The Industrial Production Index is based on input data from three different sources. The majority of the industries are calculated with information on deliveries, which corresponds to roughly 95 percent of the total added value. The conversion of delivery information into constant prices is done using the Producer Price Index, (PPI). Calculations for other industries are based on information about quantities produced and the number of hours worked.
Information about deliveries is collected via a monthly online questionnaire sent out to approximately 2 300 enterprise units. The survey's response rate is 80-85 percent, while the weighted response rate (where the size of deliveries for the responding companies is also considered) amounts to more than 90 percent.
All time series use 2005 as the reference base period. All monthly comparisons are based on working day adjusted and seasonally adjusted index values. Seasonal adjustment means making the corrections for the seasonal variations that reappear from year to year. The purpose is partly to show those changes that are not dependent on seasonal variations and thus can allow for comparisons with other months, and partly to study evident trends. Annual comparisons are only revised for calendar effects.
When the Industrial Production Index for a new month is published, the index for previous months is also revised. The material is normally revised for five months retroactively. This is mainly due to new and revised information that has been received. Seasonally adjusted figures and trend figures are always revised from January 2000 onwards.
When seasonally adjusting the Industrial Production Index, every series is seasonally adjusted individually using the TRAMO-SEATS program. TRAMO-SEATS was introduced in 2004 for the Industrial Production Index and is recommended by Eurostat for seasonal adjustment of official statistics.
An important part of this method is to identify a model for the actual time series for each industry. These models are used for forecasts of the actual Industrial Production Index for two years forward and the forecasts are used in the seasonal adjustments. Because the forecasts are completely dependent on the choice of the model, this may cause revisions of seasonally adjusted data to a greater or lesser extent. To reduce the effects of revisions in seasonally adjusted data, Statistics Sweden has chosen to follow Eurostat's recommendation to use fixed models during the period of one year. According to Eurostat recommendations, seasonal adjustments should be reviewed at least once every year, including the selection of models. This recommendation has been applied to the Industrial Production Index since 2004.
Review of the model
A new review of the model was done in connection with the publication in April 2012 for the data of February 2012 due to the correction of the original series done at the publication in March 2012.
Models for a number of series changed in connection with the review, mostly because the models are no longer optimally adapted for the input data. Due to the change in the model, revisions occur in the seasonally adjusted data to a greater or lesser extent, even back in time.
The next review of the model is planned to take place in connection with the publishing concerning December 2012.
For international comparisons, please refer to Eurostat:
Eurostat, Short-term business statistics