Page 72 - Special Topic Session (STS) - Volume 3

STS515 Steve MacFeely
4. What Universities could teach
A course that prepares statisticians for a career in official statistics would
3
ideally cover 4 broad domains : statistical systems; statistical techniques;
policy issues; and for want of a better heading, the political economy of data.
In the limited space available, a few elements of these domains are
highlighted. ‘Official statistical literacy’, which comprises of this wider mix of
issues would enrich the content of university courses, stimulate discussion and
give statistics students a better flavor of what their future career might involve.
4.1 Statistical Systems: This would include an introduction to the official
statistics eco-system comprising of national, regional and global statistical
systems. Understanding the mandate and function of the UN Statistical
Commission including: how internationally recognized classifications,
4
6
5
such as the ISIC , and framework methodologies, such as the SNA , are
developed; and how other regional and national statistical systems,
including international organisations coordinate their work. Statisticians
should also be introduced to: the UN Fundamental Principles of Official
Statistics [2], the Principles Governing International Statistical Activities [3]
and any regionally or nationally appropriate adaptations; professional
principles, such as, the ISI Declaration of Professional Ethics [4]; and
internationally recognized statistical quality assurance frameworks and
codes of practice, such as, the UN System statistical quality assurance
framework [5], or the UN National QAF [6] and any regionally or nationally
appropriate adaptations. An important element of any statistician’s work
(whether official or otherwise) will be dealing with legislation. Official
statisticians will need to be conversant with the national statistical law (and
those in Europe will also need to know their way around European statistical
legislation). But increasingly, concerns regarding privacy and
confidentiality 7 mean that all statisticians and data scientists must
understand the legal environment in which they work, in particular, data
protection and freedom of information legislation and how they interrelate.
As we expect more and more secondary digital data to be generated, the
legal issues of accessing and using these data are critical to ensuring a
statistician does no harm .
8
4.2 Statistical (and technological) Techniques: Traditional topics like distribution
theory, probability, sampling/weighting, multivariate analyses and

3 Although the focus of this paper is preparation for a career as an official statistician, most of
what is discussed in this section, would arguably be very valuable for any statistician.
4 https://unstats.un.org/unsd/statcom/
5 ISIC - International Standard Industrial Classification of All Economic Activities
6 SNA - System of National Accounts
7 UN Fundamental Principle of Official Statistics No. 6
8 ISI Professional Value 1.2.
61 | I S I W S C 2 0 1 9