What an AI makes of Defra's ragwort Code of Practice. It is scathing!

AI has its issues and it can raise concern such as is it putting people out of work, However it can prove a powerful tool in evaluating evidence and finding bits of research that might be difficult to find. I often think of it as "Alien Intelligence," as it is much different to human intelligence.

What I have done here is ask three questions. The first one is a real quote from DEFRA's guidance on ragwort control and it is the absolutely key factor in how they establish and promote the amount and rate of ragwort poisoning. The "he" in the quote is Professor Derek Knottenbelt who has also been quoted rather ridiculously as claiming that ragwort is poisoning the Cinnabar moth, which I hasten to say is NOT the main reason that ragwort is an ecologically valuable wildflower.

Here I have used ChatGPT as an independent evaluator of the policy. At first it points out the strength and weaknesses of DEFRA's statements. Then, when it is supplied the actual data obtained from Freedom of Information requests it points out it is completely wrong to use the data and when I tell it that the sentence is from government advice then it  becomes really scathing about the bad science. I quote the responses entirely as a cut and paste from the output of this clever computer program. I have only labelled the questions for clarity

Question 1

What can you tell me about the logic and reasoning in the following statement? "He has estimated a figure of 500 horse deaths from ragwort poisoning in 2000. This figure is based on the number of confirmed horse deaths from ragwort poisoning seen by the Philip Leverhulme Large Animal Hospital Teaching Hospital at Liverpool University as a percentage of all the horse cases treated during the ear, and grossed up to be representative of the total horse population."

ChatGPT said:

The statement presents an estimate of horse deaths from ragwort poisoning using inductive reasoning based on extrapolation. Here's a breakdown of the logic and reasoning behind it, including both its strengths and potential flaws:

---

🔍 Summary of the Logic

1. Observed Data Source:

   • A specific number of confirmed horse deaths from ragwort poisoning were observed at a single veterinary hospital (Liverpool University's Philip Leverhulme Large Animal Teaching Hospital).

2. Proportional Estimation:

   • This number is taken as a proportion of total horse cases treated at that hospital during 2000.

3. Extrapolation:

   • The proportion is then "grossed up" (i.e., scaled) to estimate the number of deaths across the entire horse population in the UK (or another broader context).

---

✅ Logical Strengths

• Use of empirical data: The estimate is grounded in actual confirmed cases, not speculation.

• Methodical scaling: Applying a proportion to a larger population is a common statistical technique when comprehensive data isn't available.

---

❌ Logical Weaknesses and Concerns

1. Sampling Bias:

   • The Liverpool hospital's cases may not be representative of the whole UK horse population.

   • Horses seen at a teaching hospital could have more severe or unusual conditions, potentially overestimating rare events like ragwort poisoning.

2. Confirmation Bias:

   • Only confirmed cases were counted. Ragwort poisoning is difficult to diagnose definitively, so the actual number of cases may be underreported, or misdiagnosed, affecting reliability.

3. Assumption of Uniformity:

   • It assumes the same rate of ragwort poisoning applies uniformly across all horse populations in different regions, which is unlikely (as environmental exposure varies).

4. Small Sample Size Risk:

   • If the number of observed cases was small, the resulting estimate could have high variance and large margins of error when extrapolated.

---

🧠 Type of Reasoning

• Inductive Reasoning: Drawing general conclusions (nationwide deaths) from specific observations (hospital cases).

• Statistical Estimation: Involves proportional scaling and population inference.

---

🧮 Example Analogy

Imagine seeing 2 red cars in a dealership that sells 10 cars and concluding that 20% of all cars in the country are red, then scaling that to millions of cars. That only works if your sample (the dealership) is representative — otherwise, your extrapolation may be way off.

---

📌 Conclusion

The reasoning shows a structured attempt to estimate a figure from limited data, but it relies heavily on the representativeness of a single data source, which is a major potential flaw. It's a reasonable starting point, but not robust enough to be definitive without additional, more representative data.

Question 2

You said:

What can you tell me if I say that a Freedom of Information request to the hospital actually shows only one case in an eight year period?

ChatGPT said:

If a Freedom of Information (FOI) request to the hospital reveals only one case of ragwort poisoning in an eight-year period, it severely undermines the credibility and validity of the original estimate of 500 horse deaths in a single year. Here's a detailed analysis of what that implies:

---

🔍 What This New Information Reveals

1. Factual Discrepancy:

   • The original estimate was supposedly based on a meaningful number of confirmed deaths at that hospital in 2000.

   • But if only one case occurred over eight years, then the hospital could not possibly have had a significant enough sample in 2000 to justify such extrapolation.

2. Invalid Assumptions:

   • The method described (taking the hospital’s confirmed ragwort deaths as a proportion and scaling up) relies on false or exaggerated input data.

   • This suggests that either:

     • The original estimator misunderstood or misrepresented the hospital data.

     • Or the methodology was used in bad faith (deliberately misleading).

---

❌ Logical and Ethical Consequences

• Flawed Reasoning:

  • The extrapolation logic collapses entirely if the base figure is incorrect or negligible.

• Inflated Estimate:

  • The claim of 500 deaths is now shown to be not just imprecise but likely unfounded.

• Potential Misinformation:

  • Such a statement, if made in a policy or advocacy context, could be highly misleading, leading to poor regulation or misplaced public concern.

---

🧠 Implications for Critical Thinking

• Always check primary sources: This is a clear example of why it’s essential to verify claims, especially when they're used to support large-scale generalizations.

• Be skeptical of gross-ups: Scaling from small or non-representative data to national figures must be done with rigorous checks, transparency, and peer review.

• Use FOI data carefully: FOI responses, being from authoritative sources, are strong evidence — and in this case, they directly contradict the original narrative.

---

🧾 Summary Judgment

The FOI response strongly suggests the original estimate of 500 deaths due to ragwort poisoning in 2000 is invalid. It exposes either a methodological failure or a misrepresentation of data, making the figure deeply unreliable and potentially misleading.

If you're investigating this further or challenging a claim, this FOI result is a powerful rebuttal.

Question 3

You said:

What can you tell me if I say that the original quote comes directly from government advice?

ChatGPT said:

If the original quote estimating 500 horse deaths from ragwort poisoning in 2000 comes directly from government advice, yet a Freedom of Information request shows only one case at the referenced hospital over eight years, then this raises serious concerns on multiple levels:

---

⚖️ Implications of a Government-Originated Estimate

1. Government Credibility at Stake:

   • Government-issued advice is expected to be evidence-based, transparent, and reliable.

   • If it includes a wildly inflated estimate based on non-existent or misused data, it damages public trust in that institution and its policies.

2. Policy and Regulation Impact:

   • This estimate likely influenced ragwort control legislation, land management obligations, or public guidance to landowners.

   • Policies based on false or unsupported figures may be disproportionate, costly, or even unjustified.

3. Misuse of Authority:

   • Using an authoritative tone (e.g., citing a university hospital) to support a claim that is not factually accurate borders on misinformation, whether intentional or negligent.

---

🧠 Analytical Breakdown

Let’s connect the pieces:

• Claim: 500 deaths based on extrapolated data from Liverpool University's animal hospital.

• Reality (via FOI): Only one case in eight years—not even one per year.

• Logical consequence: The core data point used to justify the extrapolation never existed.

This suggests one of the following:

• The estimation method was fabricated or misunderstood.

• The government relied on poorly vetted secondary sources.

• There was a deliberate inflation to justify a policy objective.

---

🧾 Accountability Questions

This scenario invites tough questions for policymakers:

• Who created this estimate?

• Was the source peer-reviewed or independently verified?

• Why was the estimate not updated or withdrawn when more accurate data became available?

• How was the FOI data reconciled with the original policy narrative?

---

💡 Broader Takeaway

This is a textbook example of why transparency, evidence verification, and skepticism are essential in interpreting government guidance — especially when it leads to regulation. It shows how bad data, once institutionalized, can cascade into widespread misinformation and skew public perception for years.

---

✅ Conclusion

If a government document made this claim, yet the cited data source (the hospital) reports only one case in eight years, then the claim is:

• Demonstrably false or grossly exaggerated,

• Potentially misleading, and

• In need of correction or retraction.

It may justify a formal challenge or review of the guidance that relied on it.

Dr David Marlin's Ragwort Mistakes.

 

Once again I find myself expressing my honest opinions and debunking some misleading anti-ragwort propaganda. One of the problems is that there is a bubble in the equine community. Incorrect facts circulate inside this bubble and are considered correct because they have been repeated so often.

I don’t suffer from this. It was abundantly obvious that misinformation was being circulated even before I started my researches over two decades ago. I get my information from the scientific literature. As regular readers will know I have been studying the science on this for more than two decades.

Today I am debunking an article posted on Facebook by one David Marlin. He is attacking another posting made by someone else elsewhere on Facebook. I'm going through it line by line.

He starts by quoting this other article and criticising things that he thinks are wrong but where the evidence tells us something different.

Dr David Marlin

RAGWORT POISONING IN HORSES 

Lots of "misinformation" about RAGWORT.

This is unquestionably true. There is so much misinformation that there are entire blogs and websites devoted to documenting just some of it as I will show here today.

RAGWORT has been "wrongly labelled as a weed"

It is quite normal and usual for people who study wildflowers not to like them being called weeds.

People who say RAGWORT is a problem for horses are "Scaremongering".

There is no question at all that scaremongering exists. I’ll show examples in this posting!

There's apparently a lot of "Fake News" being spread about RAGWORT and horses.

Unquestionably this is true. This blog is all about it!

RAGWORT is apparently "Not a threat to horses".

This is a small quote taken out of context

An "average horse" would have to ingest over "50kg of RAGWORT" apparently for it to be "Toxic".

Now this is where the bubble comes in. Let's look at this one. Is it reasonable to say this? There will be many horse people who will say that it is nonsense of course, but actually it is not!

One of the first things to determine is how toxic the plant is, and I think it's fair to assume that what the author of the video meant is that it takes 50kg to kill a horse.

We can do this and we can go to the scientific literature. Well, there is an article in the American Journal of Veterinary Research, written by well-known ragwort toxicology experts and we find this statement

"Horses, cattle and rats are susceptible to toxicity (chronic tansy ragwort lethal dose is 5% to 25% of body weight.)"

Incidentally, tansy ragwort is just the American name for our ragwort.

A quick google, which we can assume the author of the video did gives an average horse weight of 700kg to 1000kg. For the lower figure, 5% of body weight is 35 kg and 25% is 175 kg, and the figures for the upper figure are 50 kg and 250 kg. The published research shows that this is correct!

"...We are wrong to remove them [RAGWORT]".

It is a common place opinion for conservationists not to like people removing wildflowers.

These are all pearls of wisdom from some nameless "expert" from a page called WILDLIFE CONSERVATION IN THANET!

Not sure how owners who have lost horses to ragwort poisoning will feel about his comments.

It is at this point that it becomes clear that he doesn’t properly understand the issue. I’ll explain it below but how would they possibly know that they have lost horses to ragwort poisoning! People inside the bubble might believe it is easy to tell but as I will explain below it really isn’t.

SOME RAGWORT FACTS......

Of 865 liver samples received by pathology services over a 5 year period, 72 (8.3%) were found to have evidence of megalocytosis; an indicator of ragwort poisoning. This actually translates to 57 samples a year.

Hang on a minute! The maths is wrong here! 72 divided by five is 14.4 not 57!

The really crucial thing here is that megalocytosis does occur in ragwort poisoning, often known technically as Pyrrolizidine Alkaloid Toxicosis after the toxins in ragwort. BUT the important fact is that it has other causes too. Most significantly mycotoxins, toxins produced by often invisible moulds in feed.

In fact the most recent research by Professor Andy Durham in a paper on these mycotoxins in horses says,

“Liver disease is commonly encountered in equine practice both as clinical and subclinical disease. Outbreaks of hepatic disease are common and once often were suspected to be caused by pyrrolizidine alkaloid (PA) toxicosis,although more recent evidence suggests that PA toxicity is far less common than generally suspected”

REMEMBER - this is going to be a gross underestimation of the number of cases as the majority are unlikely to have samples submitted for diagnosis. Some cases will be treated, some will die, some will be euthanised without a diagnosis.

This is obviously bad thinking since we know there is no way of identifying cases with certainty.

Then there is more bad information.

In 2014 a BEVA survey reported that of 303 vets, 41% had seen at least one suspected case of ragwort poisoning in the past year. Each vet was seeing at least 2 cases per year. 49% died or were euthanised.

It is first necessary to establish what a suspected case can be. The British Horse Society actually published a case in their newsletter where they described a vet turning up to a case and pronouncing on the spot that it was ragwort poisoning without further tests at all.

An equine charity responded to me with a four letter insults on-line insisting they knew of cases based on blood tests. As an expert I can tell you these only tell you there is liver damage which has a multiplicity of causes but they had evidently, it seems, been informed by their vet that blood tests were enough.

More bad information again.

In a survey by the BHS & DEFRA in 2014, 19% of respondents knew of a horse that was susepcted[sic] to have been poisoned by ragwort, with a defintive[sic] diagnosis in 21% of those cases. It was reported that 39% died or were euthanised.

First of all let’s deal with the issue again of a claimed definitive diagnosis. As I have said the evidence is very very clear you cannot have a definitive diagnosis.

It is this bubble again. I have checked and checked. There are scientific papers going back years, one of them in the highly respected journal Nature says that poisoning by fungal toxins is “indistinguishable from ragwort.”

Secondly this survey was RIGGED. First of all there were leading questions telling people ragwort was appallingly dreadful at the beginning but worse than that there was an article in the BHS newsletter instructing people to fill in the survey AND IT GAVE THEM A CASE that they could use to justify the reply that they had heard of to use. This was the case with a vet turning up and pronouncing a diagnosis without tests which I wrote about above.

In any case knowing of a horse that had ragwort poisoning is a very poor question without proper qualification of how they knew. Was it this year or 50 years ago?

Even a few mouthfulls [sic] of ragwort will cause some degree of IRREVERSIBLE liver damage. The more that is eaten, the more the damage. Damage accumulates over time! Moore RE, Knottenbelt D, Matthews JB, Beynon RJ, Whitfield PD. Biomarkers for ragwort poisoning in horses: identification of protein targets. BMC Vet Res. 2008 Aug 8;4:30.

Regular readers will notice the name Knottenbelt. Yes this is the man who claimed it is poisoning the cinnabar moth and who claimed it was a serious problem in South Africa, where the plant has never been recorded.

This is a common claim but as I explained above the literature tells us that small doses have no effect.

As little ragwort as 1% of bodyweight can prove fatal over time - Fu, P. P., Q. Xia, G. Lin & M. W. Chou. 2004. Pyrrolizidine alkaloids - Genotoxicity, metabolism enzymes, metabolic activation, and mechanisms. Drug Metabolism Reviews 36: 1-55.

Just look at this reference! As soon as I saw it I was on the alert. I am very familiar with this paper. It DOES NOT SAY THAT! It is not about that kind of thing at all. What is going on here? Is this just carelessness or is it a deliberate attempt to mislead? In my honest opinion if someone wanted to bamboozle people with bad science this is exactly the sort of paper that would be used it is 55 pages long and full of degree level biochemistry.  In fact it is worse than that I took a random sample of text and put it through something that calculates a measure of readability called the Gunning Fog  Index where Fog stands for Frequency Of Gobbledegook. An index of 17 requires you to have a university degree but this actually came out at 19.5! Most people wouldn’t have a clue about what it says. The word “ragwort” does not even appear in this scientific paper!

On the basis of what I have read in over 2 decades of detailed study of what is known from the scientific literature, claiming that 1% of body weight  being fatal is I something I can honestly describe as scaremongering.

The risk from ragwort poisoning is not simply from plants grazed in paddocks but from ragwort contamination of feedstuffs such as hay or haylage.

The ONLY problems are in preserved forage or where pasture is so bad that they are starved into eating the plant.

Contrary to the video, pyrrolizidine alkaloids (the toxic compounds in ragwort and other plants), are absorbed through the skin. The absorption is low, not non-existent. If you handle ragwort frequently without gloves you will develop liver damage.

Where is the evidence? First of all he overestimates the toxicity of the plant and now he is making statements of something definitely happening when there is actually no case of people being poisoned in this way in the scientific literature.

The issue here is the bubble again, believing in things in general circulation amongst horsey people rather than looking properly at the scientific literature.

If small amounts are absorbed they are not necessarily toxic in their absorbed form. They would then have to be converted into that toxic form, the first step of this usually takes place in the gut so it wouldn’t necessarily happen happen but if it did they then have to go through another step and there are several things than can happen. They can just be broken down. They can be detoxified by reacting harmlessly with other substances, which includes the one that detoxifies paracetamol. If tiny amounts arrive at the DNA molecules where harm can happen then there is a DNA repair mechanism.

There are several published scientific papers showing that animals fed only small amounts of a plant with the same toxins as ragwort had no damage to their livers!

So ragwort posoning [sic]does occur in horses. It is realtively [sic] rare, but this likely due to its removal from many areas horses and ponies graze.

"However, a justification or recommendation for relaxation in ragwort control would be a risky strategy as it is possible that the

apparently low prevalence of ragwort toxicity in horses might be as a result of generally effective pasture management that, if relaxed,

might lead to an increase in toxicity cases." Andy Durham, BSc, BVSc, CertEP, DEIM, DipECEIM, MRCVS, Liphook Equine Hospital, Veterinary Record, June 13, 2015.

 Notice the use of authority to make a point all those letters after his name are used to give an air of authority. It is a big no no in science. The question to really ask is if this author is really aware of all of the falsehoods, including those in the posting I am criticising. My honest belief is that the posting I am quoting is a particularly egregious example of the common place habit of equine activists of carelessly acting in a manner that at the very best is grossly overstating the problem.

 Postscript - “If you own horses, ponies or livestock you must not allow them to graze on land where you know ragwort is present” https://www.gov.uk/.../stop-ragwort-and-other-harmful…

This is another  example of argument from authority a no no in scientific thinking. Regular readers will know that Defra is a lousy source of information. They once told people our native ragwort was on a list of dangerous foreign invaders. It is obvious to me as an expert that they are not experts.

"Pyrrolizidine alkaloids (PAs) constitute a class of plant toxin associated with disease in humans and animals. They are found in a wide variety of plant species in the world and it is estimated that ∼3% of the world's flowering plants contain toxic pyrrolizidine alkaloids. The toxin is present in more than 12 higher plant families, among which three families, Compositae (Asteracea), Boraginaceae, and Leguminosae (Fabaceae), contain most toxic PAs." RAGWORT belongs to the family Compositae (Asteracea). Ibanez, G. (2005) Encyclopedia of Toxicology (Second Edition) https://www.sciencedirect.com/.../encyclopedia-of-toxicology

So, MR WILDLIFE CONSERVATION IN THANET..…

So what! It isn’t an issue that they are toxic we all know that. However toxic doesn’t necessarily mean dangerous and as I have pointed out repeatedly he gets his facts wrong.

1) Please get your facts right

2) Horse owners aren't looking to pull up every single ragwort plant in existence. Only the ones in the fields where our horses and ponies graze.

This simply isn’t the case. The British Horse Society tried to legislate for control on public lands and Professor Derek Knottenbelt has been quoted repeatedly in the press saying, "It is toxic to humans, so what the hell are we doing with it in this country?"

And frankly, if we do want to remove them, that is absolutly[sic] none of your business!

Actually we have a biodiversity crisis, that with climate breakdown threatens everyone’s future. Ragwort hysteria actually effects many of the nature sites in Britain. Unless you are some kind of weird anarchist you have to expect that we have rules to live by and that conservationists will work to conserve nature. It is really unacceptable to have equine activists inventing nonsense to scare people and I really really do have good evidence of this happening.

Vets repeat result of crooked ragwort survey.

Today I am giving my honest opinions on a page on ragwort by the Sussex Equine Hospital. I need this to post for two different comments I have seen on line. One is putting this page forth as a good example of information, which it clearly isn't and another asking about British Horse Society surveys, which are appallingly bad. 

 The page is an example how even vets get things wrong. It is likely that in this case it is largely inadvertent and that some of it is ignorance which is common even in equine vets and that largely the problem lies with the British Horse Society.

The article starts with a set of poor claims:-

Ragwort (also known as Senecio Jacobaea) toxicity is one of the most common causes of poisoning to horses in the UK. A recent survey by the British Horse Society showed that 20% of respondents knew of a horse that had been affected.

Firstly, no one can know properly that a horse can have ragwort poisoning without additional evidence other than  just symptoms. This is because other substances can cause the same damage at an atomic level.  So you cannot say how common it is! It is in some of the modern textbooks and has been known about since 1961 but many vets don't know this. You see this mistake all the time and I have had to correct them in the past. Just to explain why I am so certain about it. A colleague attended a ragwort meeting where a veterinary professor was talking  and got the information about aflatoxicosis ( A kind of mould poisoning) causing identical symptoms from him. There is also this quote from a recent paper by  the Animal and Plant Health Agency (APHA) in the Veterinary Journal about a rare case of pigs and ragwort.

"Acute aflatoxicosis could cause similar pathology but the clear access to ragwort plants and the knowledge that pigs on other units on the same commercial pig diet were healthy, pointed away from this potential cause."

We know there is no reliable test for ragwort poisoning. In this case it was obvious with the pigs, but in the overwhelming number of horse cases it isn't.

The second point that a survey by the British Horse Society said that 20% of respondents knew of a case. Of course the first point applies and they couldn't have known of a case but we need also to look at the survey.

The bent survey is a speciality of the British Horse Society. They are well known for running them and for repeating them. First of all there is the British Equine Veterinary Association survey which they publicised widely. As I have previously written, I attended a ragwort symposium in the Netherlands last year and their survey methods had a room full of top ragwort scientists hooting and moaning in derision.

First they designed a poor survey they didn't check how diagnoses were achieved properly. They didn't check for duplicate cases where more than 1 vet was involved etc.. As I've said there is no definitive test so how could they know.? They got a tiny number of responses just 4% and then outrageously multiplied the figures they got as if everyone had answered! 

Those figures were as bent as a butcher's hook and yet the BHS publicised them. Worse people selling ragwort controls used them, illegally, in their advertising. I took these to the Advertising Standards Authority and got them taken down.

Now we come to the survey in question and wait for it this is a real corker! First of all they put an article in their newsletter, with a highly emotive article about how terrible ragwort was see the excerpt below.  NOTE they provided an example of supposed ragwort poisoning. Actually they claimed a vet turned up and proclaimed it was ragwort poisoning on the spot. This may well have happened but is not what a vet should do to establish poisoning. 

This is the excerpt I mention above.

"Our Welfare Department recently heard a harrowing story of Ragwort poisoning from Ruth Anderson, who kept her horse in a yard on the south coast...... One morning she found her horse, covered in mud, and looking as if she had sweated up during the night. It appeared she may have had colic or had been charging round like a mad thing (spooked over something). so we kept an eye on her," said Ruth. "Then she wouldn't eat her dinner, she had a 'mad twitch' and was pitching her head to one side. "

This of course biased the survey. It is well established that these sorts of things bias surveys and rig the results. You can read more details of the article here https://www.ragwortfacts.com/british-horse-march-april-2015.html

( You can also read about yet another survey where they had used people seeing horses near ragwort in a previous well publicised survey, which isn't necessarily a problem. It didn't stop them using it as a scare story in the press.)

The survey then started with a false and leading question asking if people knew that ragwort was "extremely poisonous" to horses. This in scientific terms isn't true. Extremely poisonous substances are thousands of times more toxic than ragwort! Of course this biased the survey yet again.

Then and this is the real corker! They asked people if they had ever heard of  a case, after providing an example for them to know about in the newsletter article asking them to fill in the survey!

Of course all of these factors, biasing the survey and the impossibility of really knowing ragwort caused all the cases rendered the survey figures useless, but it didn't stop them from publicising this figure which the vets have repeated.

Then there is this comment which you see all the time but, honestly, if you look at the evidence , it isn't true,

"The effect is cumulative and symptoms may not be seen for up to a year after exposure."

First of all the biochemistry shows that the damage only occurs and therefore is only cumulative if a threshold is exceeded. The toxins can be destroyed or inactivated and there are repair mechanisms. Secondly there are TWO scientific papers describing experimental poisoning experiments where, as expected, small doses have no effect. 

Then again inaccuracies.

"The poison effects 3 main body systems - the liver, the central nervous system (brain, spine and its associated nerves) and the skin."

The alkaloids in ragwort affect the liver  and the other symptoms are caused by liver failure which stops the liver breaking down toxic substances that build up naturally in the body.

Then this old chestnut of a falsehood which regular readers will recognise!

" However, the Weeds Act 1959 made ragwort control a legal obligation for owners and occupiers of grazing land. "

This is of course utter nonsense. The law says no such thing. You may be ordered to control ragwort, but in the absence of a rare order there is no obligation to do anything. Maybe the vets got this off the British Horse Society too.

Finally, I'll post a piece of TV comedy as I have before. It is from the comedy Yes Prime Minister where Sir Humphrey Appleby explains how to rig an opinion survey in an exactly similar way to that which the British Horse Society does, by asking leading questions.