Predictive Odds are Questionable

houghton_hunter said:
There are lies, damn lies, and statistics.

Just drew an Elk tag in CO with 10 points, that GOHUNTs predictive odds said was a 0% chance, as they say "based on our simulations we anticipate a 95% confidence level in our predictive odds". As a statistician myself I could have told you that this was silly, its based off of last years data, and really has no way of telling you about application behavior in response to policy changes, season date influence, people who believe in moon phases, as just some of the variables, despite running "simulations". Basically there is no way to know for sure, and without disclosing their model, I probably could have told them there predictions are going to be dead wrong if they only based it on "trends" and don't consider why those trends occur.

Anyone else beat the odds, if you will?
Click to expand...
@houghton_hunter - appears you are the only one here that beat the odds. "I guess you'll just have to keep beating yourself"

 
AZ_Hunter_2000 said:
Once I drew AZ Unit 10 early rifle bull elk with 2 points; at the time it took 19 points to get drawn.
Click to expand...
I have a family member that I used to joke was the luckiest person on earth. Dude drew all sorts of tags each year and some really good ones at that. He would always say "you got to play to win." I finally started playing and I have drawn two tags that should have been multiple digit points with low single digits points.

Like you said in your other post. I know people that are always trying to scheme a way to drawing tags. Pick the unit you want to hunt, apply for it and hope for the best. Since I started doing that, I am way farther ahead.
 
CorbLand said:
I have a family member that I used to joke was the luckiest person on earth. Dude drew all sorts of tags each year and some really good ones at that. He would always say "you got to play to win." I finally started playing and I have drawn two tags that should have been multiple digit points with low single digits points.

Like you said in your other post. I know people that are always trying to scheme a way to drawing tags. Pick the unit you want to hunt, apply for it and hope for the best. Since I started doing that, I am way farther ahead.
Click to expand...
That old lottery winner quote "got to be in it to win it" is true. I just spread things around to keep being able to hunt. Some years I get really lucky and others years not so much; but I'm hunting something no matter what every year.

I know that there are some things I will likely never draw, such as sheep and bison in AZ, but I'm not too concerned about gambling less than $30 each year to give it a shot. I am thankful that I already have a Goulds turkey from Mexico as I have mid-20s points for turkey in AZ and cannot draw a Goulds tag to save my life.
 
Bison and sheep , there are the grail for sure. Agreed you can't draw if you don't play the game. We all know guys who draw consistently with minimum points . Like the man said, "Luck of the draw".
 
AZ_Hunter_2000 said:
That old lottery winner quote "got to be in it to win it" is true. I just spread things around to keep being able to hunt. Some years I get really lucky and others years not so much; but I'm hunting something no matter what every year.

I know that there are some things I will likely never draw, such as sheep and bison in AZ, but I'm not too concerned about gambling less than $30 each year to give it a shot. I am thankful that I already have a Goulds turkey from Mexico as I have mid-20s points for turkey in AZ and cannot draw a Goulds tag to save my life.
Click to expand...
Same here. I spend the 15 bucks every year in AZ for sheep. You never know. That same family member has drawn both bison and sheep in AZ. His wife also drew a bison tag. Neither had max points. Far from it.
 
Yep, I personally know 2 guys who drew early bull rifle tags back to back and then drew again 2 years later. Go Figure.
 
The random portion of the draw (thinking AZ specifically here) really is a wild card. I shot a 3D tournament with a dude who drew early archery bull in a premium unit in AZ 3 years in a row. Ridiculously low odds of that happening.
 
Yep, makes no sense at times. Especially if your carrying 20-30 points.
 
I drew an early rifle bull tag this year in Az with only my loyalty and hunter Ed points. Id imagine the tag I drew would take 20-30 years, to be in the bonus point "guranteed" spot. Can't win if you don't play!!
 
HuntHarder said:
I drew an early rifle bull tag this year in Az with only my loyalty and hunter Ed points. Id imagine the tag I drew would take 20-30 years, to be in the bonus point "guranteed" spot. Can't win if you don't play!!
Click to expand...
I drew a late tag this year. Doing research many people were saying “I got lucky and drew x unit with 9-15 points.” I drew with 2.
 
houghton_hunter said:
There are lies, damn lies, and statistics.

Just drew an Elk tag in CO with 10 points, that GOHUNTs predictive odds said was a 0% chance, as they say "based on our simulations we anticipate a 95% confidence level in our predictive odds". As a statistician myself I could have told you that this was silly, its based off of last years data, and really has no way of telling you about application behavior in response to policy changes, season date influence, people who believe in moon phases, as just some of the variables, despite running "simulations". Basically there is no way to know for sure, and without disclosing their model, I probably could have told them there predictions are going to be dead wrong if they only based it on "trends" and don't consider why those trends occur.

Anyone else beat the odds, if you will?
Click to expand...
We anticipate a 95% confidence in our predictive odds, but only 2% that we will be correct.
 
They can pitch it however they want, but when we have 3-5 variables changing and new ones added every year, they’ll never be able to accurately predict how tens of thousands of different people will react.

And we don’t even know what actually happened in Colorado yet. I can’t wait to see the recap and find out how people really reacted to all the changes this year.
 
Fact is no one, not even the self proclaimed Rokslide math savants, knows if the predictive odds are accurate per their estimates until the actual results and data are published and can be analyzed.
 
Tilzbow said:
Fact is no one, not even the self proclaimed Rokslide math savants, knows if the predictive odds are accurate per their estimates until the actual results and data are published and can be analyzed.
Click to expand...

I can predict with 100% accuracy that people will complain about it though.

My AI also tells me they under-perform as hunters compared to those who don't complain.
 
IMG_1570.jpeg
Don’t underestimate luck. 🍀 Arizona nonresident desert bighorn sheep tag in 2022 with 13 points.

Apply, apply, apply…sooner or later, you will hit a premium tag!

Good luck and happy hunting to all, TheGrayRider a/k/a Tom.
 
everyone knew that Colorado was going to be a mess this year.

Most of us were smart enough not to bet our company’s reputation by flippantly throwing around the phrase “95% confidence interval”.

Clearly GoHunt doesn’t employ a real statistician who hunts and understands western draws. Because that person would have explained to management that they couldn’t move forward with this “predictive odds” product.
 
If onX hunt research could get the basics together, I kind of hope they will also throw their hat in the ring on predictive odds. Competition is generally good for the consumer.

Consistently predicting draw odds is likely not possible at scale, but having 2 companies in the industry throw resources at it will allow us to evaluate them against each other. At the very least that's an interesting thing to consider and discuss after the draws - even if it is just mostly marketing BS at the end of the day.

Maybe (?) one of the 2 will consistently be better at it.
 
You must log in or register to reply here.

Latest posts

Featured Video

Latest Articles

Back
Top