One Incontrovertible, Unequivocal, Undeniable Fact Which Refutes the Diary

[caz]

Ike, you have fallen at the first hurdle.

You do not KNOW when the first day "they could have happened on the same day" because you do not know where the diary came from, who wrote it, nor when it was created. It’s an unknown.

You are formulating your “denominator” based largely on your belief that the scrapbook is likely to be the genuine diary of James Maybrick’s and that it was placed somewhere in Battlecrease as early as March 11th 1889.

But since you are forced to make your calculations from a position of ignorance (because no one knows or at least agrees to the diary’s origins), it is entirely possible that your ‘earliest’ date is entirely wrong and flawed and an impossibility---yet you insist on using it.

In a sense, your calculations aren't so much wrong, as they are invalid, and incorrectly formulated.

In other words, by setting the first possible date as May 12, 1889, [strangely, Maybrick actually died on the 11th], you are, in effect, irrationally insinuating that it WAS placed under the floorboards on that date, and then you are simply counting forwards until you reach March 9, 1992 (the date of Barrett's call) which gives you the number 37,618, which you then convert to 37, 618 to 1.

No. No. No.

You are adding hundreds and thousands of what could be entirely imaginary ‘possible’ days to your denominator without having the faintest idea where the diary actually came from. And, because you are basing your calculations on an assumption, you are left with no way of knowing whether or not your resulting ‘denominator’ is accurate.

Your calculations are a group of goblins dancing on the head of an imaginary pin

But I’ve tried many ways to express this, Ike, and, with a heavy heart, I must give up.

Someone else will have to carry the baton, and I pray for your sake that they do not whack you over the head with it.

Good luck.

Wow! It's Major Misunderstanding and The Drunken Bakers rolled into one.

I hope you were joking, RJ, for your sake. If you were serious, you need some lessons in critical thinking and leave the statistics to the statisticians.

I don't think I have ever read a post of yours that manages to get so wide of the jolly old mark.

And talking of marks, all hail Mark Cavendish, bicycle repair man supreme! Equal to the record of Eddy Merckx, of 34 bicycle repairs.

[rjpalmer]

I hope you were joking, RJ, for your sake. If you were serious, you need some lessons in critical thinking and leave the statistics to the statisticians.

I don't think I have ever read a post of yours that manages to get so wide of the jolly old mark.

I thought you were going shopping, Caz? If so, pick up a grade-school book on logic before you (wrongly) lecture me.

My critical thinking skills are fine. Ike is making the same stupid error that many make, not understanding the differences between causality, correlation, and coincidence, and foolishly attempting to calculate the odds of two (probably) unrelated incidents, not even knowing if one of them happened!!

His statistical analysis is asinine and irrelevant.

Are you telling me you genuinely cannot see the assumption that is hiding in the middle of his equation?

I seem to recall your brother having helped you in the past, Caz, when you couldn't quite grasp a logical point. He probably wouldn't be interested, but if so, run it all past him and see if he agrees. Or give Jeff Hamm a shout out, and see if he agrees that Ike's statistical analysis is valid.

I'm happy to be corrected by someone who actually knows what they are talking about. But I won't be.

You can then come back wiser...and maybe even apologetic.

[rjpalmer]

Well, I’ve promised not to post further, but seeing that Ike has managed to confused Caz—despite Scott’s friendly warnings—perhaps it would be useful to go over this one last time.

It would simply be a question of calculating the odds of those two events coinciding by chance, and therefore being unconnected.

Love,

Caz
X

Sounds great on paper. 'Simply a question'??

I think your post shows some hope for insight. Caz. You are smelling a rat, and sensing that someone is “missing the point,” but you wrongly ascribe it to Orsam rather than Ike. As I say, maybe your brother can help.

To be blunt, the calculation you suggest is a fool's errand.

Millions of events happen at any given moment. Most of them are unrelated. A boy sets off a firecracker on his front porch and two blocks away an apple falls from a tree.

My God, you ask, what are the odds?

The odds aren’t actually relevant, because you haven’t shown that one event caused the other, but we can calculate them if you wish, even though any answer would be meaningless.


One event—the boy firing off a firecracker—(like Barrett calling Doreen on March 9th) will be our constant. It is a real event. It happened. It is not under dispute (unlike Eddy finding something under Dodd’s floorboards).

So, let’s say it took 1 second for the firecracker to explode. To find out the approximate odds of this explosion coinciding with an apple randomly dropping, we just need to find out how many apples fall from the tree on a given day.

Let’s say it is 10. There are 3,600 seconds in a hour, and 24 hours in a day, so that’s 84,400 seconds in a day. Thus, an apple falls every 8,400 seconds, provided it is autumn, and it was in autumn that the boy fired off the firecracker; if he had fired it off in winter there wouldn’t have been any opportunity for the ‘coincidence’ to have even happened, since apples aren’t on trees in mid-winter. But I digress.

Therefore, it is 8400 to 1 that an apple will have fallen when the firecracker went off.

This is similar to what Orsam was calculating. Barrett coming forward on March 9th was the constant. It happened. It is not under dispute. Dodd having work done on his house also happened and is not in dispute. What are the odds that Dodd would be have had someone working on his house that day? (just like the apple falling from the tree). That is the only issue that is known and is not under dispute—Eddie and the floorboards and a diary being found ARE under dispute-- so that is what Orsam is rationally trying to calculate.

Well, here our data is very much limited, but judging by the timesheets that Keith was able to find, Dodd had electricians in 14 times in 1992. When adjusted for weekends and holidays, that’s an average of once every 18 days.

The odds are 18 to 1.

This is based on what we actually know. But of course, the odds are dumb. Until proven otherwise, the ‘coincidence’ is strictly in the mind of the observer, like the firecracker and the apple. Other things could have happened that would have triggered Keith’s suspicions, and any causality had not been proven.

In our firecracker example, a dog could have barked. A shingle could have slid off a roof. Millions of events coincide at any moment, and it doesn’t show that they are cause and effect.

In Ike’s case, his analysis is simply PIFFLE, because he doesn’t know how old the diary is. He doesn’t know where it came from. His attempts to date the “possible” range of dates back to May 11, 1889 is wishful thinking. It may have never been under the floorboards. The diary could be a week old. His analysis hides an assumption, and if you can’t see that, then you shouldn’t be insulting anyone!!!

It’s a bit like Ike is trying to calculate the firecracker/apple analogy without even knowing that an apple actually fell. He calculating a known with an unknown. It’s a pointless exercise, a fantasy, dressed up as if it has proved something, when it hasn’t. It’s junk statistics.

How bloody hard can this be?

[Iconoclast]

Or give Jeff Hamm a shout out, and see if he agrees that Ike's statistical analysis is valid.

I don't know who Jeff Hamm is but - if he knows his onions - please someone bring him out.

Remember, we are calculating the probability of two things happening by chance alone (the lifting of Maybrick's floorboards in his study and someone seeking a literary agent for a Jack the Ripper scrapbook purporting to be written by James Maybrick) happening on the same day for the very first time (on the record) on March 9, 1992 and the only assumption that we are making is that we can safely start on May 12, 1889 (because it is rather obvious that either or both events could have happened on May 12, 1889 and every day thereafter until March 9, 1992, when they cunningly contrived to happen on the SAME day for the first time).

Bring on Jeff Hamm. Bring on absolutely anyone at all who understands statistics. In truth, I suspect that you could bring on many people who don't understand statistics as it's so basic that most 4th graders could understand it (I say 'most' as the evidence is not good that they all do - how was school today, by the way, RJ?).

So two events which we know happened on the same day, both Maybrick-related, relative to the first day this could have happened which I am giving as May 12, 1889. No need for obfuscation with talk of missing assumptions or unknown facts.

This was the FIRST of a perfectly-implausible double event on March 9, 1992. Not content with that gem of a probability value (1/37,557), Fate decreed that another miracle should happen - namely, that a member of the Rhodes' team should drink in the same pub as the guy who contacted the literary agent! DO YOU KNOW HOW BIG MERSEYSIDE IS AND HOW MANY PEOPLE LIVED THERE IN 1992????? Can you imagine how unlikely it would be that a member of the Rhodes' team would live so close (and drink even closer) to Michael Barrett?

RJ and LO obviously realise how bang-to-rights their pathetic Barrett-as-master-forger fabrication is by this crippling 'double miracle' on March 9, 1992 which possibly explains their frantic bluff and bluster posts and blogs desperately trying to salvage a theory which long since wet its pants and ran away.

You're welcome.

Ike

[Iconoclast]

Well, I’ve promised not to post further, but seeing that Ike has managed to confused Caz—despite Scott’s friendly warnings—perhaps it would be useful to go over this one last time.

...

How bloody hard can this be?

It is pointless asking RJ or LO to check the premises I gave in my previous post (above) but I strongly advise that everyone else does.

This truly feeble 'analogy' (Lord, it's not even that) falls at the point that Mike Barrett contacts a literary agent (the firecracker going off), and thousands of Paul Dodds' houses have their floorboards lifted that day (the apples falling all over the world in that moment). Even if there was just the one apple falling (as indeed there was) all that is required is a link between the two events for us to dispense with chance once the probability falls so unbelievably low. Was there a link between the two events? Indeed there was and his name was James Maybrick. Was there a link between our mythical firecracker and our mooted falling apple? Clearly not. Enough apples fall all of the time that one is perfectly likely to fall when our firecracker goes off. Clearly, these two events can occur simultaneously without invoking any form of association. As Paul Dodds (actually, James Maybrick) had one house not thousands, we are simply unable to compare apples with flares.

If anyone is keen on believing that Mike Barrett hoaxed the scrapbook (I'm not saying it wasn't hoaxed, note), then they are welcome to get excited by RJ/LO's astonishing post, above. We'll call it The Firecracker One for posterity. Feel free to believe that the longwinded ecstasy of monstrous stupidity proves that my simple statistical analysis is in some way faulty. You absolutely must understand that I don't give a **** whether anyone thinks my analysis is wrong unless that person can demonstrate why it is wrong. If you return to my simple premises, and don't add any or twist any, or just be plain and obviously utterly mendacious, then you will see that this is genuinely not hard at all.

By the way, I didn't think the Pedant Pair would attempt to salvage the 1-in-18 probability nightmare, but they have. Such egos as these cannot be trusted with your confidence, dear readers. They are mugging you off. Don't buy it.

Ike

[rjpalmer]

Bring in anyone you want, Ike, but I'm not going to help you, because you're apt to just insult them when they point out the basic flaw in your analysis.

You've been a very naughty boy, Tom.

But, as I say, since you are so confident, may I suggest that you submit your findings to The Journal of Forensic Science and Criminology for peer review?

The more I think it over, the more shocking it is that your important discovery is being ignored, but perhaps, as you imply, most people simply don't have the brain power to understand the flawlessness of your logic.

You might also calculate the odds that the name 'Diego Laurenz' was generated by random chance in a city now known for the suspect James Maybrick. There are dozens of male given names in Spanish, and there must hundreds if not thousands of possible surnames. I'm thinking 40,000 to 1 or somewhere in that neighborhood?

If you combine those long odds with the floorboard odds, you've all but prove your case.

Good luck with your scholarly paper.

[Iconoclast]

Bring in anyone you want, Ike, but I'm not going to help you, because you're apt to just insult them when they point out the basic flaw in your analysis.

You've been a very naughty boy, Tom.

But, as I say, since you are so confident, may I suggest that you submit your findings to The Journal of Forensic Science and Criminology for peer review?

The more I think it over, the more shocking it is that your important discovery is being ignored, but perhaps, as you imply, most people simply don't have the brain power to understand the flawlessness of your logic.

You might also calculate the odds that the name 'Diego Laurenz' was generated by random chance in a city now known for the suspect James Maybrick. There are dozens of male given names in Spanish, and there must hundreds if not thousands of possible surnames. I'm thinking 40,000 to 1 or somewhere in that neighborhood?

If you combine those long odds with the floorboard odds, you've all but prove your case.

Good luck with your scholarly paper.

Why would I do that when I did all of that and so much more in my brilliant Society's Pillar?

You're all going to have to wait quite a while for the next update, by the way, dear readers - but boy it is going to be dynamite!

You heard it here first, folks!

Ike

[Scott Nelson]

Probability example: A guy tosses a coin in the air 9 times. 8 times it comes up heads, 1 time tails. What are the chances the 10th toss will come up heads?

Exactly 50-50.

[Iconoclast]

Probability example: A guy tosses a coin in the air 9 times. 8 times it comes up heads, 1 time tails. What are the chances the 10th toss will come up heads?

Exactly 50-50.

Obviously. And your point is what, caller?

But we are not talking about a single day when one of two things could have happened. We are talking about 37,557 days in which either event could have happened separately, and yet they happened to happen on the SAME day, 37,557 days after the possibility started. Staggering.

As a matter of interest, do you know what the probability is of '[a] guy [tossing] a coin in the air 9 times. 8 times it comes up heads, 1 time tails'?

Ike

[Scott Nelson]

Eddie was working full-time hours, from Monday to Saturday, from December 1991 to 7th March 1992, over in Skem, so opportunities to bump into Mike in the Saddle during that time would have been limited, unless they both drank there outside of Eddie's working hours, for example on Saturday nights. But the landlord, speaking to Feldy in 1993, only said he remembered Mike - and Tony - and occasionally Mike's father, coming in for lunchtime drinks.

Caroline, so Tony knew Eddie?

[Scott Nelson]

That's how statistics work: they tell you how likely certain agreed facts might occur by chance alone, but they do not imply that those facts will happen at all.

So the issue is always 'What question am I asking?', and 'Do I have sufficient data to use statistical analysis to give me a probability for it happening by chance alone?'.

OK, got it. Thanks.

[rjpalmer]

I genuinely hope that everyone sleeps sounder tonight now that we have established that the p value of our analysis has been corrected by the crucial 0.0000001

I slept great, but, to be pedantic, the correct number is .1624. That's the percentage you inflated your imaginary statistic, by adding an additional 61 days. If you can't work it out, always feel free to send me a PM.

That's how statistics work: they tell you how likely certain agreed facts might occur by chance alone, but they do not imply that those facts will happen at all.

So the issue is always 'What question am I asking?', and 'Do I have sufficient data to use statistical analysis to give me a probability for it happening by chance alone?'.

And the answer is a resounding, "NO!"

You do not have sufficient data, because you are trying to analyze a still theoretical event that you don’t know happened, and don’t even know whether it COULD have happened. At its bleakest, you don’t even know if the diary physically existed on 9 March 1992, and that stark reality turns your probability analysis into moonshine.

No one is disputing that James Maybrick died on 11 May 1889. (Though, for some reason, you keep using May 12th). Nor are they disputing that there is a span of 35, 557 days between 11 May 1889 and 9 March 1992.

Those are indeed facts. But as seductive as they may appear to you, they are entirely IRRELEVANT to the matter at hand, because we don’t know the diary is Maybrick’s, nor where it came from, nor how old it is.

How frickin' hard is this to grasp?

What keeps leading you astray again & again & again is that you are so convinced that your calculations are correct (and they weren’t correct until I corrected them) that you don’t stop to consider that the REAL problem isn’t so much your math, but that you are calculating illegitimate and irrelevant data.

Using the date 11 May 1889 is a theory disguised as a fact.

It’s garbage in and can only lead to garbage out.

If we wanted to stay afoul of Voodoo Statistics, we could re-formulated your statement something like the following:

“Working on the assumption that the diary was 37, 557 days old on March 9th (which we don’t actually know; this is not a ‘certain agreed fact,’ and is heavily disputed), and provided that the floorboards were lifted for the first time on March 9th (which again we don’t know--it even runs counter to the claims of the owner), and provided that Barrett really did call an agent or a publisher for the first time on March 9th (which we also don’t know), then we can calculate the odds as….yadda yadda yadda…37,557…

Doesn’t quite have the same ring, does it?

Being generous, I haven’t even confronted you about your last two assumptions, but I’ll be damned if I’m not going to call your bluff on the first assumption.

What you are really doing is calculating the probabilities of your baseless theory—and this is the sticking point you can’t seem to grasp. You evidently believe it is the same thing as an actual probability.

It isn’t.

I ran your analysis past my bookkeeper friend last night. She rolled her eyes and exclaimed. “No! You can’t do it like that!”

Indeed. But the odds of Ike ever admitting that are almost zero.

--The Pedant

[Iconoclast]

I slept great, but, to be pedantic, the correct number is .1624. That's the percentage you inflated your imaginary statistic, by adding an additional 61 days. If you can't work it out, always feel free to send me a PM.

...


I ran your analysis past my bookkeeper friend last night. She rolled her eyes and exclaimed. “No! You can’t do it like that!”

Dear Readers,

You and I have presumably had enough of the statistics?

I have explained how they work and have shown that my understanding of statistics is impeccable. In contrast, RJ has spewed out a barrage of obfuscation and misinformation in order to confuse you over and over again. "The correct number is" is a classic example of how he simply has to be right and everyone he disagrees with simply has to be wrong. I haven't checked his 0.1624% number, but it's irrelevant whether it is accurate or not. It is irrelevant because no-one was discussing by what per centage the p value changed. All I showed was the absolute change in value, a perfectly legitimate number to quote you all. This shift to a different way of looking at the same number and then calling it "the correct number" speaks volumes for how he thinks - his way is right, even if it's just another means of stating the same thing. Sad, to be honest.

By the way, I can honestly say that I was hoping his 'authority' (it was inevitable he would produce one and that they would 'diss' my stats) on research methods and statistics might have been slightly more qualified than an accountant.

Last time on statistics, RJ: if you're such a whizz and I'm such an idiot, tell us all how to calculate Scott's probability example of yesterday (and give us the answer while you're at it).

Someone tosses a coin nine times and gets eight heads and one tails. What are the odds of that happening by chance alone? So:

Tell us how the probability is to be calculated, and then
Give us the result of that calculation.

Don't ask your 4th-grade classmates for help, though.

Ike

[Iconoclast]

I ran your analysis past my bookkeeper friend last night. She rolled her eyes and exclaimed. “No! You can’t do it like that!”

By the way, I love the dramatic way you claim she 'rolled her eyes' and her effusive response. What do you think she meant by "You can't do it like that!"? Do you think her years of training on double-entry accounting instinctively told her that statisticians had been calculating simple probabilities incorrectly for decades before she came along with her DIY Chi-Squared Test?

Funnily enough, just yesterday I called in our local carpenter because one of our lights had stopped working. He looked at the switches and fuses and he rolled his eyes and exclaimed - in bold no less - No! You can't do it like that!

For the record, I'm now suing the firm which originally installed the lighting system and will in future steer well clear of Theodora Potter Painting & Decorating Co. Inc. and I suggest everyone else does so too. Fortunately for me, our milkman works on Saturdays so I could give him my legal instructions immediately. He said he would get his secretary on it as soon as she had fixed the sewage system in the local Nissan factory.

Seriously, RJ, once again I pissed myself at your desperation to be right at all times.

[rjpalmer]

Last time on statistics, RJ: if you're such a whizz and I'm such an idiot, tell us all how to calculate Scott's probability example of yesterday (and give us the answer while you're at it).

Someone tosses a coin nine times and gets eight heads and one tails. What are the odds of that happening by chance alone?

No Ike, I'm not going to give you the answer, and I'll tell you why.

It will leave the impression that this example is relevant, and somehow analogous to your own statistical analysis, and that the difficulty we face is one that can be resolved through simple mathematics.

That would be wrong, because the example you give involves calculating the odds of events that we know happened.

By contrast, you are attempting to calculate the odds of a theoretical event, that you don't know happened, and that is what is leading you into the quagmire.

My final advice to you is to read post #6568 over and over and over again until you realize what you are doing wrong.

Good luck with that, and I'm sorry to hear that you've been living in the dark.

You should have consulted an electrician (and one who wasn't merely repeating confused gossip or trying to get a cameo in Feldman's video).

--The Pedant.