Page 6 of 11 FirstFirst ... 2 3 4 5 6 7 8 9 10 ... LastLast
Results 101 to 120 of 211
  1. #101
    Registered User
    Join Date
    07-21-2005
    Location
    Garner, NC
    Age
    54
    Posts
    570
    Images
    279

    Default

    Quote Originally Posted by illabelle View Post
    I'm not a statistician, though I do have a degree in Math Education (high school algebra and geometry). I haven't tried to understand all the points made above. I just wanted to point out what I think might be a hole in the considerations:

    Where are the criminals? Given that nearly all hikers I've met (day, section, or thru) appear to be decent law-abiding people, there would appear to be very few individuals on the trail who have murderous inclinations. Criminals tend to stay in cities. Yes, I know small towns have criminals also. If the people who wish to kill aren't on the trail [very much], what difference does it make how many miles, or hiker-hours, or person-years, or whether I sleep at home or on the trail? If the bad people aren't there, I'm safe from bad people.

    So shouldn't the calculations take into account the distribution of bad people among the population?
    I agree that most people I see on the trail are decent. However, I don't see why we would need to consider the distribution of bad people when we know incontrovertibly that people have been murdered while hiking.

    If we look at shark attacks along US coast, I find a website that says there have been 30 so far this year. This could be 1 million nice sharks and 30 bad sharks along our coasts. It could be 1 single bad shark that really gets around. It is absolutely unnecessary to know how many actual sharks are involved, we can measure the rate at which attacks are happening use that information to predict future year's attacks.

  2. #102
    Registered User
    Join Date
    07-21-2005
    Location
    Garner, NC
    Age
    54
    Posts
    570
    Images
    279

    Default

    Quote Originally Posted by Puddlefish View Post
    I'm retired, no one's paying me to spend the time to gather the data properly and to look for patterns. Like you said, in another post. You're doing word problems, at an 8th grade level maybe (probably even lower, the kids are learning a lot more math at earlier grades these days.)

    Your person hours idea isn't a terrible way of looking at it. But, you have to start at the beginning and decide if the initial question even makes sense. No one starts a hike with 100% certainty that they'll be a successful thru-hiker. There are questions on what makes a specific hiker more, or less vulnerable, there are questions on the motive of the murderers, there need to be control groups, the sample size of murders is tiny!, and that creates it's own problems with statistical significance.

    My initial point is correct however, as there are already quite a few people tossing out variants of the 7 out of 100,000 number as of it's gospel. It isn't.

    How to correct this number and this conclusion. I can't even explain everything wrong with it without hours of effort. At a minimum you'd have to take a solid college statistics course or two to even understand what's involved. Here's a link to just a basic structure of how to conduct a study.

    http://gchang.people.ysu.edu/class/pstudy.htm

    If I were world emperor, every High School would require a statistics course, a formal logic course and a debating course.

    Edit: My posts sometimes come across as know it all, so I'll just state that there's a hell of a lot I don't have a clue about. Bad statistics just happens to be a peeve of mine.
    Obviously all calculations start with some known numbers and some estimations (e.g. how long on the trail does each thru-hiker spend). Everyone familiar with the trail can join in and debate the estimated numbers. I contend my methodology has been reasonable. And FWIW, I have some college level statistics. Although I wasn't a math major, in the classes I did take in college that had math majors, I generally fared well in comparison with the math majors even for senior level course.

    And let's not forget. What is thrown around more often is the assertion that "the trail is totally safe, a lot more safe than civilization". Whether or not my methodology is open to weaknesses that I've overlooked, it is A LOT more solid than the assertions that the trail is safer than civilization.

    When Baltimore calculates it's murder rate, it does not have control groups and it doesn't consider the motivation of murders. Those are questions others can ask, but they are not necessary to calculate a murder rate. There are some towns that have very few murders. They can still calculate their murder rate for any given year. Whether it is useful for predicting future years can be up for debate, but the rate is the rate. If a town of 50,000 has 1 murder, it's murder rate is 0.5 per 100,000.

    You say: But, you have to start at the beginning and decide if the initial question even makes sense. No one starts a hike with 100% certainty that they'll be a successful thru-hiker.

    My question is "How does the risk of a thru-hiker, when adjusted for time compare to the murder rate of big cities?" Possibly some may not care about the answer, but the question is a valid question and I don't see how it needs to "make sense" anymore than it already does. And whether one will successfully thru-hike has been addressed already by estimating how many months "thru-hikers" including successful and not successful average for their hike. Virtually anyone can answer this question while hiking... "If I were murdered today, would the news say 'thru-hiker killed' or would it say 'section-hiker killed'?" If the former, you are a thru-hiker. If the later, you are not.

    To get a rough estimate of how life on the trail (for thru-hikers) compares to life in the city in terms of risk of homicide, I say takes a few minutes, especially when given the ATC estimate of about 20,000 completed thru-hikes. Whatever you're doing that would take hours I do not think will help produce a substantially more accurate estimate especially since we are already limited to a very small sample of actual homicides anyway.

  3. #103
    Registered User
    Join Date
    02-01-2016
    Location
    Chattanooga, Tennessee
    Posts
    813

    Default

    Quote Originally Posted by Puddlefish View Post
    Your person hours idea isn't a terrible way of looking at it.

    Not terrible? Jeez, that doesn't even rise to the level of damning with faint praise.

    Not all statisticians have studied actuarial science. I'm an actuary. For incidence rates you need a good measure of exposure to the risk that is of interest. The word "exposure" isn't even brought up on the page you link, though of course it's full of other useful concepts.

    "8th grade level maybe"? "Probably even lower"? Watch your balance ... that horse you're on is awfully high.

  4. #104

    Default

    Quote Originally Posted by FlyPaper View Post
    Obviously all calculations start with some known numbers and some estimations (e.g. how long on the trail does each thru-hiker spend). Everyone familiar with the trail can join in and debate the estimated numbers. I contend my methodology has been reasonable. And FWIW, I have some college level statistics. Although I wasn't a math major, in the classes I did take in college that had math majors, I generally fared well in comparison with the math majors even for senior level course.

    And let's not forget. What is thrown around more often is the assertion that "the trail is totally safe, a lot more safe than civilization". Whether or not my methodology is open to weaknesses that I've overlooked, it is A LOT more solid than the assertions that the trail is safer than civilization.

    When Baltimore calculates it's murder rate, it does not have control groups and it doesn't consider the motivation of murders. Those are questions others can ask, but they are not necessary to calculate a murder rate. There are some towns that have very few murders. They can still calculate their murder rate for any given year. Whether it is useful for predicting future years can be up for debate, but the rate is the rate. If a town of 50,000 has 1 murder, it's murder rate is 0.5 per 100,000.

    You say: But, you have to start at the beginning and decide if the initial question even makes sense. No one starts a hike with 100% certainty that they'll be a successful thru-hiker.

    My question is "How does the risk of a thru-hiker, when adjusted for time compare to the murder rate of big cities?" Possibly some may not care about the answer, but the question is a valid question and I don't see how it needs to "make sense" anymore than it already does. And whether one will successfully thru-hike has been addressed already by estimating how many months "thru-hikers" including successful and not successful average for their hike. Virtually anyone can answer this question while hiking... "If I were murdered today, would the news say 'thru-hiker killed' or would it say 'section-hiker killed'?" If the former, you are a thru-hiker. If the later, you are not.

    To get a rough estimate of how life on the trail (for thru-hikers) compares to life in the city in terms of risk of homicide, I say takes a few minutes, especially when given the ATC estimate of about 20,000 completed thru-hikes. Whatever you're doing that would take hours I do not think will help produce a substantially more accurate estimate especially since we are already limited to a very small sample of actual homicides anyway.
    The question to be initially asked is that are you going to change your life choices based on a .00001% risk difference between one activity and another activity/no activity. I mean, I don't particularly enjoy walking in a circle around my house for hours on end, but it lowers the risk of falling off a ledge on the AT by a considerable amount. Why would anyone want to think like this?

  5. #105

    Default

    Quote Originally Posted by FlyPaper View Post
    I agree that most people I see on the trail are decent. However, I don't see why we would need to consider the distribution of bad people when we know incontrovertibly that people have been murdered while hiking.

    If we look at shark attacks along US coast, I find a website that says there have been 30 so far this year. This could be 1 million nice sharks and 30 bad sharks along our coasts. It could be 1 single bad shark that really gets around. It is absolutely unnecessary to know how many actual sharks are involved, we can measure the rate at which attacks are happening use that information to predict future year's attacks.
    The risk of dying in a shark attack is less than that of cow attacks and vampire attacks combined.

  6. #106
    Registered User
    Join Date
    07-21-2005
    Location
    Garner, NC
    Age
    54
    Posts
    570
    Images
    279

    Default

    Reply to colorado_rob:

    Sorry, I just don't get it. I just don't understand why you separate the small number of thru hikers from the huge population of hikers, it seems to be this totally skews any possible results, hence why I made my initial brash and rude remarks.
    I have not taken the time to study all known murders. Some sites have slightly different numbers. It is my understanding that 7 thru-hikers have been murdered. I found a link that is saying 10 hikers have been murdered, and I saw another link that said 11. I am just assuming that some section-hikers have been murdered too, and am accepting 7 as the number of thru-hikers murdered. If someone wants to scour the web and get very precise numbers on this, I'd be glad to take their data and use it.

    One can go to Baltimore and calculate the homicide rate of Asian-Americans. To do that, one would take the total number of Asian-Americans living in Baltimore and dividing by the total number of Asian-Americans murdered. The final number might be similar to other ethnic groups or it might not. But for sure there would be a lot more people who are not Asian-Americans both living in Baltimore and murdered while living in Baltimore. The murder rate of Asian-Americans can be calculated and discussed and things can be gleaned from it even without knowing the total numbers. Ignoring African-American population in Baltimore does not make the Asian-American calculations wrong. My guess is that the murder rate of Asian-Americans in Baltimore is very different from the murder rate of African-Americans. If I am an Asian-American and want to estimate how dangerous it is to live in Baltimore as an Asian-American, what do you think is the most important thing to know? The total murder rate, or the murder rate of the sub-population of Asian-Americans?

    If I only had numbers available to estimate the Asian-American murder rate of Baltimore and I was an Indian-American (from India), I might reasonably guess that my risk was the same as theirs. One can bring in anecdotal data to contest this, but for rough estimates I think this is a reasonable guess. That is not a mathematical assessment, but rather my guess based on my knowledge of culture in the US. An Indian-American could reasonably guess his risk while living in Baltimore by considering the murder rate of Asian-Americans even if he does not know the total murder rate of all citizens of Baltimore.
    If one wants to claim that a person spending a night during his/her hiker-hours is in more danger, that's fine, I doubt if it's a factor of 2, but call it that, so call it 1 in 30,000 chance of getting murdered on a thru hike.

    I really am curious though, what makes any of us think that being murdered is more likely if you are camping? Being dark and scary isn't enough of an argument. Does anyone know, of the 7 murders, how many of these murders occurred at night with a camping victim? (tent, shelter, whatever). We all know the most recent one was indeed a camper, in his tent, poor soul.

    I just think most of the murders are happening when people stop for the night. Not necessarily asleep. I haven't heard of any murders while people were on the move mid day. I could be wrong and am open to correction for anyone who wants to read more carefully. But it doesn't really matter. If you are long distanced hiking you are both hiking and sleeping on the trail and you accept the aggregate risk. The only reason this matters is that it leads me to guess that thru-hikers and section-hikers are more at risk than day-hikers. If we know that 7 thru-hikers have been murdered out of 90,000 attempts, it doesn't really matter when it happened. Thru-hikers could average sleeping 8 hours per night or 4 hours per night. The aggregate murder rate per day on the trail is the same.
    That's my rough number. 1 in 60,000 (or 30000 if we think camping makes it twice as likely, which is a stretch). It seems pretty different from anything I see below, like 7 out of 90000 (or one in 12000), but I do admit it is in the same order of magnitude.

    If you count all hikers including day-hikers then I think we have say there have been 10 or 11 murders. But, I would say the risk profile of a day hikers may be a lot different than the risk profile of a section or thru-hiker. A large number of people who safely walk 1 hour on the trail may skew the numbers and make it seem like thru-hiking is safer than it is. For example, if one wanted to gauge how dangerous cave-diving is (scuba diving in caves), it would make sense to only consider cave-divers while ignoring ordinary scuba divers and deaths of ordinary scuba divers. One can estimate the danger of thru-hiking without being obligated to also measure the danger of day hiking.

    The one other factor is that thru-hikers spend 6 months on the trail. People that live in Baltimore spend 12 months in Baltimore. The average thru-hiker that attempts to thru-hike spends probably 2 or 3 months on the trail. If you get killed while thru-hiking, you will not be a successful thru-hiker, but rather someone who attempted a thru-hike and thus population-wise indistinguishable from a thru-hiker that quit early. If you estimates 1 in 30,000 thru-hikers would be killed, then that would be equivalent to a murder rate of about 1 in 7500 for a whole year.

    There can be two questions:

    1. What is the odds of being murdered while thru-hiking.
    2. What is the odds of being murdered for every 12 months of hiking done.

    I am trying to answer the second question because that's a way to compare the murder rate on the trail to the murder rate in the city. You seem to be trying to answer the first question, which is an okay question to answer, but not quit as useful as a basis for comparison against typical per-capita murder rates of US cities.


    Here is a summary:

    1. Thru-hiking murder rate is about 31 homicides per 100,000 person-years on the trail counting only thru-hikers. This I've done by a few calculations based on estimated numbers.
    2. Section-hiking is roughly the same risk as thru-hiking. This I am guessing not based on mathematics, but by my familiarity with the culture of the trail.
    3. Day-hiking is less dangerous than thru-hiking in terms of homicide rate. This is just an slightly educated guess.

    One be on the brink of thru-hiking and say that my 31 per 100,000 is garbage because I've ignored the day-hikers. But if you are contemplating a thru-hike, doesn't it make sense you would WANT to ignore the potentially lower risk to a group when you're NOT in that group?

  7. #107
    Registered User
    Join Date
    07-21-2005
    Location
    Garner, NC
    Age
    54
    Posts
    570
    Images
    279

    Default

    Quote Originally Posted by Puddlefish View Post
    The risk of dying in a shark attack is less than that of cow attacks and vampire attacks combined.
    Interesting. But if I were on a boat in the ocean considering going swimming, I'd only care about the risk of shark attack.

  8. #108
    Registered User
    Join Date
    07-21-2005
    Location
    Garner, NC
    Age
    54
    Posts
    570
    Images
    279

    Default

    Quote Originally Posted by Puddlefish View Post
    The question to be initially asked is that are you going to change your life choices based on a .00001% risk difference between one activity and another activity/no activity. I mean, I don't particularly enjoy walking in a circle around my house for hours on end, but it lowers the risk of falling off a ledge on the AT by a considerable amount. Why would anyone want to think like this?
    I wasn't even considering not hiking on the AT.

    One of my hobbies is hiking.

    Another of my hobbies is mathematics. I've enjoyed making these estimations more than many other things I do each year.

  9. #109
    ME => GA 19AT3 rickb's Avatar
    Join Date
    12-12-2002
    Location
    Marlboro, MA
    Posts
    6,904
    Journal Entries
    1
    Images
    1

    Default

    Quote Originally Posted by FlyPaper View Post
    There can be two questions:

    1. What is the odds of being murdered while thru-hiking.
    2. What is the odds of being murdered for every 12 months of hiking doneI wasn't even considering not hiking on the AT.
    One quibble.

    Your analysis is reasonably good at determining what the thru hiker murder rate has been. Establishing the odds of being murdered (future tense) may be informed by that understanding, but cannot necessarily be used to predict the future.

    Sort of like how backtesting the performance of your portfolio and the S&P is only of limited value in predicting the future. Even if that is highly recommended for those willing to assume a bit of risk.

  10. #110
    ME => GA 19AT3 rickb's Avatar
    Join Date
    12-12-2002
    Location
    Marlboro, MA
    Posts
    6,904
    Journal Entries
    1
    Images
    1

    Default

    Quote Originally Posted by FlyPaper View Post
    Another of my hobbies is mathematics. I've enjoyed making these estimations more than many other things I do each year.
    Google up “Monte Hall Problem” and work to really understand it.

    Then discuss with the smartest person you know (or the one who thinks he is smartest) after Thanksgiving dinner.

    Yea, that will be fun.

  11. #111
    Registered User colorado_rob's Avatar
    Join Date
    08-20-2012
    Location
    Denver, CO
    Age
    63
    Posts
    4,175
    Images
    3

    Default

    All interesting stuff, and again, I'm sorry for my initial knee-jerk brash dismissal of these attempts to figure "the odds".

    FP: my quick/dirty analysis takes into account the time spent on the trail, however long a thru-hiker-wannabe is on the trail, meaning if instead of being on the trail for the full 5 months, he quits after 2.5 months, of course his odd drops to 1/2, all things being equal.

    (For the record, strictly speaking, NO thru hiker has been murdered on the trail, right? You're only a thru hiker if you make it to the end of the 2192 mile trail, how ever you do this).

    So, the rough odds I propose are only for a 5-month hiker. Extrapolating that to a year, obvious multiply by 12/5ths.

    Odds over 5 months are 1/60000. So that times 12/5 = 12/300000 = 1 in 25,000 chance if an AT hiker stayed on the trail for an entire year.

    Bringing that to the 100,000 standard, I'm saying very roughly, that compared to city murder rates, the AT hiker murder rate would be "4" (100,000/25,000).

    Or "8 per 100,000 per year" if you think it twice as likely to be murdered if you sleep on the trail the entire time, which I don't buy. Again, what evidence is there to this?

    It is a real stretch to do any stats on such low sample sizes, seven murders over 45 years. It is even more of a stretch to say that campers on the trail are at a significantly higher risk than simple hikers, without actually checking the situations of those 7 murders. It would be nice to know this, but again, with such a minute sample, its dicey to extrapolate. But as you say FP, that's all we have to go on.

    Looking at my own results, it is surprising on a statistical basis how relatively "dangerous" the trail is. I was going on faith at the news reports that say "one in a gazillion" chance of being murdered, but of course for a single day's hike, the odds are very low.

    What I'm saying is that for a rough order of magnitude, we're not far off. 8 per 100,000 per year vs 31, and if I correct to your claimed 10-11 murders FP, I'm at 10-ish/100,000, even closer. different assumptions, different results.
    Last edited by colorado_rob; 11-15-2019 at 20:06.

  12. #112

    Default

    ............
    Last edited by Traffic Jam; 11-15-2019 at 22:48.

  13. #113

    Default

    We do know some of the motivation behind some of these murders, and for some of the murders it wasn't because they were thruhiking.

    If every thruhiker signed a pledge to skip and hike one 10 mile section the next year, would no AT hikers be murdered ever? Would you suddenly be safer because you did that? Like the murderer would know? "You're killing the wrong person dude, I'm only a section hiker!" "Oh man I'm sorry, I only kill thruhikers, my bad."
    "Sleepy alligator in the noonday sun
    Sleepin by the river just like he usually done
    Call for his whisky
    He can call for his tea
    Call all he wanta but he can't call me..."
    Robert Hunter & Ron McKernan

    Whiteblaze.net User Agreement.

  14. #114

    Default

    Wow,way more math than I ever imagined I would find here..but for me,it boils down to this-everywhere I go,and everything I do has risks. I am not immortal,I have to die somewhere,sometime. If it happens on the trail,by whatever means,so be it. i much prefer to take my last breath on the AT than in a nursing home.

  15. #115
    Registered User
    Join Date
    12-28-2015
    Location
    Bad Ischl, Austria
    Age
    62
    Posts
    1,150

    Default

    Quote Originally Posted by illabelle View Post
    ....
    Where are the criminals? Given that nearly all hikers I've met (day, section, or thru) appear to be decent law-abiding people, there would appear to be very few individuals on the trail who have murderous inclinations. Criminals tend to stay in cities. Yes, I know small towns have criminals also. If the people who wish to kill aren't on the trail [very much], what difference does it make how many miles, or hiker-hours, or person-years, or whether I sleep at home or on the trail? If the bad people aren't there, I'm safe from bad people.
    ....
    Exactly the way I'm thinking:
    Where there are few people, there is much less chance for meeting bad people.
    Criminals tend to stay at the cities, and terrorists, mass shooters and such try to get to the crowds.

  16. #116
    Registered User
    Join Date
    07-03-2015
    Location
    Center Conway, NH
    Age
    67
    Posts
    78

    Default

    Shhhhh, or one might show up a Trail Days. God forbid.

  17. #117

    Default

    After careful consideration of all the information presented I am inclined to wonder how many people who would not consider any sort of weapon or preparation for an on trail assault because of the low statistical probability of that occurrence would still buy a Power Ball Lottery Ticket because,after all,somebody is going to win?

  18. #118
    ME => GA 19AT3 rickb's Avatar
    Join Date
    12-12-2002
    Location
    Marlboro, MA
    Posts
    6,904
    Journal Entries
    1
    Images
    1

    Default

    Thank
    Quote Originally Posted by Five Tango View Post
    After careful consideration of all the information presented I am inclined to wonder how many people who would not consider any sort of weapon or preparation for an on trail assault because of the low statistical probability of that occurrence would still buy a Power Ball Lottery Ticket because,after all,somebody is going to win?
    The odds of winning $1 million (second place) are slim about 1 in 12,000,000.

    Buy 180 tickets and your chances of winning go up.

    If you get together with 2500 like minded individuals and 500 them buy 180 tickets, 1250 of them buy 90 tickets, and 750 of them buy just 45 tickets (236,250 total tickets purchased) the odds at least on of your buddies winning that $1 million go up.

    Way, way up.

  19. #119

    Default

    There have been 11 murders on the AT in it's history.

    The first was 1974 at low gap shelter in GA.
    In 1975, Janice Balza was murdered for her backpack
    In 1981, two hiker were killed, no details.
    In 1988, one woman was killed for having sex in a shelter with another woman, who survived.
    In 1990, a drifter killed 2 hikers at Cove Mountain in PA The male hiker was shot and killed, the woman raped and then killed.
    In 1996, two woman were killed in the SNP -still unsolved.
    In 2011, a hiker was found asphyxiated, not solved.
    In 2019, a hiker was killed by a deranged hiker with a machete.

    Interestingly, nearly half of the victims were woman. Only a couple of these murders were committed by other hikers.

    At most, only 2 people have been murdered in the same year and as a couple. We go years between murders.

    All in all, there really isn't anything to worry about.
    The AT - It has it's ups and downs...

  20. #120
    ME => GA 19AT3 rickb's Avatar
    Join Date
    12-12-2002
    Location
    Marlboro, MA
    Posts
    6,904
    Journal Entries
    1
    Images
    1

    Default

    Your details on the 1988 murder are factually incorrect.

Page 6 of 11 FirstFirst ... 2 3 4 5 6 7 8 9 10 ... LastLast
++ New Posts ++

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •