisited for
canvassing revisit schedule. At the time of revisit if any sample household is not found, same may
be treated as casualty and a substitute household need not be surveyed. If any sample household is
found to have split, then, among the split households available in the FSU/Sub-block, the
household where the head/senior most member of the erstwhile household is available will be
covered. In the PLFS scheme, each selected household of urban FSUs only will be visited four
times, one in each quarter.

1.3.6 Outline of the design: A stratified multi-stage design has been adopted. The first stage units
(FSU) are the Urban Frame Survey (UFS) blocks in urban areas and 2011 Population Census
villages (Panchayat wards for Kerala) in rural areas. The ultimate stage units (USU) are
households. As in usual NSS rounds, in the case of large FSUs one intermediate stage unit, called
hamlet group/sub-block, will be formed.

3
Note on sample design and estimation procedure
Periodic Labour Force Survey

1.3.7 Sampling Frame for First Stage Units: The list of latest available Urban Frame Survey
(UFS) blocks is considered as the urban sampling frame. List of 2011 Population Census villages
(Panchayat wards for Kerala) constitutes the rural sampling frame. Since the duration of rotational
panel is of two-year, the urban sampling frame once updated incorporating the changes made in
the current phase of UFS will remain unchanged for two years. Similarly the rural sampling frame
with changes, if any, for urbanisation of village(s) will remain unchanged for two years. After
completion of every two-year period, the frames will be updated for incorporating the changes
likely to occur during this period. When next Population Census details will be available, the new
frame will be used only when UFS blocks for all newly declared Census Towns and Statutory
Towns are available for preparation of sampling frame, as the new list of census villages will not
include those villages which will be considered as urban areas.

1.3.8 Stratification: In urban areas strata have been formed within each NSS region on the basis
of size class of towns as per Population Census 2011. The stratum numbers and their composition
(within each region) are as follows:

stratum 1 : all towns with population less than 50,000

stratum 2 : all towns with population 50,000 or more but less than 3 lakhs
stratum 3 : all towns with population 3 lakhs or more but less than 15
lakhs
stratum 4, 5, 6,... : each city with population 15 lakhs or more

The rural areas of each NSS region constitute rural stratum. In case of rural sectors of Nagaland, a
special stratum will be formed within the State consisting of all the villages which are difficult to
access.

1.3.9.1 Sub-Stratification: Urban: In urban areas there is no sub-stratification.

1.3.9.2 Rural: ‘r/8’ sub-strata have been formed in each rural stratum, if ‘r’ is the annual sample
size allocated for a rural stratum. The villages within a stratum as per frame are first arranged in
ascending order of population. Then sub-strata 1 to ‘r/8’ are demarcated in such a way that each
sub-stratum comprised a group of villages of the arranged frame and have more or less equal
population.

1.3.10 Total sample size (FSUs): 12800 FSUs (7024 villages and 5776 UFS blocks) are being
covered annually at all-India level.

1.3.10.1 State/UT level sample size will be allocated between two sectors in proportion to
population as per Census 2011 with double weightage to urban sector in general. Within each
sector of a State/UT, the respective sample size has been allocated to the different strata (in the
case of urban areas) and strata/ sub-strata (in the case of rural areas) in proportion to the
population as per Census 2011. Urban allocations at stratum level have been adjusted to multiples
of 8 with a minimum sample size of 8 (for 4 panels, each of size multiple of 2). Rural allocation
for each stratum is also multiple of 8 with minimum sample size of 8 (for 4 quarters, each of size

4
Note on sample design and estimation procedure
 Periodic Labour Force Survey

2). For special stratum formed in rural areas of Nagaland as discussed in para 1.3.8, 16 FSUs will
be allocated.

1.3.10.2 It may be noted that quarterly allocation of FSUs is same for an NSS state-region although
25% of the urban FSUs rotate over the quarters according to the rotational scheme. However,
quarterly allocation of urban FSUs for FOD regions and FOD sub-regions may vary over the
quarters since new FSUs entering the sample according to the rotational scheme may or may not
belong to the same FOD region or FOD sub-region.

1.3.11 Selection of first stage units: Urban FSUs are selected by probability proportional to size
with replacement (PPSWR) scheme, size being the number of households in the UFS block.
Samples for a panel within each stratum are drawn in the form of two independent sub-samples.
To implement the rotational scheme, 4 groups of sample FSUs of equal size (each multiple of size
2, half for each of sub-sample 1 and sub-sample 2) are drawn randomly. In the rural areas, samples
for a stratum/sub-stratum are drawn randomly in the form of two independent sub-samples with
probability proportional to size with replacement (PPSWR) scheme, size being the population of
the village and equal number of samples are allocated among the four quarters.

1.3.12 Criterion for hamlet-group/ sub-block formation: After identification of the boundaries
of the FSU, it is to be determined whether listing is to be done in the whole sample FSU or not. In
case the population of the selected FSU is found to be 1200 or more, it is to be divided into a
suitable number (say, D) of ‘hamlet-groups’ in the rural sector and ‘sub-blocks’ in the urban sector
by more or less equalising the population as stated below.

approximate present population of the sample FSU no. of hg’s/sb’s to be formed

less than 1200 (no hamlet-groups/sub-blocks) 1
1200 to 1799 3
1800 to 2399 4
2400 to 2999 5
3000 to 3599 6
…………..and so on

For rural areas of Himachal Pradesh, Sikkim, Andaman & Nicobar Islands, Uttarakhand (except
four districts Dehradun, Nainital, Hardwar and Udham Singh Nagar), Punch, Rajouri, Udhampur,
Reasi, Doda, Kishtwar, Ramban, Leh (Ladakh), Kargil districts of Jammu and Kashmir and Idukki
district of Kerala, the number of hamlet-groups to be formed as follows:
approximate present population of the sample village no. of hg’s to be formed

less than 600 (no hamlet-groups) 1

600 to 899 3
900 to 1199 4
1200 to 1499 5
1500 to 1799 6
.………..and so on

5
Note on sample design and estimation procedure
Periodic Labour Force Survey

1.3.13 Formation and selection of hamlet-groups/ sub-blocks: In case hamlet-groups/ sub-

blocks are to be formed in the sample FSU, the same will be done by more or less equalizing
population. Two hamlet-groups (hg)/ sub-blocks (sb) are to be selected from a large FSU wherever
hamlet-groups/ sub-blocks will be formed in the following manner – one hg/ sb with maximum
percentage share of population will always be selected and termed as hg/ sb ‘1’; one more hg/ sb
will be selected from the remaining hg’s/ sb’s by simple random sampling (SRS) and will be
termed as hg/ sb ‘2’. Listing and selection of the households will be done independently in the two
selected hamlet-groups/ sub-blocks. The FSUs without hg/ sb formation will be treated as sample
hg/ sb number ‘1’. It is to be noted that if more than one hg/ sb are found to have same maximum
percentage share of population, the one among them which listed first will be treated as hg/ sb ‘1’.

Listing and selection of the households is to be done independently in the two selected hg’s/sb’s.

1.3.14 Formation of second stage strata and allocation of households:

1.3.14.1 Second stage stratification (SSS) in each FSU/hg/sb is to be done based on the number of
members in each household who have completed secondary level of education considering general
type of education. In urban FSUs 4 SSS while in rural FSUs 3 SSS are to be formed in rural areas.
Details are given in the following table.

number of households to be
surveyed
number of
composition of SSS (rural) SSS FSU with hg
members FSU without
formation
hg formation
(for each hg)

number of members in the SSS 1 2 or more 2 1

household having level of general
SSS 2 1 4 2
education as secondary (10th
standard) or above SSS 3 0 2 1
TOTAL 8
number of households to be
surveyed
number of
composition of SSS (urban) SSS FSU with sb
members FSU without
formation
sb formation
(for each sb)

SSS 1 3 or more 2 1
number of members in the
household having level of general SSS 2 2 2 1
education as secondary (10th
SSS 3 1 2 1
standard) or above
SSS 4 0 2 1
TOTAL 8

6
Note on sample design and estimation procedure
 Periodic Labour Force Survey

1.3.15 Selection of households: From each SSS the sample households are to be selected by
SRSWOR.

7
Note on sample design and estimation procedure
Periodic Labour Force Survey

2. Estimation Procedure

2.1 Subscripts
s = subscript for s-th stratum
t = subscript for t-th sub-stratum (for rural only)
r = panel number (for urban only)
m = subscript for sub-sample (m =1, 2)
i = subscript for i-th FSU [village (panchayat ward)/ block]
d = subscript for a hamlet-group/ sub-block (d = 1, 2)
j = subscript for j-th second stage stratum in an FSU/ hg/sb [ j = 1, 2, 3 (for rural) or 1, 2, 3, 4 (for
urban)]
k = subscript for k-th sample household under a particular second stage stratum within an FSU/
hg/sb
D = total number of hg’s/ sb’s formed in the sample FSU
D* = 0 if D = 1
= (D – 1) for FSUs with D > 1
Z = total size of a rural/urban stratum/sub-stratum (= sum of sizes for all the FSUs of a
stratum/sub-stratum)
z = size of sample village/UFS block used for selection
n = number of sample FSUs surveyed including ‘uninhabitated’ and ‘zero cases’ but excluding
casualty for a particular sub-sample and stratum/sub-stratum/panel
H = total number of households listed in a second-stage stratum of an FSU / hamlet-group or sub-
block of sample FSU
h = number of households surveyed in a second-stage stratum of an FSU / hamlet-group or sub-
block of sample FSU
x, y = observed value of characteristics x, y under estimation
X̂ , Yˆ = estimate of population total X, Y for the characteristics x, y

Under the above symbols,

y srmidjk = observed value of the characteristic y for the kth household in the jth second stage stratum
of the dth hg/ sb (d = 1, 2) of the ith urban FSU belonging to the mth sub-sample of the rth panel of
sth stratum
y stmidjk = observed value of the characteristic y for the kth household in the jth second stage stratum
of the dth hg/ sb (d = 1, 2) of the ith rural FSU belonging to the mth sub-sample of the tth sub-
stratum of sth stratum

However, for ease of understanding, a few subscripts have been suppressed in following
paragraphs where they are obvious.

8
Note on sample design and estimation procedure
 Periodic Labour Force Survey

3. Formulae for Quarterly Estimates of Aggregates for a particular stratum × panel × sub-
sample of the urban sector from Schedule 10.4:

3.1 The estimate for a stratum × panel × sub-sample may be obtained as follows:
Zs nsrm
1 4 H srmi1 j hsrmi1 j 4 H srmi 2 j hsrmi 2 j
Yˆsrm =
n srm
∑z [ ∑ h
i =1 j =1
∑y k =1
srmi1 jk +D *
srmi ∑h
j =1
∑y
k =1
srmi 2 jk ]
srmi srmi1 j srmi 2 j

3.2 The estimate for aggregates for a particular stratum × panel based on two sub-samples may
be obtained as:

ˆ 1 2 ˆ
Ysr = ∑ Ysrm
2 m =1

3.3 The estimate for aggregates for a particular stratum based on ‘r’ panels and two sub-samples
may be obtained as:
1
Yˆs = ∑ Yˆsr , r = 1, 2, 3, 4
r r
( r will be ‘4’ from fourth quarter and r may be less than ‘4’ till third quarter)

3.4 From fourth quarter onwards, estimate for aggregates for a particular stratum based on all the 4
panels and two sub-samples may be generated as:

1 4
Yˆs = ∑ Yˆsr
4 r =1

3.5 Estimate of an aggregate character for a State may be obtained by summing the stratum
estimates as follows:

Yˆ = ∑ Yˆs
s

3.6 Let Yˆ and X̂ be the estimates of the aggregates Y and X for two characteristics y and x
Y
respectively at the State/ UT/ all-India level. Estimate of a ratio R = at State level may be
X
Yˆ
obtained as the ratio of aggregates of two characters at State levels: Rˆ =
Xˆ
3.7 The estimates of change over the quarters will be measured by the simple difference between
the estimates of aggregates or ratios of the corresponding quarters.

9
Note on sample design and estimation procedure
Periodic Labour Force Survey

3.8 Estimates of Error: The estimated variances of the above estimates will be as follows:

3.8.1 For aggregate Yˆ :

() 1  1 4
( )
4
Varˆ Yˆ = ∑ ∑Varˆ Yˆsr  = ∑ ∑Varˆ Yˆsr where
s r =1  4  16 r =1 s
( ) 1
( )
Varˆ Yˆsr = Yˆsr1 − Yˆsr 2 , where Yˆsr1 and Yˆsr 2 are the estimates for sub-sample 1
4
2

and sub-sample 2 respectively for stratum ‘s’ and panel ‘r’.

3.8.2 For ratio R̂ :

∑ (Yˆ ) ( ) ( )( )
1
− Yˆs 2 + Rˆ 2 Xˆ s1 − Xˆ s 2 − 2 Rˆ Yˆs1 − Yˆs 2 Xˆ s1 − Xˆ s 2 
2 2
MSˆE ( Rˆ ) =
4 Xˆ 2 s
s1 

1 4 1 4
where Yˆs1 = ∑ Yˆsr1 and Yˆs 2 = ∑ Yˆsr 2 ;
4 r =1 4 r =1

1 4 1 4
Xˆ s1 = ∑ Xˆ sr1 and Xˆ s 2 = ∑ Xˆ sr 2
4 r =1 4 r =1

3.9 Estimates of Relative Standard Error (RSE):

Vaˆr Yˆ ( )
( )
RSˆE Yˆ =
Yˆ
× 100

MSˆE Rˆ ( )
( )
RSˆE Rˆ =
Rˆ
× 100

3.10 For urban samples, multipliers for panel ‘r’ will be as follows:

sch. sector formula for multipliers

segment 1 segment 2
Zs 1 H srmi1 j Zs 1 H
10.4 urban × × × × Dsrmi
*
× srmi 2 j
nsrm z srmi hsrmi1 j nsrm z srmi hsrmi 2 j
j = 1, 2, 3, 4

10
Note on sample design and estimation procedure
 Periodic Labour Force Survey

4. Formulae for Annual Estimates of Aggregates for a particular sub-sample and stratum ×
sub-stratum in the rural/urban sector from Schedule 10.4:

4.1 For rural:

4.1.1 For rural areas, annual estimates of aggregates may be obtained from the data collected in
four quarters.

(i) For jth second-stage stratum of a stratum × sub-stratum, for a particular sub-sample:

Z st nj 1  H stmi1 j H stmi 2 j 
hstmi1 j hstmi 2 j
ˆ
Ystmj = ∑  ∑y +D *
× ∑y 
stmi1 jk stmi stmi 2 jk
n j i =1 z stmi  hstmi1 j k =1 hstmi 2 j k =1 

(ii) For all second-stage strata combined:

Yˆstm = ∑ Yˆjstm
j

4.1.2 Estimate for aggregates for a sub-stratum:

Estimate for aggregates for a sub-stratum ( Ŷst ) based on two sub-samples in a sub-stratum is
obtained as:

1 2
Yˆst = ∑ Yˆstm
2 m =1

4.1.3 Estimate for aggregates for a stratum:

Estimate for a stratum ( Yˆs ) will be obtained as

Yˆs = ∑ Yˆst
t

4.1.4 Estimate of Aggregates at State/UT/all-India level:

The estimate Yˆ at the State/ UT/ all-India level is obtained by summing the stratum estimates
Yˆs over all strata belonging to the State/ UT/ all-India.

4.1.5 Estimates of Ratios:

Let Yˆ and X̂ be the estimates of the aggregates Y and X for two characteristics y and x
respectively at the State/ UT/ all-India level.

Y Yˆ
Then the combined ratio estimate (Rˆ ) of the ratio ( R = ) will be obtained as Rˆ =
X Xˆ

11
Note on sample design and estimation procedure
Periodic Labour Force Survey

4.1.6 Estimates of Error: The estimated variances of the above estimates will be as follows:

4.1.6.1 For aggregate Yˆ :

Vaˆr (Yˆ ) = ∑ Vaˆr (Yˆs ) = ∑∑ Vaˆr (Yˆst ) where Vaˆr (Yˆst ) is given by
s s t

( ) ( 1 2
)
Varˆ Yˆst = Yˆst1 − Yˆst 2 , where Yˆst1 and Yˆst 2 are the estimates for sub-sample 1 and sub-
4
sample 2 respectively for stratum ‘s’ and sub-stratum ‘t’.

4.1.6.2 For ratio R̂ :

MSˆE ( Rˆ ) =
1
∑∑
4 Xˆ s t 
2 st1 (st 2 st1) st 2 (
 Yˆ − Yˆ 2 + Rˆ 2 Xˆ − Xˆ 2 − 2 Rˆ Yˆ − Yˆ Xˆ − Xˆ 
st1 st 2 st1 )
st 2 

( )( )
4.1.6.3 Estimates of Relative Standard Error (RSE):

( )
RSˆE Yˆ =
Vaˆ r Yˆ ( )
× 100
Yˆ

( )
RSˆE Rˆ =
MSˆE Rˆ ( )
× 100
Rˆ

4.2 For urban:

4.2.1 Considering first visit schedules for each of the four panels of four quarters, annual estimates
of aggregates for a particular sub-sample and stratum may be obtained for urban areas. For
rural areas, annual estimates of aggregates may be obtained from the data collected in four
quarters.

(i) For jth second-stage stratum of a stratum, for a particular sub-sample:

Z s nj 1  H smi1 j H smi 2 j 
hsmi1 j hsmi 2 j
ˆ
Ysmj = ∑  ∑ ysmi1 jk + D *
× ∑ y
smi smi 2 jk 
n j i =1 z smi  hsmi1 j k =1 hsmi 2 j k =1 

(ii) For all second-stage strata combined:

Yˆsm = ∑ Yˆjsm
j

4.2.2 Estimate for Aggregates for a stratum:

Estimate for aggregates for a stratum ( Yˆs ) based on two sub-samples in a stratum is obtained as:

1 2
Yˆs = ∑ Yˆsm
2 m =1

12
Note on sample design and estimation procedure
 Periodic Labour Force Survey

4.2.3 Estimate of Aggregates at State/UT/all-India level:

The estimate Yˆ at the State/ UT/ all-India level is obtained by summing the stratum estimates
Yˆs over all strata belonging to the State/ UT/ all-India.

4.2.4 Estimates of Ratios:

Let Yˆ and X̂ be the estimates of the aggregates Y and X for two characteristics y and x
respectively at the State/ UT/ all-India level.

Y Yˆ
Then the combined ratio estimate (Rˆ ) of the ratio ( R = ) will be obtained as Rˆ =
X Xˆ

4.2.5 Estimates of Error: The estimated variances of the above estimates will be as follows:

4.2.5.1 For aggregate Yˆ :

Vaˆr (Yˆ ) = ∑Vaˆr (Yˆs ) where Vaˆr (Yˆs ) is given by
s

( ) (
1 2
)
Varˆ Yˆs = Yˆs1 − Yˆs 2 , where Yˆs1 and Yˆs 2 are the estimates for sub-sample 1 and sub-sample 2
4
respectively for stratum ‘s’.

4.2.5.2 For ratio R̂ :

∑ [(Yˆ ]
1
MSˆE ( Rˆ ) = − Yˆs 2 ) 2 + Rˆ 2 ( Xˆ s1 − Xˆ s 2 ) 2 − 2 Rˆ (Yˆs1 − Yˆs 2 )( Xˆ s1 − Xˆ s 2 )
4 Xˆ 2
s1
s

4.2.5.3 Estimates of Relative Standard Error (RSE):

( )
RSˆE Yˆ =
Vaˆ r Yˆ ( )
× 100
Yˆ

( )
RSˆE Rˆ =
MSˆE Rˆ ( )
× 100
Rˆ

13
Note on sample design and estimation procedure
Periodic Labour Force Survey

5. Multipliers:

The formulae for multipliers at stratum/sub-stratum/second-stage stratum level for a sub-sample

are given below:

formula for multipliers

schedule sector
hg / sb 1 hg / sb 2
Z st 1 H Z st 1 H
rural × × stmi1 j × × Dstmi
*
× stmi 2 j
nstmj zstmi hstmi1 j nstmj z stmi hstmi 2 j
j = 1, 2, 3 for rural
10.4
Zs 1 H smi1 j Zs 1 *
H smi 2 j
urban × × × × Dsmi ×
nsmj z smi hsmi1 j nsmj z smi hsmi 2 j
j = 1, 2, 3, 4 for urban

Note:
(i) For estimating any characteristic for any domain not specifically considered in sample
design, indicator variable may be used.
(ii) Multipliers have to be computed on the basis of information available in the listing
schedule irrespective of any misclassification observed between the listing schedule
and detailed enquiry schedule.

6. Treatment for zero cases, casualty cases etc.:

6.1 While counting the number of FSUs surveyed (n sm or n stm ) in a stratum/sub-stratum, all the
FSUs with survey codes 1 to 6 in Schedule 0.0PL will be considered. In addition, if no SSU is
available in the frame for Schedule 10.4, then also that FSU will be treated as surveyed in respect
of that schedule. However, if SSUs are available in the frame of the FSU but none of these could
be surveyed then that FSU has to be treated as casualty and it will not be treated as surveyed in
respect of Schedule 10.4.

6.2 Casualty cases: FSUs with survey code 7 as per Schedule 0.0PL are treated as casualties. In
addition to this, an FSU, although surveyed, may have to be treated as casualty for Schedule 10.4
and a particular second stage stratum as given in the following para:

6.2.1 FSUs with survey codes 1 or 4 as per Schedule 0.0PL having number of households in the
frame of jth second stage stratum greater than 0 but number of households surveyed according to
data file, considering both hg/sb together, as nil (i.e. H i1j + H i2j >0 but h i1j + h i2j =0) will be taken
as casualties for jth second stage stratum.

All the FSUs with survey codes 1 to 6 as per Schedule 0.0PL minus the number of casualties as
identified above will be taken as the number of surveyed FSUs (n stmj ) for that (stratum/sub-
stratum) ×( second stage stratum).

14
Note on sample design and estimation procedure
 Periodic Labour Force Survey

When casualty for jth second stage stratum occurs for a particular hg/sb but not for the other hg/sb,
the FSU will not be treated as casualty but some adjustments in the value of H for the other hg/sb
will be done as follows:

(i) Suppose for hg/sb 1, H i1j > 0 but h i1j = 0 while for hg/sb 2, H i2j > 0 and h i2j > 0. In that
case Di* × H i 2 j will be replaced by ( H i1 j + Di × H i 2 j ) in the formula for multiplier of
*

hg/sb 2.

(ii) Suppose for hg/sb 1, H i1j >0 and h i1j > 0 while for hg/sb 2, H i2j >0 but h i2j =0. In that case
H i1 j will be replaced by ( H i1 j + Di* × H i 2 j ) in the formula for multiplier of hg/sb 1.

It may be noted that n smj or n stmj would be same for segment 1 & 2 of an FSU.

7. Treatment in cases of void second-stage strata/sub-strata /strata at FSU or household

level:

7.1 A stratum/sub-stratum may be void because of the casualty of all the FSUs belonging to the
stratum/sub-stratum. This may occur in one sub-sample or in both the sub-samples. If it relates to
only one sub-sample, then estimate for the void stratum/sub-stratum may be replaced with the
estimate as obtained from the other sub-sample for the same stratum/sub-stratum.

7.2 When a stratum/sub-stratum is void in both the sub-samples, the following procedure is
recommended:
Case (I): Stratum/Sub-stratum void cases at FSU levels (i.e. all FSUs having survey code 7):
(i) If a rural/urban sub-stratum is void then it may be merged with the other sub-stratum of
the stratum.
(ii) If a rural/urban stratum is void due to all FSUs being casualty, it may be excluded from
the coverage of the survey. The state level estimates will be based on the estimates of
districts for which estimates are available and remarks to that effect may be added in
appropriate places.

Case (II): Stratum/Sub-stratum void case at second stage stratum level (i.e. all the FSUs were
casualties for a particular second stage stratum):

An FSU may be a casualty for a particular second stage stratum although survey code was not 7.
If all the FSUs of a stratum/sub-stratum become casualties in this manner for a particular second
stage stratum, the stratum/sub-stratum will become void. In such cases, the void second stage
stratum will be merged with the nearby second stage stratum within the FSU.

15
Note on sample design and estimation procedure
Periodic Labour Force Survey

8. Reference to the values of Z st , n s, z sti , D sti , D* sti , D si , D* si , H sti1j , h sti1j , H sti2j , h sti2j:

(a) Values of Z st and the number of FSUs allotted for the whole round are given in Appendix
Table 2 for rural sector and in Appendix Table 3 for urban sector.
(b) Surveyed number of FSUs (n st ) should not be taken from the tables. The value of n stm for
each sub-sample is to be obtained following the guidelines given in para 6 above. It
includes uninhibited and zero cases but excludes casualty cases.
(c) The value of z sti for the samples selected by PPS is to be taken from the column of sample
list under the heading ‘frame population’ for rural samples and ‘block size’ i.e. total
number of households in each UFS block for urban samples.
(d) Value of D sti is to be taken from item 14 of Block 1, Schedule 0.0PL. D* sti is to be
calculated from the value of D sti .
(e) Values of H sti1j , H sti2j are to be taken from column (5), Block 6 of Schedule 0.0PL for
respective segment and second-stage stratum.
(f) The value of h sti1j and h sti2j should not be taken from column (9), Block 6 of Schedule
0.0PL. The figures should be obtained by counting the number of households available in
the data file excluding the casualty households.

16
Note on sample design and estimation procedure
 Periodic Labour Force Survey

Table 1: allocation of sample villages and blocks for PLFS

number of sample villages/blocks
State/UT
total rural urban
(1) (2) (3) (4)
ANDHRA PRADESH 496 272 224
ARUNACHAL PRADESH 216 136 80
ASSAM 440 328 112
BIHAR 568 400 168
CHHATTISGARH 280 176 104

GOA 56 24 32
GUJARAT 440 208 232
HARYANA 328 168 160
HIMACHAL PRADESH 256 208 48
JAMMU & KASHMIR 424 240 184
JHARKHAND 344 208 136
KARNATAKA 520 224 296
KERALA 568 264 304
MADHYA PRADESH 584 336 248
MAHARASHTRA 1008 448 560
MANIPUR 320 160 160
MEGHALAYA 160 104 56
MIZORAM 192 64 128
NAGALAND 128 72 56
ODISHA 496 360 136

PUNJAB 400 192 208

RAJASTHAN 528 312 216
SIKKIM 96 56 40
TAMIL NADU 832 392 440
TELANGANA 360 160 200

TRIPURA 232 152 80

UTTAR PRADESH 1136 728 408
UTTARAKHAND 216 120 96
WEST BENGAL 800 424 376
A & N ISLANDS 64 32 32
CHANDIGARH 48 8 40
D & N HAVELI 24 8 16
DAMAN & DIU 16 8 8
DELHI 128 8 120
LAKSHADWEEP 24 8 16
PUDUCHERRY 72 16 56
ALL- INDIA 12800 7024 5776

17
Note on sample design and estimation procedure