This section shows how the SHS data tables have been derived. It then explains the calculations used most frequently to manipulate the data. Users are advised to refer to this section before undertaking their data analysis.
As stated previously, only a subsample of the households is selected to fill out the diary. Therefore, different weights are calculated for the interview questionnaire and for the diary.
5.1 Estimates of number of households
Estimates are generated using two sets of weights; one for the interview and the other for the diary. Adjustments made during weighting ensure that the estimated number of households at the provincial level is the same for both sets of weights for the following domains:
- household sizes of one, two, or three or more persons
- household income groups defined according to provincial quintiles
By default, the estimate of the number of households for any aggregation of these domains is also the same for both sets of weights.
For any other domain, an estimate of the number of households may differ somewhat between the two sets of weights, depending on the reliability of these estimates. The estimated number of households in the SHS tables has been produced using interview weights, as opposed to diary weights. The average household size is also estimated using the interview weights.
The estimated number of households and the average household size of the various domains for which expenditure estimates are produced in CANSIM tables are available in Appendix H.
5.2 Estimates of average expenditure per household
Estimates using both interview and diary expenditure data are produced in two steps: estimates are produced separately from the interview and the diary, and are then added together.
For average expenditure per household, the interview average expenditure per household is calculated using the weighted sum of expenditure data obtained from the interview divided by the sum of the interview weights. Similarly, the diary average expenditure per household is estimated using the weighted sum of expenditure data obtained from the diary divided by the sum of the diary weights. The two components are then added to obtain the average expenditure per household. With this approach, for domains in which the interview and diary estimates do not match, the combined interview and diary average expenditure per household does not exactly match the combined interview and diary weighted sum of expenditure divided by the estimated number of households (produced using the interview weights). Nevertheless, the approach ensures that the sum of the average expenditure per household for all categories equals the total average expenditure per household.
5.3 Examples of expenditure estimates
The tables in this section contain examples of expenditure estimates derived using data from either the interview or the diary, as well as an example of expenditure estimates produced using a combination of interview and diary data.
5.3.1 Examples of expenditure estimates obtained from interview data
The CANSIM tables include estimates of average expenditure per household. The estimated number of households and the average household size are also available at the national, regional and provincial levels. The estimated number of households and the average household size for other domains are not included in these tables but are provided in Appendix H. In this document, we present an example of the estimated number of households in Table 7 associated with estimates of average expenditure per household from Table 8 in order to help in the understanding of the examples in Section 5.4. The estimates in Tables 7 to 12 are based on 2011 data.
Table 7
Estimated number of households based on interview weights, by household tenure
Table summary
This table displays the results of Estimated number of households based on interview weights All households, Owner with mortgage, Owner without mortgage and Renter, calculated using number units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| number |
| Estimated number of households |
13,514,009 |
4,812,813 |
4,219,949 |
4,481,247 |
Table 8
Average household expenditures obtained from interview data, by household tenure
Table summary
This table displays the results of Average household expenditures obtained from interview data All households, Owner with mortgage, Owner without mortgage and Renter, calculated using dollars units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| dollars |
| Shelter |
15,210 |
23,712 |
9,643 |
11,320 |
| Household furnishings and equipment |
2,027 |
2,699 |
2,235 |
1,115 |
| Clothing and accessories |
3,360 |
4,289 |
3,268 |
2,448 |
| Transportation |
11,229 |
14,505 |
12,389 |
6,638 |
5.3.2 Examples of expenditure estimates obtained from diary data
Table 9
Estimated number of households based on diary weights, by household tenure
Table summary
This table displays the results of Estimated number of households based on diary weights All households, Owner with mortgage, Owner without mortgage and Renter, calculated using number units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| number |
| Estimated number of households |
13,514,009 |
4,785,857 |
4,214,778 |
4,513,374 |
Table 10
Average household expenditures obtained from diary data, by household tenure
Table summary
This table displays the results of Average household expenditures obtained from diary data All households, Owner with mortgage, Owner without mortgage and Renter, calculated using dollars units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| dollars |
| Food expenditures |
7,795 |
9,234 |
8,465 |
5,642 |
| Food purchased from stores |
5,588 |
6,583 |
6,053 |
4,098 |
| Food purchased from restaurants |
2,207 |
2,652 |
2,412 |
1,544 |
5.3.3 Examples of estimates obtained from both interview and diary expenditure data
Table 11 shows the estimated number of households and the average household size by household tenure as provided in Appendix H (not available in CANSIM tables), while Table 12 represents a typical example of an average household expenditures table available to users through the SHS CANSIM tables.
Table 11
Estimated number of households and average household size based on interview weights, by household tenure
Table summary
This table displays the results of Estimated number of households and average household size based on interview weights All households, Owner with mortgage, Owner without mortgage and Renter, calculated using number units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| number |
| Estimated number of households |
13,514,009 |
4,812,813 |
4,219,949 |
4,481,247 |
| Average household size |
2.48 |
3.03 |
2.30 |
2.05 |
Table 12
Average household expenditures obtained from interview and diary data, by household tenure
Table summary
This table displays the results of Average household expenditures obtained from interview and diary data All households, Owner with mortgage, Owner without mortgage and Renter, calculated using dollars units of measure (appearing as column headers).
| |
All households |
Owner with mortgage |
Owner without mortgage |
Renter |
| dollars |
| Total expenditure Note 1 |
39,621 |
54,439 |
36,000 |
27,163 |
| Food expenditures |
7,795 |
9,234 |
8,465 |
5,642 |
| Food purchased from stores |
5,588 |
6,583 |
6,053 |
4,098 |
| Food purchased from restaurants |
2,207 |
2,652 |
2,412 |
1,544 |
| Shelter |
15,210 |
23,712 |
9,643 |
11,320 |
| Household furnishings and equipment |
2,027 |
2,699 |
2,235 |
1,115 |
| Clothing and accessories |
3,360 |
4,289 |
3,268 |
2,448 |
| Transportation |
11,229 |
14,505 |
12,389 |
6,638 |
Tables 7 to 10 above are not available to users; however, the following section provides examples on how to produce other estimates using tables such as Tables 11 and 12 above.
5.4 Calculating various estimates using the tables
The following section explains some of the calculation methods most commonly used to manipulate SHS expenditure estimates.
5.4.1 How to calculate average expenditure per person
To calculate average expenditure per person for a given category, divide the average expenditure per household for that category (Table 12) by the average household size (found on the second line of Table 11).
For example, the average food expenditure per person for renter households is calculated as follows:
When analyzing estimates of average expenditure per person, note that household composition (number of children and adults) is a significant factor in many expenditure patterns.
5.4.2 How to calculate percentages of total average household expenditure (budget shares)
To calculate the budget share of an individual expenditure category as a percentage of total average household expenditure, divide the average expenditure per household for that expenditure category by the total average expenditure per household, and then multiply by 100.
For example, using the Table 12, the percentage of total average expenditure per household represented by the average expenditure on food per household, for renter households, is calculated as follows:
5.4.3 Combining expenditure categories into your own groupings
The average expenditure per household for different expenditure categories can be added together to create new subtotals.
For example, the average expenditure on shelter and transportation per renter household is calculated as follows:
5.4.4 Calculating aggregate expenditures
To calculate aggregate expenditures, multiply the average expenditure per household from one column for an expenditure category (Table 12) by the estimated number of households from the same column in Table 11.
For example, the aggregate expenditure on food for renter households is calculated as follows:
Note: Since the average expenditure variable comes from diary data and the estimated number of households in the domains used differs slightly depending on whether it is calculated using interview weights or diary weights, the estimate of aggregate expenditure only approximates the value that would have been obtained using the weighted sum of expenditures. Indeed, if we use the estimated number of households based on the diary weights from Table 9 (which are not available in the CANSIM tables), we could derive the weighted sum of expenditures. We then get:
The estimates of aggregate expenditure are exact for all domains for which the sum of the interview weights and the sum of the diary weights are the same (see Section 5.1), as well as for all variables derived from the interview questionnaire.
5.4.5 Calculating aggregate expenditures by combining data columns
To calculate aggregate expenditures for a given expenditure category for multiple columns, calculate the aggregate expenditure for this category for each of the columns and then add them together.
For example, aggregate expenditure on food by owner households (with or without a mortgage) are calculated as follows:
5.4.6 How to calculate average expenditures per household by combining data columns
To calculate the average expenditure for a given expenditure category for multiple columns, calculate the aggregate expenditure for this category for each of the columns , add them together, and then divide the total by the sum of the estimated number of households in those columns (Table 11).
For example, the average expenditure on food per owner household (with or without a mortgage) is calculated as follows:
5.4.7 Calculating the expenditure share of a subgroup among all households
An expenditure share is the percentage of the aggregate expenditures for a given expenditure category that belongs to a particular subgroup of households (e.g., the percentage of all food expenditures made by renter households).
It is calculated by deriving the household subgroup’s aggregate expenditures for the expenditure category and dividing it by the aggregate expenditure for the expenditure category for all households. The result is then multiplied by 100.
For example, the percentage of food expenditures made by renter households is calculated as follows:
