Re: [Aus-soaring] Comparing accident rates
Hi Leigh, Your comment reminded me of when I was I Pennsylvania many years ago. “A” might stand for Anarchy or Avalon, but it can also stand for Amish. This sect (civilized society?), were big time settlers of Pennsylvania. Some of the names they gave to their settlements were “interesting”, like Intercourse and Paradise. If you have a look at a map of Pennsylvania you will see that the facts only slightly diverge from the fable that states that “you must go through Intercourse to get to Paradise”. Gary From: Aus-soaring [mailto:aus-soaring-boun...@lists.base64.com.au] On Behalf Of Leigh Bunting Sent: Friday, 11 March 2016 2:24 PM To: Discussion of issues relating to Soaring in Australia. Subject: Re: [Aus-soaring] Comparing accident rates What? Name calling? Mature men getting to that stage? I'll have to go to the trash bin to have a look, coz I've been wearing out the delete key on that thread. I lost interest long ago on that one. Just goes to show that Anarchy (apart from being a quaint village you fly over on the way into Avalon) really is only a thin veneer distant below civilized society. Hey Simon, is that your PC12 parked at Gawler. I couldn't see the rego from the road. The bushes are growing very well. Cheers Leigh Bunting Balaklava GC ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Dear all . I do intend to comment on this thread later. There are so many inaccuracies but I’m limited to 1 finger typing for a while. Gary. I recall henry showing me drawings of a 70-1 sailplane back in the early 70’s and bev attended a lecture he gave at rmit on this subject. We caught up with his children last year which was great as we had all impacted on each other all those years ago. From: Aus-soaring [mailto:aus-soaring-boun...@lists.base64.com.au] On Behalf Of Leigh Bunting Sent: Friday, March 11, 2016 1:54 PM To: Discussion of issues relating to Soaring in Australia. Subject: Re: [Aus-soaring] Comparing accident rates What? Name calling? Mature men getting to that stage? I'll have to go to the trash bin to have a look, coz I've been wearing out the delete key on that thread. I lost interest long ago on that one. Just goes to show that Anarchy (apart from being a quaint village you fly over on the way into Avalon) really is only a thin veneer distant below civilized society. Hey Simon, is that your PC12 parked at Gawler. I couldn't see the rego from the road. The bushes are growing very well. Cheers Leigh Bunting Balaklava GC ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
What? Name calling? Mature men getting to that stage? I'll have to go to the trash bin to have a look, coz I've been wearing out the delete key on that thread. I lost interest long ago on that one. Just goes to show that Anarchy (apart from being a quaint village you fly over on the way into Avalon) really is only a thin veneer distant below civilized society. Hey Simon, is that your PC12 parked at Gawler. I couldn't see the rego from the road. The bushes are growing very well. Cheers Leigh Bunting Balaklava GC ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
>> Can I gently suggest we might have whipped this topic hard enough at this >> point What was the topic? Something like "Is gliding dangerous"? If the answer is "gliding is dangerous", then how might we go about making it safer? Are there any specific areas or activities which are either obviously more dangerous or probably more dangerous where we might start? (Not including banning winch launching.) The accident reports from GA quoted some days ago showed many times more landing accidents than anything else. Admittedly many of these were just plain old German undercarriage collapses (how long does it take to get a design right?) but others were due landing practices which could be improved on. D ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Hey Gentlemen! (and at this point I am using the term increasingly loosely) Can I gently suggest we might have whipped this topic hard enough at this point, and that none of you are interested in being sympathetic to the views of the others sufficiently for this conversation to have any real chance of ‘converging’ from here. When it gets to name calling, its gone far enough. Whatever you’re trying to prove to each other, its turning into one of those conversations that, if held at a party, would lead to the others around wandering off quietly to find another drink and a less aggressive conversation. You are now at the point that reminds me of the classic gag about academia: Q: Why are arguments between academics so vehement? A: Because the stakes are so low. Thanks, Simon ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Justin, It is a flight REVIEW, not an exam. It is also one of the causes of private/recreational pilots giving up aviation because it all gets too hard. Too many hoops to jump through (I've met several the past year who have given up or are about to). I really don't care if you have to do this at work as you get paid to put up with it and the cost and inconvenience doesn't come out of your pocket. People are generally willing to put up with a lot less when it comes to a recreational activity which they are paying for. The number one problem in private aviation of all sorts is the falling number of participants, not safety. In some recreational pursuits perceived danger is regarded as a feature, not a bug, as is taking responsibility for the outcomes yourself. See solo round the world yachting etc etc. There are reasons for the existence of aviation regulation which I'll go into later in another post but protecting people from themselves isn't one of them. That last is a very slippery slope leading to totalitarianism. Emotive claptrap like "The fact that their remains are nothing more than blood and guts wrapped in fibreglass and metal should not be forgotten and someone has to clean that up as well." has no place in a serious discussion on safety. I'll repeat " The number one problem in private aviation of all sorts is the falling number of participants, not safety. " Mike Borgelt Instruments - design & manufacture of quality soaring instrumentation since 1978 www.borgeltinstruments.com tel: 07 4635 5784 overseas: int+61-7-4635 5784 mob: 042835 5784: int+61-42835 5784 P O Box 4607, Toowoomba East, QLD 4350, Australia ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Not just gliding, all of aviation. Instructors are supposed to be able to provide evidence, years and years later, that they covered every god damn thing imaginable. “Do you have evidence, in writing, that you specifically educated the deceased that a powered aircraft can not maintain altitude without an adequate supply of fuel?” Blame the lawyers and the ’it’s not my fault, who can I blame’ attitude of modern society Record keeping in powered flying schools underwent a massive overhaul some 15 years ago to create this traceability. The fact that gliding has gotten away without it for as long as it has is, quite frankly, amazing. CJ > On 11 Mar 2016, at 09:51, Al Borowski wrote: > > On 11/03/2016, Optusnet wrote: >> That's all fine and well Mark until it comes to your CFI and ultimately >> Chris Thorpe to authorise your operations as a pilot. > >> At some point some poor bunny has to put their neck on the block and be >> prepared to look your wife and kids in the eye and say. " I conducted his >> AFR as required by a approved revalidation program, a program that is >> authorised by an authority that has been shown to lower the risk of >> sailplane flying. I am terribly sorry and devastated that he has had a fatal >> accident however he deliberately chose to -insertSOPbreachhere- and that >> substantially increased the risk to his operation. My sign off on his AFR >> was very clear in the expectation to follow the guidance given by those that >> authorise our operation. > > If I crashed my car, my driving instructor and the person who > conducted my driving test would not be placed in this position. Ditto > for my boat. Why is gliding special? > > Cheers, > > Al > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 11/03/2016, Optusnet wrote: > That's all fine and well Mark until it comes to your CFI and ultimately > Chris Thorpe to authorise your operations as a pilot. > At some point some poor bunny has to put their neck on the block and be > prepared to look your wife and kids in the eye and say. " I conducted his > AFR as required by a approved revalidation program, a program that is > authorised by an authority that has been shown to lower the risk of > sailplane flying. I am terribly sorry and devastated that he has had a fatal > accident however he deliberately chose to -insertSOPbreachhere- and that > substantially increased the risk to his operation. My sign off on his AFR > was very clear in the expectation to follow the guidance given by those that > authorise our operation. If I crashed my car, my driving instructor and the person who conducted my driving test would not be placed in this position. Ditto for my boat. Why is gliding special? Cheers, Al ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Sorry Mark it wasn't personal. Your statement came across as someone who seemed not to understand the reality of what responsibility of checking can mean. You can read all about it here https://www.atsb.gov.au/publications/investigation_reports/2001/aair/aair200100348/ He was a mate and I was the instructor who did his initial twin rating after he had issues at another school, I did the rating in a B58 and gave him the most thorough twin endorsement I have ever done. I passed him and wrote "to std" on his logbook. It was a few years later that he had his accident and ultimately it was a system issue, fatigue and other factors that got him. Unfortunately I still think about it every now and then as Western Australia lost four excellent policeman and four families still miss their fathers and sons. I can't help but wonder if I had missed something or passed him when I shouldn't have. The other one is here https://www.atsb.gov.au/media/2486613/ao2010023.pdf So let me reiterate my passionate feelings, every time you check someone you are standing up and saying you are willing to let that person operate to a set of standards in accordance with the relevant rules and regulations. It doesn't matter what the rules say or what a court says, if there is an incident you have to be able to live with yourself. If you are lazy or not on the ball and someone dies you are morally responsible. As much as the GFA, CASA and others are criticised they are there to stop some poor bugger knocking on a door late at night to tell them that their loved ones are not coming home. The fact that their remains are nothing more than blood and guts wrapped in fibreglass and metal should not be forgotten and someone has to clean that up as well. So Mark it wasn't personal however perhaps you might see how someone who takes safety very seriously wants to minimise the risk. I have to share the airspace as well as a slow glider pilots in my ancient Nimbus 2, I get very tired of sailplane pilots not wanting to man up and get their stuff together. If you had of heard the lack of calls in CTAFS during the pre-worlds you would have been horrified. As a holder of a PPL you know that every two years you front up to an examiner with up to date logbook, current charts and free of alcohol and drugs. You do that to ensure that you will get to keep the privileges of your licence. The examiner is essentially putting his future mental health and possible lively hood on the line and entrusting you to act within the risk mitigators as laid out by the regs. So next time someone signs you out say thankful for the trust they are putting in you. Sent from my iPad > On 11 Mar 2016, at 11:00 AM, Mark Newton wrote: > > >> On 11 Mar 2016, at 11:36, Optusnet wrote: >> >> >> Mark, would you mind letting me know when you are flying next, I just don't >> want to be in the same airspace as you and expose myself to the increased >> risk. > > Personal attack, JJ? > C'mon, that's just weak. > > >> As to your statement >> >> Incidentally: People die in aircraft all the time, and what you just wrote >> never happens. It’s 24 carat rolled-gold bullshit. >> >> It's happened to me twice in 30 years > > I don't want to downplay your experience of how traumatic it'd be to > participate in a coronial inquest for someone you knew who died in an > aircraft. > > But: you were questioned, not held responsible. > >> Incidentally both pilots had a history of poor check performances. > > So the check/review system didn't work? > > - mark > > > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 11 Mar 2016, at 11:36, Optusnet wrote: > > > Mark, would you mind letting me know when you are flying next, I just don't > want to be in the same airspace as you and expose myself to the increased > risk. Personal attack, JJ? C'mon, that's just weak. > As to your statement > > Incidentally: People die in aircraft all the time, and what you just wrote > never happens. It’s 24 carat rolled-gold bullshit. > > It's happened to me twice in 30 years I don't want to downplay your experience of how traumatic it'd be to participate in a coronial inquest for someone you knew who died in an aircraft. But: you were questioned, not held responsible. > Incidentally both pilots had a history of poor check performances. So the check/review system didn't work? - mark ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
The checking instructor who does the AFR every two years is not assuming responsibility for my Ops. - mark -- Tiny screen, imaginary keyboard. > On 11 Mar 2016, at 11:43, Ross McLean wrote: > > Hmm, well a lot of glider pilots have a PPL Mark, quite a few are CPL and a > lot are ATPL. Some are ATPL and CFI too.. but we all still have to do an AFR > to continue gliding Mark, even you. > ROSS > _ > > > -Original Message- > From: Aus-soaring [mailto:aus-soaring-boun...@lists.base64.com.au] On Behalf > Of Mark Newton > Sent: Friday, 11 March 2016 10:06 AM > To: Discussion of issues relating to Soaring in Australia. > Subject: Re: [Aus-soaring] Comparing accident rates > >> On 11 Mar 2016, at 9:16 AM, Optusnet wrote: >> >> That's all fine and well Mark until it comes to your CFI and ultimately >> Chris Thorpe to authorise your operations as a pilot. > > I have a PPL, so I�m trusted globally to take responsibility for my own > safety. > > - mark > > > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring > > > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Hmm, well a lot of glider pilots have a PPL Mark, quite a few are CPL and a lot are ATPL. Some are ATPL and CFI too.. but we all still have to do an AFR to continue gliding Mark, even you. ROSS _ -Original Message- From: Aus-soaring [mailto:aus-soaring-boun...@lists.base64.com.au] On Behalf Of Mark Newton Sent: Friday, 11 March 2016 10:06 AM To: Discussion of issues relating to Soaring in Australia. Subject: Re: [Aus-soaring] Comparing accident rates On 11 Mar 2016, at 9:16 AM, Optusnet wrote: > > That's all fine and well Mark until it comes to your CFI and ultimately Chris > Thorpe to authorise your operations as a pilot. I have a PPL, so I�m trusted globally to take responsibility for my own safety. - mark ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Mark, would you mind letting me know when you are flying next, I just don't want to be in the same airspace as you and expose myself to the increased risk. As to your statement Incidentally: People die in aircraft all the time, and what you just wrote never happens. It’s 24 carat rolled-gold bullshit. It's happened to me twice in 30 years and let me tell you being summoned to a coronial inquest in front of a full bench where 4 policeman died is nothing compared to the utter devastation of watching a mother dying of terminal cancer being told how her Husband had died in an accident in his twin in poor weather due to poor choices. Incidentally both pilots had a history of poor check performances. JJ > On 11 Mar 2016, at 10:09 AM, Mark Newton wrote: > > Incidentally: People die in aircraft all the time, and what you just wrote > never happens. It’s 24 carat rolled-gold bullshit. ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Oh, may I bow down to your PPL superiority. Thank you for your efforts in making our airspace safe. JJ Sent from my iPad > On 11 Mar 2016, at 10:06 AM, Mark Newton wrote: > >> On 11 Mar 2016, at 9:16 AM, Optusnet wrote: >> >> That's all fine and well Mark until it comes to your CFI and ultimately >> Chris Thorpe to authorise your operations as a pilot. > > I have a PPL, so I’m trusted globally to take responsibility for my own > safety. > > - mark > > > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 11 Mar 2016, at 9:16 AM, Optusnet wrote: > At some point some poor bunny has to put their neck on the block and be > prepared to look your wife and kids in the eye and say. " I conducted his AFR > as required by a approved revalidation program, a program that is authorised > by an authority that has been shown to lower the risk of sailplane flying. I > am terribly sorry and devastated that he has had a fatal accident however he > deliberately chose to -insertSOPbreachhere- and that substantially increased > the risk to his operation. My sign off on his AFR was very clear in the > expectation to follow the guidance given by those that authorise our > operation. Incidentally: People die in aircraft all the time, and what you just wrote never happens. It’s 24 carat rolled-gold bullshit. Giving someone a flight review is not the same as taking responsibility for their safety. Their safety is their responsibility. The fact that GFA has deliberately gone out of their way to implement a misalignment between safety responsibility and safety accountability adds unnecessary complexity, but doesn’t change anything else. - mark ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 11 Mar 2016, at 9:16 AM, Optusnet wrote: > > That's all fine and well Mark until it comes to your CFI and ultimately Chris > Thorpe to authorise your operations as a pilot. I have a PPL, so I’m trusted globally to take responsibility for my own safety. - mark ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
That's all fine and well Mark until it comes to your CFI and ultimately Chris Thorpe to authorise your operations as a pilot. Sure every standards position holder could use the statement ("I don’t care about accident rates in aviation generally. I care about my personal accident rate.I can control my personal culture, and certain parts of my environment. I can influence, but not control, the culture of those around me") Naturally no-one would sign off your AFR, form 2 or aircraft certification because that would require them making a statistical risk based analysis on you and your standards, in no time and we would all be grounded. At some point some poor bunny has to put their neck on the block and be prepared to look your wife and kids in the eye and say. " I conducted his AFR as required by a approved revalidation program, a program that is authorised by an authority that has been shown to lower the risk of sailplane flying. I am terribly sorry and devastated that he has had a fatal accident however he deliberately chose to -insertSOPbreachhere- and that substantially increased the risk to his operation. My sign off on his AFR was very clear in the expectation to follow the guidance given by those that authorise our operation. Statistics and accident rates are important, it doesn't matter how they are presented or even if they are way off. Statistically no one has ever been wounded by an unloaded gun yet statistically the number of soundings by people who thought the gun was unloaded is high. Therefore all you need to know is to treat every gun as if it's loaded, by doing this you statistically reduce your risk by a massive margin JJ Sent from my iPad > On 11 Mar 2016, at 4:44 AM, Mark Newton wrote: > >> On 10 Mar 2016, at 9:38 PM, >> wrote: >> Be aware that the accident reporting system some years ago going into the >> GFA system was significantly deficient. In one state reporting was running >> at about 50 -70% of the claims rate. >> >> If we had not seen a change in the culture, discussions were going to be >> taken with the insurance industry to obtain actual claims data. > > I don’t care about accident rates in aviation generally. I care about my > personal accident rate. > > I can control my personal culture, and certain parts of my environment. I can > influence, but not control, the culture of those around me. > > I’ll go through my life trying to be the centre of a little bubble of > accident-free aviation, immersed in the frothy statistical noise of whatever > Teal and Michael are discussing. > > When evaluating any question with statistics, one of the first questions to > ask is whether your sample is reflective of your population. I’m a sample > size of 1 in a population of 1. Everything outside that is pretty > uninteresting to me. > > - mark > > > ___ > Aus-soaring mailing list > Aus-soaring@lists.base64.com.au > http://lists.base64.com.au/listinfo/aus-soaring ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 10 Mar 2016, at 9:38 PM, wrote: > Be aware that the accident reporting system some years ago going into the GFA > system was significantly deficient. In one state reporting was running at > about 50 -70% of the claims rate. > > If we had not seen a change in the culture, discussions were going to be > taken with the insurance industry to obtain actual claims data. I don’t care about accident rates in aviation generally. I care about my personal accident rate. I can control my personal culture, and certain parts of my environment. I can influence, but not control, the culture of those around me. I’ll go through my life trying to be the centre of a little bubble of accident-free aviation, immersed in the frothy statistical noise of whatever Teal and Michael are discussing. When evaluating any question with statistics, one of the first questions to ask is whether your sample is reflective of your population. I’m a sample size of 1 in a population of 1. Everything outside that is pretty uninteresting to me. - mark ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Be aware that the accident reporting system some years ago going into the GFA system was significantly deficient. In one state reporting was running at about 50 -70% of the claims rate. If we had not seen a change in the culture, discussions were going to be taken with the insurance industry to obtain actual claims data. Peter Heath Teal wrote: = On 10/03/2016 6:50 PM, Texler, Michael wrote: >> I've not seen them described that way in the road safety literature that >> I'm familiar with. How would that work? If the number of accidents is on the >> Y axis, what variable would the X axis have? If we go with road accidents >> (my field of expertise) it can't be age/driving experience, because the >> accident stats in NO way form a poisson distribution when age/experience is >> your X-axis variable. (Actually, road prangs by age/experience gives you >> more of a U-shaped curve.) Also, rate of accidents (be they road prangs or >> glider prangs) aren't constant over time (as required for a poisson >> distribution to be your distribution of > choice) - they vary by time of day, for fairly obvious reasons, as well as > other things (day of the week, long weekends, etc etc). > >> You appear to be approaching the issue from a rather different statistical >> approach to the ones I'm familiar with. Could you spell out your >> approach/methods in more detail? It's always interesting to hear how folk in >> other fields approach problems I'm familiar with. :-) > I am approaching it as counting events occurring over a duration of time > (analogous to say counting disintegrations per second for radioactive decay). > > Y axis would be the accident rate with any metric that you care to choose > (i.e. accidents per 1,000 hours flown, accidents per 100km travelled, > accidents per 1,000 flights etc.). > Y axis would be a duration of time, i.e over one year, over 10 years, over > 100 years. > > Then it is a case of using the appropriate test to compare the two groups > (null hypothesis being that the accident rate between two groups is the same). I'm afraid I'm still not with you. *Which* two groups, exactly? Displaying all recorded traffic accidents over time in that way will (if you use Australian data) give you a single line that (depending on the period covered, but lets go with "the last 20 years") trends downward over time. Who are you comparing again whom, in your example? > A fairly blunt measure granted. > > Given your experience with road accidents analysis, how would you approach it? Well, it would depend on exactly which question was being asked. If we were interested in the numbers of accidents had by drivers of different ages, my previous example (up in the first para quoted above) was a simple descriptive graph showing difference in number of accidents by age, for a set amount of time (a year, say). Or we could do it another way, and have a graph with dates along the X axis, and separate lines (one for each age group, maybe 16-25, 26-35 and so on) showing how accident numbers have changed over time for each age group, if we were interested in seeing if there were any obvious differences in crash rates over time by age group. Or, if the question whether a particular time of day is more crash-prone than other times, we could graph all the accidents occurring in the last year with the X axis showing hours of the day (midnight-0200, 0201-0400, etc). Or whatever. All this is pretty basic stuff. We could go on from there, and report means and standard deviations for age groups/time periods/whatever of interest, and see if anything leaps out in terms of obvious differences or trends. But that still isn't going to get you anything you might want to discuss using null hypotheses or p values ... for that you really do need actual *inferential* statistical tests, with specific groups that you are comparing. And this broad-brush descriptive approach isn't going to give you that. You need to narrow it down a bit. So: lets come back to the original topic that started all this - glider accidents. How would I approach that? Well, first would be deciding exactly what question I want an answer to. Do I want to know if the glider prang rate is increasing or decreasing over time? Or do I want to know whether more crashes are happening in comps than in cross-country gliding? Or how the glider crash rate as a whole compares with the number of motorcycle crashes for a given period? Lets go with the last one, since we were also discussing that earlier. Firstly, getting a good source of data for *both* of those elements in the comparison is tricky. So I'm gonna handwave past that and assume that we have good quality data on both of these, including exposure data (i.e. how much time was spent per pilot/cyclist actually flying/cycling during that time period), because exposure is critical for topics like this: it means absolutely not
Re: [Aus-soaring] Comparing accident rates
Without getting into the nitty gritty of statistics, I think it is reasonable to suggest the following: Based on the reported incidents over a recent 12 month period for gliding and motorcycles, the basic incident per hour rate is broadly similar as per Mark Newton's estimate. The percentage of incidents reported is likely to be the same between both groups Let us say that for the moment that the rate is roughly 1 incident per 1600 hrs. If you assume (yes I know an assumption) that the basic rate is the same for comps as it is for everyday flying, then a large comp is 'likely' to generate at least one incident purely from the number of hours being flown at that event. So the claim that a significant proportion of accidents happen at comps could be considered to be true, but only because a significant proportion of the national gliding hours occur at those events. I have not found any data for comp versus non-comp incident rates. -Original Message- From: Aus-soaring [mailto:aus-soaring-boun...@lists.base64.com.au] On Behalf Of Teal Sent: Thursday, 10 March 2016 8:22 PM To: Discussion of issues relating to Soaring in Australia. Subject: Re: [Aus-soaring] Comparing accident rates On 10/03/2016 6:50 PM, Texler, Michael wrote: >> I've not seen them described that way in the road safety literature >> that I'm familiar with. How would that work? If the number of >> accidents is on the Y axis, what variable would the X axis have? If >> we go with road accidents (my field of expertise) it can't be >> age/driving experience, because the accident stats in NO way form a >> poisson distribution when age/experience is your X-axis variable. >> (Actually, road prangs by age/experience gives you more of a U-shaped >> curve.) Also, rate of accidents (be they road prangs or glider >> prangs) aren't constant over time (as required for a poisson >> distribution to be your distribution of > choice) - they vary by time of day, for fairly obvious reasons, as well as other things (day of the week, long weekends, etc etc). > >> You appear to be approaching the issue from a rather different >> statistical approach to the ones I'm familiar with. Could you spell >> out your approach/methods in more detail? It's always interesting to >> hear how folk in other fields approach problems I'm familiar with. >> :-) > I am approaching it as counting events occurring over a duration of time (analogous to say counting disintegrations per second for radioactive decay). > > Y axis would be the accident rate with any metric that you care to choose (i.e. accidents per 1,000 hours flown, accidents per 100km travelled, accidents per 1,000 flights etc.). > Y axis would be a duration of time, i.e over one year, over 10 years, over 100 years. > > Then it is a case of using the appropriate test to compare the two groups (null hypothesis being that the accident rate between two groups is the same). I'm afraid I'm still not with you. *Which* two groups, exactly? Displaying all recorded traffic accidents over time in that way will (if you use Australian data) give you a single line that (depending on the period covered, but lets go with "the last 20 years") trends downward over time. Who are you comparing again whom, in your example? > A fairly blunt measure granted. > > Given your experience with road accidents analysis, how would you approach it? Well, it would depend on exactly which question was being asked. If we were interested in the numbers of accidents had by drivers of different ages, my previous example (up in the first para quoted above) was a simple descriptive graph showing difference in number of accidents by age, for a set amount of time (a year, say). Or we could do it another way, and have a graph with dates along the X axis, and separate lines (one for each age group, maybe 16-25, 26-35 and so on) showing how accident numbers have changed over time for each age group, if we were interested in seeing if there were any obvious differences in crash rates over time by age group. Or, if the question whether a particular time of day is more crash-prone than other times, we could graph all the accidents occurring in the last year with the X axis showing hours of the day (midnight-0200, 0201-0400, etc). Or whatever. All this is pretty basic stuff. We could go on from there, and report means and standard deviations for age groups/time periods/whatever of interest, and see if anything leaps out in terms of obvious differences or trends. But that still isn't going to get you anything you might want to discuss using null hypotheses or p values ... for that you really do need actual *inferential* statistical tests, with specific groups that you are comparing. And this broad-brush descriptive approach isn
Re: [Aus-soaring] Comparing accident rates
On 10/03/2016 6:50 PM, Texler, Michael wrote: I've not seen them described that way in the road safety literature that I'm familiar with. How would that work? If the number of accidents is on the Y axis, what variable would the X axis have? If we go with road accidents (my field of expertise) it can't be age/driving experience, because the accident stats in NO way form a poisson distribution when age/experience is your X-axis variable. (Actually, road prangs by age/experience gives you more of a U-shaped curve.) Also, rate of accidents (be they road prangs or glider prangs) aren't constant over time (as required for a poisson distribution to be your distribution of choice) - they vary by time of day, for fairly obvious reasons, as well as other things (day of the week, long weekends, etc etc). You appear to be approaching the issue from a rather different statistical approach to the ones I'm familiar with. Could you spell out your approach/methods in more detail? It's always interesting to hear how folk in other fields approach problems I'm familiar with. :-) I am approaching it as counting events occurring over a duration of time (analogous to say counting disintegrations per second for radioactive decay). Y axis would be the accident rate with any metric that you care to choose (i.e. accidents per 1,000 hours flown, accidents per 100km travelled, accidents per 1,000 flights etc.). Y axis would be a duration of time, i.e over one year, over 10 years, over 100 years. Then it is a case of using the appropriate test to compare the two groups (null hypothesis being that the accident rate between two groups is the same). I'm afraid I'm still not with you. *Which* two groups, exactly? Displaying all recorded traffic accidents over time in that way will (if you use Australian data) give you a single line that (depending on the period covered, but lets go with "the last 20 years") trends downward over time. Who are you comparing again whom, in your example? A fairly blunt measure granted. Given your experience with road accidents analysis, how would you approach it? Well, it would depend on exactly which question was being asked. If we were interested in the numbers of accidents had by drivers of different ages, my previous example (up in the first para quoted above) was a simple descriptive graph showing difference in number of accidents by age, for a set amount of time (a year, say). Or we could do it another way, and have a graph with dates along the X axis, and separate lines (one for each age group, maybe 16-25, 26-35 and so on) showing how accident numbers have changed over time for each age group, if we were interested in seeing if there were any obvious differences in crash rates over time by age group. Or, if the question whether a particular time of day is more crash-prone than other times, we could graph all the accidents occurring in the last year with the X axis showing hours of the day (midnight-0200, 0201-0400, etc). Or whatever. All this is pretty basic stuff. We could go on from there, and report means and standard deviations for age groups/time periods/whatever of interest, and see if anything leaps out in terms of obvious differences or trends. But that still isn't going to get you anything you might want to discuss using null hypotheses or p values ... for that you really do need actual *inferential* statistical tests, with specific groups that you are comparing. And this broad-brush descriptive approach isn't going to give you that. You need to narrow it down a bit. So: lets come back to the original topic that started all this - glider accidents. How would I approach that? Well, first would be deciding exactly what question I want an answer to. Do I want to know if the glider prang rate is increasing or decreasing over time? Or do I want to know whether more crashes are happening in comps than in cross-country gliding? Or how the glider crash rate as a whole compares with the number of motorcycle crashes for a given period? Lets go with the last one, since we were also discussing that earlier. Firstly, getting a good source of data for *both* of those elements in the comparison is tricky. So I'm gonna handwave past that and assume that we have good quality data on both of these, including exposure data (i.e. how much time was spent per pilot/cyclist actually flying/cycling during that time period), because exposure is critical for topics like this: it means absolutely nothing to say that there were 12 glider prangs and 355 bike prangs in a given period, if we don't *also* know that there were a lot more cyclists on the road, driving for a lot more overall hours, than there were glider pilots in the air during the same period. OK. So now I hypothetically have ten years' worth of crash rates per hour of flying or riding for the respective groups, and I want to compare them. This is where the inferential
Re: [Aus-soaring] Comparing accident rates
At 04:35 PM 3/10/2016, you wrote: It is always difficult to compare accidents rates for 'rare' events due to the wide 95% confidence intervals. Somebody should tell Chris Thorpe before he embarrasses himself in print again. (the spin accident stats) Mike Borgelt Instruments - design & manufacture of quality soaring instrumentation since 1978 www.borgeltinstruments.com tel: 07 4635 5784 overseas: int+61-7-4635 5784 mob: 042835 5784: int+61-42835 5784 P O Box 4607, Toowoomba East, QLD 4350, Australia ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
> I've not seen them described that way in the road safety literature that I'm > familiar with. How would that work? If the number of accidents is on the Y > axis, what variable would the X axis have? If we go with road accidents (my > field of expertise) it can't be age/driving experience, because the accident > stats in NO way form a poisson distribution when age/experience is your > X-axis variable. (Actually, road prangs by age/experience gives you more of a > U-shaped curve.) Also, rate of accidents (be they road prangs or glider > prangs) aren't constant over time (as required for a poisson distribution to > be your distribution of choice) - they vary by time of day, for fairly obvious reasons, as well as other things (day of the week, long weekends, etc etc). > You appear to be approaching the issue from a rather different statistical > approach to the ones I'm familiar with. Could you spell out your > approach/methods in more detail? It's always interesting to hear how folk in > other fields approach problems I'm familiar with. :-) I am approaching it as counting events occurring over a duration of time (analogous to say counting disintegrations per second for radioactive decay). Y axis would be the accident rate with any metric that you care to choose (i.e. accidents per 1,000 hours flown, accidents per 100km travelled, accidents per 1,000 flights etc.). Y axis would be a duration of time, i.e over one year, over 10 years, over 100 years. Then it is a case of using the appropriate test to compare the two groups (null hypothesis being that the accident rate between two groups is the same). A fairly blunt measure granted. Given your experience with road accidents analysis, how would you approach it? ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 10/03/2016 5:53 PM, Texler, Michael wrote: Not actually true; the degree of difference between groups/cases/whatever that you'll need to to get a statistically significant result (be it for p=.05 or p=.01 or whatever) will depend on the sample size, and on the characteristics of the sample and the population you're drawing the sample from. There is in fact a whole sub-topic of stats that is about working out what size sample you need for a given situation in order to be able to plausibly see any real differences between groups, should there be a real difference to be found. When comparing accident rates, you are not sampling per se, but estimating the occurrence of an event in a selected population (i.e. descriptive statistics). Also for 'rare' events such as accidents, estimating the mean rate and standard deviations from year to year can show such variability that statistical testing becomes problematic. Yup, descriptive stats are definitely where one should start, on a subject like this. But in your earlier post you also said "there often needs to be an order of magnitude difference (i.e. a 10 tenfold increase or decrease of an accident rate) to demonstrate statistical significance at the 95% level". That's inferential statistics, not descriptive stats. When you start talking about "statistical significance" it means running actual statistical tests to *test* the significance. You can't tell just from looking, as a rule. (At least, not unless it's *really* *really* obvious...) OK, you could sample the different accident rates annually for say 10 years (or look at historical data) to estimate an average and median accident rate, as well as estimate a standard deviation Yup, that's descriptive stats again, which is more or less how we were approaching the topic earlier in the discussion... and then do comparative statistical testing. ...And there's the inferential stuff, where you get your sampling issues, p values, statistical power and all that.. Even working which out which metric to use can be controversial, i.e. accident rate per km? per hours flown? per number of flights? Don't I know it! My PhD is on road safety. Let me count the ways that people have assessed accident numbers/rates over the years *sigh* You are talking about working out the power of a test. Working out statistical power is, as you say, a whole field of applied maths that keeps statisticians employed! ;-) Accident rates may be approximated by Poisson distributions because of their 'rare' nature. I've not seen them described that way in the road safety literature that I'm familiar with. How would that work? If the number of accidents is on the Y axis, what variable would the X axis have? If we go with road accidents (my field of expertise) it can't be age/driving experience, because the accident stats in NO way form a poisson distribution when age/experience is your X-axis variable. (Actually, road prangs by age/experience gives you more of a U-shaped curve.) Also, rate of accidents (be they road prangs or glider prangs) aren't constant over time (as required for a poisson distribution to be your distribution of choice) - they vary by time of day, for fairly obvious reasons, as well as other things (day of the week, long weekends, etc etc). You appear to be approaching the issue from a rather different statistical approach to the ones I'm familiar with. Could you spell out your approach/methods in more detail? It's always interesting to hear how folk in other fields approach problems I'm familiar with. :-) Teal ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
Thanks Teal, >Not actually true; the degree of difference between groups/cases/whatever that >you'll need to to get a statistically significant result (be it for p=.05 or >p=.01 or whatever) will depend on the sample size, and on the characteristics >of the sample and the population you're drawing the sample from. There is in >fact a whole sub-topic of stats that is about working out what size sample you >need for a given situation in order to be able to plausibly see any real >differences between groups, should there be a real difference to be found. When comparing accident rates, you are not sampling per se, but estimating the occurrence of an event in a selected population (i.e. descriptive statistics). Also for 'rare' events such as accidents, estimating the mean rate and standard deviations from year to year can show such variability that statistical testing becomes problematic. OK, you could sample the different accident rates annually for say 10 years (or look at historical data) to estimate an average and median accident rate, as well as estimate a standard deviation and then do comparative statistical testing. Even working which out which metric to use can be controversial, i.e. accident rate per km? per hours flown? per number of flights? You are talking about working out the power of a test. Working out statistical power is, as you say, a whole field of applied maths that keeps statisticians employed! ;-) Accident rates may be approximated by Poisson distributions because of their 'rare' nature. A binomial distribution may also be used, however a Poisson distribution becomes a limiting case of the binomial distribution. One could also use less assumptions about the underlying distribution of accident rates and use non-parametric or more robust measures. ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
Re: [Aus-soaring] Comparing accident rates
On 10/03/2016 5:05 PM, Texler, Michael wrote: It is always difficult to compare accidents rates for 'rare' events due to the wide 95% confidence intervals. http://www.evanmiller.org/ab-testing/poisson-means.html As mentioned by others, there often needs to be an order of magnitude difference (i.e. a 10 tenfold increase or decrease of an accident rate) to demonstrate statistical significance at the 95% level (this also means that there is a 5% chance of accepting a chance variation as being significant). Not actually true; the degree of difference between groups/cases/whatever that you'll need to to get a statistically significant result (be it for p=.05 or p=.01 or whatever) will depend on the sample size, and on the characteristics of the sample and the population you're drawing the sample from. There is in fact a whole sub-topic of stats that is about working out what size sample you need for a given situation in order to be able to plausibly see any real differences between groups, should there be a real difference to be found. It is not lies and damned statistics, but a 5% chance that the result is in error (using commonly accepted practice). See: https://en.wikipedia.org/wiki/Poisson_distribution Comments from statisticians welcome. I'm an experimental psychologist - not an actual full-time statistician, but I do play one on TV (if you know what I mean). Teal ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring
[Aus-soaring] Comparing accident rates
It is always difficult to compare accidents rates for 'rare' events due to the wide 95% confidence intervals. http://www.evanmiller.org/ab-testing/poisson-means.html As mentioned by others, there often needs to be an order of magnitude difference (i.e. a 10 tenfold increase or decrease of an accident rate) to demonstrate statistical significance at the 95% level (this also means that there is a 5% chance of accepting a chance variation as being significant). It is not lies and damned statistics, but a 5% chance that the result is in error (using commonly accepted practice). See: https://en.wikipedia.org/wiki/Poisson_distribution Comments from statisticians welcome. Mark Newton's comments about threat and error management are very useful! ___ Aus-soaring mailing list Aus-soaring@lists.base64.com.au http://lists.base64.com.au/listinfo/aus-soaring