Guide For
Cross-Sectional Public-Use Microdata File
Survey of Labour and Income
Dynamics (SLID)
Reference Year 1999
Table of Contents
3. USING THE RECORD LAYOUTS, DATA DICTIONARY AND
UNIVARIATE DISTRIBUTIONS
5. GUIDELINES FOR APPLYING WEIGHTS
6. GUIDELINES FOR RELEASE (DATA QUALITY AND ROUNDING)
7. CONFIDENTIALITY OF THE PUBLIC‑USE MICRODATA
8. SOURCES, METHODS AND ESTIMATION PROCEDURES
10. RELATED PRODUCTS AND SERVICES
The cross-sectional public-use microdata file for the Survey of Labour
and Income Dynamics (SLID) is a collection of income, labour and family
variables on persons in
The
Survey of Labour and Income Dynamics began collecting data for reference year
1993. Initially, SLID was designed to be, first and foremost, a longitudinal
survey, with primary focus on labour and income and the relationships between
them and family composition. Initially, two versions of SLID public-use
microdata files were released: the first cross-sectional set covering reference
year 1993 and the second longitudinal covering reference years 1993 and 1994.
Both cross-sectional and longitudinal public-use files were released.
After the
release of the 1993 and 1994 files, the decision was made to extend the
objectives of SLID to be the primary source of cross-sectional household income
data. The type of income data collected by SLID was identical to that of the
former household income survey SCF (Survey of Consumer Finances), with the distinction
that SLID respondents had the choice of a traditional income interview and
granting permission to Statistics Canada to use their T1 income tax data.
For many years, the Survey of Consumer Finances had
provided public-use microdata files (PUMFs) to meet
the needs of cross-sectional household income data users. SCF PUMFs were released up to and including reference year
1997. For the purpose of standard publications, Statistics Canada has made the
transition from SCF to SLID between 1995 and 1996. Therefore, SLID
cross-sectional PUMFs are being made available
beginning with reference year 1996. The SLID files have been designed to be analogous
to those produced for the SCF.
How to cite SLID in
publications
For publication of any information based on
the SLID microdata files on CD‑ROM (75M0010XCB), the following form of
accreditation is recommended:
"This analysis is based on Statistics
Canada's Survey of Labour and Income Dynamics Public Use Microdata, which
contains anonymized data collected in the Survey of
Labour and Income Dynamics. All computations on these microdata were prepared
by (Name of user). The responsibility for the use and interpretation of these
data is entirely that of the author(s)".
Although often referred to as one file, the
SLID cross-sectional PUMF is four separate flat files: key, person, economic
family and census family. To a large extent, the file structure used for SCF PUMFs has been maintained.
On the person file, there is one record per person in
the sample aged 16 and over. Job characteristics such as industry, wage rates
and work schedule are included on the person file and relate to the person's
main job during the reference year (the job at which the most hours were worked
during the year). Although SLID collects data on all jobs held during the year
by each person under 70 years old, the characteristics of all other jobs are
not included on the SLID PUMFs.
The person file does contain identifiers that allow a
researcher to group persons into households, economic families and census
families.
The sizes
of the 1999 public‑use files are:
|
Files |
Number
of Records |
Number
of Variables |
Record length (bytes) |
|
Key
file |
13 |
41 |
|
|
Person
file |
131 |
500 |
|
|
Economic
family file |
30,410 |
73 |
401 |
|
Census
family file |
33,845 |
70 |
398 |
3. USING THE RECORD LAYOUTS, DATA DICTIONARY
AND UNIVARIATE DISTRIBUTIONS
Additional
information files are provided to assist users of the SLID public-use microdata
files. For each of the four data files (key, person, economic family and census
family), record layout, data dictionary and univariate
distributions are provided. These information files are organized by content
themes and in some cases sub‑themes.
The following
describes the structure of the additional information files:
A. The columns of the record layout file
B. Data Dictionary
The data
dictionary presents the complete information about each survey variable on each
of the four files. For each variable in the record layout the following
information is shown: the variable name, the description or definition, code
lists with descriptions or alternatively the range of values that the variable
can take on, the variable type, its length (or format), and the population to
which the variable pertains, i.e. for whom it is applicable.
C. Univariate
Distributions
These distributions are provided to allow
users of the public use microdata files to verify totals
that they produce. These distributions relate to the public-use files and not
to the internal database; the distributions will be similar but not identical
due to confidentiality processing procedures used to produce the public-use
files.
For character variables, the weighted and unweighted
frequencies for each code, including reserved codes (see below), are provided. For numeric variables, the values
are broken into several ranges and weighted and unweighted
frequencies are provided for each range. The minimum value, the maximum value
and the weighted mean (excluding reserved codes) are also provided.
Missing
Values and Reserved Codes
There are a few types of missing values on
the public use file. SLID has adopted standard codes which have a particular
meaning. It is important to account for reserved codes in any analysis,
particularly with numeric variables. If your calculation of means or aggregates
seems too high, check to ensure that you have excluded reserved codes from the
calculation. With only a few exceptions, the reserved codes are the highest
four values permitted according to the length of the variable. A brief
explanation of reserved codes is provided below.
If the
coverage of a variable does not extend to a certain population sub-group, then
there are no valid values for that sub-group and the values (reserved codes) that
do appear are in the form 9, 99, 9.9 and so on, which indicates that the
variable is not applicable. The coverage of each variable on the file is
referred to in the data dictionary as the “population”.
For
certain records, no valid value is available, although the value is applicable.
Possibly, the respondent did not provide the information or it failed an edit
in processing and the value was not imputed. Such missing values appear with a reserved
code such as 7, 97, 9.7 and so on depending on the
format. For certain variables, the number of missing values has been reduced
through imputation. Missing values for the income variables have been entirely
imputed, but most other variables may have missing values.
Finally,
a few values may have been coded as 8, 98, 9.8, etc. These represent refusals
to particular items in the interview. The approach for dealing with missing
values of this last kind depends on the type of analysis being carried out and
the extent of missing data. Although the end solution may be to exclude the
records with missing values from the analysis a review should first be carried
out to assess the impact of missing values on the overall representativeness
of the data. Is it possible that a bias results from
the missing data – for example, are the (other) characteristics of the people
with missing values different from those of the observed part of the sample? It
may be necessary to take into account the possible impact in some way. In all
cases, analysts should note exclusions of records with missing values in their
published results.
This section reviews the definitions of the main income concepts and
their components. In order to highlight the relationships between them, this
section is organized according to the “Classification of Income Sources”, shown
as a table under Total income, below.
Total
income
Total income refers to income from all sources including government
transfers and before deduction of federal and provincial income taxes. It may
also be called income before tax (but after transfers). All sources of income
are identified as belonging to either market income or government transfers.
Table
A
Classification
of Income Sources
Market income
Earnings
Wages and salaries
Farm
Non‑farm
Investment
income
Retirement
pensions
Other
income
Government transfers
Old Age Security and Guaranteed Income
Supplement/Spouse's Allowance
Canada
Pension Plan/Quebec Pension Plan benefits
Child tax
benefits
Employment
Insurance benefits
Workers'
compensation benefits
GST/HST
Credit
Provincial/territorial
tax credits
Social
assistance
Other
government transfers
While a justification of the definition of income is not attempted here,
some important inclusions and exclusions are noted.
Market
income
Market income is the sum of earnings (from employment and net
self-employment), investment income, (private) retirement income, and the items
under “Other income”. It is equivalent to total income minus government
transfers. It is also called income before taxes and transfers.
Earnings
This includes earnings from both paid employment (wages and salaries)
and self-employment.
Wages
and salaries
These are gross earnings from all jobs held as an employee, before
payroll deductions such as income taxes, employment insurance contributions or
pension plan contributions, etc. Wages and salaries include the earnings of
owners of incorporated businesses, although some amounts may instead be
reported as investment income. Commission income received by salespersons as
well as occasional earnings for baby‑sitting, for delivering papers, for
cleaning, etc. are included. Overtime pay is included.
Self-employment
income
This is net self-employment income, i.e. after deduction of expenses.
Negative amounts (losses) are accepted. It includes income received from self‑employment
on own account, in partnership in an unincorporated business, or in independent
professional practice. Income from roomers and boarders (excluding that
received from relatives) is included. Note that because of the various
inclusions, receipt of self-employment income does not necessarily mean the
person held a job.
Self-employment income is subdivided into farm self-employment income
and non-farm self-employment income. Farm self‑employment income is
reported by individuals who operate their own or a rented farm, either on own
account or in partnership. Included are money receipts from the sale of farm
products as well as related supplementary and assistance payments from
governments. Income in kind is excluded.
Investment
income
This includes interest received on bonds, deposits and savings
certificates from Canadian or foreign sources, dividends received from Canadian
and foreign corporate stocks, cash dividends received from insurance policies,
net rental income from real estate and farms, interest received on loans and
mortgages, regular income from an estate or trust fund and other investment
income. Realized capital gains from the sale of assets are excluded. Negative
amounts are accepted.
Retirement
pensions
This is retirement pensions from all private sources, primarily employer
pension plans. Amounts may be received in various forms such as annuities,
superannuation or RRIFs (Registered Retirement Income
Funds). Withdrawals from RRSPs (Registered Retirement
Savings Plans) are not included in retirement pensions. However, they are taken
into account as necessary for the estimation of certain government transfers
and taxes. For data obtained from administrative records, income withdrawn from
RRSPs before the age of 65 is treated as RRSP withdrawals,
and income withdrawn from RRSPs at ages 65 or older
is treated as retirement pensions. Retirement pensions may also be called
pension income.
Government
transfers
Government transfers include all direct payments from federal,
provincial and municipal governments to individuals or families. See the table
“Classification of Income Sources” for a list of the government transfers
identified separately in the latest reference year. It should be noted that
many features of the tax system also carry out social policy functions but are
not government transfers per se. The tax system uses deductions and
non-refundable tax credits, for example, to reduce the amount of tax payable,
without providing a direct income.
Child
tax benefits
Federal child tax benefits began in 1993 and replaced
both the federal Family Allowances and the Child Tax Credit. Several provincial
and territorial programs have since been introduced, in addition to
Old
Age Security (OAS) benefits
The Old Age Security (OAS) pension is targeted to Canadian residents
aged 65 and over. OAS recipients who have little or no other income may also
receive the federal Guaranteed Income Supplement (GIS); and their spouses, if
aged 60 to 64 (and not yet eligible for OAS and GIS themselves), receive the
Spouse’s Allowance.
The CPP and QPP are compulsory contributory social insurance programs
that provide a source of retirement income and protect workers and their
families against loss of income due to disability or death.
Employment
Insurance benefits
Employment Insurance is a federal program which includes the following
types of benefits: regular unemployment benefits, sickness benefits, maternity
and parental benefits, and benefits for persons taking approved training
courses or participating in job creation or job‑sharing projects. To
qualify, the claimant must have ceased receiving employment income and have
worked a minimum number of weeks or hours of insurable employment over the
preceding period.
Social
assistance
Social assistance covers many provincial and municipal income
supplements to individuals and families. It is usually provided only after all
other possible sources of support have been exhausted.
Workers'
compensation benefits
Workers' compensation is provided to protect all full-time and part-time
employees from loss of salary due to work accidents or occupational diseases
and help them to pay their medical expenses and other costs.
Goods
and Services Tax/Harmonized Sales Tax Credit
This credit was introduced in conjunction with the Goods and Services
Tax in 1990. It is intended to offset the GST/HST for lower-income families and
individuals. In
Provincial/territorial
tax credits
Included
here are refundable tax credits other than those for children (included with
child tax benefits). Some are designed to help low-income individuals and
families to pay property taxes, education taxes, rent and living expenses, and
so on. Provincial sales tax credits such as the Quebec Sales Tax Credit and the
Other
government transfers
This includes government transfers not included elsewhere, mainly any
other non-taxable transfers. In SLID, these amounts are included with “Other
income”. This is partly because the coverage of any transfers not taxed through
the income tax system is low. In survey interviews, there may be
under-reporting of these transfers, which are mainly collected using an open
question. Nonetheless, the types of transfers which have come under this
heading include: training program payments not reported elsewhere, the
Veteran's pension, pensions to the blind and the disabled, regular payments
from provincial automobile insurance plans (excluding lump‑sum payments),
and benefits for fishing industry employees.
Other
income
This subtotal includes all items of market income not included
elsewhere. Among them are support payments received (also called alimony and
child support). The coverage of other items depends at least to some extent on
the method of income data collection, whether from administrative income tax
records or by interview. Those items that are included on line 130 of the T1
tax return are well covered. These include, but are not restricted to, retiring
allowances (severance pay/termination benefits), scholarships, lump-sum payments from pensions and deferred profit-sharing
plans received when leaving a plan, the taxable amount of death benefits other
than those from CPP or QPP, and supplementary unemployment benefits not included
in wages and salaries.
Income
tax
Income tax is the sum of federal and provincial income taxes payable
(accrued) for the taxation year. Income taxes include taxes on income, capital
gains and RRSP withdrawals, after taking into account exemptions, deductions,
non-refundable tax credits, and the refundable
After-tax
income
After-tax income is total income, which includes government transfers as
defined here, less income tax. It may also be called income after tax.
Dwelling
In general terms, a dwelling is defined as a set of living quarters. A
private dwelling is a separate set of living quarters with a private access. A
collective dwelling may be institutional, communal or commercial in nature. Of
the different types of collective dwellings, only communal dwellings are
covered in the SLID.
Household
A household is defined as a person or group of persons residing in a
dwelling.
Economic
family
An economic family is defined as a group of two or more persons who live
in the same dwelling and are related to each other by blood, marriage, common‑law
or adoption.
Unattached
individual
An unattached individual is a person living either alone or with others
to whom he or she is unrelated, such as roommates or a lodger.
Census
family
The term “census family” corresponds to what is commonly referred to as
a "nuclear family" or "immediate family". In general, it
consists of a married couple or common-law couple with or without children, or
a lone-parent with a child or children; furthermore, each child does not have
his or her own spouse or child living in the household.
Persons “not in census families” are those living
alone, living with unrelated individuals, or living with relatives but not in a
husband-wife or parent-unmarried child (including guardianship child)
relationship.
By definition, all persons who are members of a census
family are also members of the same economic family.
Adults
Adults are defined in SLID as 16 or older as of December 31 of the
reference year.
Family
income
Family income is the sum of income of each adult in the family as
defined above. Household income is likewise the sum of incomes of all adults in
the household. Family and household membership is defined at a particular point
in time, while income is based on the entire calendar year. The family members
or “composition” may have changed during the reference year, but no adjustment
is made to family income to reflect this.
SLID defines households and families according to the living arrangements
on December 31 of the reference year.
Major
income earner
This characteristic is important for the derivation of detailed family
types. For each household and family, the major income earner is the person
with the highest income before tax, with one exception; a child living in the
same census family as his/her parent(s) cannot be identified as the major
income earner of the census family (this does not apply to economic families).
For persons with negative total income before tax, the absolute value of
their income is used, to reflect the fact that negative incomes generally arise
from losses “earned” in the market place and are not meant to be sustained. In
the rare situations where two persons have exactly the same income, the older
person is the major income earner.
Table
B
Classification
of Family Types
Economic families (or Census families), two persons or
more
Elderly families
Married
couples
All other
elderly families
Non-elderly families
Married couples without children
No
earner
One earner
Two
earners
Two-parent
families with children
No
earner
One
earner
Two
earners
Three
or more earners
Married
couples with other relatives
Lone-parent
families
Male
lone-parent families
Female
lone-parent families
No earner
One
earner
Two
or more earners
Other
non-elderly families
Unattached individuals (or persons not in Census
families)
Elderly male
Non-earner
Earner
Elderly female
Non-earner
Earner
Non-elderly male
Non-earner
Earner
Non-elderly female
Non-earner
Earner
Within this classification, the following definitions apply:
Elderly family: The major income earner in the economic family is aged
65 or over.
Married couples/Spouses: Married couples include legally married, common-law
and same-sex relationships where one of the spouses is the major income earner.
Children: A child or children (by birth, adopted, step, or foster) of
the major income earner under age 18. Other relatives may also be in the
family.
Lone-parent family: Includes at least one child as defined above. Families where the parent is 65 years or
older are excluded.
Relative: A person related to the major income earner by blood,
marriage, adoption or common-law.
Other relative: A person in the economic family who is not the major
income earner nor his/her spouse or child under age 18.
Current
dollars versus constant dollars
“Current dollars” are what we usually mean when we refer to a currency
in the current time period. The term “constant dollars” refers to dollars of
several years expressed in terms of their value (“purchasing power”) in a
single year, called the base year. This type of adjustment is done to eliminate
the impact of widespread price changes. Current dollars are converted to
constant dollars using an index of price movements. The most widely used index
for household or family incomes, provided that no specific uses of the income
are identified, is the Consumer Price Index (CPI), which reflects average
spending patterns by consumers in
The following table shows the annual rates of the Consumer Price Index. To convert current dollars of any year to constant dollars, divide them by the index of that year and multiply them by the index of the base year you have chosen (remember that the numerator contains the index value of the year you want to move to). For example, using this index, $10,000 in 1997 would be $10,548 in 2000 constant dollars ($10,000 × 113.5/107.6 = $10,548).
Table
C
Consumer
Price Index, annual rates, 1992=100
1980 52.4 1990 93.3 2000 113.5
1981 58.9 1991 98.5 2001 116.4
1982 65.3 1992 100.0
1983 69.1 1993 101.8
1984 72.1 1994 102.0
1985 75.0 1995 104.2
1986 78.1 1996 105.9
1987 81.5 1997 107.6
1988 84.8 1998 108.6
1989 89.0 1999 110.5
Earner/Income
recipient
An earner is a person who received income from employment (wages and
salaries) and/or self-employment during the reference year. The term income
recipient is generally used for someone who received a positive (or negative)
amount of income of any given type.
Mean
income (average income)
The mean or average income is computed as the total or
"aggregate" income divided by the number of units in the population.
It offers a convenient way of tracking aggregate income while adjusting for
changes in the size of the population.
There are two drawbacks to using average income for analysis. First,
since everyone's income is counted, the mean is sensitive to extreme values:
unusually high income values will have a large impact on the estimate of mean
income, while unusually low ones, i.e. highly negative values, will drive it
down. (See also "Recipients versus non‑recipients" and
"Negative values".) Secondly, it does not give any insight into the
allocation of income across members of the population. For this, measures such
as percentiles or Gini coefficients may be used.
Recipients
versus non-recipients (zero values)
For every table showing average incomes, it must be kept in mind whether
non-recipients of that type of income are included or excluded from the
population. In the case of total family income, the difference of including or
excluding units with zero income is small since there are very few such
families. However, if one is interested in the average amount of individual self-employment
earnings, the value will be quite different if one includes those persons who
were not self-employed. Zero values are included in all tables focussing on the
three main income concepts (market, total, or after-tax income), government
transfers or taxes.
Negative
values
Negative income amounts can arise in two ways: net losses from
self-employment (expenses exceed receipts), or net investment losses (losses
exceed gains). As with zero values, negative values can have a large impact on
results. In general, the published income tables treat negative values no
differently than positive values, but there are a few exceptions: for the
calculation of both Gini coefficients and the low income gap, negative values
are converted to zeroes; and in the derivation of the major income earner of a
family or household, the absolute value is used instead (see “Major income
earner” under “Family definitions”).
Percentiles
Income percentiles like quintiles and deciles are a convenient way of
categorizing units of a given population from lowest income to highest income
for the purposes of drawing conclusions about the relative situation of people
at either end or in the middle of the scale. Rather than using fixed income
ranges, as in a typical distribution of income, it is the fraction of each
population group that is fixed.
First, all the units of the population, whether individuals or families,
are ranked from lowest to highest by the value of their income of a specified
type, such as after-tax income. Then, the ranked population is divided into
five groups of equal numbers of units, called quintiles. Analogously, dividing
the population ranked by income into ten groups, each comprising the same
number of units, produces deciles.
Most analyses should be carried out on the people of different
percentiles within a distribution. Care should be taken in making comparisons
between quintiles that resulted from different distributions, because any
difference in either the population or the income concept used to rank units
could have a large effect. It is probable that both the income ranges
represented by each quintile and the people making up each quintile will be
different.
Median
income
The median income is the value for which half of the units in the
population have lower incomes and half have higher incomes. To derive the
median value of income, units are ranked from lowest to highest according to
their income and then separated into two equal‑sized groups. The value
that separates these groups is the median income. It corresponds to the 50th
percentile.
Because the median corresponds exactly to the mid‑point of the
income distribution, it is not, contrary to the mean, affected by extreme
income values. This is a useful feature of the median, as it allows one to abstract
from unusually high values held by relatively few people.
Since income distributions are typically skewed to the left ‑ that
is, concentrated at the low end of the scale ‑ median income is usually
lower than mean income.
Implicit
rate of government transfers or taxes
The
implicit rate of either transfers or taxes, as the case may be, is a way of
showing the relative importance of transfers received or taxes paid for
different families or individuals. This concept is similar, but not identical,
to the effective rate of taxation. For a given individual or family, the
effective rate is the amount of transfers/taxes expressed as a percentage of
their income, usually market income, total income, or after-tax income. The
implicit rate for a given population is the average (or aggregate) amount of
transfers/taxes expressed as a percentage of their average (or aggregate)
income.
Family
size adjustment (equivalence scale)
When comparing family incomes to study such things as income adequacy or
socio-economic status, one often wants to take the family size into account.
Basically stated, the income amount itself is not sufficient to understand a
family’s financial well-being without knowing how many people are sharing it.
Two approaches have been used to help with the analysis of family income. One
is to produce data by detailed family types, so that within a given family
type, differences in family size are not significant. In fact, many income
measures have been crossed by detailed family types in the published tables.
The other way to take family
size into account is to adjust the income amount, for the purposes of analysis
only. The major challenge of this approach is to select an appropriate
adjustment factor. While there is no single best method, it is still better to
apply some kind of adjustment factor rather than no adjustment at all.
The simplest method is to use per capita income, that is, to divide the
family income by the family size. A limitation of per capita income, however,
is that it tends to underestimate economic well-being for larger families as
compared to smaller families. This is due to the fact that it assumes equal
living costs for each member of the family, but some costs, primarily those
related to shelter, decrease proportionately with family size (they may also be
lower for children than for adults). For example, the shelter costs for an
adult married couple with no children are arguably not much more than those for
an adult living alone.
To take such economies of scale
into account, it is common to use an “equivalence scale” to adjust family
incomes. Instead of implicitly assuming equal costs for additional family
members as the per capita approach does, the equivalence scale is a set of
decreasing factors assigned to the first member, the second member, and so on.
Dividing the income value by the sum of the factors assigned to each member
derives the adjusted income amount for the family.
There is no single equivalence scale in use in
For example, this translates into a total factor for dividing income of
just 1.4 for a married couple instead of 2.0 (the family size). Such a family
with total income of $56,000 would be considered to have a standard of living
equivalent to an adult living alone with a total income of $40,000, as compared
to an adult with $28,000 when calculated on a per capita basis.
Gini coefficient
The Gini coefficient measures the degree of
inequality in an income distribution. Gini
coefficients are published for a variety of income measures such as market
income, total income and after-tax income, and are used to compare the
uniformity of income allocation between different income concepts across
different populations or within the same population over time.
Values of the Gini coefficient
can range from 0 to 1. A value of zero indicates income is equally divided
among the population with all units receiving exactly the same amount of
income. At the opposite extreme, a Gini coefficient of 1 denotes a perfectly
unequal distribution where one unit possesses all of the income in the economy.
A decrease in the value of the Gini coefficient can, by and large, be
interpreted as reflecting a decrease in inequality, and vice versa. As a rough rule of thumb when using data from SLID at the
Low
income cutoff (LICO)
Low income cutoffs
(LICOs) are established using data from the Family
Expenditure Survey, now known as the Survey of Household Spending. They convey
the income level at which a family may be in straitened circumstances because
it has to spend a greater proportion of its income on necessities than the
average family of similar size. Specifically, the threshold is defined as the
income below which a family is likely to spend 20 percentage points more of its
income on food, shelter and clothing than the average family. There are
separate cutoffs for seven sizes of family – from
unattached individuals to families of seven or more persons – and for five
community sizes – from rural areas to urban areas with a population of more
than 500,000.
Calculation
of low income cutoffs
The first step in the production of a set of low income cutoffs is to calculate the average proportion of income
that a family spends on food, shelter and clothing. The 1992 Family Expenditure Survey found
that, on average, families spend 44% of their after-tax income (and 35% of
their total “before-tax” income) on these necessities. Then, 20 percentage points
are added, giving 64% of after-tax income. This is done on the grounds that a
family spending more than this proportion of its income on necessities is
significantly worse off than the average family. The final step is to look at
the distribution of income by expenditure and determine, using a regression
line, the level of income at which a family tends to spend 20 percentage points
more than the average on the necessities of food, shelter and clothing.
Updating
and rebasing the low income cutoffs
There are two reference years that play a part in the calculation of a
set of low income cutoffs: the base year and the
income reference year. The base year supplies the average spent on food,
shelter and clothing. This percentage is used to derive a set of cutoffs that are suitable for use with income data from
that year. Cutoffs for other income reference years
may be obtained by applying the corresponding Consumer Price Index (CPI)
inflation rate to the basic set of cutoffs.
Using the CPI to update the cutoffs takes
inflation into account, but does not reflect any changes that might occur in
the average spending on necessities. In the past, Statistics Canada has
developed a new set of cutoffs after each Family
Expenditure Survey. These are referred to as ‘bases’ because the average
spending on necessities in that base year drives the calculation of the cutoffs. The two most recent base years are 1992 and 1986. Cutoffs based on 1992 are most commonly applied by data
users, and are available for the income reference years from 1980 onwards.
Low
income rate
Low income rates can be
calculated for persons or for families. In either case, the income that is
compared to the cutoff is the income of the entire
economic family. “Persons in low income” should be interpreted as persons who
are part of low income families including persons living alone whose income is
below the cutoff. Similarly, “children in low income”
means “children who are living in low income families”. In other words, all
members of an economic family have the same low income status, but they are
counted separately when person-based low income rates are calculated.
To calculate the low income rates, the family size and community size
are used to find the appropriate cutoff. Then the
family income is compared to that cutoff. If a family
low income rate is being calculated, then the family is counted as being in low
income if its income is less than the cutoff. If a
person low income rate is being calculated, then all persons in the family are
counted as being in low income if the family income is less than the cutoff.
Use
of after-tax and before-tax LICOs
The average portion of income that families spend on food, shelter and
clothing, which figures prominently in the low income cutoffs,
is undoubtedly a useful gauge of economic well-being no matter which income
concept is used. The choice of after-tax income or total income – or even
market income for that matter – depends on whether one wants to take into
account the added spending power that a family gets from receiving government transfers
and its reduced spending power from paying taxes.
In the past, Statistics Canada has produced two sets of low income cutoffs and corresponding rates – those based on total
income (i.e. income including government transfers, before the deduction of income
taxes) and those based on after-tax income.
The choice to highlight after-tax rates was made for two main reasons.
First, income taxes and transfers are essentially two methods of income
redistribution. The before-tax rates only partly reflect the entire
redistributive impact of
A note about the calculation of before-tax versus after-tax low income cutoffs: the derivation of each set of cutoffs
is done independently. There is no simple relationship, such as the average amount
of taxes payable, that distinguishes the two levels.
Instead, the entire calculation of cutoffs is done
twice – both on a before-tax basis and on an after-tax basis.
Differences
in after-tax rates and before-tax rates
After-tax low income cutoffs, and the resulting after-tax rates, have been
published back to 1980. The number of people falling below the cutoffs has been consistently lower on an after-tax basis
than on a before-tax basis. This result may appear inconsistent at first
glance, since incomes after tax cannot be any higher than they are before tax,
considering that all transfers, including refundable tax credits, are included
in the definition of “before-tax” total income. However, with a relative
measure of low income such as the LICO, this result is to be expected with any
income tax system which, by and large, taxes those with more income at a higher
rate than those with less. “Progressive” tax rates, as they are often called,
make the distribution of income more compressed. Therefore, some families that are in low income before taking taxes into account are
relatively better off and are not in low income on an after-tax basis.
Low
income gap
The low income gap, previously called “low income deficiency”, is the
amount that a low income family falls short of the relevant low income cutoff. For the calculation of this gap, negative incomes
are treated as zero.
For example, a family with an income of $15,000 and a relevant low
income cutoff of $20,000 would have a low income gap
of $5,000. In percentage terms this gap would be 25%. The average gap for a
given population, whether expressed in dollar or percentage terms, is the
average of this value as calculation for each unit.
Market
basket measure (MBM)
Human Resources Development
The same argument that can be made for using after-tax low income rates
can be made for using after-tax income to compare to the MBM thresholds. That
is, a measure of well-being should take into account what is actually available
to spend. The income concept that has been proposed for comparisons with the
MBM thresholds goes even further than after-tax income by also removing other
non-discretionary expenses such as support payments, work-related child care
costs and employee contributions to pension plans and to Employment Insurance.
Statistics
This type of measure is often called an “absolute” measure, even though
there is clearly judgement involved in specifying the contents of the basket of
goods and services. Nevertheless, the line is absolute in the sense that it does
not depend directly on the distribution of income.
On
Poverty and Low Income
Ivan P. Fellegi
Chief Statistician of
Recently the news media have
provided increasing coverage of Statistics Canada's low income cutoffs and their relationship to the measurement of
poverty. At the heart of the debate is the use of the low income cutoffs as poverty lines, even though Statistics Canada has
clearly stated, since their publication began over 25 years ago, that they are
not. The high profile recently given to this issue has presented Statistics
Canada with a welcome opportunity to restate its position on these issues.
Many individuals and
organizations both in
In spite of these efforts, there
is still no internationally-accepted definition of poverty - unlike measures
such as employment, unemployment, gross domestic product, consumer prices, international trade and so on. This is not surprising,
perhaps, given the absence of an international consensus on what poverty is and
how it should be measured. Such consensus preceded the development of all other
international standards.
The lack of an internationally-accepted definition has also reflected
indecision as to whether an international standard definition should allow
comparisons of well-being across countries compared to some international norm,
or whether poverty lines should be established according to the norms within
each country.
The proposed poverty lines have included, among others, relative
measures (you are poor if your means are small compared to others in your
population) and absolute measures (you are poor if you lack the means to buy a
specified basket of goods and services designated as essential). Both
approaches involve judgmental and, hence, ultimately arbitrary choices.
In the case of the relative approach, the fundamental decision is what
fraction of the overall average or median income constitutes poverty. Is it
one-half, one-third, or some other proportion? In the case of the absolute approach,
the number of individual judgements required to arrive at a poverty line is far
larger. Before anyone can calculate the minimum income needed to purchase the
"necessities" of life, they must decide what constitutes a
"necessity" in food, clothing, shelter and a multitude of other
purchases, from transportation to reading material.
The underlying difficulty is due to the fact that poverty is
intrinsically a question of social consensus, at a given point in time and in
the context of a given country. Someone acceptably well off in terms of the
standards in a developing country might well be considered desperately poor in
It is through the political process that democratic societies achieve
social consensus in domains that are intrinsically judgmental. The exercise of
such value judgements is certainly not the proper role of
In
Once governments establish a definition, Statistics Canada will
endeavour to estimate the number of people who are poor according to that
definition. Certainly that is a task in line with its mandate and its objective
approach. In the meantime, Statistics Canada does not and cannot measure the
level of "poverty" in
For many years, Statistics Canada has published a set of measures called
the low income cutoffs. We regularly and consistently
emphasize that these are quite different from measures of poverty. They reflect
a well-defined methodology that identifies those who are substantially worse
off than the average. Of course, being significantly worse
off than the average does not necessarily mean that one is poor.
Nevertheless, in the absence of an accepted definition of poverty, these
statistics have been used by many analysts to study the characteristics of the
relatively worst off families in
Many people both inside and outside government have found these and
other insights to be useful. As a result, when Statistics Canada carried out a
wide-ranging public consultation a decade ago, we were almost unanimously urged
to continue to publish our low income analyses. Furthermore, in the absence of
a generally accepted alternative methodology, the majority of those consulted
urged us to continue to use our present definitions.
In the absence of politically-sanctioned social consensus on who should
be regarded as "poor", some people and groups have been using the
Statistics Canada low income lines as a de facto definition of poverty. As long
as that represents their own considered opinion of how poverty should be
defined in
5. GUIDELINES FOR APPLYING WEIGHTS
The microdata
on the public use file are unweighted. It is the
responsibility of data users to apply the appropriate weights in any estimates
they wish to produce. If proper weights are not used, the results derived from
the microdata cannot be considered to be
representative of the survey population, and will not correspond to those that
would be produced by Statistics Canada. The weights are provided as variables
under "Sample control". On the SLID PUMF, the weight variable is named
ICSWT26.
6. GUIDELINES FOR RELEASE (DATA QUALITY AND
ROUNDING)
Microdata users should apply the rules for assessing data quality, below, to all
estimates they produce, and retain only those that satisfy the release
criteria. Estimates that do not satisfy the release criteria are not reliable.
Introduction
The
guidelines for release and publication make use of the concept of sampling
variability to determine whether the estimates obtained from the microdata are reliable. Sampling variability is the error
in the estimates caused by the fact that we survey a sample rather than the
entire population. The concept of standard error and the related concept of
coefficient of variation and confidence interval provide an indication of the
magnitude of the sampling variability.
The
standard error and coefficient of variation do not measure any systematic biases
in the survey data which might affect the estimate. Rather, they are based on
the assumption that the sampling errors follow a normal probability distribution.
Subject
to this assumption, it is possible to estimate the extent to which different
samples that have the same design and the same number of observations would
give different results. This indicates the margin of error that is likely to be
included in the estimates derived from our single sample.
For a more
complete description of the measures of sampling variability, see A. Satin and
W. Shastry, Survey Sampling: A Non‑Mathematical
Guide, Statistics Canada, Catalogue 12‑602E.
Minimum
sizes of estimates for release
In general, the smaller the sample, the greater the sampling variability. Consequently, estimates of small population subgroups are less reliable
than estimates of large population subgroups. The minimum allowable sizes of
estimates, also called the release cut‑offs, are a quick rule for
determining whether an estimate can be released, before applying the more
rigorous test that uses the coefficient of variation. The release cut‑offs
are calculated specifically for the Survey of Labour and Income Dynamics based
on the sample size and the sample design.
Both the
cut‑offs for the unweighted count and the
weighted count must be satisfied:
Table
D
Release
cut‑offs based on the weighted estimate/count
|
|
13,000 |
|
|
2,500 |
|
1,500 |
|
|
|
4,000 |
|
|
2,500 |
|
|
14,000 |
|
|
14,500 |
|
|
6,500 |
|
|
2,500 |
|
|
6,000 |
|
|
11,000 |
Estimates
of provincial aggregates and means
When producing estimates for provincial aggregates and means it should be noted that for a small number of records, province of residence has been suppressed. This will result in a small bias in provincial estimates.
Rounding
guidelines
Once it
has been determined whether the results obtained are reliable, the level of
rounding indicates the level of precision that the data can actually support.
The following guidelines for rounding should be used:
Note that
all calculations are to be derived from their unrounded
components, and then rounded using the normal rounding technique.
In normal
rounding, if the first or only digit to be dropped is 0 to 4, the last digit to
be retained is not changed. If the first or only digit to be dropped is
Hypothesis tests provided by statistical
software packages
Microdata
users should be aware that the results of hypothesis tests (such as the p
values accompanying t statistics or Pearson statistics) that are provided
automatically by most standard statistical software packages are incorrect for
data provided by surveys with a complex survey design, such as SLID. Such
packages calculate these test results under the assumption of simple random
sampling. That is, they do not take into account the special sample design
features of SLID such as stratification, clustering, and unequal selection
probabilities. While many of the standard packages can account for the unequal
selection probabilities in the production of estimates by allowing the use of
weights, these packages do not properly take the sample design into account
when producing variance estimates that form part of most test statistics.
To
perform hypothesis tests, a two‑step method can be employed with the
standard statistical software to form the test statistics. First, estimate the
characteristics of interest (total or mean) using the weights provided on the
microdata file. Second, obtain approximate variance estimates of these
characteristics by rerunning the same software procedure as that used for
producing the characteristic estimates but using a scaled weight that consists
of the original weight divided by the average of the original weights of all
the observations being used in your computations. The standard error can be
derived by using the estimate and the rough estimate of the variance. These
quantities (estimate, variance, standard error) can then be combined to form
test statistics. It must be noted that this method provides only rough
approximations to the variance.
It should
be noted that users of the SLID PUMF cannot readily obtain better design‑based
variance estimates through the use of statistical software specifically
designed for survey data. This is because the design information required by
these software packages is not currently available on the SLID data file due to
confidentiality considerations. However, better variance estimates can be
produced by Statistics Canada on a cost-recovery basis.
7. CONFIDENTIALITY OF THE PUBLIC‑USE
MICRODATA
The production of a public‑use
microdata file includes many safeguards to prevent
the identification of any one person. Longitudinal surveys are faced with an
extra challenge when it comes to ensuring confidentiality, because data are
collected for the same people for several years. For this reason, Statistics
Canada plans to release only cross-sectional files from SLID. The number of
topics covered in SLID also contributes to the amount of processing required
specifically to ensure confidentiality. Confidentiality of the public‑use file is ensured
mainly by reducing information, i.e. deleting whole variables or suppressing or
collapsing some of their detail.
SLID uses a number of techniques to ensure
confidentiality:
8. SOURCES, METHODS AND ESTIMATION PROCEDURES
Survey
content
SLID was designed to capture changes in the economic well-being of
individuals and families over time and the determinants of labour market and
income changes. The survey supports analysis on transitions into and out of the
labour force associated with the life cycle or with the business cycle; on the
impact of family events on labour market activity and remuneration; on the
determinants of income instability; on what triggers shifts into and out of low
income and on changes in the composition of income through time. Since SLID
additionally carries a broad selection of human capital variables, it is also
used for studies of such topics as gender wage and earnings gaps.
The major content themes of SLID are illustrated in
the following chart.
|
|
|
|
|
|
|
|
|
|
|
PERSON |
|
|
|
|
|
|
|
|
|
||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|||||||||||||
|
LABOUR
|
|
INCOME
AND WEALTH |
|
EDUCATION |
|
PERSONAL
CHARACTERISTICS |
|
|
|
|
|||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LABOUR
MARKET ACTIVITY PATTERNS |
|
|
INCOME SOURCES |
|
|
EDUCATIONAL
ACTIVITY |
|
|
DEMOGRAPHICS
|
||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
WORK EXPERIENCE |
|
|
MONTHLY
RECEIPT OF EI/WC/SA |
|
|
EDUCATIONAL ATTAINMENT |
|
|
ETHNO- CULTURAL |
||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
JOBLESS PERIODS |
|
|
|
|
|
|
|
|
|
|
|
DISABILITY
|
|||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
JOB INFORMATION |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
INFORMATION
ON PERSON’S CHILDREN |
||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
GEOGRAPHY |
|||||||||||||
|
JOB
CHARACTERISTICS |
|
ABSENCES
FROM WORK |
|
EMPLOYER
ATTRIBUTES |
|
|
|
|
|
|
|||||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
||||||||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
HOUSEHOLD/ FAMILY
INFORMATION |
||||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
||||
Survey
universe
SLID covers all individuals in
The
sample
The samples for SLID are selected from the monthly Labour Force Survey
(LFS) and thus share the latter’s sample design. The LFS sample is drawn from
an area frame and is based on a stratified, multi-stage design that uses
probability sampling. The sample is
composed of six independent samples. These samples are called rotation groups
because each month one sixth of the sample (or one rotation group) is replaced.
The SLID sample is composed of two panels. Each panel consists of two
LFS rotation groups and includes roughly 15,000 households. A panel is surveyed
for a period of six consecutive years. A new panel is introduced every three
years. Thus two panels are always overlapping. The following diagram
illustrates how and when panels overlap.
Chart
B
Overlapping
design of SLID sample
|
1993 |
1994 |
1995 |
1996 |
1997 |
1998 |
1999 |
2000 |
2001 |
2002 |
2003 |
2004 |
|
Panel 1 |
|
|
|
|
|
|
|||||
|
|
|
|
Panel 2 |
|
|
|
|||||
|
|
|
|
|
|
|
Panel 3 |
|||||
|
|
|
|
|
|
|
|
|
|
Panel 4 |
||
Data
collection
For each sampled household in SLID, up to 12 interviews are conducted
over a six-year period. Every year in January, interviewers collect information
regarding respondents’ labour market experiences during the previous calendar
year. Information on educational activity and family relationships is also
collected at that time. The demographic characteristics of family and household
members represent a snapshot of the population as of the end of each calendar
year.
Every May information on income is
collected from the same sampled households. The income interview is deferred
until May to take advantage of income tax time when respondents are more
familiar with their income situation. The reference period for income is the
previous calendar year.
To reduce response burden, respondents can give Statistics Canada
permission to use their T1 tax form information for the purposes of SLID. Over
80 percent of SLID’s respondents give their consent
to the use of their tax records. They are not contacted in May for the income
interview.
The SLID interviews are conducted over the telephone using computer
assisted interviewing (CAI). The interviewer reads the questions as they appear
on the computer screen and keys in the reported information. Skip patterns and
edits are built into the collection software, allowing interviewers to
immediately detect and resolve response inconsistencies. Collection of
date-related information (e.g., employment spells, jobless spells, interruption
of work) is greatly improved by the use of such an interactive data capture
technique. Another advantage of the CAI technology is the feeding back of
details from the previous interview assisting the respondents to recall past
events.
Proxy response is accepted in SLID. This procedure allows one household
member to answer questions on behalf of any or all other members of the
household, provided he or she is willing to do so and is knowledgeable.
Data
quality
There are two types of errors inherent to sample survey data, namely,
sampling errors and non-sampling errors. The reliability of survey estimates
depends on the combined impact of sampling and non-sampling errors.
Sampling
errors
Sampling errors occur because inferences about the entire population are
based on information obtained from only a sample of the population. The results
are usually different from those that would be obtained if information were
collected from the whole population. Errors due to the extension of conclusions
based on the sample to the entire population are known as sampling errors. The
sample design, the variability of the population characteristics measured by
the survey, and the sample size determine the magnitude of the sampling error.
In addition, for a given sample design, different methods of estimation will
result in sampling errors of different sizes.
Standard
error and coefficient of variation
A common measure of sampling error is the standard error (SE). The
standard error measures the degree of variation introduced in estimates by
selecting one particular sample rather than another of the same size and
design. The standard error may also be used to calculate confidence intervals
associated with an estimate (Y). Confidence intervals are used to express the
precision of the estimate. It has been demonstrated mathematically that, if the
sampling were repeated many times, the true population value would lie within
the Y ± 2SE confidence interval 95 times out of 100 and within the narrower
confidence interval defined by Y ± SE, 68 times out of 100. Another important
measure of sampling error is given by the coefficient of variation, which is
computed as the estimated standard error as a percentage of the estimate Y
(i.e. 100 x SE /Y).
To illustrate the relationship between the standard error, the
confidence intervals and the coefficient of variation, let us take the
following example. Suppose that the estimated average income from a given
source is $10,000, and that its corresponding standard error is $200. The
coefficient of variation is therefore equal to 2%. The 95% confidence interval
estimated from this sample ranges from $9,600 to $10,400, i.e. $10,000 ± $400.
This means that with a 95% degree of confidence, it can be asserted that the
average income of the target population is between $9,600 and $10,400.
The bootstrap approach is used for the calculation of the standard
errors of the SLID estimates. For more information on standard errors and
coefficients of variation, refer to the Statistics Canada publication
Methodology of the Canadian Labour Force Survey (Catalogue 71-526-XPB).
Standard errors and coefficients of variation of the estimates produced
from this file are available on request. An approximate method is provided in
Section 6 of this document.
Non-sampling
errors
Non-sampling errors generally result from human errors such as
inattention, misunderstanding or misinterpretation. The impact of randomly
occurring errors over a large number of observations will be minimal. Errors
occurring systematically can, on the other hand, have a major impact on the
reliability of estimates. Considerable time and effort is invested into
reducing non-sampling errors in SLID.
Non-sampling errors may arise from a variety of sources such as
coverage, response, non-response and processing errors.
Coverage error arises when sampling frame units do not exactly represent
the target population. Units may have been omitted from the sampling frame (undercoverage), or units not in the target population may
have been included (overcoverage), or units may have
been included more than once (duplicates). Undercoverage
represents the most common coverage problem.
Slippage is a measure of survey coverage error. It is defined as the
percentage difference between control totals (Census population projections)
and weighted sample counts. Slippage rates for household surveys are generally
positive because some people who should be enumerated are missed. According to
the numbers below, in 1999, SLID covered 87.98% of its target population.
Table
E
Slippage
rates in SLID
|
Year |
1999 |
2000 |
|
|
12.02 |
12.64 |
Rates are also available upon request for sex, province and age
groupings.
Response errors may be due to many factors, such as faulty questionnaire
design, interviewers’ or respondents’ misinterpretation of questions, or
respondents’ faulty reporting. Great effort is invested in SLID to reduce the
occurrence of response error. Measures undertaken to minimize response errors
include the use of highly-skilled and well-trained interviewers, and
supervision of interviewers to detect misinterpretation of instructions or
problems with the questionnaire design. Response error can also be brought about
by respondents who, willingly or not, provide inaccurate responses.
Income data are especially prone to misreporting, as income is a
sensitive issue and includes many items with which respondents are not always
familiar. To obtain more accurate information, income data for SLID are
collected after the income tax “season” when respondents are more familiar with
their tax records. Respondents receive information about the income interview
prior to the interviewer’s telephone call. This gives them time to consult
documents and have information available at the time of the interview. For
respondents who grant Statistics Canada permission to access their tax files
(the majority of respondents), SLID collects income data directly from
administrative files. This procedure reduces misreporting of income in the
SLID.
Non-response errors occur to some extent in any survey for reasons such
as household members being on vacation during the interview period or refusing
to supply requested information, despite attempts to obtain complete response
from sampled units. For these individuals, the missing data are imputed either
explicitly by assigning data to each non-respondent on the basis of a similar
respondent record, or implicitly by redistributing the weight of the
non-respondent individual to other responding individuals. The bias introduced
by non-response increases with the differences between respondent and
non-respondent characteristics. Methods employed to compensate for non-response
make use of information available for both respondents and non-respondents in
an attempt to minimize this bias.
Processing errors can occur at various stages in the survey: data
capture, editing, coding, weighting or tabulation. The computer-assisted
collection method used for SLID reduces the chance of introducing capture
errors because checks for consistency and completeness of the data are built
into the computer application. To minimize coding, weighting or tabulation
errors, diagnostic tests are carried out periodically. These tests include
comparisons of results with other data sources.
Cross-sectional
representativeness of SLID
Each longitudinal sample, or “panel” in SLID initially constitutes a
representative cross-sectional sample of the population. However, because the
real population changes each year, whereas by design the longitudinal sample
does not, the sample must be modified to properly reflect these changes to the
composition of the population. This is done by adding to the sample all new
people in the population who are found to be living with the initial
respondents (and likewise dropping them from the sample if they leave at later
time-points). Conversely, any original respondents who leave the target
population (by moving abroad, into institutions, etc.) are given a zero weight
for cross-sectional purposes. In this way, the cross-sectional sample, composed of the original respondents minus those who
left the target population plus those who have entered it, is virtually fully
representative of the population at each subsequent time-point. The missing
group is composed of persons who have newly entered the target population and
are not living with anyone who was in the target population when the most
recent panel was selected. Since SLID introduces a new panel every three years,
however, this group is quite small.
Response
rates
High response rates are essential for the data quality of any survey and
thus considerable effort is invested to encourage effective participation from
SLID respondents.
The response rates are relatively high in SLID. SLID’s cross-sectional rate of response varied from a low of 79.2% in reference
year 2000 to a high of 86.0% in reference year 1996. The response rate is based
on household response in SLID. For purposes of calculating cross-sectional
response rates in SLID, households are defined according to the January
household composition. The calculation of the response rate at the household
level is based on the response codes for individuals in the household,
including both longitudinal respondents and cohabitants. A respondent household
is defined as a household that has at least one respondent individual. An
individual is defined as a respondent if he or she responded to either the labour or the income interview.
Respondent households are divided into completely
respondent households and partially respondent households. Partially respondent
households are weighted and the missing income data in these households are
imputed.
Table
F
Response
rate in and SLID (1996-2000)
|
Year |
1996 |
1997 |
1998 |
1999 |
2000 |
|
Response Rate (%) |
86.0 |
84.1 |
82.8 |
82.7 |
79.2 |
Imputation
for non-response
In some cases, income data are imputed in SLID using a “nearest
neighbour” approach. This method involves identifying another individual with
certain similar characteristics, who becomes the “donor” for the imputed value.
SLID also uses other imputation techniques. In fact, the primary
method employed for imputing income data in this survey is to use the previous
year’s data, updated for any changes in circumstances. Only in the absence of
such data are income figures imputed using the “nearest neighbour” technique in
SLID.
Amounts received through government programs such as the Child Tax
Benefits, the Goods and Services/Harmonized Sales Tax Credit, the Guaranteed
Income Supplement, are derived from other information collected by the survey.
Data obtained from the tax route are considered complete and thus require no
imputation.
The SLID content organization is presented
earlier in this document. Themes are organized under the topics of labour,
income and wealth, education, and personal characteristics, including
selections of the variables they contain. This section provides more detail on
the content of SLID by content theme. Variables appearing on the public use
file are marked with an asterisk *.
I. Labour
Nature and pattern of labour
market activities
·
major
activity during year *
·
spells
of employment and unemployment (start and end dates, durations)
·
monthly
labour force status *
·
total
weeks of employment, unemployment and inactivity by year *
·
multiple
job‑holding spells
·
work
absence spells
·
years of
full‑time and part‑time employment
·
years of
experience in full‑time, full‑year equivalents *
Characteristics of jobless spells
·
job
search during spell
·
dates of
search spells
·
desire
for employment
·
reason
for not looking
Job characteristics (all characteristics
updated each year and dates of changes recorded; collected for up to six jobs
per year)
·
start
and end dates, first date ever worked for this employer
·
wages *
·
work
schedule (hours and type) *
·
benefits
*
·
union
membership *
·
occupation
*
·
supervisory
and managerial responsibilities
·
class of
worker *
·
tenure
·
how job
was obtained
·
reason
for job separation
Characteristics of work absences lasting one
or more weeks (collected on first and last absence each year, for each
employer)
·
absence
dates
·
reason
·
paid or
unpaid
·
industry
*
·
firm
size *
·
public
or private sector *
·
annual
information on 15 income sources *
·
total
income *
·
taxes
paid *
·
after
tax income *
Receipt of compensation (whether
benefits were received from each source and, if so, in which months)
·
Employment
Insurance * - yes/no only on PUMF
·
Social
Assistance * - yes/no only on PUMF
·
Workers'
Compensation * - yes/no only on PUMF
III. Education
·
enrolled
in a credit program, months attended
·
type of
institution *
·
full‑time
or part‑time student *
·
certificates
received (if applicable) *
Educational attainment (updated
annually)
·
years of
schooling *
·
degrees
and diplomas *
·
major
field of study
·
year of
birth / age *
·
sex *
·
duration
of current marital status
·
year/age
at first marriage
·
ethnic
background
·
member
of an Employment Equity designated group
·
mother
tongue
·
date of
immigration*
·
country
of birth
·
parents'
schooling and place of birth
·
annual
information on activity limitations and their impact on working
·
satisfaction
with work
Information
on person's children
·
number
of children born, raised *
·
year and
person's age when first child born
Geography
and geographic mobility
·
economic
region or census metropolitan area of current residence
·
size of
community *
·
moved
during year
·
move
dates
·
reason
for move
·
nature
of move (full household/household split)
Household and economic family and
census family information (annual summary information, e.g., size, type)
·
key
characteristics of other individuals in household/family (e.g., age, sex, relationship, income, annual
hours worked)
·
relevant
low‑income cutoff
·
family
events (marriage, separation, death, birth)
·
dwelling
type and tenure *
10. RELATED PRODUCTS AND SERVICES
Canadian
Statistics on the Internet
The following data are available, free of charge, on Statistics Canada’s
website (www.statcan.ca):
·
Average Market Income by Selected Family Types,
·
Average Total Income by Selected Family Types,
·
Average After-Tax Income by Selected Family Types,
·
Government Transfers and
·
Persons in Low Income Before
·
Persons in Low Income After
The menu path to download the above-listed tables is “Canadian
Statistics”, then “The People”, followed by “Families, Households and Housing”
and “Income”.
·
Average Earnings by Sex and Work
The menu path to download the above-listed tables is “Canadian
Statistics”, then “The People”, followed by “Labour, Employment and
Unemployment” and “Earnings”.
Income in
An
electronic version of the present publication is available on Statistics Canada’s
website
(www.statcan.ca).
The
menu path to download the electronic version is “Our Products and Services”,
then “Browse our Internet Publications (for sale)”, followed by “75-202-XIE,
Income in Canada”.
Income Trends in
This
annual CD-ROM, which includes over 2 million data points, is the complement to
Income in
Longitudinal data from the Survey of Labour
and Income Dynamics (SLID)
SLID is a
longitudinal survey – the same people are interviewed from one year to the next
for a period of six years – that began collecting data with the 1993 reference
year.
SLID includes
a large selection of variables that capture transitions in Canadians’ jobs,
income and family events. Therefore, SLID opens new research avenues that will
provide greater insights on important issues, such as how many Canadians remain
in low income situations and what makes it possible for others to emerge from
periods of low income.
The
comprehensive data that make SLID so valuable, also makes it more complex for
Statistics Canada to ensure that confidentiality of respondents is maintained.
In order
to comply with the strict confidentiality provisions of the Statistics Act,
SLID longitudinal data are made available through new modes of dissemination,
namely:
Research
and Working Papers
Statistics
The
menu path to download the papers listed above is “Our Products and Services”
then “Browse our Internet Publications (free)” followed by the catalogue
number.
SLID
Documentation for Researchers
·
SLID
questionnaires 75F0002MIE1999003, 75F0002MIE1999004, 75F0002MIE1999005
The
menu path to download the papers listed above is “Our Products and Services”
then “Browse our Internet Publications (free)” followed by the catalogue
number.
Perspectives on Labour and Income 75-001-XPE
Perspectives on Labour and Income is a quarterly journal that features analytical
articles on the latest trends. It includes a section that summarizes recent
reports and studies released by Statistics Canada. Subscribing to Perspectives
on Labour and Income will prove to be an excellent way to keep up-to-date on
what’s new, all year long!
11. QUESTIONS
AND COMMENTS
If you have any questions or comments about the data in this CD-ROM
product, you can contact the Income Statistics Division.
Telephone: 1-888-297-7355 or 613-951-7355
Facsimile Number: 613-951-3012
Statistics
K1A 0T6