Reported impressive reduction in accidents due to ADS-B In

[PeterNSteinmetz]

I didn't read the report cover to cover. But I see now you're right, they did check for statistical significance. And you're wrong, there was none as far as mid-airs are concerned.

View attachment 73527

Good point about the mid-airs lacking statistical significance. That may be due to a change in a low rate being difficult to detect, thus a lack of power in this sample, as previously suggested. There is a non-significant trend in the direction of lower mid-airs caused by installing ADS-B.

Per the classic theory of hypothesis testing, the failure to find a significant result does not say there is absence of an effect, rather, it is just says there is no statistically significant evidence of an effect.

It is a puzzling pattern to the results I think though. The mechanism for ADS-B reducing mid-air accidents seems more plausible than some of the other categories. Possibly strange though the lack of power may explain that.

It would be nice to see the numbers of operations they are using for the denominators as well as their mechanism of correction for multiple comparisons. Perhaps a fuller report will deal with that.

 

[PeterNSteinmetz]

View attachment 73527

Do all 3 of the categories where there is a significant effect involve, directly or indirectly, weather?

Could it be the main significant effects are due to weather information being available to the pilot in the cockpit.

Or maybe even the CFIT is related to the presence of GPS position being displayed?

 

[Capt. Geoffrey Thorpe]

Is it plausible that having information about the location of other aircraft and weather in the cockpit helps pilots to avoid collisions and fatalities?

Yes.
But given that collisions are just a few percent of all accidents, what is not plausible is:

Initial report of 53% reduction in accidents overall and 89% reduction in fatal accidents with use of ADS-B In.

How does ADS-B in eliminate stall/spin which is about 20ish percent of all fatalities? Fuel management - on the order of 10ish percent?
Weather is up there with stall spin, but totally eliminating those gets you 20ish, not 89.

How do they come up with a "Overall reduction"? They don't. They come up with a reduction in accidents in very limited categories, not overall reductions.
Second, they did not acuually compare accidents rates between aircraft equipped with and without ADS-B. They just correlate the data against estimates of the fleet average ADS-B equipped rate over five years of data - hardly a case for causality...

Look at the pre-ADS-B accidents per year for Cessna 150's for an example of how much things can change over a few years that would be totally unrelated to any new technology:

 

[Ravioli]

what is not plausible is:

You clearly did not understand the outcome these datas were supposed to support.

Well, actually, you probably did,

 

[chemgeek]

Where are the p-values?

I'm guessing they would not pass muster for statistical significance.

It looks like the average proportion of ADS-B in equipage during the 5-year study period was about 5% while the average number of mid-airs per year was 0 for equipped and about 10 for non-equipped.

Some simple math, 5% (equipage rate) of 10 (number of non-equipped mid-airs) is less than 1 so how could you possibly draw a conclusion about whether or not ADS-B reduces mid-airs?

P-values won't tell the whole story. If implying causation from a particular factor it is important to control for covariant factors. For example, if ADS-B equipage correlates strongly with safety training or operational experience, one could attribute to one factor which is really due to another, highly correlated factor. There is also the problem of correcting for similar, alternate equipage: many ADS-B noncompliant aircraft have portable traffic and/or weather reception. I don't think this kind of control was attempted, and may not be easily achievable.

Having said that, I do suspect ADS-B confers significant safety advantages, but my inner skeptic doubts it it a 53% effect without strong, sound supporting data.

 

[dmspilot]

P-values won't tell the whole story. If implying causation from a particular factor it is important to control for covariant factors. For example, if ADS-B equipage correlates strongly with safety training or operational experience, one could attribute to one factor which is really due to another, highly correlated factor. There is also the problem of correcting for similar, alternate equipage: many ADS-B noncompliant aircraft have portable traffic and/or weather reception. I don't think this kind of control was attempted, and may not be easily achievable.

You're assuming I thought the p-value would reveal statistical significance but I suspected the opposite. If it's not statistically significant, which it isn't as far as mid airs are concerned, those other factors are not relevant.

 

[PeterNSteinmetz]

How do they come up with a "Overall reduction"? They don't. They come up with a reduction in accidents in very limited categories, not overall

Good question. They did not say how they are weighting this to make the overall claims as in the headlines.

Look at the pre-ADS-B accidents per year for Cessna 150's for an example of how much things can change over a few years that would be totally unrelated to any new technology:
View attachment 73528

There are a lot better statistical models they could have constructed, even with this dataset, to try and control for an overall trend, etc. Definitely not up to peer review standards at this point.

 

[dmspilot]

There is a non-significant trend in the direction of lower mid-airs caused by installing ADS-B.

What trend? You just agreed there is no statistically significant difference between the two populations, and then you say there's a trend of lower accidents in one? There is no evidence of that. You can't say there is a trend.

Per the classic theory of hypothesis testing, the failure to find a significant result does not say there is absence of an effect, rather, it is just says there is no statistically significant evidence of an effect.

What do you mean by "an effect"? There's no statistically significant difference between the two populations.

The mechanism for ADS-B reducing mid-air accidents seems more plausible than some of the other categories.

There is no statistically significant difference in the rate of mid-airs between ADS-B equipped and non-equipped aircraft. You can't infer or speculate from the data that ADS-B caused a reduction in mid-airs when there wasn't a reduction.

 

[chemgeek]

You're assuming I thought the p-value would reveal statistical significance but I suspected the opposite. If it's not statistically significant, which it isn't as far as mid airs are concerned, those other factors are not relevant.

True, and just because you do have a p-value <0.05 doesn't necessarily mean there is a correlation, much less causation. A p-value of 0.05 still means there is a 5% chance the correlation is entirely random. There is even a higher chance a p<0.05 correlation is meaningless if you go correlation-hunting, that is, looking for various things that correlate and then coming up with a hypothesis rather than the other way around.

 

[dmspilot]

True, and just because you do have a p-value <0.05 doesn't necessarily mean there is a correlation, much less causation. A p-value of 0.05 still means there is a 5% chance the correlation is entirely random. There is even a higher chance a p<0.05 correlation is meaningless if you go correlation-hunting, that is, looking for various things that correlate and then coming up with a hypothesis rather than the other way around.

I don't disagree with that. Just thought it might be doubtful there is even a correlation at all.

 

[EdFred]

I don't know about the rest of you "clowns" but if it costs 5,000 bucks to save my happy as*... That's a burden I'm going to bear all day long. Might it be a waste? Sure. I might die tomorrow, so why did I bother remodeling my kitchen? But how the hell can anyone argue that something that increases situational awareness is a bad thing?

What's the rate of mid airs and hitting other airplanes versus going off the runway or stalling/spinning or CFIT.

ADSB doesn't prevent any of those.

The S sure as hell doesn't stand for safety.

 

[kyleb]

If someone gave me a million bucks I'm not going to say it's stupid and refuse it because they didn't give me 10 million.

Here's the problem. You are paying $3-$7k or thereabouts for a device that is way down on the priority list to improve safety. Most light aircraft would get far more safety benefit from a $4k single axis autopilot than they will from ADS-B.

 

[EdFred]

You're right. If there was some gadget or doodad that was mandatory for that, I'd probably like it more than adsb. A midair is a low probability but high consequence event. May not happen often, but it's all bad when it does.

If someone gave me a million bucks I'm not going to say it's stupid and refuse it because they didn't give me 10 million.

There is. It's called recurrent training; you don't have to see your CFI every two years, you can see them more often.

 

[PeterNSteinmetz]

What trend? You just agreed there is no statistically significant difference between the two populations, and then you say there's a trend of lower accidents in one? There is no evidence of that. You can't say there is a trend.

This is a phrase often used in scientific discussion to mean that the averages go a certain way, but there is no significant difference. In this case, the average rate of mid-air collisions is lower for ADS-B equipped aircraft than for those without such equipment, though this difference is not statistically significant. It is not a statement which would normally be used in a publication but is often used in less formal discussions when trying to simply understand what the data are saying.

I think of the discussion here as such an informal discussion trying to understand the data, versus say a formal scientific presentation or debate trying to prove one person right or wrong.

What do you mean by "an effect"? There's no statistically significant difference between the two populations.

A statistically significant effect would be one where the presence or absence of ADS-B equipment, the independent factor, had an effect on the outcome, the likelihood of having a mid-air collision. A statistically significant effect is lacking here.

There is no statistically significant difference in the rate of mid-airs between ADS-B equipped and non-equipped aircraft. You can't infer or speculate from the data that ADS-B caused a reduction in mid-airs when there wasn't a reduction.

Actually, I don’t believe I ever stated there was statistically significant effect of ADS-B equipage on the rate of mid air collisions.

And yes, I think it is reasonable to speculate on possible causes and the reasons for possible lack of significance due to inadequate statistical power, provided that it is clearly labeled as such. That is how reasonable people proceed when they want to understand what the data mean in an objective manner. For example, such non-significant trends can indicate areas where further observations would be fruitful.

I would say overall there is some evidence here to suggest that mid-airs may be reduced by ADS-B, but that it is not convincing at this point. In a 3 alternative forced choice situation, in other words, if I had to pick between ADS-B reduces mid-air, or had no effect, or increased them, I would choose reduces. But the level of certainty on that point is certainly low enough that there is room for reasonable people to disagree. Further data could easily prove my choice to be wrong.

 

[PeterNSteinmetz]

Here's the problem. You are paying $3-$7k or thereabouts for a device that is way down on the priority list to improve safety. Most light aircraft would get far more safety benefit from a $4k single axis autopilot than they will from ADS-B.

This is an excellent point. Even if the statistics were to be born out by further study and analysis, does not imply it is a good use of funds for safety. Sadly, regulatory agencies often fail to perform this type of cost-benefit analysis. They tend to adopt an attitude of “our mission is safety, and we will always err on the side of safety, no matter the cost”.

 

[PeterNSteinmetz]

necessarily mean there is a correlation, much less causation. A p-value of 0.05 still means there is a 5% chance the correlation is entirely random. There is even a higher chance a p<0.05 correlation is meaningless if you go correlation-hunting, that is, looking for various things that correlate and then coming up with a hypothesis rather than the other way around.

Yes, this where they should have disclosed how they corrected for multiple comparisons. They also don’t give the actual p-values, which would permit better understanding.

The description of the methods suggests they classified the accidents and then tested each category separately, not omitting any, which would argue in favor of their results. So I don’t see any evidence of cherry picking the tests in their description. But it would be much better to see that issue explicitly addressed.

I gather this will be presented in more detail in September, so hopefully we will learn more then.

 

[dmspilot]

This is a phrase often used in scientific discussion to mean that the averages go a certain way, but there is no significant difference.

I didn't ask what the word "trend" means. I'm asking where you see a trend. I don't see any trends. Otherwise, I don't know what you're trying to say. Whether a correlation is statistically significant or not means the same thing whether the context is a scientific paper or an informal discussion. The word trend is an English word also means the same whether the discussion is scientific or informal.

The average rate of mid-air collisions is lower for ADS-B equipped aircraft than for those without such equipment, though this difference is not statistically significant.

This sentence is doubletalk. If the difference is not statistically significant, then there might as well be no difference.

A statistically significant effect would be one where the presence or absence of ADS-B equipment, the independent factor, had an effect on the outcome, the likelihood of having a mid-air collision. A statistically significant effect is lacking here.

No, you are jumping one step ahead. First you must determine if a correlation exists, then determine why or how. There is no correlation between ADS-B equipage or non-equipage and mid-air collisions. Therefore, you can't determine whether ADS-B affected the rate of mid-air collisions, when there is no discernible difference in the rate of collisions. You can't determine a cause for something that doesn't exist.

And yes, I think it is reasonable to speculate on possible causes and the reasons for possible lack of significance due to loss of power, provided that it is clearly labeled as such. That is how reasonable people proceed when they want to understand what the data mean in an objective manner.

You can speculate on the relationship between ADS-B and midair collisions all you want, but I thought this thread was about this particular study, which shows no difference between equipped and non-equipped. I am discussing the study, not ADS-B in general.

I would say overall there is some evidence here to suggest that mid-airs may be reduced by ADs-B, but that it is not convincing at this point.

What evidence is that? From the data in the study, there is literally zero evidence that ADS-B equipage affects the mid-air rate.

 

[WannFly]

There is. It's called recurrent training; you don't have to see your CFI every two years, you can see them more often.

No ones stopping any pilot going thru a recurrent training every 6 months, but that doesn’t help with another guy heads down looking at his iJunk ramming you from behind. ADSB does.

 

[Sundancer]

Mid-airs weren't significant before ADS-B; no surprise there was no effect on something so rare.

The rest of the categories look dubious to a degree, in connecting those results directly to ADS-B - methinks someone's agenda is showing. . .

 

[PeterNSteinmetz]

I'm asking where you see a trend. I don't see any trends.

Table 2 shows total of 0 mid-airs for aircraft equipped with ADS-B in. It also shows 49 mid-airs for non equipped aircraft.

Thus, Table 3 shows there is an observed decrease of the rate of mid-airs in ADS-B equipped aircraft.

That is a trend in the common use of the term. “
trend /trend/ noun 1. a general direction in which something is developing or changing.” though it is not significant in this dataset, and thus a “non-significant trend”.

 

[dmspilot]

Thus, Table 3 shows there is an observed decrease of the rate of mid-airs in non ADS-B equipped aircraft.

No, the table does not show that. The "Reduction in rate for ADS-B" is omitted for mid-airs, replaced with "NSS" for not statistically significant. Meaning there is no difference.

That is a trend in the common use of the term.
trend /trend/ noun 1. a general direction in which something is developing or changing.”

Again, I don't need another vocabulary lesson on the word "trend". I know what it means. A trend is something that occurs over time. We're comparing two populations against each other, not looking at what one population, sample, or variable does over time. The word trend therefore does not apply.

though it is not significant in this dataset, and thus a “non-significant trend”.

"Not significant" and "not statistically significant" are two different things and you keep using them interchangeably. They're not interchangeable. A difference between two samples or populations can be statistically significant while being practically insignificant. For example, a study could find that ADS-B increases the average distance by which near-misses occur by 1 inch. This could be statistically significant, but 1 inch is, practically speaking, non-significant.

Without statistical significance, there is no discernible difference between the two populations to speak of. It's not a non-significant difference. The populations are not different at all.

 

[RyanShort1]

No ones stopping any pilot going thru a recurrent training every 6 months, but that doesn’t help with another guy heads down looking at his iJunk ramming you from behind. ADSB does.

Actually, no it doesn't, unless you use it effectively. Pilots who think they see "everything" because they have ADS-B showing up on their iPad just might be more likely to hit a buzzard while staring at their iThingy than they were before... or they might not have the audio hooked up on their iJunk while messing with the throttle settings.

I'm finding I don't mind having the ADS-B out because of others, but I'm almost - almost to the point of selling off the Stratux we got and relying exclusively on the Mk 1 eyeballs again for myself... and yeah, a ton of us would be better off doing voluntary recurrent and mixed-up training sharpening skills twice a year.

 

[Mooney Fan]

lol at the ADS-B hate relative to traffic avoidance. My I-Pad is just another instrument (Tool) incorporated into my instrument scan. Ads 5 seconds to my scan. Outside the cockpit is the end of the scan. Then it’s back inside. It’s just a seamless loop. Wash, rinse, repeat. VFR flight has evolved beyond navigating by railroad tracks and water towers. Ok, OSH notwithstanding.

 

[EdFred]

lol at the ADS-B hate relative to traffic avoidance. My I-Pad is just another instrument (Tool) incorporated into my instrument scan. Ads 5 seconds to my scan. Outside the cockpit is the end of the scan. Then it’s back inside. It’s just a seamless loop. Wash, rinse, repeat. VFR flight has evolved beyond navigating by railroad tracks and water towers. Ok, OSH notwithstanding.

You completely missed the point of what we were saying.

 

[Matthew Rogers]

Here's the problem. You are paying $3-$7k or thereabouts for a device that is way down on the priority list to improve safety. Most light aircraft would get far more safety benefit from a $4k single axis autopilot than they will from ADS-B.

My ADSB-OUT install was only $1400 with the rebate (skybeacon) and ADSB-IN I had the year before for $130 with a Stratux. That is a lot less than $3k-$7k. Even before the ADSB-OUT mandate, the Stratux gave great weather, traffic, and GPS navigation.

One thing that may be overlooked is that ADSB IN devices are providing the impetus for many VFR planes and pilots to get GPS navigation. While not necessary, Having a “fool proof” navigation source certainly results in fewer people getting lost, overflying their airport and getting low on fuel, or otherwise task saturated.

 

[Capt. Geoffrey Thorpe]

One thing that may be overlooked is that ADSB IN devices are providing the impetus for many VFR planes and pilots to get GPS navigation. While not necessary, Having a “fool proof” navigation source certainly results in fewer people getting lost, overflying their airport and getting low on fuel, or otherwise task saturated.

One thing overlooked is that you can have GPS navigation without Automatic dependent surveillance—broadcast. Even this senile old coot has GPS moving map, MLOD on a tablet.

 

[Mooney Fan]

You completely missed the point of what we were saying.

OK, I'll listen slower this time

 

[chemgeek]

I have a distrust of statistics...how can you verify they are not skewed to reflect the agenda of the presenter ? Imagine how much better the statistics would improve if we all stopped flying...

You minimize bias by designing a study to control for factors not related to, but possibly inconveniently correlated with, the hypothesis being tested. There is no shortage of poorly constructed statistical studies, including many in the scientific literature. The best defense to such rot is thorough and thoughtful peer review, which doesn't always happen even in peer reviewed journals.

 

[Mooney Fan]

I have a distrust of statistics...how can you verify they are not skewed to reflect the agenda of the presenter ? Imagine how much better the statistics would improve if we all stopped flying...

True... There are even statistics for folks who drown in 3' feet of water. Everyone wants to bring outliers to the peak of the bell curve

 

[kyleb]

My ADSB-OUT install was only $1400 with the rebate (skybeacon) and ADSB-IN I had the year before for $130 with a Stratux. That is a lot less than $3k-$7k. Even before the ADSB-OUT mandate, the Stratux gave great weather, traffic, and GPS navigation.

One thing that may be overlooked is that ADSB IN devices are providing the impetus for many VFR planes and pilots to get GPS navigation. While not necessary, Having a “fool proof” navigation source certainly results in fewer people getting lost, overflying their airport and getting low on fuel, or otherwise task saturated.

What did the Avionics shop charge to install and setup the skybeacon?

Go stand at the FBO and ask the next 10 pilots who walk in what they are using for GPS. They will all have some sort of GPS, whether panel mounted, handheld, or a smartphone. The mandate is forcing many of those pilots to purchase another GPS which meets the spec's for ADSB.

 

[JOhnH]

I found it odd that in table 2, weather related accidents took a big jump in 2017 (some in 2016 too) even with the ADS-B equipped planes.

Yes, I do know that is a large reduction from non-equipped, but wondering why the increase all of a sudden for the equipped planes.

Perhaps people with (delayed) ADSB weather look at the picture as it was 15 minutes ago and think they can fly where that big red splotch isn't (wasn't) but is now.
I think that makes sense.

 

[PaulS]

Two words, fat tail. Can ruin your day at any time. Is ads-b responsible for a 50+ percent decrease in issues? Maybe, but even if it is 5% it's significant. It's another tool in the toolbox and should be treated as such.

Even worse is a black swan event, statisticians tend to ignore those events, generally to everyone's peril.

 

[Skyrys62]

Perhaps people with (delayed) ADSB weather look at the picture as it was 15 minutes ago and think they can fly where that big red splotch isn't (wasn't) but is now.
I think that makes sense.

Quite possible
Yet why the increase of weather related incidents from 2013,14,15, to 2016, then even more in 2017? All were equipped equally with ADSB.

Conversely, and oddly enough, there was also a decrease in 2017 of weather related incidents for non-equipped planes (compared to the earlier 4 years)

 

[PeterNSteinmetz]

No, the table does not show that. The "Reduction in rate for ADS-B" is omitted for mid-airs, replaced with "NSS" for not statistically significant. Meaning there is no difference.

Please see second and third columns from the left. First non label row. Rate for unequipped is 0.3. Rate for equipped is 0. Thus there is a reduction in the observed rates.

The fraction of reduction in the 4th column is replaced by NSS as noted to indicate the failure of the test to produce a statistically significant result. For the way they are computing the fractions, it would be 100%, but this is apparently how the authors chose to indicate their significance results. Not the clearest way to do so. Normally in scientific papers all the fractions would be given and the significant ones marked with a separate symbol or the actual p-values from the tests would be given in a separate column or in parentheses.

A trend is something that occurs over time. We're comparing two populations against each other, not looking at what one population, sample, or variable does over time.

In the discussions I have been in, in the context of discussion of possible effects of independent variables, it can also refer the effect on a putative dependent variable of an independent variable as it changes in a particular direction, such as an increase or decrease. Sort of a generalization of time as the independent variable. But I would agree that is a bit different than daily usage and is a shorthand.

"Not significant" and "not statistically significant" are two different things and you keep using them interchangeably.

Again a shorthand. In this case we have been discussing primarily statistical significance and I had assumed it was clear from context.

But in any case, if the difference is true, namely a 100% reduction in the rate of mid-airs, I think most people would regard that as important or significant, in the non-statistical sense.

Now some might argue that given the relative infrequency of mid-airs that this is still not practically that important or significant, not worth the cost, etc. Good points for discussion but beyond the questions regarding the statistical interpretation of the data in this report.

 

[Groundpounder]

What the didn't track was the number of times someone would log into ads-b exchange, see that you are flying, look up your address that is listed to your aircraft reg, then go to your house and rape your dogs. I bet there has been a YUUUUUGE increase in dog rape since ADS-B has come into existence. And what about The Man being able to track you, and then send black helicopters to circle your house? We need a study to track the amount of times The Man tracks you and sends helicopters. I bet the helicopters have ADS-B!!! See, its all a conspiracy!!! AHHHHHH!!!!!!!!!!!!!

 

[dmspilot]

But in any case, if the difference is true, namely a 100% reduction in the rate of mid-airs, I think most people would regard that as important or significant, in the non-statistical sense.

Any perceived reduction is due to the much smaller population of ADS-B equipped aircraft and random chance. That's what statistically insignificant means. The "reduction" is an illusion. It doesn't exist. So stop referring to a phenomenon that doesn't exist in the given data set as a "important or significant 100% reduction".

Again, if ADS-B correlated with a reduction in mid-airs, we would want to ask why. But there is no correlation to speak of.

 

[ElPaso Pilot]

... but that doesn’t help with another guy heads down looking at his iJunk ramming you from behind. ADSB does.

Ummm, while your heads-down watching him on your ADS-B iJunk??

 

[Skyrys62]

Well.... I know a fairly crappy pilot. If I can see when/where he's flying, I don't fly there.

See, ADSB is safer. Case closed.
Who needs stupid studies...

 

[PeterNSteinmetz]

Any perceived reduction is due to the much smaller population of ADS-B equipped aircraft and random chance. That's what statistically insignificant means.

This is where the question of the meaning of a failure to reject the null hypothesis enters in. In the classic interpretation of hypothesis testing, that is all it is, a failure to reject. One is not supposed to ascribe meaning to that per se.

The failure to find a statistically significant difference (SSD) can be caused by at least two things. Either the observations are due to random chance or there is simply not enough power (enough observations) to detect a difference. Either one may be true.

So I would contend that it is not correct to assert that it is necessarily due to random chance, as stated above, when the other alternative, low power, is a real possibility.

To understand this distinction a bit more, consider the case where there is no data at all. Clearly there will be no SSD. Does that mean there is no difference? Or that there can’t be one? Or that it is nonsense to discuss the possible existence of one? The best explanation in such a case is that there is no data.

Similarly in this case. Given the low rates of mid-airs, there may not be enough data to detect these small differences. Given there are two possible explanations for a failure to obtain an SSD, I don’t think it is reasonable to assume it it is due to no actual difference, especially since estimation theory tells us that the best estimate of the rates, given this data, is that it is 0.3 for unequipped and 0.0 for equipped.

One way to resolve this would be to compute the power of the test to detect a change in the rate of mid-airs, given the sample size. If that power is high, I would then agree that it becomes more likely there is no real difference. The study may have been poorly designed in that it has low power to detect an SSD given the low rate of mid-airs. I suspect that is what happened here, but since the denominator numbers are not given, it is not possible to compute the power. The estimated difference in rate is low enough and the likely number of operations is high enough that my intuition is not very good, the power could go either way. Really would have to be computed. The numbers could be found in the references if one is sufficiently interested in arguing that point.

Practically speaking we should be suspect that there is a real difference here, given the lack of a statistically significant difference, but if we want to understand the effect of ADS-B equipment on mid-airs more clearly, it may be fruitful to collect more data.

 

[dmspilot]

This is where the question of the meaning of a failure to reject the null hypothesis enters in. In the classic interpretation of hypothesis testing, that is all it is, a failure to reject. One is not supposed to ascribe meaning to that per se.

Yet that's exactly what you're doing — ascribing meaning to a non-statistically significant correlation (which is an oxymoron, there is no such thing) between ADS-B and mid-airs.

The failure to find a statistically significant difference can be caused by at least two things. Either the observations are due to random chance or there is simply not enough power (enough observations) to detect a difference. Either one may be true.

I did not mean to ascribe cause but to make a point about statistics. The difference between the populations is indistinguishable from random chance. But you keep insisting there is a difference. There isn't.

I don’t think it is reasonable to assume it it is due to no actual difference

I am not assuming there is no "actual" difference—and I'm not sure what you mean by actual. Fact, the mid-air rate between the two populations is indistinguishable from random chance. Fact, not assumption.

Practically speaking we should be suspect that there is a real difference here, given the lack of a statistically significant difference, but if we want to understand the effect of ADS-B equipment on mid-airs more clearly, it may be fruitful to collect more data.

Again, you are calling the kettle black here. You are ascribing meaning to a non-statistically significant result.

Now, where you might be confused is that you think I'm trying to say that ADS-B has no effect on mid-air collisions in general, or that it won't several years from now. But I'm not saying that. I'm talking about the data in THIS study, the one you started the thread about. The data show no effect.