• baker
    2.9k
    Hold your horses.

    My proposal sets the bar high, so high that few mandatory impingements on bodily autonomy measure up.

    The right to bodily autonomy is much harder to consistently argue for than high standards.

    (For example, it would not be acceptable for a person infected with rabies to be allowed to do as they please; the bodily autonomy of such a person needs to be compromised for the wellbeing of others. Similar with smallpox, tuberculosis, and some other highly infectuous diseases with high death or complication rates.)
  • Benkei
    4.9k
    So it appears you have to accept that according to their nature these models aren’t to be relied on.AJJ

    Second comment that just underlines you don't know what stochastic models are and what you can and can't do with it. The model is fine and you can rely on the results. This one specifically just happens to have a large range of probabilities, making it difficult to base decisions on. That says nothing about the reliability of the model itself.
  • AJJ
    818


    “Me smart, you dumb.”

    We’ve established that your opinions are just that: opinions; not facts. Do you think people should be confined to their homes and coerced into receiving medical treatments on the basis of opinion? I don’t, you do. So we’ve reached our prejudices, and I find yours abhorrent.
  • Xtrix
    2.4k
    The discussion was about people refusing the vaccine out of fear of risks like stroke and death. Those risks are minuscule -- no matter how you slice the data. They remain so.
    — Xtrix

    Those minuscule risks don't simply translate into minuscule strokes or minuscule deaths.
    baker

    :lol:

    Because you brought up the fact that people are having strokes. So while you may not make this argument yourself (as I would assume, given you’re vaccinated), I assumed you were bringing it up to demonstrate how others may be reasoning about this. If that’s not true, I wonder why you brought it up at all?
    — Xtrix

    For one, because your position lacks empathy.
    baker

    Oh, so because I'm mean you feel it necessary to raise a stupid argument. Got it. Well done.

    Of course I'm scared.baker

    No kidding.

    And what do you have to offer to me as consolation? Luck?!!baker

    No, the probability of something happening to you, which is extremely low. The "consolation" you mention wasn't for you, anyway -- you asked for consolation for those who had strokes, to which I said I had no real consolation, other than that they made the right choice but were unlucky. I'm sorry you struggle with that.

    Also, what’s the consolation for the millions who have died of coronavirus?
    You need consolation for those people?
    baker

    And you need consolation for the 150 stroke victims?

    You're incredibly poor at argument.
  • jorndoe
    1.5k
    As far as I can see there's a potential cohort of 150 for whom the risk is 1.Isaac

    Nah, not 1 beforehand.
    Kids are an example of where an assessment has led to caution, hence ineligible (as of typing).
    Whatever factors continue to be assessed; not just for COVID-19.
  • Xtrix
    2.4k
    I'm talking about proper risk analysis, not whatever you just did. My claim is that it's not actually risk-based. What you call it, or think it is, is irrelevant.Isaac

    And whatever you think is "proper" or "actually" risk-based is irrelevant. There are many levels to assessing risk. Since you can always gather more information, by your definition nothing is risk-based.

    Maybe it goes slightly above or below overall numbers — but not by much. Why?

    Because 150 strokes out of 10 million people, for example, is astronomically low.
    — Xtrix

    Show me the maths then. What is it about 150/10,000,000 as a prevalence rate which makes it impossible for any cohort to have a high risk. As far as I can see there's a potential cohort of 150 for whom the risk is 1.
    Isaac

    Is this a joke?

    If it turns out that 90% of those 150 people were over 65, that’s important to know — no doubt (especially if you’re over 65). Does that significantly change the overall odds? As I mentioned before: no, it doesn’t. It simply means if you’re over 65, you have a slightly greater chance of having a stroke after taking the vaccine.
    — Xtrix

    That is changing the odds. It's literally what changing the odds is. You've taken one odds (the national prevalence), and you've changed them to get the risk for a 65 year old.
    Isaac

    Yes, I just said that...

    it doesn’t change the odds much at all — perhaps by 0.00001% or something to that effect.
    — Xtrix

    For some variables that may well be the case. For others we know it's much higher. Obesity, for example has an OR of over 13. Age above 65 even higher, making your estimate more than a thousand-fold out.
    Isaac

    No, it isn't higher. Because what I was discussing was strokes -- whatever your discussing, I can only guess.

    How do I support this claim? With mathematics — which can be checked by everyone.
    — Xtrix

    I've yet to see any mathematics, despite several requests.
    Isaac

    Let me try one more time: 150/10,000,000 = 0.000015%. That's some pretty easy mathematics. Let's say everyone in that group was over 65 -- what would someone's, age 65 years or older, odds be of getting a stroke in that case?
  • AJJ
    818
    Let me try one more time: 150/10,000,000 = 0.000015%. That's some pretty easy mathematics.Xtrix

    So easy you got it wrong.
  • Isaac
    5.5k
    Since you can always gather more information, by your definition nothing is risk-based.Xtrix

    Risk is determined by variables. Assessing the impact of those variables is a risk-based decision. Ignoring them is not. It's nothing to do with always being able to get more data, it's about what we do with the data we've already got.

    I was discussing was strokes -- whatever your discussing, I can only guess.Xtrix

    Why were you discussing only strokes? Did I imply the points I'm making applied only to strokes? I'm discussing the calculation of a variety of risks using known variables.

    Let me try one more time: 150/10,000,000 = 0.000015%. That's some pretty easy mathematics.Xtrix

    I'm asking how you get the risk from the prevalence. You've just divided the total cases by the total population of the sample. That gives the prevalence. I'm asking for the maths you're using to get from there to the risk.

    Let's say everyone in that group was over 65 -- what would someone's, age 65 years or older, odds be of getting a stroke in that case?Xtrix

    It would depend on their measures for any known variables affecting the likelihood of strokes - high blood pressure, atrial fibrillation, smoking, drinking too much alcohol, poor diet, a close relative who has had a stroke, high cholesterol, diabetes, being overweight, sickle cell disease, frequency of migraine with aura. All of these factors have ORs, you multiply the prevalence by the combined ORs for the person (combined dependant on co-variant factors). That's the risk. If we don't know the ORs, then failing to take them into account is irrelevant since they could be anything. If we know the ORs but ignore them, you're not basing your decision on risk anymore.

    it's being fed to us by the government. What is worse, we can not communicate with the government, the government does not discuss with us.baker

    Yeah, something that's been consistently muddled here is the representation of data, via policy, and the actual data itself. It's true that a layman may not always be in a position to assess raw data (althought it's not impossible), but to infer data from policy requires a whole slew of assumptions about the institutions doing the policymaking, and we can't ask about those, nor about the degree of certainty.

    If we imagine, hypothetically, a group of completely unbiased experts with no priors analysing the same corpus of evidence. If that corpus was 51% supportive of strategy x and 49% against, then every expert would support the strategy. Your poll of experts would come back with 100% support, but this is, obviously, a measure of the frequency of each binomial decision, not the frequency of different degrees of evidential support for it. If the corpus was 1% supportive of strategy x and 99% against, the poll of experts would come back exactly the same. In other words, the poll of experts clearly doesn't contain anywhere in it the data about certainty. For that you have to ask.
  • frank
    8.8k
    To avoid being fired for failure to get vaccinated, people claim religious exemptions. Lawyers will have to go through the exemptions and rule on them.
  • Benkei
    4.9k
    You're obviously not aware about my opinion on lockdowns and vaccines because your representation of it is wrong. I take issue with the falsehoods you proclaim in relation to lock downs and indeed submit my opinion is at least fact-based whereas yours is just "let me toss some articles out there that I agree with and not bother reading actual research intothe subject". That I'm smarter than you is obvious. You might consider that a reason to pay more attention to what I say.

    FYI, there's an important difference in saying people should get vaccines and mandating it and I think certain industries (healthcare, people working with the elderly) can be required to get a vaccine. You know, the type of vaccine mandates we've had for ages for various diseases. As to lock downs, I'm not in favour of stay at home orders but limiting movement (e.g. limiting traffic to and from hot spots) and prohibiting gatherings are definitely things I would support under circumstances where it's necessary to avoid an overload of the healthcare system.
  • AJJ
    818
    That I'm smarter than you is obvious.Benkei

    Very convincing.

    Coercion doesn’t require mandates.

    Limiting movement and prohibiting gatherings constitute a stay at home order.

    Your opinions are not facts. There are two prejudices in play: freedom in the face of uncertainty and confinement in the face of uncertainty. You have chosen the latter.
  • Apollodorus
    2.7k
    Make no mistake: I despise China, but I find less fault with China than with the Westeners who in their greed gobble up whatever China throws at them.baker

    I see your point. However, China has been an evil dictatorship from the day the Maoists seized power in 1949.

    So, I would say that China (i.e. the political system, not the Chinese people) is evil quite independently of the West.

    It may, of course, be argued that Marxism-Leninism was introduced into China from Russia and into Russia from the West, which would make the West the ultimate source of China's evil.

    And yes, it is Western corporations, governments, intergovernmental organizations like the World Bank, etc. in collaboration with Western manufacturers and consumers, that have facilitated China's rise to economic and military power.

    And precisely because the West bears a large share of culpability, it also has the responsibility to do something about it. Economic sanctions, for example, would definitely be a step in the right direction.

    As regards China leaking the virus, I don't think it would be entirely out of character. The regime clearly has global ambitions and a plan to realize those ambitions. It keeps the West under constant surveillance and it must have learned from past epidemics, their impact, and Western reactions to them.

    China's rulers are not like our politicians whose main concern in life is to win elections for a few years. They have long-term plans, the resources to implement them, and no opposition to stop them.

    BTW, research by the Lithuanian Defence Ministry's National Cyber Security Center has found that Chinese-made smart phones have in-built spying capabilities.

    https://www.techradar.com/uk/news/users-urged-to-throw-away-chinese-smartphones-over-spying-fears

    A few years ago, Krytpowire, a US mobile security firm, found that up to 700 million android devices had Chinese malware hidden as a preinstalled support app that had access to and sent information about users' text messages, contacts, calls, location, and other data to a server in Shanghai:

    The Chinese company that wrote the software, Shanghai Adups Technology Company, says its code runs on more than 700 million phones, cars and other smart devices. The episode shows how companies throughout the technology supply chain can compromise privacy, with or without the knowledge of manufacturers or customers. It also offers a look at one way that Chinese companies — and by extension the government — can monitor cellphone behavior. For many years, the Chinese government has used a variety of methods to filter and track internet use and monitor online conversations …

    Secret Back Door in Some U.S. Phones Sent Data to China, Analysts Say - New York Times

    I think China knows exactly what it is doing.
  • jorndoe
    1.5k
    , have you bothered checking historical (textbook) case studies?
    It's not like someone just came up with outbreak protocols last year.
    There's precedence, long history, subject matter experts have a large body of material, ...
    So, no, it's not just @Benkei-says-@AJJ-says. :roll:
  • AJJ
    818


    “But textbooks and history! Subject matter and experts! Durrrrr!”
  • Xtrix
    2.4k
    Since you can always gather more information, by your definition nothing is risk-based.
    — Xtrix

    Risk is determined by variables. Assessing the impact of those variables is a risk-based decision. Ignoring them is not. It's nothing to do with always being able to get more data, it's about what we do with the data we've already got.
    Isaac

    The data we've "got" can be filtered into many subsets and controlled for many variables indeed -- with nearly infinite variation. The choice of variables is up to the person assessing the data. In that case, there's always something ignored. If you're over 65, and want to see how the virus effects your age group -- you've chosen to leave out those under 65.

    So yes, what we "do" with the data we have is always going to be a matter a selection, which is a matter of choice, which is a matter of our interests. You can get close to your specific situation if you wish, but things will always be left out, and data will always be incomplete. It's still risk analysis. Likewise, if you don't care to narrow down the data, that's also a choice -- and also risk analysis.

    I'm asking how you get the risk from the prevalence. You've just divided the total cases by the total population of the sample. That gives the prevalence. I'm asking for the maths you're using to get from there to the risk.Isaac

    That is one measure of the risk. If you want to get more specific, as I've said before, you could analyze that 150 and control for sex, age, etc. That's also a measure of risk -- only more specific to whatever you want to control for. To say the latter is risk but the former isn't is an absurdity. Why? Because specificity isn't what determines risk analysis. What you were asking for is a number spefici to you -- and that's not possible. You'll never get it. Therefore, if that's all that qualifies as risk analysis, then risk analysis doesn't exist. If that isn't what you're saying, fine -- then where is the line where it goes from non-risk analysis to risk analysis?

    A 1 in 6 chance of dying from heart disease as an American shouldn't be included in risk analysis, according to you -- but knowing the fact that 82% of people who die of this are over 65 is risk analysis? At what point does the data on death from heart disease go from "prevalence" to "risk", exactly? As I said before, if you narrow the range it's still the prevelance -- just a more specific prevalence (like the prevalence of dying from heart disease for people over 65 and male versus overall prevalence).

    Let's say everyone in that group was over 65 -- what would someone's, age 65 years or older, odds be of getting a stroke in that case?
    — Xtrix

    It would depend on their measures for any known variables affecting the likelihood of strokes - high blood pressure, atrial fibrillation, smoking, drinking too much alcohol, poor diet, a close relative who has had a stroke, high cholesterol, diabetes, being overweight, sickle cell disease, frequency of migraine with aura. All of these factors have ORs, you multiply the prevalence by the combined ORs for the person (combined dependant on co-variant factors). That's the risk. If we don't know the ORs, then failing to take them into account is irrelevant since they could be anything. If we know the ORs but ignore them, you're not basing your decision on risk anymore.
    Isaac

    So you're only considering it risk if every possible variable is included in the assessment? If that's the case, that's impossible. You made a list of variables -- and I could come up with 100 more. We could come up with a 1000 more after that, and so on. But even if we exhausted the possibilities, which is an absurdity, you still won't have complete information -- as you mentioned. Thus, one could still say that you're only talking about prevalence -- just the prevalence of those with high cholesterol, diabetes, etc. A very specific group, no doubt -- but still just the prevalence within that narrowed group. I say, on the contrary, that you're talking about risk. I say that about overall prevalence as well. The difference is a matter of choice and how interested you are in restricting the data -- but you'll never get to an absolute number specific for you. You can come close, but you'll never get there, and there's nowhere along the line where we pass from non-risk to risk analysis. It's all risk analysis.

    If there's a 50% chance of dying from x, that's quite scary. If, upon looking at the data, you find out that 97% of the deaths occurred in white males, then that's a different feeling entirely. I concede that. If we argue only the latter is risk analysis, then what about the following piece of information: white males all aged 35 (and you happen to be 35)? Is now the second range of data now NOT risk analysis either? And on and on we go...
  • Xtrix
    2.4k


    True -- shouldn't have put the % sign.
  • Isaac
    5.5k
    At what point does the data on death from heart disease go from "prevalence" to "risk", exactly? As I said before, if you narrow the range it's still the prevelance -- just a more specific prevalence (like the prevalence of dying from heart disease for people over 65 and male versus overall prevalence).Xtrix

    The answer to your question is in the post. You even quoted it.

    If we don't know the ORs, then failing to take them into account is irrelevant since they could be anything. If we know the ORs but ignore them, you're not basing your decision on risk anymore.Isaac

    Clearly I should have explained. If I know all the factors determining the fall of a coin, then the chance of it landing on either heads or tails is 1, I know it will land on tails because I know the starting state and all the variables determining its trajectory (assuming determinism - we can get into quantum fluctuations, but the definition doesn't require we do). It would no longer make sense for me to say the odds of this coin landing on heads is 50%, I know it's going to land on tails. The prevalence of coins landing on heads is still 50/100, that hasn't changed, but the odds have changed.

    So the odds (chance/risk whatever term we use) are a measure of my uncertainty, whist the prevalence is a measure of the occurrence in a population.

    You asked where we stop adding variables. Never. We include all variables. So what if there's an unknown variable? Well if, say, the starting position {S} (heads/tails) may affect the fall of a coin, but it's not a variable whose affect I know, then the chances of S(heads) making the coin more likely to land on heads is 50/50 (I don't know). The chances of S(tails) making the coin more likely to land on heads is also 50/50 (I don't know that either). I we multiply those two ORs by the un-affected prevalence, we still get 50% (0.5*0.5 - S(heads) + 0.5*0.5 - S(tails)). So we haven't ignored this unknown variable, it's just that its as likely to affect the result one way as it is another so including it doesn't affect the risk. If, however, we had a variable whose affect we did know but we excluded it, we're not doing risk assessment any more because we're not measuring our uncertainty, we're just talking about the frequency of some event within a population (prevalence).
  • Benkei
    4.9k
    Limiting movement and prohibiting gatherings constitute a stay at home order.AJJ

    No, they obviously don't. It's getting downright moronic now. Is closing down air traffic a stay at home order? Oops.
  • AJJ
    818


    Err... right. I’ll just leave it with you.

    And remember: your opinions are not facts.
  • Xtrix
    2.4k
    And remember: your opinions are not facts.AJJ

    That’s your opinion. Also not a fact.
  • AJJ
    818


    Good one! Now try understanding the importance of that realisation (which you of course won’t).
  • Xtrix
    2.4k
    If I know all the factors determining the fall of a coinIsaac

    Yes, and if we knew all the factors of anything we could also make predictions. But that’s a fantasy. As I said before. If that’s what’s are restricting “risk analysis” to, then it doesn’t exist. What you’re talking about in that case is certainly.

    So the odds (chance/risk whatever term we use) are a measure of my uncertainty, whist the prevalence is a measure of the occurrence in a population.Isaac

    They’re both odds. What’s the difference between one and the other? Specificity. Will we ever get to all the factors and variables of one specific person? Of course not.

    So then it’s a matter of how much data we have and how much we’re interested in narrowing the range of that data.

    You asked where we stop adding variables. Never. We include all variables.Isaac

    No. You cannot include all variables because, as I mentioned before, there is a nearly infinite range of variables we can control for. So at what point does it become, in your mind, risk analysis? Never.

    Or put this way: what are “all” the variables? That’s like saying you’ve included all the numbers. Great — now add one.

    The odds of a white male over 65 dying of COVID is the prevalence of death among that group. What about the INDIVIDUAL white male over 65? You know, the guy named Bob who’s got red hair and saw Star Wars in the theaters— all known variables. What about him? What’s HIS specific odds?

    This entire line of argument is absurd. The odds of having a stroke from the COVID is roughly 150/10,000,000. That’s good enough for most of us — and it’s risk analysis.
  • 180 Proof
    6k
    (M)askless (A)merica's (G)ot (A)ntivaxx cunts ...
    getting killed by a "hoax", huh?

    fuck 'em. :victory: :mask:
  • Isaac
    5.5k
    If that’s what’s are restricting “risk analysis” to, then it doesn’t exist. What you’re talking about in that case is certainly.Xtrix

    Where do I say the knowing all the variables is what we're restricting risk analysis to. Read more carefully.

    They’re both odds.Xtrix

    No. Here's a primer on the differences. https://www.cdc.gov/csels/dsepd/ss1978/lesson3/section2.html

    No. You cannot include all variables because, as I mentioned before, there is a nearly infinite range of variables we can control for.Xtrix

    So? How does that affect the maths I provided? Each one of the infinite range of variables which we don't know about has an equal chance of increasing the risk as it does of decreasing the risk, so including them is a matter of multiplying each probability by the uncertainty (0.5*p + 0.5*p). I did write all this out in my reply, if you're not going to bother even reading it, there's no point in replying. We are including all the unknown variables in our measure of uncertainty (risk). What matters here is deliberately not including a known variable.

    You know, the guy named Bob who’s got red hair and saw Star Wars in the theaters— all known variables. What about him? What’s HIS specific odds?Xtrix

    I went through this in my last response. His specific odds can be calculated by multiplying the ORs for any known variables by the unadjusted OR for the control. All the unknown variables are taken account of because being unknown they are just as likely to increase his risk as they are to decrease it and so they make no difference. The known variables are not just as likely to increase his risk as decrease it (that's what being known means, we know the effect they have), so ignoring them effects the risk. Ignoring the unknown variables doesn't affect the risk because, being unknown, their effect is p(0.5) one way and p(0.5) the other, the inclusion of which leaves the original OR the same. To use your example of {red hair} the OR for having red hair is unknown so it's a Gaussian distribution around a mean OR of 1, the sum of all the possible ORs is 1, we include the variable because we multiply the unadjusted control OR by the OR for the variable (it just happens to be 1 so it makes no difference). If we exclude it instead, it makes no difference to the risk. If, however, we exclude a known variable (say BMI) we will affect the risk because the OR is not 1.

    If all you're going to do is bleat on about "we can't know all the variables" again, then don't bother replying, I've addressed that issue three times now and you've ignored it each time.
  • Xtrix
    2.4k

    They’re both odds.
    — Xtrix

    No. Here's a primer on the differences. https://www.cdc.gov/csels/dsepd/ss1978/lesson3/section2.html
    Isaac

    They’re both odds — namely your odds of getting a stroke or your odds of dying. That’s the risk — which you deny. Try reading that yourself— it’s an excellent primer indeed, and saying exactly what I’ve been saying the entire time. It also doesn’t once mention the “differences” you’re suggesting it does.

    No. You cannot include all variables because, as I mentioned before, there is a nearly infinite range of variables we can control for.
    — Xtrix

    So? How does that affect the maths I provided? Each one of the infinite range of variables which we don't know about has an equal chance of increasing the risk as it does of decreasing the risk, so including them is a matter of multiplying each probability by the uncertainty (0.5*p + 0.5*p). I did write all this out in my reply, if you're not going to bother even reading it, there's no point in replying. We are including all the unknown variables in our measure of uncertainty (risk). What matters here is deliberately not including a known variable.
    Isaac

    Yes, take your own advice and try “bother reading.” If you try it, you’ll not once find that I say “unknown variables.” There’s an infinite number of KNOWN variables as well —or at the very least in the hundreds of millions of combinations for an individual. Since we’ll never get them all for YOU, your definition of what constitutes “risk analysis” is, I repeat, absurd.

    The risk of dying of a heart attack in America is x. That number increases or decreases depending on many factors. That’s the general risk of the population of a country. If you’re American, that’s interesting.

    Your risk of dying of a heart attack as a male of 71 years old can be calculated too. That’s y. If you’re a 71 year old male, that’s interesting.

    X and y are both odds of dying of a heart attack. That’s risk — the same data, filtered in different ways depending on one’s interest.

    It’s really that simple— whatever else you want to go on about is your business, but it’s delusional at best.
  • Isaac
    5.5k
    it’s an excellent primer indeed, and saying exactly what I’ve been saying the entire timeXtrix

    Where does it say that the prevalence and the risk are the same? Provide the quote that you think supports your view.

    There’s an infinite number of KNOWN variables as well —or at the very least in the hundreds of millions of combinations for an individual.Xtrix

    OK, so for a stroke, say, give me the first twenty or so, a list with the ORs for each.

    X and y are both odds of dying of a heart attack.Xtrix

    You can't have two different odds of the same event.
  • Isaac
    5.5k


    Scrap my last response, I'm not interested. I've got a question I'm far more interested in, if you'll indulge me - What do you think is happening here? This conversation we're having. What do you imagine our roles are, what story have you put together that explains my posts in this educator/student story on statistical modelling? You've made clear what you imagine my politics and motives to be, but you've left out my education level, profession, age... I'm just intrigued as to how you're putting this all together.

    Normally, I'd infer all this from your responses, but with you I'm absolutely stuck on how you're putting all this together into a coherent narrative. I thought I'd try just asking for a change.

    Also, whilst I'm just asking, what's your role in this storyline? How do you see this ending, for example, what's the coup de grâce with which the hero slays the dragon here?
  • Xtrix
    2.4k
    Where does it say that the prevalence and the risk are the same? Provide the quote that you think supports your view.Isaac

    Incidence proportion -- which is nearly the same thing as prevalence, though not identical -- is stated as risk. This is what I was talking about. If we want to be precise. Here's the following from the source you apparently didn't read:

    Synonyms for incidence proportion

    Attack rate
    Risk
    Probability of developing disease
    Cumulative incidence

    Incidence proportion is the proportion of an initially disease-free population that develops disease, becomes injured, or dies during a specified (usually limited) period of time. Synonyms include attack rate, risk, probability of getting disease, and cumulative incidence. Incidence proportion is a proportion because the persons in the numerator, those who develop disease, are all included in the denominator (the entire population).

    Example A: In the study of diabetics, 100 of the 189 diabetic men died during the 13-year follow-up period. Calculate the risk of death for these men.
    Numerator = 100 deaths among the diabetic men
    Denominator = 189 diabetic men
    10n = 102 = 100

    Risk = (100 ⁄ 189) × 100 = 52.9%

    Notice the last line. Also recall my repeating the 150/10,000,000 as a measure of risk. This is saying exactly the same thing.

    There’s an infinite number of KNOWN variables as well —or at the very least in the hundreds of millions of combinations for an individual.
    — Xtrix

    OK, so for a stroke, say, give me the first twenty or so, a list with the ORs for each.
    Isaac

    No. The data is there -- look it up yourself.

    X and y are both odds of dying of a heart attack.
    — Xtrix

    You can't have two different odds of the same event.
    Isaac

    Of course you can. Winning the NBA Championship is an event. Lebron James' odds of doing so are much greater than mine, alas. Same event, different odds.

    Again, this is dependent on the observer, their own characteristics, and their interests. The odds of you dying of a heart attack, as an American, is (I believe) about 1/6 or so. That's a measure of risk, controlling only for nationality. If we narrow it down a little: what are your odds as an American male? Then those odds are changed.

    What are the odds of contracting ovarian cancer? That has a risk as well. In that case, however, it's important to note that your odds of contracting ovarian cancer are zero if you're male.

    I've got a question I'm far more interested in, if you'll indulge me - What do you think is happening here? This conversation we're having.Isaac

    What's happening is that you either have no idea what you're arguing about, or have been (deliberately or not) extremely poor in explaining what you're getting at. What is the ultimate thesis here? That you cannot measure the risk of COVID? That looking at the "prevalence" of a disease is unrelated to risk? I have no real idea, and if it's a technical point you're making it's entirely irrelevant.

    Remember how this started:

    If it's all about risk profiles, then help me make my choice. What are my numbers? [...]

    Because if you can't produce figures for my risk then my decision is not risk based is it?
    Isaac

    So I repeat what I did back then: if you want to narrow the data range, do so yourself -- it's out there. Or consult your doctor, who knows your family history, age, sex, ethnicity, etc -- variables that can give you a better (more specific) idea of your risk. Presuming he's up on the latest data.

    Others who simply look at the data and say "a lot of people have gotten the vaccine, and there have been very few cases of strokes or deaths -- good enough for me" are also making a calculation of risk. In the case of strokes, it's 150/10 million. Very low, very rare. Most don't care if all 150 are black, or old, or female, or Seinfeld fans. It doesn't matter much, because either way the risk is extremely low. That's the level of calculation going on for a lot of people who are even remotely worried about the vaccines -- others don't think about it at all, they just do it.

    If you can't agree with these points, you're missing the point.

    You've made clear what you imagine my politics and motives to be, but you've left out my education level, profession, age... I'm just intrigued as to how you're putting this all together.Isaac

    You've made your motives quite clear, so I don't have to guess. You said not long ago that discussing points of agreement is boring, and so you're attempting to either play Devil's advocate or identify some weaknesses in the logic or argumentation of those advocating vaccination. I think the way you've gone about it lacks clarity, is frequently disingenuous, and often shades into absurdity.

    I have no clue about your age, education level, or profession. You seem to want to portray yourself as a statistician of some kind. If you are one, however, I'd be shocked.

    Also, whilst I'm just asking, what's your role in this storyline? How do you see this ending, for example, what's the coup de grâce with which the hero slays the dragon here?Isaac

    For my part, I have a bad habit of arguing with people until they see my point, give up, the conversation reduces to pettiness/insults, in which case I usually withdraw -- or there's a resolution of some kind.

    In this case, either your case is truly ridiculous or I've misunderstood, in which case it's on you to explain yourself better. You've had multiple opportunities to do so, and have not succeeded. Rather than staying on point, you've repeatedly diverted the conversation from one thing to another, and even quoted something you apparently didn't read.

    And we stand where we are.
  • Isaac
    5.5k
    Notice the last line. Also recall my repeating the 150/10,000,000 as a measure of risk. This is saying exactly the same thing.Xtrix

    No, you've not given the incidence rate there.

    Winning the NBA Championship is an event. Lebron James' odds of doing so are much greater than mine, alas. Same event, different odds.Xtrix

    No. Someone winning the NBA and Lebron James winning the NBA are two different events, statistically.

    it's important to note that your odds of contracting ovarian cancer are zero if you're male.Xtrix

    Only important to note? So I should still take a few precautions against ovarian cancer because the overall prevalence is still relevant? Just a mere 'note' that my odds are actually zero because of a known variable?

    The data is there -- look it up yourself.Xtrix

    You're claiming that there are "hundreds of millions" of known variables affecting stroke risk and you think it doesn't even need justification. Still, if you insist...

    https://scholar.google.co.uk/scholar?hl=en&as_sdt=0%2C5&q=odds+ratio+factors+stroke+risk&btnG=

    I count five on the first two pages, the rest seem to repeat that broad set. There's only a few thousand results in total, maybe less than fifty key papers, when do they start getting into the first million known variables?

    What is the ultimate thesis here? That you cannot measure the risk of COVID? That looking at the "prevalence" of a disease is unrelated to risk? I have no real ideaXtrix

    Indeed. And yet vociferous disagreement nonetheless, against a position for which you have no idea what the argument is.


    Anyway, the more interesting matter. Thanks for answering. One last question, how have you arrived at your beliefs on the matter? Let's just take the statistical disagreement about what constitutes risk. You're very sure of your position, you don't cite any external sources so where does your knowledge on the matter come from?
bold
italic
underline
strike
code
quote
ulist
image
url
mention
reveal
youtube
tweet
Add a Comment