{"id":4483,"date":"2016-01-16T11:17:36","date_gmt":"2016-01-16T10:17:36","guid":{"rendered":"http:\/\/www.saasoft.com\/blog\/?p=4483"},"modified":"2016-01-16T11:17:36","modified_gmt":"2016-01-16T10:17:36","slug":"hot-and-cold","status":"publish","type":"post","link":"https:\/\/hcse.blog\/?p=4483","title":{"rendered":"Hot and Cold"},"content":{"rendered":"

\"stick_figure_on_cloud_150_wht_9604\"<\/a>Last week Bob and Leslie were exploring the data analysis trap\u00a0called a\u00a0two-points-in-time comparison: as illustrated by the headline\u00a0“This winter has not been as bad as last\u00a0… which proves that our winter action plan has worked.<\/em>”<\/p>\n

Actually it doesn’t.<\/strong><\/p>\n

But just saying that is not very helpful. We need to explain the reason why this conclusion is invalid and therefore potentially dangerous.<\/p>\n

\n

So here is the continuation of Bob and Leslie’s conversation.<\/p>\n

<Bob><\/em> Hi Leslie, have you been reflecting on the two-points-in-time challenge?<\/p>\n

<Leslie><\/em> Yes indeed, and\u00a0you were correct, I did\u00a0know the answer …\u00a0I just didn’t know I knew if you get my\u00a0drift.<\/p>\n

<Bob><\/em> Yes, I do.\u00a0So, are you willing to share\u00a0your story?<\/p>\n

<Leslie> OK,\u00a0but before I do that I would like to share what happened when\u00a0I described what we talked about to some colleagues.\u00a0 They sort\u00a0of got the idea but\u00a0got lost in the\u00a0unfamiliar language of ‘variance’ and I realized that I needed\u00a0an example to illustrate.<\/p>\n

<Bob><\/em> Excellent … what example did you choose?<\/p>\n

<Leslie><\/em> The UK weather – or more specifically the temperature.\u00a0 My reasons for choosing this\u00a0were many: first it is something that everyone can relate to; secondly it has strong seasonal cycle; and thirdly because\u00a0the data is readily available on the Internet.<\/p>\n

<Bob><\/em> OK, so what\u00a0specific question were you trying to answer and what data did you\u00a0use?<\/p>\n

<Leslie><\/em>\u00a0The question was “Are our winters getting warmer?”<\/em>\u00a0and my\u00a0interest in that is because many people assume that the colder the winter the more people suffer from respiratory\u00a0illness and the more that\u00a0go to hospital … contributing to the winter A&E and hospital pressures.\u00a0 The data that I used was the maximum monthly temperature from 1960 to the present\u00a0recorded at our closest weather station.<\/p>\n

<Bob><\/em> OK, and what did you do with that data?<\/p>\n

<Leslie><\/em>\u00a0Well, what I did not<\/strong> do was to compare this winter with last winter and draw my conclusion from that!\u00a0 What I did first was just to plot-the-dots\u00a0… I created a time-series chart … using the BaseLine\u00a9<\/a> software.<\/p>\n

\"MaxMonthTemp1960-2015\"<\/a><\/p>\n

And it shows what I expected to see, a\u00a0strong, regular, 12-month\u00a0cycle, with peaks in the summer and troughs in the winter.<\/p>\n

<Bob><\/em> Can you explain what the green and red lines are and why some dots are red?<\/p>\n

<Leslie><\/em> Sure. The green line is the average for all the data.\u00a0The red lines are called the upper and lower process limits.\u00a0\u00a0They are calculated from the data and what they say is “if the variation in this data is random then we will expect more than 99% of the points to fall between these two red lines<\/em>“.<\/p>\n

<Bob><\/em> So, we have 55 years of monthly data which is nearly 700 points which means we would expect fewer than seven to fall outside these lines … and we clearly have\u00a0many more than that.\u00a0 For example, the winter of 1962-63 and the summer of 1976 look exceptional – a run of three consecutive dots outside the red lines. So can\u00a0we conclude the\u00a0variation we are seeing is not random?<\/p>\n

<Leslie><\/em> Yes,\u00a0and there is more evidence to\u00a0support that conclusion.\u00a0First is the reality check …\u00a0I do not\u00a0remember either of those exceptionally cold or hot years personally, so I asked Dr Google.<\/p>\n

\"BigFreeze_1963\"<\/a>This picture from January 1963\u00a0shows copper telephone lines that are\u00a0so weighed down with ice, and for so\u00a0long,\u00a0that they have stretched down to the ground.\u00a0 In this era of mobile phones we forget this was what telecommunication was like!<\/p>\n

 <\/p>\n

 <\/p>\n

\"HeatWave_1976\"<\/a><\/p>\n

And just look at the young Michal Fish in the Summer of ’76! Did people really wear clothes like that?<\/p>\n

And there is more evidence on the chart.\u00a0The red dots that you mentioned are\u00a0indicators\u00a0that BaseLine\u00a9\u00a0has detected other non-random patterns.<\/p>\n

So the large number of red dots confirms our Mark I Eyeball conclusion …\u00a0that there are signals mixed up with the noise.<\/p>\n

<Bob> <\/em>Actually, I do remember the Summer of ’76 – it was the year I did my O Levels!\u00a0 And your signals-in-the-noise<\/em> phrase\u00a0reminds me of\u00a0SETI –\u00a0the search for extra-terrestrial intelligence!\u00a0 I really enjoyed the 1997 film of Carl Sagan’s book\u00a0Contact<\/em> with Jodi Foster playing the role of the determined scientist who ends up taking a faster-than-light trip through space in a machine designed by\u00a0ET and built by humans. And especially the line about 10 minutes from the end when those-in-high-places who had discounted her story\u00a0as “unbelievable” realized\u00a0they may have made an error … the line\u00a0‘Yes, that is interesting isn’t it’<\/em>.<\/p>\n