**BACKGROUND NOTES **

**Definitions and Release Policy**

1. Gross Domestic Product (GDP) is a measure of the value added to materials and other inputs in the production of goods and services by resident organisations; before allowing for depreciation or capital consumption. Net receipts from interest, profits and dividends abroad are excluded.

2. The estimates produced in this publication measure **GDP at basic prices**, also referred to as **Gross Value Added (GVA)**, which does not account for taxes or subsidies on products. The estimates are produced in **constant prices**, meaning that they been adjusted for inflation to represent changes in the volume of output rather than value; in other words growth is estimated in real terms.

3. This publication includes data available to 13^{th} April 2012.

4. The next publication of GDP for Scotland, covering the first quarter of 2012, is planned for Wednesday 18^{th} July 2012.

**Revisions**

5. Results in this Statistical Bulletin incorporate revisions to previously published estimates. Tables 8 – 13 identify the extent of revisions since the last publication in October 2011. Revisions to index numbers (not to growth rates) are shown to one decimal place for total GVA and GVA excluding oil & gas. Revisions are shown to zero decimal places for all other sectors.

6. The latest estimates of total GVA growth show that 2011 Q3 has been revised to 0.4% from 0.5% published in January 2012. Growth in 2011 Q2 is revised to 0.0% from 0.2%. The 2011 Q1 growth is unchanged at 0.2%.

7. There are revisions to some industry sub-series due to updated source data, including business survey returns and price indices. Small revisions also occur where the most recent data causes re-estimation of previous quarters, or updating of seasonal adjustment parameters

8. In this publication, the most significant revisions are to the Electricity and Gas supply and Construction sectors. These revisions are driven by updates to source data and associated refinement of seasonal adjustment parameters.

9. The Scottish Government’s revisions policy for economic statistics is available at:

http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/ScotStat/revisionspolicy

**Key quality issues**

*10. Common pitfalls in interpreting series: *Scottish GVA estimates will generally be less reliable than the equivalent estimates for the UK, primarily because the UK figures are produced by balancing three independent sets of estimates (Output (GVA), Income and Expenditure-based approaches).

11. Furthermore, the survey data for Scotland tend to be based on smaller numbers of units, making figures for Scotland more likely to be susceptible to statistical variance. Statistical variance in estimates is directly proportional to the variability in the underlying population of interest. In the current economic climate, the variability in the economy is increased and users should bear this in mind when interpreting all economic indicators.

12. Very few statistical revisions arise as a result of 'errors' in the popular sense of the word. All estimates, by definition, are subject to statistical 'error' but in this context the word refers to the uncertainty inherent in any process or calculation that uses sampling, estimation or modelling. Most revisions reflect either the adoption of new statistical techniques, or the incorporation of new information which allows the statistical error of previous estimates to be reduced. Only rarely are there avoidable 'errors' such as human or system failures, and such mistakes are made quite clear when they do occur.

**Reliability**

13. Revisions to time series provide one indication of the reliability of key indicators. The tables below show summary information on the size and direction of the revisions which have been made to results covering a five-year period. A statistical test has been applied to the average revisions to find out if they are statistically significantly different from zero. An asterisk (*) shows that the test is significant.

14. Table 1 below shows the revisions to estimates of GDP between their first publication and next publication one quarter later, for the period 2006 Q4 to 2011 Q3. Table 2 shows the revisions to GDP estimates between their first publication and one year later, using estimates for the period 2006 Q1 to 2010 Q4.

15. The *average revision* can be used as an indicator of bias (systematic over- or under-estimation) in the initial estimates of GDP. Both tables suggest that there is no bias in the initial release of these statistics. The *average absolute revision* gives an indication of how much users might expect the initial estimate to be revised up or down in future publications.

Table 1.

| Value in latest period (2011 Q4) | **Revisions between first publication and estimates one quarter later (covering period 2006Q4-2011Q3)** |

Average revision | Average absolute revision (without regard to sign) |

Quarterly GDP growth (per cent) | **-0.1** | **-0.03** | **0.12** |

Table 2.

| Value in latest period (2011 Q4) | **Revisions between first publication and estimates one year later (covering period 2006Q1-2010Q4)** |

Average revision | Average absolute revision (without regard to sign) |

Quarterly GDP growth (per cent) | **-0.1** | **-0.03** | **0.17** |

16. A paper summarising analysis of revisions to these GDP statistics, and identifying the main sources of revision, is available on the Scottish Government website at: http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/GDP/research/Revisions2010

**Cash estimates of GVA**

17. Estimates of the cash value of Gross Value Added (GVA) at current prices for Scotland (and other regions of the UK) are produced by the Office for National Statistics. Estimates for 2010 were published on 14th December 2011. The ONS current price value estimates are methodologically different from the Scottish Government volume (constant price) index and are based on different data sources.

18. The Scottish National Accounts Project team are developing a number of National Accounts measures for Scotland, including estimates of cash value GVA and GDP (including taxes and subsidies on products). These statistics are not classed as National Statistics and are released as soon as they are ready following the GDP statistics. For further information on these statistics please see the SNAP website http://www.scotland.gov.uk/SNAP.

**Methodology Notes**

*Chain-linking*

19. Annual chain-linking is the technique used to compile the overall measure of GVA growth and also the other, lower-level published aggregates. The resultant indices represent changes in the value added, at constant prices, in the production of goods and services in individual industries.

20. Series are derived from indicators based on data from a wide range of sources. Examples include: deflated turnover, deflated production, the volume of a good or service sold or produced and, for some parts of the public sector, employee numbers.

21. The weights used to produce growth rates for Scotland reflect the latest Scottish Input-Output Supply and Use Tables published on 13 October 2010, with the latest weights relating to 2007.

22. The Office for National Statistics updated the weights used to compile their aggregate measures, including GVA, in the 2011 Q2 Quarterly National Accounts published on 5 October 2011. UK data are now calculated using weights relating to 2008.

*Seasonal Adjustment*

23. The data used in the production of these quarterly GDP estimates are seasonally adjusted in accordance with the European System of Accounts guidelines and international practice.

24. The X-12-ARIMA technique is used where appropriate to remove regular seasonal peaks and troughs so that the underlying trends and other features of the data are easier to identify. Further information about the seasonal adjustment of the GDP data can be found in section A3 of Scottish Economic Statistics 2006 (www.scotland.gov.uk/stats/ses).

*Methodology developments*

25. The Scottish GDP indices are under a continuing program of methodological development which is regularly peer reviewed by the Scottish Economic Statistics Consultants Group (SESCG). Information about SESCG, including papers and minutes from recent meetings, is available on the Scottish Government website at http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/ScotStat/comms.

**National Statistics**

26. National Statistics are produced to high professional standards set out in the National Statistics Code of Practice. They undergo regular quality assurance reviews to ensure that they meet customer needs. They are produced free from any political interference.

27. Detailed results for all industries, are available to download from the Scottish Government website www.scotland.gov.uk/gdp.

###### Issued by

Office of the Chief Economic Adviser

St Andrew’s House

Regent Road

Edinburgh, EH1 3DG

###### Telephone

Press Office: Karen MacKinnon 0131-244-2175

Statistician: Richard Morrison 0131-244-3768