Putting data in context can make a lot of difference to what a percentage really means. A 15% increase might mean a lot if you are dealing with big numbers, next to nothing if you start with small numbers.
A 100% increase in ten in a million becomes twenty in a million. Not any big deal. But an incorrect 100% increase in the volume of drugs injected by a doctor makes a big difference.
Take what it means to be 99.9% effective, in Six Sigma statistics we use this example quite a lot. In a health service in the UK it might mean 135 botched operations and 13 babies given to the wrong parents, every week.
A percentage is not really a number, it is a share. The simple question to keep in mind is one that always strives to put it into a proper, human context: "A share of what? A share of a lot - or a share of a little?"
Did you know that 87.5% of all statistics are made up on the spot.
Monday, 16 February 2009
Thursday, 12 February 2009
Percentages in Context
Just a reminder that before I talk about biblical facts I feel that I need to discuss just how data and it's interpretation can be manipulated to suit a particular persons point of view or particular slant. People take so called facts without question and believe that data. My objective is to show just how we can easily be fooled with numbers.
I heard it last week once again. In my career I have heard it many times. "I want all my staff to be above average", the speaker was a very senior manager and he was serious in his intent. Above what average was not discussed, and if he was talking about his own team he did not realise that is the team performance improves then guess what! The team operates with a new average and 50% of the people will be below that average. (No-body likes to think that they are below average, so like to think that they are above average) again in the 50% bracket.
Percentages might make news stories stand out, but without a connection to the human experience, can become meaningless. Take the following story on a breakfast news programme. The story was about taking a particular type of vitamin that researchers said could kill if taken in larger quantities. The television announcer said that taking these vitamins caused a 15% increase in death. Maybe I have got something wrong, but isn't the risk of death very high already? As far as I know the likelihood of death is 100%. It falls into the same arena when people say that they give 110% in work. Taking this particular type of vitamin apparently makes death even more certain.A 115% if you want a 'accurate' number.......
I heard it last week once again. In my career I have heard it many times. "I want all my staff to be above average", the speaker was a very senior manager and he was serious in his intent. Above what average was not discussed, and if he was talking about his own team he did not realise that is the team performance improves then guess what! The team operates with a new average and 50% of the people will be below that average. (No-body likes to think that they are below average, so like to think that they are above average) again in the 50% bracket.
Percentages might make news stories stand out, but without a connection to the human experience, can become meaningless. Take the following story on a breakfast news programme. The story was about taking a particular type of vitamin that researchers said could kill if taken in larger quantities. The television announcer said that taking these vitamins caused a 15% increase in death. Maybe I have got something wrong, but isn't the risk of death very high already? As far as I know the likelihood of death is 100%. It falls into the same arena when people say that they give 110% in work. Taking this particular type of vitamin apparently makes death even more certain.A 115% if you want a 'accurate' number.......
Wednesday, 11 February 2009
Two key lessons about surveys:
Surveys often 'merge' data. The bus company survey covered in the previous post had bundled together the people who answered the survey as 'more and the less inclined', and the people who are classified as 'definites' and the 'probables'.
Blurring the middle rankings in a survey is common tactic, even in some serious surveys. Imagine a survey on the support for President Obama. Completely hypothetical, but let's say it asks if you are "pro" or "anti". There are three choices
1: wholly for,
2 wholly against,
3 partly for and partly against.
The result is that one third are wholly for, one third wholly against and one third in the middle. If you want to make it look like a vote for, you report that 67 per cent were "wholly or partly" in favour of President Obama. If you want to make it look like a vote against, you report that two thirds ("well over half") were "wholly or partly" against President Obama. It's common to try to amalgamate the undecided or half-hearted opinions with those who favour your stance on the matter in order to make the 'statistics' show that you have a clear majority on your side.
Another problem with surveys that often puts a spanner in the works is who they ask. In Northern Ireland a few years ago the government asked people to compile a voluntary survey on the police force. Who was surveyed? A cross-sample of the population. NO. How did they do the survey? By internet and post, with people who 'wanted' to take part. Not so good.
Even with a little thought you can see that those who most likely wanted to comment on the police force were not that happy with them. At that time one third of the community was against the police due to political allegiances. Anyone who thought logically about the situation would have seen the recipe for bias was in place before the survey began. All surveys can suffer from bias - deliberately or not - by picking up or missing too many of a vital groups and simply extrapolating data - as if everyone in the country thought the same way as the people who completed the survey. Good surveys require excellent planning......
Surveys often 'merge' data. The bus company survey covered in the previous post had bundled together the people who answered the survey as 'more and the less inclined', and the people who are classified as 'definites' and the 'probables'.
Blurring the middle rankings in a survey is common tactic, even in some serious surveys. Imagine a survey on the support for President Obama. Completely hypothetical, but let's say it asks if you are "pro" or "anti". There are three choices
1: wholly for,
2 wholly against,
3 partly for and partly against.
The result is that one third are wholly for, one third wholly against and one third in the middle. If you want to make it look like a vote for, you report that 67 per cent were "wholly or partly" in favour of President Obama. If you want to make it look like a vote against, you report that two thirds ("well over half") were "wholly or partly" against President Obama. It's common to try to amalgamate the undecided or half-hearted opinions with those who favour your stance on the matter in order to make the 'statistics' show that you have a clear majority on your side.
Another problem with surveys that often puts a spanner in the works is who they ask. In Northern Ireland a few years ago the government asked people to compile a voluntary survey on the police force. Who was surveyed? A cross-sample of the population. NO. How did they do the survey? By internet and post, with people who 'wanted' to take part. Not so good.
Even with a little thought you can see that those who most likely wanted to comment on the police force were not that happy with them. At that time one third of the community was against the police due to political allegiances. Anyone who thought logically about the situation would have seen the recipe for bias was in place before the survey began. All surveys can suffer from bias - deliberately or not - by picking up or missing too many of a vital groups and simply extrapolating data - as if everyone in the country thought the same way as the people who completed the survey. Good surveys require excellent planning......
Tuesday, 10 February 2009
Do not let the data get in the way of a Good Story
One intention of this blogg is to eventually look at biblical facts. But before that I feel I must cover some ways that data can be manipulated to suit the goals & outcomes that people want to see. I will look at some common problems in gathering and interpreting data. The first method open to abuse is conducting surveys and their analysis.
"Motorists turn to public transport as fuel price bites" "More than three in five drivers are turning to public transport due to high fuel prices". The headline was on the front page of a daily paper in the UK last year.
Unfortunately digging into the survey data which was conducted by a major bus company in the UK (any alarm bells ringing yet)? They 'found' that 61 per cent of car users were definitely or probably considering using public transport due to the rise in fuel prices at the gas pumps.
This story gives the impression that over 60% of motorists in the UK are leaving their cars at home, due to high fuel prices. In fact, due to the wording of the survey the data produced tell us that UK motorists are not necessarily doing anything. They are "definitely or probably" thinking about doing something, which in the future they might do. How often they will do it, if they ever do it at all is anyone's guess.
In my next post I will discuss the lessons we can derive about surveys......
One intention of this blogg is to eventually look at biblical facts. But before that I feel I must cover some ways that data can be manipulated to suit the goals & outcomes that people want to see. I will look at some common problems in gathering and interpreting data. The first method open to abuse is conducting surveys and their analysis.
"Motorists turn to public transport as fuel price bites" "More than three in five drivers are turning to public transport due to high fuel prices". The headline was on the front page of a daily paper in the UK last year.
Unfortunately digging into the survey data which was conducted by a major bus company in the UK (any alarm bells ringing yet)? They 'found' that 61 per cent of car users were definitely or probably considering using public transport due to the rise in fuel prices at the gas pumps.
This story gives the impression that over 60% of motorists in the UK are leaving their cars at home, due to high fuel prices. In fact, due to the wording of the survey the data produced tell us that UK motorists are not necessarily doing anything. They are "definitely or probably" thinking about doing something, which in the future they might do. How often they will do it, if they ever do it at all is anyone's guess.
In my next post I will discuss the lessons we can derive about surveys......
Monday, 9 February 2009
Lies, Damn Lies and Statistics
Last night I watched an advert on the television that stated that 9 out of 10 women preferred a particular brand of hair lotion being 'peddled' to any other brand. The lady in the advert with the beautiful soft voice that complemented her beautiful soft hair said that these 9 out of 10 women noticed a difference in the 'shine' of the hair when they started to use this wonderwork product?
Tucked away at the bottom of the screen was the all important information data used to derive this 9 out of 10 statistic. How big a sample of women were questioned in conducting this survey? Twenty eight people, TWENTY EIGHT. What did the reachers do to carry out such an in depth study? Ask members of their immediate family? Implying facts with limited data is not just confined to adverts!
Last week on the BBC morning news programme the 'hosts' kept announcing a time slot when Sir David Attenborough would be in to talk about his new television programme on Charles Darwin. How did the announcers give out this information? Each time the announcement was made opening line was 'he is a man who has been told that he should rot in hell'.
Not quite in the 9 out of 10 category but such a 'fact' tweaked my ears to hear what Mr Attenborough had to say about this. The implication was that these intolerant Christians were at it again, coming down on this gentleman with their outmoded views of the afterlife, all this heaven & hell stuff. Interestingly Mr Attenborough (with his soft voice but on that particular morning not so manageable hair) said that he got a FEW letters in his life saying that he should rot in hell. He did go on about the fact that in some Southern states in the USA the children were so indoctrinated into Christianity that they refuse to accept the theory of Evolution as a fact. Just to emphasise how stupid these children were he put on a 'southern drawl and said that a typical student when taught the theory of Evolution said "we don't believe that kind if thing around here".
As usual he was given free reign to expound what he sees as scientific fact while at the same time denigrating the biblical story of creation as a myth. No one was there to put the biblical point of view, so it was all one way traffic on BBC. But it does go to prove that on TV they do not let 'facts' stand in the way of a good story. I would have liked to have told Mr Attenborough that a true Christian would be praying that his eyes would be opened to the truth and that he would accept the Lord as his saviour before he finds out about the reality of hell. In closing this bit, it is an interesting fact that our Lord talked more about hell than heaven in the bible, yet we rarely get a sermon on hell. Some information is not easily received or given........
Last night I watched an advert on the television that stated that 9 out of 10 women preferred a particular brand of hair lotion being 'peddled' to any other brand. The lady in the advert with the beautiful soft voice that complemented her beautiful soft hair said that these 9 out of 10 women noticed a difference in the 'shine' of the hair when they started to use this wonderwork product?
Tucked away at the bottom of the screen was the all important information data used to derive this 9 out of 10 statistic. How big a sample of women were questioned in conducting this survey? Twenty eight people, TWENTY EIGHT. What did the reachers do to carry out such an in depth study? Ask members of their immediate family? Implying facts with limited data is not just confined to adverts!
Last week on the BBC morning news programme the 'hosts' kept announcing a time slot when Sir David Attenborough would be in to talk about his new television programme on Charles Darwin. How did the announcers give out this information? Each time the announcement was made opening line was 'he is a man who has been told that he should rot in hell'.
Not quite in the 9 out of 10 category but such a 'fact' tweaked my ears to hear what Mr Attenborough had to say about this. The implication was that these intolerant Christians were at it again, coming down on this gentleman with their outmoded views of the afterlife, all this heaven & hell stuff. Interestingly Mr Attenborough (with his soft voice but on that particular morning not so manageable hair) said that he got a FEW letters in his life saying that he should rot in hell. He did go on about the fact that in some Southern states in the USA the children were so indoctrinated into Christianity that they refuse to accept the theory of Evolution as a fact. Just to emphasise how stupid these children were he put on a 'southern drawl and said that a typical student when taught the theory of Evolution said "we don't believe that kind if thing around here".
As usual he was given free reign to expound what he sees as scientific fact while at the same time denigrating the biblical story of creation as a myth. No one was there to put the biblical point of view, so it was all one way traffic on BBC. But it does go to prove that on TV they do not let 'facts' stand in the way of a good story. I would have liked to have told Mr Attenborough that a true Christian would be praying that his eyes would be opened to the truth and that he would accept the Lord as his saviour before he finds out about the reality of hell. In closing this bit, it is an interesting fact that our Lord talked more about hell than heaven in the bible, yet we rarely get a sermon on hell. Some information is not easily received or given........
Sophisticated Wild Guessing
Ever wonder why people take things at face value? Why people just accept information as 'gospel', especially if it is presented from a seemingly reliable source!
I love working with data. As part of my work I teach engineers how to use statistics to make educated decisions in improving their designs / processes. However, it never fails to amaze me that many of these highly intelligent individuals would prefer to stay within their own 'comfort zone' of existing knowledge rather than explore / question the status quo, to determine if there is a better way to do their job to improve the business.
In the industry I work in we deal with highly complex manufacturing processes. Having practiced and taught Process Improvement methodologies for nearly 25 years and for as long as I can remember I have always asked this question in my training classes "How did you learn to do your job?" The replies are always "Somebody showed me!" or "I read a manual". Then I ask if they had ever questioned the accuracy or the validity of the information given to them, and 99% of the time the answer is NO.
The primary reason for this answer, was that they believe the information they had been given would be accurate. They have a belief that the information / knowledge would have been validated / tested over many years (that is usually the tribal knowledge of the business).
I would like to offer another reason for this lack of questioning the status quo, is down to the fact that most people never use data to prove or disprove their decisions. I call it the SWG system of decision making. Sophisticated Wild Guessing (SWG). Just watch this wonderful system in full operation at any meeting you attend. Decision usually made by the person with the most forceful personality / loudest voice, or the Frank Sinatra type bosses "You'll do it my way". But introduce some reliable data into the equation then the decisions can be made by facts not guesswork.
Key words in the last sentence are 'reliable data'. The abuse of data analysis is alarming and the way data is presented as fact on our television screens is in many ways a disgrace. I will talk about this abuse over my next few postings.
Ever wonder why people take things at face value? Why people just accept information as 'gospel', especially if it is presented from a seemingly reliable source!
I love working with data. As part of my work I teach engineers how to use statistics to make educated decisions in improving their designs / processes. However, it never fails to amaze me that many of these highly intelligent individuals would prefer to stay within their own 'comfort zone' of existing knowledge rather than explore / question the status quo, to determine if there is a better way to do their job to improve the business.
In the industry I work in we deal with highly complex manufacturing processes. Having practiced and taught Process Improvement methodologies for nearly 25 years and for as long as I can remember I have always asked this question in my training classes "How did you learn to do your job?" The replies are always "Somebody showed me!" or "I read a manual". Then I ask if they had ever questioned the accuracy or the validity of the information given to them, and 99% of the time the answer is NO.
The primary reason for this answer, was that they believe the information they had been given would be accurate. They have a belief that the information / knowledge would have been validated / tested over many years (that is usually the tribal knowledge of the business).
I would like to offer another reason for this lack of questioning the status quo, is down to the fact that most people never use data to prove or disprove their decisions. I call it the SWG system of decision making. Sophisticated Wild Guessing (SWG). Just watch this wonderful system in full operation at any meeting you attend. Decision usually made by the person with the most forceful personality / loudest voice, or the Frank Sinatra type bosses "You'll do it my way". But introduce some reliable data into the equation then the decisions can be made by facts not guesswork.
Key words in the last sentence are 'reliable data'. The abuse of data analysis is alarming and the way data is presented as fact on our television screens is in many ways a disgrace. I will talk about this abuse over my next few postings.
Sunday, 8 February 2009
He never fails to amaze me! the person I am talking about is my Lord and Saviour Jesus Christ. I had started this blog with the intention on talking about work related topics connected primarily to Process Improvement.
So I sent out my first blog post into the 'ether' sat back and waited to see what happened. I got one post back from 'thankful Paul' who has his own wonderful testimony of the Lord's blessing and mercy which you can read by following the comment at my first posting. This one reply has inspired me to record my own Journey with the Lord. I still want to talk about facts and data but from a Biblical perspective. I might not be a 'Control Freak' but a 'Facts with Data' freak. Thanks Paul for the reply, I believe this was not a random chance event. I believe that everything has a cause and effect relationship. So out of the millions of bloggers in the world I get a reply from Paul. It may be a search engine that picked out some key words, but the Lord just sent the right reply to me at the right time.
So I sent out my first blog post into the 'ether' sat back and waited to see what happened. I got one post back from 'thankful Paul' who has his own wonderful testimony of the Lord's blessing and mercy which you can read by following the comment at my first posting. This one reply has inspired me to record my own Journey with the Lord. I still want to talk about facts and data but from a Biblical perspective. I might not be a 'Control Freak' but a 'Facts with Data' freak. Thanks Paul for the reply, I believe this was not a random chance event. I believe that everything has a cause and effect relationship. So out of the millions of bloggers in the world I get a reply from Paul. It may be a search engine that picked out some key words, but the Lord just sent the right reply to me at the right time.
Thursday, 5 February 2009
A Control Freak?
In life the effects of variation are all around us. In my career I have spent over the past 25 years improving systems and processes. yYu could say that I am a data freak as well as a control freak. But not the type of control that you might be thinking about. I am interested in process and system control. In other words bringing systems and processes to a level of capability that means that they are operating 'On Target (meeting customer requirements) with Minimum Variation'. I thought that I might share some of the methods that I use to accomplish this in my day to day work. I will give insight into some basic tools and techniques so that those who have an interest in improving their own processes can have a go at using these methods. On thing I love about using statistics is never having to say you are certain. This is my first blog post and I am convinced that I will not get any interest in this but who knows, the statistics might say something diferent!
Subscribe to:
Posts (Atom)
