International Engagement by New Zealand Businesses: Key results from the Business Operations Survey 2007

This chapter provides a technical description of the data used to compile this report. It focuses on the data quality and the definitions and processes used for data collection and analysis.

Survey background

The New Zealand Government has many initiatives aimed at increasing the country's economic growth rate above the OECD average and sustaining this growth over a number of years. For New Zealand’s economic performance to be measured against these initiatives, a large range of data on a variety of measures needs to be collected.

Because of this need, Statistics New Zealand developed an integrated, modular survey – the BOS – as a way of collecting the required information while minimising the reporting load for New Zealand businesses. The survey was designed to include up to three ‘modules’ and has been run annually since 2005.

The survey was developed by Statistics NZ with the Ministry of Economic Development, New Zealand Trade and Enterprise, and Treasury.

The main objective of the survey is to collect information on the operations of New Zealand businesses so that business behaviour, capacity, and performance can be quantified. In addition, each module in the survey has its own specific objectives. The modules included in the BOS 2007 and their objectives are listed below.

Module A: Business operations module

This module provides a longitudinal series of information about business performance. The information required can be grouped into two main categories:

  • financial performance measures 
  • business environment measures.

The purpose of collecting financial performance measures is to measure and monitor business performance, and to relate the impact of potential enablers on this performance. An important element of these financial measures is their longitudinal dimension, which allows changes over time to be analysed. This analysis will assist in the development of models that investigate causal relationships. As well as traditional measures of performance, such as turnover and profitability, there is also a desire to collect information on areas such as export intensity. The purpose of collecting environmental information is to analyse any relationships between the environment in which a business operates and the results it achieves.

Module B: Innovation

This module provides information on the characteristics of innovation in New Zealand’s private-sector businesses. The information obtained will allow the development of policy that will encourage innovation and understand the dynamics of innovative businesses. The innovation module runs every two years, and replaced Statistics NZ's former Innovation Survey, last run in 2003. The module was designed according to OECD guidelines. It aims to understand the contribution of all aspects of innovation to the New Zealand economy by measuring:

  • levels of firm innovation 
  • how and why firms collaborate with other firms and institutions in order to innovate 
  • factors affecting the ability of firms to innovate 
  • outcomes of innovation for firms, including its effect on exports.


Module C: International engagement module

This module covers data previously uncollected on the strategies taken by New Zealand businesses towards international engagement. The objectives of this module echo and extend beyond those of the overall survey. The module collects information on the practices and behaviours associated with either current, past, or future international engagement, which may have either positive or negative impacts on a business's performance. This module has topics that measure:

  • current overseas income 
  • previous overseas income 
  • future generation of overseas income 
  • overseas production of goods and services 
  • purchases from overseas.


Data collection

The BOS 2007 was a postal survey. Initial contact was made to key and/or complex businesses by telephone before the mail-out to determine the appropriate person(s) within the business to whom the survey questions could be directed. For all other businesses, the survey form was addressed to the managing director. The survey was posted out in August 2007 and collected information for the last financial year for which the business had data available at that point.

Target population

The target population for the BOS 2007 was live enterprise units on Statistics NZ’s Business Frame that at the population selection date: 

  • were economically significant enterprises (with an annual GST turnover figure of greater than $30,000) 
  • had six or more employees 
  • had been operating for one year or more 
  • were classified to Australian and New Zealand Standard Industrial Classification – New Zealand Version 1996 (ANZSIC96) codes listed as ‘in scope’ in ‘List 1’ below 
  • were private enterprises as defined by New Zealand Institutional Sector 1996 Classification (NZISC96) listed in ‘List 2’ below.

An enterprise is defined as a business or service entity operating in New Zealand, such as a company, partnership, trust, government department or agency, state-owned enterprise, university, or self-employed individual.

The final estimated population size for the survey was 35,004 enterprises.

List 1 – ANZSIC96 codes in scope

In scope

ANZSIC96 code – description
A – Agriculture, forestry, and fishing
B – Mining and quarrying
C – Manufacturing
D – Electricity, gas, and water supply
E – Construction
F – Wholesale trade
G – Retail trade
H – Accommodation, cafes, and restaurants
I – Transport and storage
J – Communication services
K – Finance and insurance
L – Property and business services
N – Education
O – Health and community services
P91 – Motion picture, radio, and television services
P93 – Sport and recreation

Out of scope
M – Government administration and defence
P92 – Libraries, museums, and the arts
Q – Personal and other services.

List 2 – NZISC96 codes in scope

In scope
NZISC96 code – description
1111 – Private corporate producer enterprises
1121 – Private non-corporate producer enterprises
1211 – Producer boards
1311 – Central government enterprises
2211 – Private registered banks
2221 – Private other broad money (M3) depository organisations
2291 – Private other depository organisations nec
2311 – Private other financial organisations excluding insurance and pension funds
2411 – Private insurance and pension funds.

Out of scope
1321 – Local government enterprises
21 – Central bank
2212, 2213, 2222, 2223, 2292, 2293, 2312, 2313, 2412, 2413 – Central and local government financial intermediaries
3 – General government
4 – Private non-profit organisations serving households
5 – Households
6 – Rest of world

Sample design

The sample design was a two-level stratification according to ANZSIC industry and employment size groups. This information was obtained using enterprise ANZSIC industry and employment information from Statistics NZ's Business Frame.

The first level of stratification was 33 ANZSIC industry groupings. Within each of the ANZSIC groups there is a further stratification by employment size group. The four employment size groups used in the sample design are:

  • 6–19 employees (small) 
  • 20–29 employees (medium 1) 
  • 30–49 employees (medium 2) 
  • 50 or more employees (large).

The two medium groups were amalgamated and the large size group further broken down for this report, as these businesses were of particular interest for some of the results.

Measurement errors

The BOS 2007 results are subject to measurement errors, including both non-sample and sample errors. These errors should be considered when analysing the results from the survey.

Non-sample errors

Non-sample errors include mistakes by respondents when completing questionnaires, variation in the respondents’ interpretation of the questions asked, and errors made during the processing of the data. In addition, the survey applied imputation methodologies to cope with non-respondents. Statistics NZ adopts procedures to minimise these types of error, but they may still occur and are not quantifiable.
Given the nature of the data collected, there are limitations on the level of accuracy that can be expected from the survey. Businesses’ records may not be in the form required and some estimation by the respondent may be needed.

Sample errors

Total revenue was used as the numeric design variable for the survey. The sampling error on the total revenue figure was measured at 3.8 percent at the 95 percent confidence level. Most results in this report relate to percentage of businesses. For businesses with current overseas income (a key output from module C) the estimate of 20 percent has a 95 percent confidence interval from 18.2 to 21.8 percent.
Sample errors for individual variables of interest can be supplied upon request.

Response rate

The BOS 2007 targeted an 80 percent response rate and achieved an actual response rate of 80.1 percent, which represented 5,728 businesses.

Non-response and imputation

Unit non-response
Unit (or complete) non-response occurs when units in the sample do not return the questionnaire. The initial selection weight of the remaining units in the stratum was adjusted to account for the unit non-response (no item non-response imputation would occur for the units that did not return the questionnaire).

Item non-response
Item (or partial) non-response is when units return the questionnaire but some questions are not answered. No item non-response imputation was carried out for units that did not answer 60 percent or more of the questions they were required to answer (based on questionnaire routing rules). The respondents who did not meet this criterion were classified as unit non-responses and the weights were adjusted accordingly.

Imputation of numeric variables
The imputation methods used were weighted mean imputation and donor imputation.
Using the weighted mean method, a weighted mean was calculated from linked responding units for each numeric linecode within each imputation cell. Non-responding units were then imputed with the weighted mean for their imputation cell. Weighted mean imputation was used to impute totals.

Donor imputation randomly selected a donor from within each imputation cell. The non-respondent was then imputed with the value(s) from the donor. Donor imputation was used to impute components and percentages so that the distribution was maintained.

Imputation of categoric questions
For categoric imputation the method used was nearest neighbour imputation, which involved finding a donor with the most similar responses. The donor supplied responses for all categoric variables requiring imputation. If the donor unit did not respond to any of the variables requiring a response, then we chose the next best donor to supply this information. This was continued until all the variables had a response.

Definitions

ANZSIC: Australian and New Zealand Standard Industrial Classification System – New Zealand Version 1996.

Business Frame: A register of all businesses operating in New Zealand.

Employees: The number of employees is defined by an enterprise's rolling mean employment (RME) count. RME is a twelve-month moving average of the monthly employment count (EC) figure. The EC is obtained from taxation data.

Enterprise: A business or service entity operating in New Zealand. It can be a company, partnership, trust, estate, incorporated society, producer board, local or central government organisation, voluntary organisation, or self-employed individual.

Goods and services tax (GST): Respondents are asked to exclude GST if possible in the financial figures provided in the questionnaire. If they did not, Statistics NZ takes out GST to make all enterprises comparable.

Last financial year: For this survey, refers to the last financial year for which the business had results available at August 2007, as entered on the questionnaire.

Other definitions more specific to the data in this report are given in the appropriate chapters.