FOI reference: FOI-2024-2354
You asked
I was hoping to ask a few questions on the methodology used with RPI for the "Air fares" and "Mobile Phone Applications".
For the Air fares index, the ONS states in the technical manual that "the airlines chosen are those with a departure flight closest to a pre-specified time on a particular day on randomly selected routes". Is there a method to determining the pre-specified departure time for the sampling, and is it always the same time each month?
Within Mobile Phone Applications, are the top 30 apps used for price sampling inclusive of games? These are separated out in some app stores. Further, are the top 30 apps defined to be those with the most downloads for phones, or are apps for tablets also used/taken into account?
The ONS has previously said that there are multiple providers of data (retailers) for mobile phone applications. Are these retailers weighted equally, or is there a volume metric by which these are weighted?
Are the list of the top 30 apps from each provider always taken at the same time each index day from the retailer?
We said
Thank you for your request.
For the airfares index, a time has been chosen at which it is likely that flights will be departing from. The target time is the same every month and price collectors select a flight that is as close as possible to the initial day and time selected. However, we retain some flexibility when selecting flights which means we don’t need to use exactly the same time or day when collecting prices.
With mobile phone applications, the products priced include some games. There is an overlap between the apps used for phones and tablets, so our sample, though aiming to collect phone apps, includes some apps for tablets. The different retailers used are not equally weighted, the weights are based on estimated spending. The collection is taken in the middle of the month around index day but not specifically at the same time or same day each month.