SoWL 2012 Data Collection

##Response rate## The target response rate for SoWL was 80 percent. This represents Statistics NZ's minimum acceptable response rate. The achieved response rate for employed individuals was 84 percent. There were 14,335 employed individuals in households that responded to SoWL. Non-response was partly due to the increased burden of it being a supplement to the Household Labour Force Survey (HLFS), and partly because proxy responses were not accepted in most situations (even though they are accepted for the HLFS). A proxy response is a response by one member of a household on behalf of another. SoWL accepted proxy responses only for a disability or other health condition, or language difficulties. ##Population comparability## ###Seasonality### The 2008 SoWL ran in the March quarter, but SoWL 2012 was run in the December quarter – because working times and hours during the December quarter are likely to be more typical of those over a full year. Interviewing during the December quarter would also enable a similar coverage of seasonal workers to the full year. Regular seasonal factors or cycles can affect survey results. For the labour market, cyclical events that occur around the same time each year affect both labour supply and demand. For example, in summertime there is a large pool of student labour that is both available for, and actively seeking, work. We have seen seasonal differences between quarters for the HLFS. For example, the December quarter has shown a higher number of people in the retail trade industry – due to the holiday shopping period – compared with other quarters during the year. These differences can also affect SoWL. We do not have enough information within SoWL to account for these differences. Hence, we do not recommend direct comparison of the March 2008 and December 2012 SoWL – this could lead to inaccurate conclusions. ##Questionnaire changes## Five new questions were added to the SoWL 2012 questionnaire. Two relate to 90-day job trials: the first, which asked if the respondent had started their main job on a 90-day trial, was asked only of employees. All employed people were asked the second question – if they had started any (employers and self-employed), or any other (employees), job on a 90-day trial in the previous four years. Respondents who had worked in the previous four weeks were asked if they worked in one, two, three, or four of those weeks. This helps with more accurate analysis. Whether a respondents’ employment agreement was a written agreement or not was asked of all employees who said they had an individual or collective agreement. An additional health and safety question for employees was added. This asked if there were reasonable opportunities to take part in improving health and safety at their place of employment (main job). ##Table changes## ###Ethnicity classification### SoWL uses the total response output method for classifying ethnicity. Using this method, people who reported more than one ethnic group are counted once in each group reported. This means the total number of responses for all ethnic groups can be greater than the total number of people who stated their ethnicities. See the New Zealand statistical standard for ethnicity (2005) for more information. ###Australian and New Zealand Standard Industrial Classification 2006### Since the September 2009 quarter, industry statistics are based on the Australian and New Zealand Standard Industrial Classification 2006 (ANZSIC06), the latest edition of the classification. The 1996 version (ANZSIC96) was used in the previous SoWL release. Note that industry outputs defined using ANZSIC06 are not comparable with those based on ANZSIC96. ###New Zealand Standard Industrial Output Categories### With the introduction of ANZSIC06, Statistics NZ also developed the New Zealand Standard Industrial Output Categories (NZSIOC), which help standardise outputs. Under NZSIOC level one, industries are published at the 1-digit divisional level, apart from three categories which are combined ANZSIC06 divisions. The category titled ‘retail trade and accommodation’ is the combined ‘retail trade’ and ‘accommodation and food services’ divisions. The ‘professional, scientific, technical, administrative, and support services’ category is the combined ‘professional, scientific, and technical services’ division and the ‘administrative and support services’ division. The ‘arts and recreation services’ division is combined with the ‘other services’ division to form the ‘arts, recreation, and other services’ category. See the Australian and New Zealand Standard Industrial Classification 2006 (ANZSIC06) for more information. ###Reference period### SoWL is a supplement to the HLFS and was carried out in the December 2012 quarter. All eligible responding individuals in the HLFS who were employed in the reference week were asked to participate. The survey was carried out from 7 October 2012 to 5 January 2013. ##General information## ###Data source### SoWL was collected by computer-assisted interviewing (CAI). Part of the data was collected by computer-assisted personal interviewing (CAPI) for selected households (approximately 30 percent of all SoWL respondents). The remaining households were surveyed by centralised computer-assisted telephone interviewing (CATI). ###Target population### The target population for SoWL is the employed population within the HLFS target population. This is the usually resident, civilian population of New Zealanders aged 15 years and over and living in occupied private dwellings, who were employed for one hour or more in the HLFS reference week. 'Employed' includes all respondents who worked for pay or profit, or worked without pay in a family business or farm, or who had a job, business, or farm that they were away from because of sickness, holidays, or any other reason. The survey does not provide statistics for residents of institutions (eg retirement homes, hospitals, prisons), residents who are temporarily staying in non-private dwellings when contact is attempted, members of the permanent armed forces, and members of the non-New Zealand armed forces. It also excludes overseas visitors who intend to stay in New Zealand for less than 12 months, New Zealand residents temporarily overseas when contact is attempted, non-New Zealand diplomats and diplomatic staff, and those aged under 15 years. ###Accuracy of the data### This section outlines the methodology used for dealing with sampling errors in the data. Two types of error are possible in estimates based on a sample survey: sampling error and non-sampling error. ####Sampling errors#### Sampling error can be measured, and quantifies the variability that occurs by chance because a sample rather than an entire population is surveyed. We calculate sampling errors using the jackknife method. It is based on the variation between estimates, based on different subsamples taken from the whole sample. This is an attempt to see how estimates would vary if we were to repeat the survey with new samples of individuals. We calculate sampling errors for each cell in the published tables. For example, the estimated total number of employees that are on an individual agreement is 1,100,100. This estimate is subject to a sampling error of plus or minus 28,500 or 2.59 percent (measured at the 95 percent confidence level). This means that there is a 95 percent chance that the true number of employees on individual agreements lies between 1,071,600 and 1,128,600. Smaller estimates, such as the total number of casual workers whose reasons for doing casual work are lifestyle and family 19,700, are subject to larger relative sampling errors than larger estimates. This estimate is subject to a sampling error of plus or minus 3,800 or 19.6 percent (measured at the 95 percent confidence level). This means that there is a 95 percent chance that the true number of casual workers living whose reasons for doing casual work are lifestyle and family lies between 15,900 and 23,500. The following table shows the likely sampling errors of estimates of different sizes. This table can be used by finding the closest figure to the estimate of interest in the left-hand column of the table and reading off the corresponding relative sampling error in the right-hand column. For example, a total estimate of 43,200 employed people would have a sampling error of about 15 percent. Estimates of less than 10,000 within the output tables are likely to have relative sampling errors between 30 and 50 percent; hence, these estimates should be used with caution. The SoWL relative sampling errors are slightly larger than those for the HLFS employed estimates because SoWL has a smaller sample size. Guide to Survey of Working Life sampling errors Size of survey estimates Sampling error(1) Relative size of sampling error (%)(2) 3,500 1,600 45 5,000 2,000 40 7,500 2,600 35 10,000 3,000 30 20,000 4,000 20 30,000 6,000 15 40,000 6,000 15 50,000 6,500 13 75,000 8,250 11 100,000 9,000 9 300,000 15,000 5 700,000 21,000 3 1. Equivalent to the 95 percent confidence interval half-width. 2. Sampling error as a percentage of the survey estimate. ###Non-sampling errors### Non-sampling errors are all errors that are not sampling errors and are not quantifiable. Non-sampling errors include unintentional mistakes by respondents when answering questions, variation in the respondent's and interviewer's interpretation of the questions asked, and errors in recording and coding data. Statistics NZ endeavours to minimise the impact of these errors through applying best survey practices and by monitoring known indicators (eg non-response). ###Suppressed estimates in this release### All estimates provided in the output tables have a relative sampling error (measured at the 95 percent confidence level) of less than 50 percent. Some estimates are suppressed (replaced by 'S' in the tables) for reliability and confidentiality reasons. These suppressed estimates had a relative sampling error of 50 percent or more and/or reflect a low number of responses (10 or fewer). ###Editing and imputation### A minimal approach to editing was implemented for SoWL. With CAI, the computer software runs checks for validity and consistency as responses to questions are captured. If required, the software prompts the interviewer to clarify answers with the respondent at the time of interview. This keeps the number of inconsistent answers low. A further round of validity, logic, and error checks was performed on the data at the data processing stage. A unit (or complete) non-response to the SoWL occurred either when an eligible individual in the sample did not respond to the SoWL questionnaire or did not respond to all core questions in the SoWL questionnaire. Any non-responding employed individuals from the HLFS sample were dealt with by adjusting the weights of the responding SoWL individuals. Item (or partial) non-response could occur within the responses for SoWL. This includes a response of 'don't know' or 'refused' to non-core questions. Since all the core SoWL questions had been answered, the record was deemed to be a full response. No imputation has been applied to any item non-response. If a response to age, sex, or full-time/part-time status was missing in the HLFS then it will have been imputed by the HLFS and used in SoWL. There is no other imputation for variables collected in SoWL. ###Interpreting the data### ####Mean (average) and median#### The mean or average is calculated as the total divided by the number of units in the population. A mean can be sensitive to extreme values. Unusually high or low values will have a large impact on the estimate of the mean. The median is the value at which half the units in the population have lower values and half have higher, when all values are ordered from highest to lowest. It corresponds to the 50th percentile. The median is less sensitive to extreme values than the mean. ####Rounding#### All estimates provided in this release are independently rounded to the nearest hundred. For this reason estimated totals may differ from the sum of individual cells. All percentages are calculated using unrounded figures and are rounded to one decimal place. ####Questionnaire content and structure#### The SoWL questionnaire contained the following sections: #####Job tenure:##### Information on how long the respondent had been working for their employer in their main job, or in their business if they were self-employed. #####Employment relationships of employees:##### Only respondents who were employees (working for wages or salary) in their main job were asked if they were permanent or temporary employees. If temporary, they were asked additional questions about the types of temporary work they were doing to enable them to be priority classified as: a casual worker, fixed-term worker, temporary agency worker, seasonal worker (employment relationship not further defined), or some other type of temporary worker. Temporary employees were also asked if their hours of work changed from week to week to suit the needs of their employer, about their reasons for doing temporary work, and their preference for getting an ongoing/permanent job. #####Working-time patterns:##### All respondents were asked about patterns across all their jobs. We collected the following working-time information: usual working time usual number of days worked per week overall work pattern (mainly daytime, mainly evening, mainly night, changing shifts, other) preference for working at different times of the day than those usually worked whether they worked long hours and if this caused any difficulties preference for working fewer hours and earning less in their main job. Respondents who had worked in the four weeks before the interview were also asked the following information for that four-week period: incidence of work for one hour or more at non-standard times – the number of times worked at night, in the evening, in the early morning, on a Saturday, and on a Sunday payment for any work done at the weekend or in the evening any difficulties caused by working at a non-standard time number of hours of paid overtime and other extra unpaid hours. The numbers and proportions for people who did some work on Saturdays and Sundays may be slightly underestimated in the tables. These figures do not include people who did weekend work but did not specify if they worked on a Saturday or a Sunday, or those who did not know how many times they worked on a Saturday or a Sunday in the last four weeks. #####Work at home:##### Information on the number of hours worked from home in the four-week period prior to the interview was collected. Employees (working for wages or salary) were also asked if they had an arrangement with their employer to be paid for any work done at home. #####Job flexibility:##### Respondents were asked about job flexibility options available to them in their main job. This information was asked for: if they had flexible hours available in their main job (all employed) if their employer would let them take a few days unpaid leave if needed (employees only) if their employer would let them reduce their hours to less than 30 a week if wanted (full-time employees only) how much notice they had of their work schedule (temporary agency, casual, and seasonal workers, and those who worked changing shifts or some 'other' work pattern only) if they could make changes to their shifts if wanted (employees who worked changing shifts only). #####Terms and conditions of employment:##### Only employees (working for wages or salary) were asked these questions. Information on union membership, perceived job security, employer-funded study and training, annual leave entitlement, and whether the respondent was on a collective or an individual employment agreement was collected. #####Work-related health and safety:##### These questions focused on work-related health and safety issues. Respondents were asked about the extent to which they had experienced these work-related health problems in the last 12 months: finding being at work or the work itself stressful physical problems or pain because of work tiredness from work that affected life outside work. Respondents were also asked if they had experienced discrimination, harassment, or bullying at work in the last 12 months. Employees were asked how well health and safety risks were managed in their main job. #####Parent/caregiver status:##### Where there was a child in the household aged under 14 years, the respondent was asked if they were a parent or main caregiver to that child. #####Satisfaction:##### Respondents were asked about their level of satisfaction with their main job, and overall satisfaction with their work-life balance. #####Earnings:##### Information on earnings for all respondents working for pay or profit in their main job or business was collected. For employees, only earnings from the main job was collected. For the self-employed, earnings from all forms of self-employment from the previous 12 months was collected. ####Confidentiality#### Only people authorised by the Statistics Act 1975 are allowed to see your individual information, and they must use it only for statistical purposes. Your information is combined with similar information from other people or households to prepare summary statistics. ####Liability#### While all care and diligence has been used in processing, analysing, and extracting data and information in this publication, Statistics NZ gives no warranty it is error-free and will not be liable for any loss or damage suffered by the use directly, or indirectly, of the information in this publication. ####Timing#### Our information releases are delivered electronically by third parties. Delivery may be delayed by circumstances outside our control. Statistics NZ does not accept responsibility for any such delay. ####Crown copyright©#### This work is licensed under the Creative Commons Attribution 3.0 New Zealand licence. You are free to copy, distribute, and adapt the work, as long as you attribute the work to Statistics NZ and abide by the other licence terms. Please note you may not use any departmental or governmental emblem, logo, or coat of arms in any way that infringes any provision of the Flags, Emblems, and Names Protection Act 1981. Use the wording 'Statistics New Zealand' in your attribution, not the Statistics NZ logo. en-NZ