Question for Valiantman (& anyone statistically minded)

[JohnBull]

You're the MAN, Valiantman!!! I had no idea that all I had to do was ask.

 

 

Yay ! He is too !

 

[CentaurMan]

Sounds a bit of a Catch-22 if the only way you can ever get to find & buy the books is to firstly dramatically increase their value

 

This is exactly why I consider Centaurs so much FUN to collect. The scarcity is painful, but the prices right now are very reasonable. I have a very good Golden Age collection (including Detective Comics #1, Adventure Comics #40, All-American Comics #16, etc), but the pleasure of finding a 'Tec #1 is greatly mitigated by the pain in paying $10,000 for it. In many, many ways, Centaurs are the emotional highlight of my current collection.

 

With Centaurs, the pleasure of finding an early issue of Funny Pictures Stories is in fact magnified by the fact that it'll only cost you a couple hundred bucks, at most. I think this must be how it felt to collect the pre-Batman Detective Comics 15-20 years ago, before the pricing got way out of whack. Collecting genuinely scarce, historically significant comics at prices that don't force you to lie to your wife. ("So how much was THAT one?" "uhhh.....$300......and I'll cook dinner tonight, ok?")

[ghoulaid]

I enjoy collecting the obscure Golden Age comics for the very reason you mention. They are hard enough to find to present a challenge but much more affordable to me than going after DCs or Timelys (my favorite). In that way I've managed to acquire a fair collection of oddball items (Hyper Mystery#1 and near complete Speed Comics for example).

 

I would guess any low census numbers reflect the fact that those types of books are in collections that won't be sold soon, so no need to grade them. I've got some books that no one has yet submitted for grading. It would be nice to submit some books and have the "highest graded copy" but since I'm not selling, I'd rather keep it to myself.

[Aman619]

I just tried your new button...and gaain, truly amazing.

you rule!

[Aman619]

Greg,,, while youre tweaking, I ve got a few stylistic issues Id like you to address if you would.

 

Many comic titles (far lest column) get bumped to 2 and 3 lines deep. which limits the number of issues we see on a screen. Can you pick a wider width that would only rerag on the LONGEST titles?? Right now, Tales of Suspense didnt fit on one line.

 

Another side effect: the grade bars you inserted every 30 or so comics is great, BUT, can you write it to appear every 30 lines? I still dont get at least ONE line of grades per screen as is. Im on a 17" iMac set to a very small resolution. that is, Im seeing a lot of nfp per screen but STILL not enough.

 

thanx.

[valiantman]

Many comic titles (far lest column) get bumped to 2 and 3 lines deep. which limits the number of issues we see on a screen. Can you pick a wider width that would only rerag on the LONGEST titles??

I made changes that should help with this problem. Example for: Tales of Suspense

 

Another side effect: the grade bars you inserted every 30 or so comics is great, BUT, can you write it to appear every 30 lines?

In addition to the change I made above, which should help,

I've changed it to have the grade bar appear every 20 comics.

[Aces]

You are down to 3 stars!?

 

 

edit:

I just 5'd you and your still 3.

Someone else will have to help too.

[Aman619]

well there you go again! made it even better!

Does anyone still actually still use the ACTUAL CGC census site anymore when this is so much more thorough a look at the numbers?

[goldust40]

You are down to 3 stars!?

 

 

edit:

I just 5'd you and your still 3.

Someone else will have to help too.

 

Taken care of. Nice work.

[valiantman]

well there you go again! made it even better!

Does anyone still actually still use the ACTUAL CGC census site anymore when this is so much more thorough a look at the numbers?

Well, I know I use it... to build the database!

But seriously, you will need the CGC census site to find the numbers

for restored, qualified, and signature series grades.

...and until I can figure out how... you'll need it to find CGC graded magazines!

[lou_fine]

As an aside, this is where it would be most useful for CGC to include pedigree info in their survey. I can see that there's a 9.0 copy of Detective Picture Stories #5 from 1937, for example, and I'm really curious if that's Church, Larson, or just a random well-preserved comic. If it's not Church, then I also know that there's likely another 9.0 out there, unslabbed, from the Mile High collection, which increases my knowledge base on high grade scarcity of these early issues.

 

Another example: Right now, if the highest grade of an issue is 6.5, I see that 6.5 and think to myself that there's a hidden 9.0 somewhere because the Mile High owner has chosen not to slab his book. If the CGC survey were to say that actually that 6.5 is the Church copy, then I have a really good sense as to just how rare the highest grades will be.

 

 

I am in total agreement with you here. Pedigree information for early GA books would be absolutely invaluable information in providing collectors with a measuring stick for the estimated number of "high grade" copies in existence.

 

BTW, how hard is it to find early issues of Funny Picture Stories? What kind of pedigree copies are out there, and would you know the condition range that they are in? Just curious since I have a few of the early issues.

[CentaurMan]

how hard is it to find early issues of Funny Picture Stories?

 

It's scarce top to bottom, but I'd say it gets easier to find around the middle of Volume 2. Volume 1 books are extremely rare.

 

What kind of pedigree copies are out there, and would you know the condition range that they are in?

 

I don't know. I have the Larson copy of Detective Picture Stories #5 in 8.0, and I have the Church copy of Keen Detective Funnies V2#8 in 9.0. I suspect that the occasional copy of Funny Picture Stories that's been slabbed north of 6.5 is probably Larson or Mile High. But honestly, the pedigree copies very rarely ever hit the marketplace.

 

There are 41 pedigree transactions involving Centaurs in the Heritage database. Mostly Mile Highs, some Larsons, with the occasional Rockford, Cosmic Aeroplane, and Denver pedigree thrown in. Not one involved an issue of Funny Picture Stories.

 

PM me if you're looking for a bid on any of those comics, if you didn't already know to do that.

[underthebigw]

i) How many submissions do you think is the minimum needed in order to get a meaningful result of such analysis ? ...I'm looking for something that is in the order of 95% accurate (...accurate to within plus or minus 5%). My gut feeling is that about 50 submissions are needed.

I'm not a statistician, but I am dangerous with stats from time to time...

According to this "Sample Size Calculator" that I found online...

You need about 375 total examples if you're looking for numbers

that are 95% confidence with a +/- 5% interval for the results.

(Set confidence level to 95%, confidence interval to '5', and population

to the number of books estimated to be in existence (or the print run)...

anywhere from 1,000 to 10,000,000... the result is always between 275 and 385.)

Sample Size Calculator

Note: This system assumes a RANDOM sample is being selected.

Since people don't generally submit their books at random,

because they will usually submit their best copy as opposed to "any" copy...

the universe is NOT truly random... but it is fairly consistent because

everyone generally follows that same rule.

Additionally, it should be noted that you requested 95% confidence in +/- 5% intervals.

If you said 98%, 99% or +/- 2%, or +/- 1%... the sample size would definitely increase.

 

Hey Valiantman, another factor that might influence not only the sample size but other statistical analyses is the basic assumption of normality--that is, the sample is normally distributed across grades, something we know is absolutely not the case. We know that there are not as many VF's as VG's, or as many NM's as G's. How do you think this would influence the sample size needed to draw?

[valiantman]

Hey Valiantman, another factor that might influence not only the sample size but other statistical analyses is the basic assumption of normality--that is, the sample is normally distributed across grades, something we know is absolutely not the case. We know that there are not as many VF's as VG's, or as many NM's as G's. How do you think this would influence the sample size needed to draw?

It's hard to say what the true "normal distribution" of ungraded comics would be.

For a given comic, since more raw high-grade copies are CGC graded than raw mid-grade,

and since more raw mid-grade copies are CGC graded than raw low-grade...

It's likely that when we say that we think 2% of all copies of a book

like ASM #1 have been graded by CGC...

We're probably saying that 20% of high grade copies have been graded...

2% of mid-grade copies have been graded...

and 0.2% of low-grade copies have been graded.

(Assuming those amounts would combine to for a 2% overall.)

But it could be 10%, 1% and 0.1%... or it could be 4%, 3%, and 0.01%,

we just don't know. We just know it "decreases from high-grade to low-grade".

 

Since it will probably never be the case that every copy of a comic book

is submitted to CGC according to its normal distribution (random)...

we will not ever know the "real answer" about mid- and low-grade copies

in existence.

In this respect, the sample size would not really need to change...

The data "is what it is" after about 350 or 375 copies have been graded.

We would just need to remember that we don't know much about

mid-grade and low-grade issues, except that they are most likely

"out there" ungraded a whole lot more than the remaining "high-grade" raws.

 

An interesting situation that has not been discussed in this thread is pre-screening.

Even though it currently only affects a few books from about 2001 - present,

there are situations where the majority of CGC graded copies of books were

pre-screened for a particular grade (9.6 or 9.8). In those cases there is a

very large skew to the distributions, since the 9.4 and lower books aren't

represented at all for the pre-screened quantity.

 

A perfect example would be: Star Wars: Tales - A Jedi's Weapon

61 copies graded... none below CGC 9.8.

If we assume that this is the result of 100 copies pre-screened for 9.8...

then there are 39 out of 100 that did not meet the 9.8 criteria...

but all we know from the CGC census is that 61 out of 61 copies are 9.8 or better.

We might assume that 9.8's are possible 100% of the time... when it's probably

only true that 9.8's were possible 61% of the time at the time the book was brand new.

(But what if it took 200 pre-screened copies to achieve these numbers?)

 

Pre-screening probably doesn't affect many books prior to the year 2000,

unless someone submits multiple titles or a particularly overstocked book,

but the books that were (and are) pre-screened in the first month of their release

will forever skew the CGC census in terms of distributions for that particular book.