The sample for the Labour Force Survey (LFS) was designed to provide estimates for indicators labour force participation, unemployment, under employment, persons not in the labour force the national level, for urban and rural areas, and for six regions: Corozal District, Orange Walk District, Belize District, Cayo District, Stann Creek District Toledo District. Disaggregation is also provided by sex, ethnicity and age groups.
The urban and rural areas within each region were identified as the main sampling strata and the sample was selected in two stages.
Within each stratum, twenty-eight census enumeration districts (ED) were selected systematically with probability proportional to size. After a household listing was carried out within the selected enumeration areas, a systematic sample of twenty-five households was drawn in each sample enumeration district. Each ED was visited during the fieldwork period. The sample was stratified by region, urban and rural areas, and is not self-weighting. For reporting national level results, sample weights are used.
Deviations from Sample Design None
Response Rates
Of the 2,800 households selected for the sample, 2,113 were found to be occupied. Of these, 1,986 were successfully interviewed for a household response rate of 94.0 percent. In the interviewed households, 3,972 persons (age 14 and over) were identified. Of these, 3,655 were successfully interviewed, yielding a response rate of 92.0 percent within interviewed households.
Sample Design
Sample Size Calculation
Sample size of 2500 households (HH) for April LFS 2013 was calculated using the indicator, “Female Labour Force Participation rate”. Various indicators were tested and it was observed that the Female Labour Force Participation rate yielded a sample that is representative of Belize’s population.
The calculation took into account the 2010 Census population figures by District and Urban/Rural.
Table 1
Census 2010 population by district, urban/rural
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Population | 41,061 | 45,946 | 95,291 | 75,046 | 34,324 | 30,785 | 322,453 |
| Urban | 10,287 | 13,708 | 68,936 | 37,957 | 9,593 | 5,351 | 145,832 |
| Rural | 30,774 | 32,238 | 26,355 | 37,089 | 24,731 | 25,434 | 176,621 |
Owing to the indicator used, the calculation of Sample Size required the inclusion of the Sub Population, i.e. females of working age population; figures stemming from the results of the 2012 April LFS.
Table 2
Sub-population for females 14 years or older by district
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Sub Population | 14,836 | 15,955 | 36,327 | 26,564 | 11,802 | 9,874 | 115,358 |
Calculation allowed for a ten percent (10%) non-response rate, with an adjustment in the form of a Design Effect (Deff) of 3 for each district.
Additionally, prevalence rates (Female Labour Force Participation Rates) used in the calculation also reflect figures from April LFS 2012 results; while, Average Household Size reflect that found in the 2010 Census.
Table 3
Prevalence of Female Participation Rates and average household sizes by district
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Prevalence | 0.534 | 0.439 | 0.571 | 0.551 | 0.537 | 0.326 | 0.519 |
| Ave. HH Size | 4.4 | 4.4 | 3.5 | 4.4 | 3.8 | 4.7 | 4.1 |
Sample Size, then, was calculated after the error allowed per district was decided upon, along with Population and Average Household Size per district according to the 2010 Census and the Sub Population and Prevalence figures from the April 2012 LFS.
Table 4
Number of households sampled and resulting error predicted by district
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Error | 0.134 | 0.157 | 0.131 | 0.137 | 0.148 | 0.2 | 0.058 |
| Sample Size (HH) | 400 | 400 | 400 | 400 | 400 | 400 | 2500 |
Sample Size (HH) was calculated using: n=4r(1-r)f(1.1)/(e r)^2 p ñ
- r = prevalence
- 1.1 = 10% non-response
- f = design effect
- e = relative margin of error
- p = proportion of total proportion on which indicator is based
- ñ = average household size
- 4 = 95% confidence interval ~= (1.96)^2
A further break down by number of Clusters by Urban/ Rural and number of Households by Urban/Rural was also allowed for by Sample calculation, information needed in Sample Selection of Households.
Table 5
Number of clusters sampled by district and urban/rural areas
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Total Clusters | 16 | 18 | 16 | 16 | 16 | 18 | 100 |
| No. of Urban | 4 | 5 | 12 | 8 | 4 | 3 | 36 |
| No. of Rural | 12 | 13 | 4 | 8 | 12 | 15 | 64 |
a. Total Clusters = Sample Size (HH)/25
25 is the number of HH to be selected from each cluster
b. No. of Urban Clusters = Urban Population/Population x Total Clusters
c. No. of Rural Clusters = Rural Population/Population x Total Clusters
Table 6
Number of households sampled by district and urban/rural areas
| COROZAL | ORANGE WALK | BELIZE | CAYO | STANN CREEK | TOLEDO | COUNTRY | |
|---|---|---|---|---|---|---|---|
| Urban | 100 | 125 | 300 | 200 | 100 | 75 | 900 |
| Rural | 300 | 325 | 100 | 200 | 300 | 375 | 1600 |
a. No. of Urban Households selected = No. of Urban Clusters x 25
b. No of Rural Households selected = No. of Rural Clusters x 25
At the second stage, households were selected within each of the clusters selected at the first stage. A total of 2,500 households were randomly selected in all six districts with 25 households to be sampled within each cluster.
The sample selection was done in a two-step process. First, to select the clusters, the sample frame was prepared from the updated database of visitation records. The sample was stratified using the 12 stratum (Urban/Rural by district). The sample was then designed to have a greater probability of sampling the larger units; thus, the probability proportional to size (PPS) without replacement method was used. The units were then defined as per the outcome in Table 5. The second step in selecting the households was completed using the simple systematic method with unit counts of 25 for each stratum. To draw the sample, a randomly chosen number was used.
Weighting
To obtain population estimates, weights were attributed to each sampling region. First, the sampling regions were determined taking into consideration the district, urban/rural, sex, and age group where:
s = District * 1000 + U/R * 100 + sex * 10 + age group
District: 1 = Corozal, 2 = Orange Walk, 3 = Belize, 4 = Cayo, 5 = Stann Creek, and 6 = Toledo
U/R: 1 = Urban and 2 = Rural
Sex: 1 = Male and 2 = Female
Age group: 1 = 0 to 13
2 = 14 to 24
3 = 25 to 34
4 = 35 to 44
5 = 45 to 54
6 = 55+
Second, the estimate of the population for each sampling region was determined where:
Ps = population assigned to sampling region s obtained from the current mid-month estimate weighted by totals from the 2010 census.
i.e. Ps = E * Rs / C
where E = total population by district, U/R, Sex from the latest mid-month estimates
Rs = total population of sampling region from 2010 census
C = total population by district, U/R, sex from 2010 census
Finally, the weight for each sampling region was determined by:
Ws = Ps/Ns
where Ns = number of sample observations in sample region s.