Misleading statistics

It's always been recognised that statistics can be very misleading.

Unfortunately though, too many people can be fooled by misleading statistics. Remember the £350m per week for the NHS?. Boris Johnson subsequently admitted that was untrue.

www.theneweuropean.co.uk/brexit-news/boris-johnson-350-million-a-week-nhs-claim-55554

We need to learn to question statistics, but not to blythly dismiss them all as "lies and damned lies".

Its not the statistics that are misleading, its the way they are presented and interpreted.

It's the same with surveys. The results can be skewed depending on the questions asked, how they are worded and the people who take part.

You are right Smileless Newspaper surveys have to be taken with a huge pinch of salt as they often turn out to be based on a sample of their readers, whose opinions, unsurprisingly coincide with those of the newspaper.

Alegrias1

Its not the statistics that are misleading, its the way they are presented and interpreted.

The statistics are factual, however they can be used to prove or disprove anything. Changing the baseline or the scale can give a completely false picture.

Statistics honestly and carefully collected are meaningful. No matter how much effort is made to deceive, they cannot be used to prove or disprove anything.

All civilised societies need good authentic statistics and it is wrong to willfully dismiss them as meaningless. We need to plan for the future which is why a census is undertaken every ten years.

Alegrias1

Its not the statistics that are misleading, its the way they are presented and interpreted.

This x a million plus the motivation behind the way in which they are presented in the way they are. One of my ‘favourites’ this last year has been the use of the log scale (or not) in graphs.

Re motivation, there is a famous quote from Churchill to I believe a young Iain McCloud

‘I gather young man that you wish to be a Member of Parliament. The first lesson that you must mean is, that when I call for statistics about the rate of infant mortality, what I want is proof that fewer babies died when I was Prime Minister than when anyone else was Prime Minister. That is a political statistic’

Damn it - learn not mean - I thought I’d been so careful gggrrrrrr

“Most people use statistics like a drunk man uses a lamppost; more for support than illumination”

Andrew Lang

But as we make sense of these numbers we need to put some thought into how we use them.

We need to ensure that we don’t miss the woods for the trees. We should always keep an eye on the larger picture and our ultimate goal.

We need to ensure our tools are tuned correctly. Errors in measurement can result in a garbage-in-garbage-out decision making loop.

We need to plan the information we want to collect very early so that we don’t have a lot of missing data points.

We should look for biases we may have which could flaw our conclusions.

Correlation does not mean causation. We will need to be scientific about measuring root causes.

Numbers are emotionless and can be trusted blindly but only if the above is true.

medium.com/the-innovation/using-statistics-the-case-of-a-drunken-man-and-a-lamppost-3bb8532d66a6

Sadly most people even use the word statistics incorrectly. Statistics is the discipline that concerns the collection, organization, analysis, interpretation, and presentation of data - each of these aspects - collection, organisation, analysis, interpretation and presentation needs considering when trying to understand and make sense of information we are presented with. I could wax lyrical for ever on all aspects of this. Yes I know ......🙄

Perhaps one of the very few positive outcomes of the pandemic might be an increase in the general public's awareness of the importance of statistics.

For the first time we have seen statisticians and epidemiologists on tv and heard them on radio most days. I suspect that two years ago many British people would not have known these professions existed, let alone understand the importance of the work they do.

IMO, what most people understand by statistics is, that they can be used to support whichever viewpoint you are promoting and the same figures can be presented in a negative or positive way.

The problem is that most people aren’t taught about understanding statistics and therefore are unable to differentiate between or evaluate so much information they are presented with. They rely on the interpretation provided by for example, the politician or journalist providing the information without asking themselves what is the agenda/ motive behind that. This means that really important, valid information gets tarred with the same brush as dishonestly presented information.

Exactly SW. In a simplified form, it’s also the words that go with it.
X% of people still haven’t been vaccinated makes it sound negative
whereas
Y% of people have already been vaccinated sounds positive.
People will use the X or Y version depending on what they are saying.

Yes exactly. Here’s another example beloved of ‘journalists’

Risk of x cancer doubles because of y behaviour

The research shows that the absolute risk doubles from 1 in a million to 2 in a million

I do feel that most of our reporters/journalists are... well lets say "statistically challenged" if we're being nice . Figures get passed on either with no understanding at all or with the intent of misleading the audience.

The whole thing about "x people died after they had the vaccine", for instance. And the announcement that a new variant is 30% more fatal, to use suzie's example.

Drives me mad. This statistician is worth listening to, I find: twitter.com/d_spiegel

The Government Statistical service publishes advice for journalists, businesses and other organisations to present figures in a more understandable way, but I wonder how many take the trouble to read it and try to put it into practice?

gss.civilservice.gov.uk/policy-store/tips-for-communicating-the-impact-of-coronavirus-covid-19/

One of my favourite pieces of data analysis from 30 odd years ago is:
People in Brighton have the least fillings dentist's report.
But taking into account the demographics of the area then; an aging population in a time when most elderly people had full sets of false teeth! 😂

There are Lies
Damned Lies
And Statistics !

Statistical knowledge helps you use the proper methods to collect the data, employ the correct analyses, and effectively present the results. Statistics allows you to understand a subject much more deeply *

We need to teach the critical thinking required as we won't stop needing data to make decisions and prove or disprove theories.

*The Importance of Statistics

TwiceAsNice

There are Lies
Damned Lies
And Statistics !

I have said it before TwiceAsNice, that is just not clever any more if it ever was.

There are liars
Damned liars
And those who misuse statistics.

Statistics cannot do anything without humans interpreting them.

varian

The Government Statistical service publishes advice for journalists, businesses and other organisations to present figures in a more understandable way, but I wonder how many take the trouble to read it and try to put it into practice?

gss.civilservice.gov.uk/policy-store/tips-for-communicating-the-impact-of-coronavirus-covid-19/

There's also the Office for Statistical Regulation and other bodies that criticise politicians when they misuse statistics but as the misuse is invariably deliberate and for political ends, it makes not the slightest difference.