(08-25-2022 05:52 PM)Yosef181 Wrote:  

(08-25-2022 04:59 PM)bullet Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

Read the article. You might then understand. As pointed out above, if you use Vanderbilt's 2 data points in 2018, they average better than Miami (FL) does on their 11. All schools have declining curves on their ratings as shown in Miami's curve earlier in the thread.

I read the article. Are you reading my replies? Analyzing a larger dataset gives a clearer picture of what's actually happening. That's what I've been saying this entire time. The findings are more accurate when you use the entire dataset (all 8 years, or all 37 ECU games), not just the records you want to use (only 2018, only the top 27 ECU games).

Based on the complete dataset, Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).

So then you don't understand what the author is saying. What you are saying is true and it is also meaningless.

bullet, I don't know how else to explain sample size and averages to you if you don't understand it by now. It's starting to feel like you're just trolling. I recommend reading e-parade's response near the bottom of Page 2 of this thread if you want further explanation. I can only go back-and-forth with a brick wall for so long.

(08-25-2022 05:53 PM)e-parade Wrote:  

(08-25-2022 04:59 PM)bullet Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

Read the article. You might then understand. As pointed out above, if you use Vanderbilt's 2 data points in 2018, they average better than Miami (FL) does on their 11. All schools have declining curves on their ratings as shown in Miami's curve earlier in the thread.

Of course they do, the curves are showing the games in order of highest viewership to lowest. It's impossible to show anything BUT a decline. The assumption you're making is that the more games you add the lower the viewership becomes, but that's not correct. That would be the case if all the games were in the same season and you plotted them by order of when they happened and it showed a decline, but that's not at all what the data is doing. Dates are irrelevant and it's simply most to least. Ohio State could have a game tomorrow that's their highest rated game. More likely it'll fall somewhere in the middle of their curve though, but it's not a case where adding an additional game will make the curve decline more.

The issue here is that what you're doing is assuming that an additional 10 games for App State would be at the end of the curve as opposed to in the middle of the curve, or even at the beginning of the curve (meaning: any 10 additional games could be their highest viewed one, their lowest viewed one, or somewhere else in the middle).

This is statistical analysis, and therefore you need decent sample sizes to extrapolate what games outside of the given data set will look like. A sample of 2 is not big enough (same with a sample of 6 from my own UMass). A sample of 27 compared to a sample of 37 is much more reasonable. It's not perfect, yeah, but it does a pretty good job at showing a trend.

He is completely correct that you can't just take the lowest 10 and remove them from the East Carolina dataset for a comparison. What you would need to do is randomly remove 10 of them if you want the same number of games to compare against. It should end up showing about what the average is showing now because of how probability works, but it could also make the average higher or lower (but it won't change much if it was truly randomly selected).

The point is that the better games are on rated TV channels. The lesser games are on conference networks or streaming. In a conference like the Big 12, schools usually have 9 games on measured channels. In the ACC, it might be 6 because 3 games will be on the unrated ACC network. So a school like Baylor would have its worst games on FS1 and get really low ratings and be measured on that. An ACC school wouldn't have its 3 worst games rated. So it is not logical to think the unrated games would equal the rated games.

Now if you had a school that only played one season in FBS vs. one that played 8, that could skew their results as you suggest. But when all are dealing with the same time frame, they all have that same decline. The article has the charts on every school. Every school has a decline. Most look very, very similar, just that an Ohio St. starts higher and ends higher than an Oregon St.

(08-24-2022 07:10 PM)10thMountain Wrote:  Which just goes to show the B12 needs to be very afraid of their next contract without OU and UT

Based on those numbers I'd say that OU will be a lot harder for them to replace than texas.

(08-25-2022 06:13 PM)Yosef181 Wrote:  bullet, I don't know how else to explain sample size and averages to you if you don't understand it by now. It's starting to feel like you're just trolling. I recommend reading e-parade's response near the bottom of Page 2 of this thread if you want further explanation. I can only go back-and-forth with a brick wall for so long.

That's because YOU are the brick wall.

We aren't going to convince each other.

(08-25-2022 06:18 PM)bullet Wrote:  

(08-25-2022 06:13 PM)Yosef181 Wrote:  bullet, I don't know how else to explain sample size and averages to you if you don't understand it by now. It's starting to feel like you're just trolling. I recommend reading e-parade's response near the bottom of Page 2 of this thread if you want further explanation. I can only go back-and-forth with a brick wall for so long.

That's because YOU are the brick wall.

We aren't going to convince each other.

I agree with you on us not being able to convince each other. It's all in good fun, but I could use a drink after that.

(08-25-2022 10:33 AM)1845 Bear Wrote:  

(08-24-2022 05:50 PM)e-parade Wrote:  Didn't expect to see UMass on here, with our 6 games and 0.468 million viewers. Very small sample size for sure, but somehow not the worst - really goes to show how few people actually have access to see a lot of the CUSA games and such.

CUSA is basically invisible unless you have CBS College Sports on your cable (not consistently there across providers in my experience)

The rest of the games you tend to have to hunt for online. BU at UTSA 2018 was on Facebook!

What's up with UTSA? First they don't let Tech steal their coach, now on the radio last night they were predicting 30-40k fans for a game next week against #24 UH. I remember when UTSA didn't even have football, now they're all growed up!

(08-25-2022 12:40 PM)Yosef181 Wrote:  

(08-25-2022 12:32 PM)1845 Bear Wrote:  

(08-25-2022 12:26 PM)Yosef181 Wrote:  

(08-25-2022 12:22 PM)1845 Bear Wrote:  

(08-25-2022 11:43 AM)Yosef181 Wrote:  You're talking about unknown data though, which we can't do anything with besides speculate. Based on the data we have, Appalachian State averages more viewers than East Carolina.

App State has 27 games averaging 587k.

ECU has 37 averaging 546.

It's unlikely App State would have averaged enough on the next ten to be higher on a 37 game sample.

ECU's top 27 average 707k but albeit against a much better opposing schedule.

Why not? You don't know that. No one does, because that data doesn't exist.

It's easy to make an educated guess when the worst AppSt games averaged in the low 100k range. Besides the top 27 average we do have data for and it's not close.

That's all it is, a speculative guess. Not only that, but a guess which isn't based on fact.

The actual, real conclusion, based on real data: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).

You, my friend, are clearly going for the "There's lies, there's damn lies, and there's Statistics" award. Bravo!

(08-25-2022 05:53 PM)e-parade Wrote:  

(08-25-2022 04:59 PM)bullet Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

Read the article. You might then understand. As pointed out above, if you use Vanderbilt's 2 data points in 2018, they average better than Miami (FL) does on their 11. All schools have declining curves on their ratings as shown in Miami's curve earlier in the thread.

Of course they do, the curves are showing the games in order of highest viewership to lowest. It's impossible to show anything BUT a decline. The assumption you're making is that the more games you add the lower the viewership becomes, but that's not correct. That would be the case if all the games were in the same season and you plotted them by order of when they happened and it showed a decline, but that's not at all what the data is doing. Dates are irrelevant and it's simply most to least. Ohio State could have a game tomorrow that's their highest rated game. More likely it'll fall somewhere in the middle of their curve though, but it's not a case where adding an additional game will make the curve decline more.

The issue here is that what you're doing is assuming that an additional 10 games for App State would be at the end of the curve as opposed to in the middle of the curve, or even at the beginning of the curve (meaning: any 10 additional games could be their highest viewed one, their lowest viewed one, or somewhere else in the middle).

This is statistical analysis, and therefore you need decent sample sizes to extrapolate what games outside of the given data set will look like. A sample of 2 is not big enough (same with a sample of 6 from my own UMass). A sample of 27 compared to a sample of 37 is much more reasonable. It's not perfect, yeah, but it does a pretty good job at showing a trend.

He is completely correct that you can't just take the lowest 10 and remove them from the East Carolina dataset for a comparison. What you would need to do is randomly remove 10 of them if you want the same number of games to compare against. It should end up showing about what the average is showing now because of how probability works, but it could also make the average higher or lower (but it won't change much if it was truly randomly selected).

Actually that is incorrect. One school only had 27 games that were broadcast at all, the other had 37. You would have to look at the next 10 best games from the 27 member school, you could either make an educated guess on those, use 0, or just take top 27 from both of them to compare.

Yosef is biased b/c he went to one of the schools. I don't blame him for it, I was trying to figure out a way to get A&M ahead of bama, or at least Auburn or LSU, but I couldn't abuse the numbers coherently enough to make it work.

(08-25-2022 06:53 PM)bryanw1995 Wrote:  

(08-25-2022 05:53 PM)e-parade Wrote:  

(08-25-2022 04:59 PM)bullet Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

Read the article. You might then understand. As pointed out above, if you use Vanderbilt's 2 data points in 2018, they average better than Miami (FL) does on their 11. All schools have declining curves on their ratings as shown in Miami's curve earlier in the thread.

Of course they do, the curves are showing the games in order of highest viewership to lowest. It's impossible to show anything BUT a decline. The assumption you're making is that the more games you add the lower the viewership becomes, but that's not correct. That would be the case if all the games were in the same season and you plotted them by order of when they happened and it showed a decline, but that's not at all what the data is doing. Dates are irrelevant and it's simply most to least. Ohio State could have a game tomorrow that's their highest rated game. More likely it'll fall somewhere in the middle of their curve though, but it's not a case where adding an additional game will make the curve decline more.

The issue here is that what you're doing is assuming that an additional 10 games for App State would be at the end of the curve as opposed to in the middle of the curve, or even at the beginning of the curve (meaning: any 10 additional games could be their highest viewed one, their lowest viewed one, or somewhere else in the middle).

This is statistical analysis, and therefore you need decent sample sizes to extrapolate what games outside of the given data set will look like. A sample of 2 is not big enough (same with a sample of 6 from my own UMass). A sample of 27 compared to a sample of 37 is much more reasonable. It's not perfect, yeah, but it does a pretty good job at showing a trend.

He is completely correct that you can't just take the lowest 10 and remove them from the East Carolina dataset for a comparison. What you would need to do is randomly remove 10 of them if you want the same number of games to compare against. It should end up showing about what the average is showing now because of how probability works, but it could also make the average higher or lower (but it won't change much if it was truly randomly selected).

Actually that is incorrect. One school only had 27 games that were broadcast at all, the other had 37. You would have to look at the next 10 best games from the 27 member school, you could either make an educated guess on those, use 0, or just take top 27 from both of them to compare.

Yosef is biased b/c he went to one of the schools. I don't blame him for it, I was trying to figure out a way to get A&M ahead of bama, or at least Auburn or LSU, but I couldn't abuse the numbers coherently enough to make it work.

That's not how statistics or ratings work. If one has a sample size of 27 because only 27 games were aired, then you cannot simply create additional games with 0 ratings. If there were no additional games that could be counted then it's your full data set.

Edit here: also, the "educated guess" you'd use for the next 10 games would be the average of the previous 27 games. It's the only reasonable educated guess you could use because the expectation is you'd perform at your average over the long run.

You can't take a TV show that has 10 episode seasons and compare it to a 14 episode season by saying "one of them had only 10 episodes, so we average in 4 0s to compare which did better" nor can you say "we compare only the top 10 to the entire 10." If the 10 episode show averaged 1.5 million viewers per episode and the 14 episode show averaged 1.3 per episode, then the 10 episode show had better average ratings than the 14 episode one. The expectation is that those ratings would continue at the average moving forward.

Now you can say the total viewership was better for the one with more episodes, but there was also extra cost to producing those extra episodes. The bang for your buck is better with the one that had higher average ratings for 10 episodes.

And don't come back talking about ratings declining through the season and say it's the same for these games. That's not what the charts are showing for the games. Their data points are not in order of when they happened.

You also cannot simply remove the bottom 10 from the other for comparison purposes because, as I said before, this isn't a scenario when you add more games it results in lower ratings. The curve isn't declining further because there are additional games. It's declining because they're ordering it from best performance to worst performance. If you remove the bottom 10, you're no longer calculating an average of an entire portfolio, you're calculating an average of the highest performing parts of your portfolio.

If you want to compare top 10 to top 10, then that's one thing. But you also have to present it as an average of just the top 10s.


Two things can be true here:
1) App State had better average viewership across its complete portfolio of aired games.
2) ECU had better total viewership across its complete portfolio of games.


With the original statement being about averages, that's it. The statement was correct. There's no "truing up the data" to adjust for it. The data is the data. There's enough data from both schools for it to be a reasonably calculated average.

ECU had more eyeballs across all of their games. App state had more average eyeballs watching their games.

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  

(08-25-2022 02:09 PM)bullet Wrote:  

(08-25-2022 01:17 PM)Yosef181 Wrote:  That's extremely biased, because you're choosing which of ECU's 27 games to use.

You're choosing to look at ECU's 27 best games instead of all 37. In order to gain a more accurate and truthful representation of any dataset, you can't ignore the 10 records you don't like.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).

Read the article. Look at the graphs. There's a clear dropoff for even Alabama and Ohio St. the more games you add.

Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

You are the one trying to only sample the games you like and you accuse the author of it? Laughable.


The reality of this data set is that with VERY rare exception the worst games get the worst networks and the best games get chosen for better spots. It’s overwhelming and it’s constant since the schools and the networks benefit more from broadcasting the most attractive matchups and placing the weaker games on PPV or subscription channels to squeeze some money out of them.


Which 10 app state games that didn’t get broadcast on a nationally rated network do you think would have a chance to get above ASU’s average? The odds are VERY small. You’ve got games Vs FCS schools like Elon and whoever is among the weakest conference games that fall to espn+ most years. This is true for basically all the schools.

(08-25-2022 06:02 PM)bryanw1995 Wrote:  It was shocking to me to see how close OSU was to texas. And sure OSU has been better on the field since 2013, but not that much better. 6 top 25 finishes vs 3 for texas, with only 1 top 10 between the 2 of them.

Each has a spotlight game vs OU. However only one elevated their other league games in November since UT typically lost at least once in noncon and OU or more by mid October many of these years and OSU had 2-3 major seasons and missed no bowls since 2005.

National & conference implications during the league slate were higher for the pokes.

(08-25-2022 10:21 PM)1845 Bear Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  

(08-25-2022 02:09 PM)bullet Wrote:  Read the article. Look at the graphs. There's a clear dropoff for even Alabama and Ohio St. the more games you add.

Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

You are the one trying to only sample the games you like and you accuse the author of it? Laughable.


The reality of this data set is that with VERY rare exception the worst games get the worst networks and the best games get chosen for better spots. It’s overwhelming and it’s constant since the schools and the networks benefit more from broadcasting the most attractive matchups and placing the weaker games on PPV or subscription channels to squeeze some money out of them.


Which 10 app state games that didn’t get broadcast on a nationally rated network do you think would have a chance to get above ASU’s average? The odds are VERY small. You’ve got games Vs FCS schools like Elon and whoever is among the weakest conference games that fall to espn+ most years. This is true for basically all the schools.

Man, if you would actually read any of my 18,000 replies on this thread, you know that I'm using the entire dataset. I'm not leaving anything out. I'm talking about real statistics, and you want to argue with pure speculation. If you want to know what my response is to what you just wrote, read my previous replies. It's already been addressed.

I was over this thread hours ago, and I'm not hoping back in.

Solid numbers for Memphis. Hopefully we get our football seasons back on track soon.

(08-25-2022 12:26 PM)Yosef181 Wrote:  

(08-25-2022 12:22 PM)1845 Bear Wrote:  

(08-25-2022 11:43 AM)Yosef181 Wrote:  

(08-24-2022 08:26 PM)1845 Bear Wrote:  

(08-24-2022 07:47 PM)Yosef181 Wrote:  Woah, Appalachian State averages more viewers than East Carolina.

Technically yes but it’s another example of the Vandy/Miami available data being misleading. It’s a narrow edge for App St but it’s also comparing ten fewer games. It’s not realistic to assume App would average enough over the next ten if we had the data for those games so ECU is likely ahead. Also ECU’s number goes up if you take the average of ten fewer games to even it out with App’s sample.

You're talking about unknown data though, which we can't do anything with besides speculate. Based on the data we have, Appalachian State averages more viewers than East Carolina.

App State has 27 games averaging 587k.

ECU has 37 averaging 546.

It's unlikely App State would have averaged enough on the next ten to be higher on a 37 game sample.

ECU's top 27 average 707k but albeit against a much better opposing schedule.

Why not? You don't know that. No one does, because that data doesn't exist.

Gotta go with Yosef on this one!!!

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  

(08-25-2022 02:09 PM)bullet Wrote:  

(08-25-2022 01:17 PM)Yosef181 Wrote:  That's extremely biased, because you're choosing which of ECU's 27 games to use.

You're choosing to look at ECU's 27 best games instead of all 37. In order to gain a more accurate and truthful representation of any dataset, you can't ignore the 10 records you don't like.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).

Read the article. Look at the graphs. There's a clear dropoff for even Alabama and Ohio St. the more games you add.

Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

Arrgghh. This whole debate shows exactly why I can't stand using averages!!!!!!!!
I would rather see the median number of viewers for both App and ECU. And I have zero dawg in this fight other being a UGA Dawg fan. Tech can be fart smellers, lol

(08-25-2022 11:08 PM)Yosef181 Wrote:  

(08-25-2022 10:21 PM)1845 Bear Wrote:  

(08-25-2022 02:40 PM)Yosef181 Wrote:  

(08-25-2022 02:28 PM)bullet Wrote:  

(08-25-2022 02:19 PM)Yosef181 Wrote:  Do you not understand how "Average" is calculated?

Do you not understand the concept of "lies, damn lies and statistics?" You clearly don't understand the article and may not have even read it. Taking one school's best 27 games and comparing it to someone else's 37 games gives you a meaningless result.

There's no "27 best games" against "someone else's 37". One school has 27 data records. Another has 37 data records. That's the complete dataset. It's beyond ridiculous to assume that if you added 10 App games, they would automatically be the 10 lowest App games. That's speculation, and has no basis in the reality of this dataset.

Data "lies" when bias and tampering is introduced. One example of that is to intentionally leave out 10 records you don't like. One way to lessen the effect of bias and tampering is to look at the most complete dataset possible.

The actual, real conclusion, based on the complete dataset: Appalachian State averages more viewers (0.587mm) than East Carolina (0.547mm).


Could that change if more App games were on TV? The only way to find out is to put more App games on TV.

You are the one trying to only sample the games you like and you accuse the author of it? Laughable.


The reality of this data set is that with VERY rare exception the worst games get the worst networks and the best games get chosen for better spots. It’s overwhelming and it’s constant since the schools and the networks benefit more from broadcasting the most attractive matchups and placing the weaker games on PPV or subscription channels to squeeze some money out of them.


Which 10 app state games that didn’t get broadcast on a nationally rated network do you think would have a chance to get above ASU’s average? The odds are VERY small. You’ve got games Vs FCS schools like Elon and whoever is among the weakest conference games that fall to espn+ most years. This is true for basically all the schools.

Man, if you would actually read any of my 18,000 replies on this thread, you know that I'm using the entire dataset. I'm not leaving anything out. I'm talking about real statistics, and you want to argue with pure speculation. If you want to know what my response is to what you just wrote, read my previous replies. It's already been addressed.

I was over this thread hours ago, and I'm not hoping back in.

Yosef181's Rule: Whatever favors App State

Have fun claiming Vandy averaged more than Miami because "pure speculation" despite everyone knowing the reality of what the remaining games are.




App State has a lower average at every interval of equally sampled games,
Top 1
Top 2 average
Top 3 average
all the way through top 27 and even their top 34 is higher than App's top 27. Unless there's some big matchup you think would get 600k plus that didn't get broadcast there really isnt any reason to believe that App's top 37 would win out.