UK Retail Sales Unexpectedly Jump in January — Looking Beyond the Headline Number to Debunk it and Uncover Flawed Methodology Used by the ONS

Optimism reached a new high in the UK on Friday and the UK equity market and the GBP jumped, when the Office of National Statistics published an unexpected jump in the retail sales index:

(The Telegraph) — Official retail sales data for January rose 0.9pc month-on-month, well above gloomy forecasts of a 0.4pc decline, as falling inflation and post-Christmas discounting lured consumers back to the shops. 

Economists said the performance was surprisingly strong because it came on the back of a 0.6pc rise in December, which was itself better than had been expected. 

"It suggests at the very least that we will be growing by 0.5pc in the first quarter and probably faster than that," said Scotia Capital economist Alan Clarke, who was one of the first to warn of a contraction before the 0.2pc decline in the final three months of last year. "This is the third strong indication that the UK economy has turned the corner."

As per usual, economists — this highly (over)paid yet ignorant and incompetent bunch — completely missed their forecast, and then tried to explain a posteriori the reason why sales jumped in January, yet again completely missing the point.

First, here are a couple of other pieces of news that were not making headlines — obviously so because market participants are in über-bullish mode and are only look at the bright side of the news:

(The Daily Mail) — Around 14 shops are shutting every day on the High Street, alarming figures show. 

Last year 5,268 shops were closed by major retailers and only 5,094 opened, according to a study by accountants PricewaterhouseCoopers and the Local Data Company. 

It was the first time since the height of the recession in 2009 that more shops were shut than opened.
[...]
The real number of closures could well be higher as the research only focused on chain stores in the 500 biggest town centres.
[...]
London fared worst in 2011, with 1,084 shops shutting and just 983 opening, according to the study.
[...]

Beyond showing the incompetence of Mervyn King, the following report confirms that debt deflation has started in the UK:

(The Daily Mail) — Bank of England Governor Sir Mervyn King yesterday spoke out against the ‘harsh treatment’ of small companies which are still ‘suffering’ at the hands of the banks.

He said ‘market failure’ meant firms are being starved of the funds they need to grow, create jobs and drive the economic recovery.

The startling statistics emerged in Bank of England figures showing that net lending fell by £10.7 billion in 2011 – in other words, the banks received £10.7billion more in loan repayments than they gave out in new loans. That took the total fall since the end of 2008 to £82.7 billion.

After all the manipulation and fiddling that the BoE is doing, the one thing that is currently working fine — small business not borrowing, and banks not lending to insolvent firms — is considered to be a "market failure". This is the favorite game of central planners and socialists: blame the market for their own failure, and make a bigger mess trying to fix it.

Summary:

• Retail sales as reported by the ONS jumped in Jan
• While business are closing at an alarming rate of 14 shops a day for the whole of 2011
• And debt has been deflating for 3 years in a row, showing that business are not trying to borrow to expand (in obvious contradiction with what would happen if sales were rising).

So, where am I going will all this?

As with any thing reported by the government, one must look a bit further than the headline number — ironically, market participants whose very job is to do so won't do it — and try to find what is really going on.

Looking at the methodology used by the ONS to calculate their retail sales index gives us the answer:

Understanding the data

Quick Guide to the Retail Sales Index (116.9 Kb Pdf)

Interpreting the data
The Retail Sales Index (RSI) is derived from a monthly survey of 5,000 businesses in Great Britain. The sample represents the whole retail sector and includes all large retailers and a representative panel of smaller businesses. Collectively all of these businesses cover approximately 95 per cent of the retail sector in terms of turnover.

There, you have it: they survey 5,000 businesses, completely ignoring the fact that many businesses are closing on a daily basis. This creates a massive survivorship bias and leads to completely distorted numbers.  Could Wikipedia's quote fit more to the ONS flawed methodology?

Survivorship bias is the logical error of concentrating on the people or things that "survived" some process and inadvertently overlooking those that didn't because of their lack of visibility. This can lead to false conclusions in several different ways. 

The survivors may literally be people, as in a medical study, or could be companies or research subjects or applicants for a job, or anything that must make it past some selection process to be considered further. 

Survivorship bias can lead to overly optimistic beliefs because failures are ignored, such as when companies that no longer exist are excluded from analyses of financial performance.

Should someone send this link to the incompetent people at the ONS so that they can fix their methodology?

Finally, not only the survivorship bias make you miss direct losses due to businesses closing, but these failures make the surviving businesses more prosperous, artificially making the retails sales numbers bigger.

Let me give an example to illustrate this last point: imagine your local baker closes down because it wasn't a viable business. Yet, some part of their customers will still want to buy bread and would divert their shopping to another other local baker. The local baker might see it sales raise by say 20%, yet that original baker lost 100% of its sales. So the surveyed shop would report a jump in sale of 20%, but the loss of that 100% from the closed-down baker will not be accounted for in the retail sales number.