Serial killers - where are they now?

[snoozeofreason]

It reminds me more than a little of the Lucia de Berk case

Except in that case there wasn't really any direct evidence - whereas in the Letby case there are 2 babies with extremely high insulin and low C-peptide. Strong evidence of exogenous insulin administration.

And the evidence of her having tampered with the medical records to change the times

As mentioned in the previous post. The prosecution did claim to have direct evidence the De Berk case.

As for the tampering with records. You may have followed the case more closely than me, but as far as I can recall the prosecution weren't able to produce any concrete evidence that Letby had altered records. The only thing they could convincingly demonstrate was that her timings differed slightly to those of other witnesses to the same events (in some cases only by minutes). This is more or less what you expect to see when different witness accounts are compared (if anything it is suspicious if you don't see such differences).

[bob sterman]

It reminds me more than a little of the Lucia de Berk case

Except in that case there wasn't really any direct evidence - whereas in the Letby case there are 2 babies with extremely high insulin and low C-peptide. Strong evidence of exogenous insulin administration.

There was direct evidence in the De Berk case. It was claimed that digoxin had been found in the body of one alleged victim and an overdose of chloral hydrate in another. This evidence was overturned on further examination. Richard Gill, who was one of the key figures in the campaign to exonerate De Berk, has pointed to similar problems with the evidence in the Letby insulin cases, as have other scientists (see the links that gosling posted earlier).

It was equivocal whether it was actually digoxin in the De Berk assays rather than cross-reactivity with a naturally occurring substance. Rather different from extremely high insulin levels and low C-peptide in the Letby case.

The statistical argument in one of those links posted earlier (the Chimp Investor investment blog - great source on epidemiology) seems to run like this...

Once you take out the deaths attributed to Letby from the statistics - the hospital still had a very high neonatal death rate during the time she was working there - therefore there must have been some other factor causing the deaths - that may also have been responsible for the deaths attributed to Letby.

The author discounts the more plausible alternative - i.e. that if you have identified a serial killer working in the hospital - she may also have been responsible for some of the other neonatal deaths (even though she is not be being prosecuted for those).

[bob sterman]

Another key difference...

The diary used in the case against de Berk contained vague notes about giving in to her "compulsion" that could be interpreted in many ways.

Letby's notes were a little more specific...e.g. one says "I killed them on purpose".

[snoozeofreason]

It was equivocal whether it was actually digoxin in the De Berk assays rather than cross-reactivity with a naturally occurring substance. Rather different from extremely high insulin levels and low C-peptide in the Letby case.

The statistical argument in one of those links posted earlier (the Chimp Investor investment blog - great source on epidemiology) seems to run like this...

Once you take out the deaths attributed to Letby from the statistics - the hospital still had a very high neonatal death rate during the time she was working there - therefore there must have been some other factor causing the deaths - that may also have been responsible for the deaths attributed to Letby.

The author discounts the more plausible alternative - i.e. that if you have identified a serial killer working in the hospital - she may also have been responsible for some of the other neonatal deaths (even though she is not be being prosecuted for those).

If the presence of digoxin in the De Berk case had been considered to be equivocal at the time of her trial, then she would not have been convicted. The judges at her trial considered the administration of digoxin to have been proved beyond reasonable doubt (and used this as part of a "chain link" argument to justify convicting her in other cases in which they would otherwise not have considered her guilt to be proved to that standard). The suggestion of a natural origin for the supposed digoxin levels was made after her conviction and was one of the reasons for her eventual acquital.

The insulin levels found in the Letby case do seem, as your underlining indicates, to have been extremely high. This, according to critics, is part of the problem. Both of the babies to whom Letby was accused of administering insulin survived, despite the fact that at least one is alleged to have received a dose that should have killed a grown man. Gill also points out that the test used in those cases is one that the manufacturers very emphatically point out should not be used to detect exogenous administration of insulin. I am not in a position to judge the merits of this contrary evidence but neither was the jury because it was not presented to them (or indeed transmitted Letby despite requests to do that being made at the time).

The main problem with the statistics in both the Letby and De Berk cases is the one pointed out by the Royal Statistical Society (and also by that curly haired bloke at the time of the De Berk case). There are huge numbers of nurses, and other people who might come under suspicion because of their connection to an "unusual pattern" of adverse events. This means that even if the pattern would be unusual if it occurred to a particular person, it would have to be very unusual indeed for something of that nature not to occur to someone.

Another key difference...

The diary used in the case against de Berk contained vague notes about giving in to her "compulsion" that could be interpreted in many ways.

Letby's notes were a little more specific...e.g. one says "I killed them on purpose".

We have already discussed that at some length upthread. It's a post-it note. You can see it here. here. She has written all sorts of random stuff in random directions. It does include the sentence you quote but also the sentence "I haven't done anything wrong". It's not clear which bits refer to things she has done, and which to things that she has heard been said about her. (And of course it would be a bit odd if someone who had been calculating enough to commit seven murders in a busy hospital without being caught in the act had also been careless enough to write a confession on a post-it note and leave it for the police to find.)

[Bewildered]

The insulin levels found in the Letby case do seem, as your underlining indicates, to have been extremely high. This, according to critics, is part of the problem. Both of the babies to whom Letby was accused of administering insulin survived, despite the fact that at least one is alleged to have received a dose that should have killed a grown man. Gill also points out that the test used in those cases is one that the manufacturers very emphatically point out should not be used to detect exogenous administration of insulin. I am not in a position to judge the merits of this contrary evidence but neither was the jury because it was not presented to them (or indeed transmitted Letby despite requests to do that being made at the time).

I haven’t looked into this at all, just based on what you wrote here. In something like this I think you will always be able to find someone disputing the scientific evidence. What I would want to know but can’t without looking more into it is if the disputes regarding this evidence are credible / come from a credible source with the appropriate expertise. Do you think it’s possible the criticisms were not presented to the jury by the defence because they were too weak/contradicted by real experts and it would have been irresponsible to do so? Or you already went down this rabbit hole and convinced yourself they are credible?

[Fishnut]

Apart from pleading not guilty (which is totally understandable where the evidence utterly unequivocal, even if you're guilty), has Letby done anything to suggest that she didn't commit these murders? Has she protested her innocence? Has her legal team said anything about the conviction? Are they appealing it? I've been able to find a statement from a solicitor representing seven families but nothing from Letby's side.

I know that miscarriages of justice do occur (Andrew Malkinson is just the latest in a long line) and I know that in situations where a certain level of mortality is to be expected, determining non-natural deaths can be difficult, but I'm not seeing anything to suggest that she's been unfairly convicted. If anything, she had everything in her favour to get away with it. She's a young, white, middle class woman and people seem to be in disbelief that a 'nice kind nurse' like her could do something like this, making them much more inclined to be believe it's coincidence or scapegoating.

[snoozeofreason]

The insulin levels found in the Letby case do seem, as your underlining indicates, to have been extremely high. This, according to critics, is part of the problem. Both of the babies to whom Letby was accused of administering insulin survived, despite the fact that at least one is alleged to have received a dose that should have killed a grown man. Gill also points out that the test used in those cases is one that the manufacturers very emphatically point out should not be used to detect exogenous administration of insulin. I am not in a position to judge the merits of this contrary evidence but neither was the jury because it was not presented to them (or indeed transmitted Letby despite requests to do that being made at the time).

I haven’t looked into this at all, just based on what you wrote here. In something like this I think you will always be able to find someone disputing the scientific evidence. What I would want to know but can’t without looking more into it is if the disputes regarding this evidence are credible / come from a credible source with the appropriate expertise. Do you think it’s possible the criticisms were not presented to the jury by the defence because they were too weak/contradicted by real experts and it would have been irresponsible to do so? Or you already went down this rabbit hole and convinced yourself they are credible?

A lot of the contrary evidence comes, either directly or indirectly, from Richard Gill. Gill is a former president of the Netherlands Society for Statistics and Operations Research, a member of the UK Royal Statistical Society, a co-author of the report which that body published on the treatment of uncertainty in medical “murder” cases, and a leading figure in the successful campaign to exonerate Lucia De Berk. None of that of course makes him infallible. It is possible that he is going down a rabbit hole and that I am following him. But it would be hard to say that he is not credible (and one could point out that the last time he went down a rabbit hole he came back with a rabbit).

The specifically medical evidence comes from a source who wishes to remain anonymous, which is hardly surprising if you have read any of the internet comments on the subject. It sounds as if Gill knows who (s)he is and trusts her/him. Again that's not a guarantee of infallibility, but its probably an indication of credibility.

The failure of the defence to use any expert evidence (apart from that provided by a plumber) has been a bit of a mystery even to people who consider Letby guilty. It is possible that the defence feared that the jury wouldn't understand it, and that if it was used unsuccesfully in the original trial it would not be usable in a subsequent appeal against conviction, but that's just speculation.

[snoozeofreason]

Apart from pleading not guilty (which is totally understandable where the evidence utterly unequivocal, even if you're guilty), has Letby done anything to suggest that she didn't commit these murders? Has she protested her innocence? Has her legal team said anything about the conviction? Are they appealing it? I've been able to find a statement from a solicitor representing seven families but nothing from Letby's side.

I know that miscarriages of justice do occur (Andrew Malkinson is just the latest in a long line) and I know that in situations where a certain level of mortality is to be expected, determining non-natural deaths can be difficult, but I'm not seeing anything to suggest that she's been unfairly convicted. If anything, she had everything in her favour to get away with it. She's a young, white, middle class woman and people seem to be in disbelief that a 'nice kind nurse' like her could do something like this, making them much more inclined to be believe it's coincidence or scapegoating.

As you say, she pleaded not guilty. Then she spent 14 days in the witness box denying the accusations against her. I am not sure what else you think she should, or even could, have done. Bear in mind that once a prosecution has started it is difficult for a defendant to make any statement outside the witness box (and if the defendant is in prison on remand, as Letby was for nearly three years prior to the guilty verdict, it is fairly easy to ensure that these rules of procedure are respected). Once a defendant is found guilty then there are other reasons why protesting innocence, outside of a formal appeal procedure, is difficult.

As far as I am aware, the only statement her legal team have made since her conviction was at the point of sentencing, when they said they would be offering no evidence in mitigation. It would be possible to interpret that as meaning that they, or Letby, have accepted the enormity of her crimes, and I have no doubt that this his how it will be reported in the press. In reality the reason is more likely to be that it is difficult to offer evidence in mitigation for an offence that a defendant denies occurred. If Letby accepted guilt then there would be options - the defence could suggest that the balance of her mind was disturbed for example. It sounds as if she still denies these offences, so that's not possible.

It is unlikely that there will be an appeal against sentence, for the same reason that there was no plea in mitigation. There might be an appeal against conviction, but as anyone who has followed the Malkinson case will realise, these are difficult to obtain.

I suppose the press reaction to her might be even more hostile if she was not young and white, but the mainstream press seems to have accepted her guilt, and is happy to publish calls for the reintroduction of the death penalty so that people such as her can be strung up, so it doesn't seem to have helped her that much.

[Millennie Al]

She has written all sorts of random stuff in random directions.

I have always found it quite puzzling that if someone says their guilty, they are believed, by if they protest their innocence we are told that we shouldn't believe a word they say. In this case, there seems to be so much random text it's hard to understand what it was intended to mean and what it really means. Statements from a defendant are only strong evidence of guilt if they show knowledge that only the guilty could know. In the case of a nurse, it seems quite plausible that she might feel responsible for deaths that she was actually trying to avoid. But at present we can only trust that the jury, who saw all of the evidence, made the right decision.

[Woodchopper]

She has written all sorts of random stuff in random directions.

I have always found it quite puzzling that if someone says their guilty, they are believed, by if they protest their innocence we are told that we shouldn't believe a word they say.

In general, guilty people have a very strong incentive to lie and say that they are innocent. Innocent people have a very strong incentive to tell the truth and proclaim their innocence. So we should be more skeptical about what is said by someone who proclaims their innocence. Obviously there are exceptional circumstances in which the guilty may be honest and the innocent may lie.

In this case, there seems to be so much random text it's hard to understand what it was intended to mean and what it really means. Statements from a defendant are only strong evidence of guilt if they show knowledge that only the guilty could know. In the case of a nurse, it seems quite plausible that she might feel responsible for deaths that she was actually trying to avoid. But at present we can only trust that the jury, who saw all of the evidence, made the right decision.

It seems to me that perhaps we are misinterpreting what Letby's writings tell us. To recap, Letby kept hundreds confidential documents which related to the infants that had died in suspicious circumstances, she frequently viewed the social media profiles of the parents of the infants that had died in suspicious circumstances, and we have her writing that appears to relate to those infants.

Put together, these look like someone with a fixation on the infants who died or were injured in suspicious circumstances. That alone would not amount to enough to convict someone, but in combination with her presence when the incidents happened, it appeared to be enough to establish guilt.

[Bewildered]

The insulin levels found in the Letby case do seem, as your underlining indicates, to have been extremely high. This, according to critics, is part of the problem. Both of the babies to whom Letby was accused of administering insulin survived, despite the fact that at least one is alleged to have received a dose that should have killed a grown man. Gill also points out that the test used in those cases is one that the manufacturers very emphatically point out should not be used to detect exogenous administration of insulin. I am not in a position to judge the merits of this contrary evidence but neither was the jury because it was not presented to them (or indeed transmitted Letby despite requests to do that being made at the time).

I haven’t looked into this at all, just based on what you wrote here. In something like this I think you will always be able to find someone disputing the scientific evidence. What I would want to know but can’t without looking more into it is if the disputes regarding this evidence are credible / come from a credible source with the appropriate expertise. Do you think it’s possible the criticisms were not presented to the jury by the defence because they were too weak/contradicted by real experts and it would have been irresponsible to do so? Or you already went down this rabbit hole and convinced yourself they are credible?

A lot of the contrary evidence comes, either directly or indirectly, from Richard Gill. Gill is a former president of the Netherlands Society for Statistics and Operations Research, a member of the UK Royal Statistical Society, a co-author of the report which that body published on the treatment of uncertainty in medical “murder” cases, and a leading figure in the successful campaign to exonerate Lucia De Berk. None of that of course makes him infallible. It is possible that he is going down a rabbit hole and that I am following him. But it would be hard to say that he is not credible (and one could point out that the last time he went down a rabbit hole he came back with a rabbit).

He is a credible person on stats, but not on the medical evidence, which I think you know and address after, but just to be clear that’s the context I had in mind when asking. You are right it could be he’s found another instance of this problem and I understand why you would take him seriously, but after the experience of finding one such case it may also have coloured his judgement / become an obsession. Just like the accusers, prosecution and their expert witnesses may be biased by seeing the stats and then interpreting everything they see with that suspicion in mind so they see evidence where they may not have, Gill may see what looks like a superficially similar cluster case to the one he debunked and then be viewing all the evidence through that biased lens, believing claims that the experts who testified in the scientific evidence are wrong and trusting instead a maybe less credible source that fits his preconceived notion etc etc.

So I think it is plausible that he has gone down a rabbit hole in the pejorative sense of strayed into fantasy world in the sense I think you are using it here ( when I used it I just meant get into a complex set of interconnecting tunnels that I’d spend ages navigating before I could emerge with what I want). Im not saying he has just that it’s possible.

Another seed of doubt related to this. In the previous case it was not him alone but many experts writing together. Why does he seem to be alone in this one? Could it be the others don’t agree on this one? Or it’s just not got to that stage yet?

The specifically medical evidence comes from a source who wishes to remain anonymous, which is hardly surprising if you have read any of the internet comments on the subject. It sounds as if Gill knows who (s)he is and trusts her/him. Again that's not a guarantee of infallibility, but its probably an indication of credibility.

It’s understandable but it means I don’t know for myself how relevant they are etc and you are then just relying on Gill being able to judge that this person really has the right expertise and can be trusted here. That inherently means much more doubt. I agree it’s more than nothing but it’s not sufficient for me to be very confident honestly or assume that the defence did something wrong in ignoring this. Also remember for the case it’s got to be credible enough to make me think that the experts who presented in court misled the jury regarding the facts.

The failure of the defence to use any expert evidence (apart from that provided by a plumber) has been a bit of a mystery even to people who consider Letby guilty. It is possible that the defence feared that the jury wouldn't understand it, and that if it was used unsuccesfully in the original trial it would not be usable in a subsequent appeal against conviction, but that's just speculation.

If they had invited their own experts to look at it and the experts agreed with prosecutions would they have to disclose this in the trial or they just wouldn’t call them? Could something like that have happened? Or if they would have to disclose maybe they just worried that is what would happen? Not sure how it works with someone contacting them to say they disagreed with the prosecutions experts.

[snoozeofreason]

It seems to me that perhaps we are misinterpreting what Letby's writings tell us. To recap, Letby kept hundreds confidential documents which related to the infants that had died in suspicious circumstances, she frequently viewed the social media profiles of the parents of the infants that had died in suspicious circumstances, and we have her writing that appears to relate to those infants.

Put together, these look like someone with a fixation on the infants who died or were injured in suspicious circumstances. That alone would not amount to enough to convict someone, but in combination with her presence when the incidents happened, it appeared to be enough to establish guilt.

You may have followed the case more carefully than I did but, so far as I recall, she looked at the social media profiles of parents whether their children had died in suspicious circumstances or not, and she kept all sorts of documents, most of which was low level stuff such as handover notes (i.e. stuff that would have been shredded rather than kept) and only some of which related to cases where she was under suspicion. Like the random scribblings on the post-it note, it only starts to look sinister or fixated if you focus on the bits that would fit a suspicious pattern and ignore the rest. Taken in total it just looks a bit odd (and I'm a bit odd myself so I am prepared to cut people some slack on that subject).

At her trial she was asked why she didn't destroy the documents (which suggests they were the sort of thing destined for shredding rather than filing) and much was made of the fact that she claimed she couldn't have done so despite possessing a shredder. It's not obvious whether that points to guilt or innocence though. If I had committed a murder and had documents that might be used against me in a trial I think I would shred them.

[Woodchopper]

It seems to me that perhaps we are misinterpreting what Letby's writings tell us. To recap, Letby kept hundreds confidential documents which related to the infants that had died in suspicious circumstances, she frequently viewed the social media profiles of the parents of the infants that had died in suspicious circumstances, and we have her writing that appears to relate to those infants.

Put together, these look like someone with a fixation on the infants who died or were injured in suspicious circumstances. That alone would not amount to enough to convict someone, but in combination with her presence when the incidents happened, it appeared to be enough to establish guilt.

You may have followed the case more carefully than I did but, so far as I recall, she looked at the social media profiles of parents whether their children had died in suspicious circumstances or not, and she kept all sorts of documents, most of which was low level stuff such as handover notes (i.e. stuff that would have been shredded rather than kept) and only some of which related to cases where she was under suspicion. Like the random scribblings on the post-it note, it only starts to look sinister or fixated if you focus on the bits that would fit a suspicious pattern and ignore the rest. Taken in total it just looks a bit odd (and I'm a bit odd myself so I am prepared to cut people some slack on that subject).

I'm sure that you are following the case far more carefully than I am. I was just speculating as I cycled into work this morning. Have only read what appears in the papers.

At her trial she was asked why she didn't destroy the documents (which suggests they were the sort of thing destined for shredding rather than filing) and much was made of the fact that she claimed she couldn't have done so despite possessing a shredder. It's not obvious whether that points to guilt or innocence though. If I had committed a murder and had documents that might be used against me in a trial I think I would shred them.

On your last point, that depends upon the murder. If the crime is purely instrumental - eg kill someone to get money - then of course the murderer will try to cover their tracks. They don't want to get caught. But mass killers are a bit different. Some do it openly and don't appear to care about getting caught. Others keep items associated with the victims.

[Bewildered]

She has written all sorts of random stuff in random directions.

I have always found it quite puzzling that if someone says their guilty, they are believed, by if they protest their innocence we are told that we shouldn't believe a word they say.

In general, guilty people have a very strong incentive to lie and say that they are innocent. Innocent people have a very strong incentive to tell the truth and proclaim their innocence. So we should be more skeptical about what is said by someone who proclaims their innocence. Obviously there are exceptional circumstances in which the guilty may be honest and the innocent may lie.

In this case, there seems to be so much random text it's hard to understand what it was intended to mean and what it really means. Statements from a defendant are only strong evidence of guilt if they show knowledge that only the guilty could know. In the case of a nurse, it seems quite plausible that she might feel responsible for deaths that she was actually trying to avoid. But at present we can only trust that the jury, who saw all of the evidence, made the right decision.

It seems to me that perhaps we are misinterpreting what Letby's writings tell us. To recap, Letby kept hundreds confidential documents which related to the infants that had died in suspicious circumstances, she frequently viewed the social media profiles of the parents of the infants that had died in suspicious circumstances, and we have her writing that appears to relate to those infants.

Put together, these look like someone with a fixation on the infants who died or were injured in suspicious circumstances. That alone would not amount to enough to convict someone, but in combination with her presence when the incidents happened, it appeared to be enough to establish guilt.

Your point here about interpreting what the post it note tells us made me think because I was assuming it was used as evidence she was saying she did it. You might be right, maybe it was presented more as part of a pattern of obsession. But going back and reading it again I still think the post it note is not evidence of guilt and probably it would be better if this wasn’t admitted as evidence. It doesn’t look like evidence of obsession to me, it looks like a perfectly ordinary reaction to extreme pressure and sad events. That post note just looks too much like what I would expect someone to wrote if innocent but suspected and in her situation.

[snoozeofreason]

...

At her trial she was asked why she didn't destroy the documents (which suggests they were the sort of thing destined for shredding rather than filing) and much was made of the fact that she claimed she couldn't have done so despite possessing a shredder. It's not obvious whether that points to guilt or innocence though. If I had committed a murder and had documents that might be used against me in a trial I think I would shred them.

On your last point, that depends upon the murder. If the crime is purely instrumental - eg kill someone to get money - then of course the murderer will try to cover their tracks. They don't want to get caught. But mass killers are a bit different. Some do it openly and don't appear to care about getting caught. Others keep items associated with the victims.

One of the other allegations made against Letby was that she had altered medical evidence to cover her tracks. So if she is a murderer, I guess she would have to be the kind of murderer that sometimes resorts to subterfuge to remove evidence against her, and sometimes deliberately preserves such evidence and leaves it lying around for the police to find (even if she was professionally obliged to destroy it).

[Woodchopper]

...

At her trial she was asked why she didn't destroy the documents (which suggests they were the sort of thing destined for shredding rather than filing) and much was made of the fact that she claimed she couldn't have done so despite possessing a shredder. It's not obvious whether that points to guilt or innocence though. If I had committed a murder and had documents that might be used against me in a trial I think I would shred them.

On your last point, that depends upon the murder. If the crime is purely instrumental - eg kill someone to get money - then of course the murderer will try to cover their tracks. They don't want to get caught. But mass killers are a bit different. Some do it openly and don't appear to care about getting caught. Others keep items associated with the victims.

One of the other allegations made against Letby was that she had altered medical evidence to cover her tracks. So if she is a murderer, I guess she would have to be the kind of murderer that sometimes resorts to subterfuge to remove evidence against her, and sometimes deliberately preserves such evidence and leaves it lying around for the police to find (even though she was professionally obliged to destroy it).

Pure idle speculation but that might fit the picture of someone who is obsessive. They don't want to get caught (if only because prison will prevent them from acting on their obsession), but they also don't want to give up things linked to their obsession.

[snoozeofreason]

...


On your last point, that depends upon the murder. If the crime is purely instrumental - eg kill someone to get money - then of course the murderer will try to cover their tracks. They don't want to get caught. But mass killers are a bit different. Some do it openly and don't appear to care about getting caught. Others keep items associated with the victims.

One of the other allegations made against Letby was that she had altered medical evidence to cover her tracks. So if she is a murderer, I guess she would have to be the kind of murderer that sometimes resorts to subterfuge to remove evidence against her, and sometimes deliberately preserves such evidence and leaves it lying around for the police to find (even though she was professionally obliged to destroy it).

Pure idle speculation but that might fit the picture of someone who is obsessive. They don't want to get caught (if only because prison will prevent them from acting on their obsession), but they also don't want to give up things linked to their obsession.

I suppose it might. For what it's worth, the article that Tessa linked to earlier suggested that female serial killers don't hang on to objects associated with their crimes. That said, it is a rather odd article, which claims that Letby fits a profile they have developed and then gives a whole list of aspects in which she doesn't. I rather got the impression that they were latching onto evidence that fitted their theory, and ignoring evidence that didn't (which is an impression I have been getting quite a lot when reading about this case).

[noggins]

That article is bogus.

[nekomatic]

I don’t think this particularly supports the view that the conviction might have been unsafe, but the Royal Statistical Society wants the Letby inquiry to look at statistics

[IvanV]

I don’t think this particularly supports the view that the conviction might have been unsafe, but the Royal Statistical Society wants the Letby inquiry to look at statistics

There have of course been infamous miscarriages of justice - the double cot death case - not just because judges misunderstood statistics, but because expert witnesses who should have known better misunderstood statistics.

As this article correctly warns,

Judging whether something is too surprising to be ‘just a coincidence’ should not be a matter for human intuition – expert statistical analysis is required.

Which, of course, was exactly the problem in the double cot death case.

The article points out that a professor of statistics is calling for a retrial, due to mistakes in the use of the statistical evidence by both prosecution and defence. That would imply he thinks the conviction is unsafe.

[snoozeofreason]

I don’t think this particularly supports the view that the conviction might have been unsafe, but the Royal Statistical Society wants the Letby inquiry to look at statistics

There have of course been infamous miscarriages of justice - the double cot death case - not just because judges misunderstood statistics, but because expert witnesses who should have known better misunderstood statistics.

As this article correctly warns,

Judging whether something is too surprising to be ‘just a coincidence’ should not be a matter for human intuition – expert statistical analysis is required.

Which, of course, was exactly the problem in the double cot death case.

The article points out that a professor of statistics is calling for a retrial, due to mistakes in the use of the statistical evidence by both prosecution and defence. That would imply he thinks the conviction is unsafe.

I supect that the CPS will argue that none of the evidence in the case was "Statistical" because no numbers were presented to the jury and no statistician gave evidence. Instead the jury were simply invited to make their own judgements as to whether similarities and patterns observed in the events that unfolded were suspicious or just coincidental. To my mind those are statistical arguments, even if no numbers or statistical terms are used. The jury were effectively left to rely on their intuition. That's exactly what David Spiegelhalter (author of Ivan's quote) was warning against.

[IvanV]

I supect that the CPS will argue that none of the evidence in the case was "Statistical" because no numbers were presented to the jury and no statistician gave evidence. Instead the jury were simply invited to make their own judgements as to whether similarities and patterns observed in the events that unfolded were suspicious or just coincidental. To my mind those are statistical arguments, even if no numbers or statistical terms are used. The jury were effectively left to rely on their intuition. That's exactly what David Spiegelhalter (author of Ivan's quote) was warning against.

I wondered if that is why the professor is criticising the defence case also, for failing to bring out the point that intuition is very faulty in this situation.

In fact Professor Gill has blogged and he seems to be saying just that, among other things. He seems to be implying that the prosecution deliberately avoided the statistical evidence, once apprised of it, because it was not helpful to their case. The RSS report is available here. And by implication, the defence could have done better to bring it up. But he also thinks the defence was underfunded to be able to put up a proper defence. He has also been researching a lot of things about the case outside his area of expertise, though he admits that.

[IvanV]

I supect that the CPS will argue that none of the evidence in the case was "Statistical" because no numbers were presented to the jury and no statistician gave evidence. Instead the jury were simply invited to make their own judgements as to whether similarities and patterns observed in the events that unfolded were suspicious or just coincidental. To my mind those are statistical arguments, even if no numbers or statistical terms are used. The jury were effectively left to rely on their intuition. That's exactly what David Spiegelhalter (author of Ivan's quote) was warning against.

I wondered if that is why the professor is criticising the defence case also, for failing to bring out the point that intuition is very faulty in this situation.

In fact Professor Gill has blogged and he seems to be saying just that, among other things. He seems to be implying that the prosecution deliberately avoided the statistical evidence, once apprised of it, because it was not helpful to their case. The RSS report is available here. And by implication, the defence could have done better to bring it up. But he also thinks the defence was underfunded to be able to put up a proper defence. He has also been researching a lot of things about the case outside his area of expertise, though he admits that.

So I've had a look through this material stuff now. The RSS report only sets out principles and looks at past cases, it does not analyse the statistics in the Letby case, disappointingly. But I think they are clearly saying someone should have done it.

Gill, one of the statistics professors behind the RSS report, does not present any statistical analysis in his blog, he only points to the RSS report he contributed to. He reproduces strong criticisms of the medical evidence presented, which he brings from an external anonymous source, links available there. But we do have some statistics we can look at in links Gill provides, from one analyst. Gill points to link and another link. A bit disappointing that Gill said nothing about it beyond point to it. Maybe given his RSS involvement he feels constrained to do no more than that.

Obviously statistics like this can rarely if ever prove someone innocent. But they can show that there is nothing unusual here that it has to be something other than chance. And, it would seem, that is just what the statistics do say. And the statistics in these links are quite simple, an A-level student could reproduce them. Maybe they are too simple. We learn:

- The 7 deaths which are argued to be the Letby "cluster" would occur with probability 1/83, if we model them as a Poisson distribution, which seems suitable. So just the kind of thing that will occur quite often by chance from time to time and from place to place, given that time passes and there are many hospitals.

- The neonatal death rate at the hospital actually went up in the period immediately following Letby's removal from the ward.

- When eventually the death rate went down, that coincided with the hospital reducing its facilities and no longer taking on such risky cases.

In other words, from a statistical perspective, there really was nothing there you could identify as so unusual it had to be something other than chance. Talk of an unusual clusters of deaths here is, statistically, quite unwarranted, if we believe this analysts stats.