Terrible graphs

Get your science fix here: research, quackery, activism and all the rest
User avatar
Stephanie
Dorkwood
Posts: 1444
Joined: Wed Sep 25, 2019 4:38 pm
Location: clinging tenaciously to your buttocks

Terrible graphs

Post by Stephanie » Mon Apr 27, 2020 5:40 pm

This one, via The Conversation, is... something
badgraph.jpg
badgraph.jpg (109.45 KiB) Viewed 1395 times
"I got a flu virus named after me 'cause I kissed a bat on a dare."

User avatar
Woodchopper
Dorkwood
Posts: 1418
Joined: Sat Oct 12, 2019 9:05 am

Re: Terrible graphs

Post by Woodchopper » Mon Apr 27, 2020 5:47 pm

That must have taken a long time.

User avatar
Bird on a Fire
Stummy Beige
Posts: 2600
Joined: Fri Oct 11, 2019 5:05 pm
Location: with the birds

Re: Terrible graphs

Post by Bird on a Fire » Mon Apr 27, 2020 6:13 pm

I think that's quite an effective way of showing the looping effect they're talking about in the article, actually. Though it's certainly not very pretty or intuitive.
now I'm falling asleep and she's calling acab

User avatar
jimbob
Dorkwood
Posts: 1018
Joined: Mon Nov 11, 2019 4:04 pm
Location: High Peak/Manchester

Re: Terrible graphs

Post by jimbob » Mon Apr 27, 2020 8:30 pm

Bird on a Fire wrote:
Mon Apr 27, 2020 6:13 pm
I think that's quite an effective way of showing the looping effect they're talking about in the article, actually. Though it's certainly not very pretty or intuitive.
It reminds me of a phone conversation with a colleague on my walk last week, when he was wondering what a graph of total cases vs hospital admissions vs deaths would look like.

I don't know if he's actually been plotting that.
Have you considered stupidity as an explanation

User avatar
jaap
Clardic Fug
Posts: 181
Joined: Mon Nov 11, 2019 2:05 pm
Location: Netherlands
Contact:

Re: Terrible graphs

Post by jaap » Tue Apr 28, 2020 6:44 am

Wouldn't any measurement with regular fluctuations show the same loops?
It's basically plotting a sine wave against its derivative, a cosine wave, which gives you a circle. And the only reason it is like a sine wave is because it's using rolling averages to smooth out the fluctuations so that they are more wave-like.
It doesn't really tell you anything particularly interesting, except may that there are weekly fluctuations due to weekends.

User avatar
Martin Y
Dorkwood
Posts: 992
Joined: Mon Nov 11, 2019 1:08 pm

Re: Terrible graphs

Post by Martin Y » Tue Apr 28, 2020 8:16 am

jaap wrote:
Tue Apr 28, 2020 6:44 am
Wouldn't any measurement with regular fluctuations show the same loops?
It's basically plotting a sine wave against its derivative, a cosine wave, which gives you a circle. And the only reason it is like a sine wave is because it's using rolling averages to smooth out the fluctuations so that they are more wave-like.
It doesn't really tell you anything particularly interesting, except may that there are weekly fluctuations due to weekends.
That's a very good point.

I had been staring at it and wondering what useful information could be gleaned at a glance from its bold spirals. The answer appears to be almost none. Thanks.

Herainestold
Snowbonk
Posts: 388
Joined: Mon Nov 25, 2019 1:23 pm

Re: Terrible graphs

Post by Herainestold » Tue Apr 28, 2020 2:03 pm

It does look cool, though.

User avatar
Stephanie
Dorkwood
Posts: 1444
Joined: Wed Sep 25, 2019 4:38 pm
Location: clinging tenaciously to your buttocks

Re: Terrible graphs

Post by Stephanie » Tue Apr 28, 2020 7:21 pm

Aww, I feel mean now
"I got a flu virus named after me 'cause I kissed a bat on a dare."

User avatar
Martin_B
Snowbonk
Posts: 424
Joined: Mon Nov 11, 2019 1:20 pm
Location: Perth, WA

Re: Terrible graphs

Post by Martin_B » Wed Apr 29, 2020 2:00 am

Stephanie wrote:
Tue Apr 28, 2020 7:21 pm
Aww, I feel mean now
Don't feel mean - it's a terrible graph and they should be able to show the information in a less confusing manner
"Don't tell me that the sky's the limit when there are footprints on the moon"

Allo V Psycho
Clardic Fug
Posts: 184
Joined: Sat Nov 16, 2019 8:18 am

Re: Terrible graphs

Post by Allo V Psycho » Wed May 06, 2020 5:26 pm

This came from the White House's Council of economic advisers. On Twitter https://twitter.com/WhiteHouseCEA
They say "To better visualize observed data, we also continually update a curve-fitting exercise to summarize COVID-19's observed trajectory. Particularly with irregular data, curve fitting can improve data visualization. As shown, IHME's mortality curves have matched the data fairly well."

I laughed out loud - did they use 'Add Trend Line' in Excel, and choose a cubic? :lol:

The cubic is the one that predicts zero deaths in 9 days time.

And what kind of curve fitting exercise gives the green line from the black one?

Plus, was that graph really drawn by hand using coloured sharpies, or is there a programme that makes your graphs look more user friendly, by making them more crap? I did think of posting this in Pandemic Jokes, but then, it ain't that funny.
Attachments
Covid.png
Covid.png (309.71 KiB) Viewed 1019 times

User avatar
shpalman
Dorkwood
Posts: 1341
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: Terrible graphs

Post by shpalman » Wed May 06, 2020 5:42 pm

Allo V Psycho wrote:
Wed May 06, 2020 5:26 pm
This came from the White House's Council of economic advisers. On Twitter https://twitter.com/WhiteHouseCEA
They say "To better visualize observed data, we also continually update a curve-fitting exercise to summarize COVID-19's observed trajectory. Particularly with irregular data, curve fitting can improve data visualization. As shown, IHME's mortality curves have matched the data fairly well."

I laughed out loud - did they use 'Add Trend Line' in Excel, and choose a cubic? :lol:

The cubic is the one that predicts zero deaths in 9 days time.

And what kind of curve fitting exercise gives the green line from the black one?

Plus, was that graph really drawn by hand using coloured sharpies, or is there a programme that makes your graphs look more user friendly, by making them more crap? I did think of posting this in Pandemic Jokes, but then, it ain't that funny.
I think we figured out that the "cubic model" was actually a cubic fit to the log of the data.

https://twitter.com/potatoffel/status/1 ... 09792?s=09

No scientific basis or predictive power whatsoever.

It does seem like the IHME predictions are massively sensitive to the data so might well be overfitting as compared to have a decent prior and/or maximizing the entropy.
molto tricky

User avatar
bolo
Fuzzable
Posts: 296
Joined: Mon Nov 11, 2019 1:17 pm
Location: Washington DC

Re: Terrible graphs

Post by bolo » Wed May 06, 2020 7:52 pm

Last time I checked, a cubic goes to +infinity in one direction and -infinity in the other. Even if it's cubic in the logarithm, it can't go to zero in both directions. So if this is a cubic at all, the coefficient of the cubic term must be zero, so really it's a quadratic (in the log) which is ... I'm not sure, is it stupider or just equally stupid?

User avatar
basementer
Snowbonk
Posts: 386
Joined: Mon Nov 11, 2019 1:03 pm
Location: Aotearoa

Re: Terrible graphs

Post by basementer » Wed May 06, 2020 8:29 pm

bolo wrote:
Wed May 06, 2020 7:52 pm
Last time I checked, a cubic goes to +infinity in one direction and -infinity in the other. Even if it's cubic in the logarithm, it can't go to zero in both directions. So if this is a cubic at all, the coefficient of the cubic term must be zero, so really it's a quadratic (in the log) which is ... I'm not sure, is it stupider or just equally stupid?
I read it as the cubic fit range is only the dashed line, and they've projected it (dotted line) using an unspecified different method because they know the cubic itself generates nonsense. Maybe.
I'll think of something.

User avatar
shpalman
Dorkwood
Posts: 1341
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: Terrible graphs

Post by shpalman » Wed May 06, 2020 9:03 pm

bolo wrote:
Wed May 06, 2020 7:52 pm
Last time I checked, a cubic goes to +infinity in one direction and -infinity in the other. Even if it's cubic in the logarithm, it can't go to zero in both directions. So if this is a cubic at all, the coefficient of the cubic term must be zero, so really it's a quadratic (in the log) which is ... I'm not sure, is it stupider or just equally stupid?
Well it does look like a Gaussian, which is what you would get if you took the log of the data and fit a quadratic to it (given that the second derivative is negative) and then exponented it back.
molto tricky

User avatar
jimbob
Dorkwood
Posts: 1018
Joined: Mon Nov 11, 2019 4:04 pm
Location: High Peak/Manchester

Re: Terrible graphs

Post by jimbob » Wed May 06, 2020 9:14 pm

bolo wrote:
Wed May 06, 2020 7:52 pm
Last time I checked, a cubic goes to +infinity in one direction and -infinity in the other. Even if it's cubic in the logarithm, it can't go to zero in both directions. So if this is a cubic at all, the coefficient of the cubic term must be zero, so really it's a quadratic (in the log) which is ... I'm not sure, is it stupider or just equally stupid?
Kevin Hansett talked about the cubic model. And we're discussing someone who has form in economics, with an absolutely barking Laffer curve, which I might dig out later.
[ETA: https://www.discovermagazine.com/the-sc ... tting-ever ]
And it only needs to have a turning point at the future zero for a dishonest/incompetent person to then take that zero gradient as all time future.

I don't know which he fails on, but he's certainly not both capable and honest - given his work I'm going for neither.
Have you considered stupidity as an explanation

User avatar
basementer
Snowbonk
Posts: 386
Joined: Mon Nov 11, 2019 1:03 pm
Location: Aotearoa

Re: Terrible graphs

Post by basementer » Wed May 06, 2020 11:56 pm

jimbob wrote:
Wed May 06, 2020 9:14 pm
bolo wrote:
Wed May 06, 2020 7:52 pm
Last time I checked, a cubic goes to +infinity in one direction and -infinity in the other. Even if it's cubic in the logarithm, it can't go to zero in both directions. So if this is a cubic at all, the coefficient of the cubic term must be zero, so really it's a quadratic (in the log) which is ... I'm not sure, is it stupider or just equally stupid?
Kevin Hansett talked about the cubic model. And we're discussing someone who has form in economics, with an absolutely barking Laffer curve, which I might dig out later.
[ETA: https://www.discovermagazine.com/the-sc ... tting-ever ]
And it only needs to have a turning point at the future zero for a dishonest/incompetent person to then take that zero gradient as all time future.

I don't know which he fails on, but he's certainly not both capable and honest - given his work I'm going for neither.
That Laffer curve is a fib of beauty. Following through the discussions that ensued, I found someone asserting that Norway is plotted in the wrong place: he took the total tax revenues including those coming from oil for the y axis, and plotted them against general corporate tax rate on the x axis But oil revenues in particular were at that time taxed at a much higher rate than that, so apparently Norway should be have been way over at about 52% rather than 28%.
I'll think of something.

Allo V Psycho
Clardic Fug
Posts: 184
Joined: Sat Nov 16, 2019 8:18 am

Re: Terrible graphs

Post by Allo V Psycho » Thu May 07, 2020 5:56 am

shpalman wrote:
Wed May 06, 2020 5:42 pm
Allo V Psycho wrote:
Wed May 06, 2020 5:26 pm
This came from the White House's Council of economic advisers. On Twitter https://twitter.com/WhiteHouseCEA
They say "To better visualize observed data, we also continually update a curve-fitting exercise to summarize COVID-19's observed trajectory. Particularly with irregular data, curve fitting can improve data visualization. As shown, IHME's mortality curves have matched the data fairly well."

I laughed out loud - did they use 'Add Trend Line' in Excel, and choose a cubic? :lol:

The cubic is the one that predicts zero deaths in 9 days time.

And what kind of curve fitting exercise gives the green line from the black one?

Plus, was that graph really drawn by hand using coloured sharpies, or is there a programme that makes your graphs look more user friendly, by making them more crap? I did think of posting this in Pandemic Jokes, but then, it ain't that funny.
I think we figured out that the "cubic model" was actually a cubic fit to the log of the data.

https://twitter.com/potatoffel/status/1 ... 09792?s=09

No scientific basis or predictive power whatsoever.

It does seem like the IHME predictions are massively sensitive to the data so might well be overfitting as compared to have a decent prior and/or maximizing the entropy.
That Twitter link led me to this:
https://twitter.com/LevyAntoine/status/ ... 3221677057
Countries are best summarized by their corporate income tax schedule description in the OECD tax database, a thread.

You've probably read it, shpallers, but for the others, trust me. It is funnier than you might think.

Allo V Psycho
Clardic Fug
Posts: 184
Joined: Sat Nov 16, 2019 8:18 am

Re: Terrible graphs

Post by Allo V Psycho » Thu May 07, 2020 7:00 am

OK, I plotted their data as best as I could estimate it (in Excel, of course). Yes, I know I'm sad, but I don't start work till 8, so it is my own personal sadness.

Both log and ln give me a curve, but it's platykurtic compared to theirs: Closest I can get is to plot a cubic on the original data then match a gaussian to part of it.

User avatar
dyqik
After Pie
Posts: 1932
Joined: Wed Sep 25, 2019 4:19 pm
Location: Masshole
Contact:

Re: Terrible graphs

Post by dyqik » Thu May 07, 2020 2:40 pm

Allo V Psycho wrote:
Thu May 07, 2020 7:00 am
OK, I plotted their data as best as I could estimate it (in Excel, of course). Yes, I know I'm sad, but I don't start work till 8, so it is my own personal sadness.

Both log and ln give me a curve, but it's platykurtic compared to theirs: Closest I can get is to plot a cubic on the original data then match a gaussian to part of it.
I think you have to pick the end points of the fit and projection carefully.

User avatar
Rich Scopie
Stargoon
Posts: 135
Joined: Mon Nov 11, 2019 1:21 pm

Re: Terrible graphs

Post by Rich Scopie » Sat May 16, 2020 1:16 pm

Allo V Psycho wrote:
Wed May 06, 2020 5:26 pm
Plus, was that graph really drawn by hand using coloured sharpies, or is there a programme that makes your graphs look more user friendly, by making them more crap? I did think of posting this in Pandemic Jokes, but then, it ain't that funny.
It does appear to have been drawn using the graphical equivalent of Comic Sans...
It first was a rumour dismissed as a lie, but then came the evidence none could deny:
a double page spread in the Sunday Express — the Russians are running the DHSS!

Holylol
Buzzberry
Posts: 34
Joined: Tue Nov 19, 2019 10:14 am

Re: Terrible graphs

Post by Holylol » Tue May 19, 2020 7:59 am


User avatar
jimbob
Dorkwood
Posts: 1018
Joined: Mon Nov 11, 2019 4:04 pm
Location: High Peak/Manchester

Re: Terrible graphs

Post by jimbob » Tue May 19, 2020 5:50 pm

Holylol wrote:
Tue May 19, 2020 7:59 am
A new one:
https://statmodeling.stat.columbia.edu/ ... his-graph/
It would be straightforward to get that in Excel, but you'd need to actually put in effort to get that - by sorting the data in descending order.

It would be very difficult to do that accidentally.
Have you considered stupidity as an explanation

User avatar
Bird on a Fire
Stummy Beige
Posts: 2600
Joined: Fri Oct 11, 2019 5:05 pm
Location: with the birds

Re: Terrible graphs

Post by Bird on a Fire » Tue May 19, 2020 6:25 pm

jimbob wrote:
Tue May 19, 2020 5:50 pm
Holylol wrote:
Tue May 19, 2020 7:59 am
A new one:
https://statmodeling.stat.columbia.edu/ ... his-graph/
It would be straightforward to get that in Excel, but you'd need to actually put in effort to get that - by sorting the data in descending order.

It would be very difficult to do that accidentally.
Although, somebody might make a graph, then sort the cells to look at the data, without realising that the graph would be automatically updated to the new order, and then not check it. Excel doesn't always handle dates well either.
now I'm falling asleep and she's calling acab

User avatar
Martin_B
Snowbonk
Posts: 424
Joined: Mon Nov 11, 2019 1:20 pm
Location: Perth, WA

Re: Terrible graphs

Post by Martin_B » Wed May 20, 2020 9:15 am

Bird on a Fire wrote:
Tue May 19, 2020 6:25 pm
jimbob wrote:
Tue May 19, 2020 5:50 pm
Holylol wrote:
Tue May 19, 2020 7:59 am
A new one:
https://statmodeling.stat.columbia.edu/ ... his-graph/
It would be straightforward to get that in Excel, but you'd need to actually put in effort to get that - by sorting the data in descending order.

It would be very difficult to do that accidentally.
Although, somebody might make a graph, then sort the cells to look at the data, without realising that the graph would be automatically updated to the new order, and then not check it. Excel doesn't always handle dates well either.
Excel handles dates better than that, though. Again, it would require sorting the data into descending order and then plotting
"Don't tell me that the sky's the limit when there are footprints on the moon"

User avatar
shpalman
Dorkwood
Posts: 1341
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: Terrible graphs

Post by shpalman » Wed May 20, 2020 9:17 am

Unless something has recently changed a lot, only one class of charts in Excel is actually an x-y plot.
molto tricky

Post Reply