| Author |
 Replies: 72 / Views: 10,975 |
|
|
|
Valued Member
United States
401 Posts |
Nice bump. As an actuary & lifelong number lover who joined CCF a few months ago, I can read threads like this all day long...
|
|
Pillar of the Community
United States
1903 Posts |
I wonder if the OP or anyone else versed in statistics could run the z scores and incorporate
Mintage
Price
And Population numbers of graded coins. Not by each grade, but in aggregate. This right be an interesting analysis. Might help shed light on why some common cents are hard to find
|
|
New Member
United States
7 Posts |
I have convinced my self that there is no foolproof way to figure out current counts of any given Lincoln, I mean that goes without saying, but I also believe that doing some brainstorming, taking into consideration some historic events and considerations,, could point me in the right direction of specific years that just might be more scarce than contemplated!
For example, I'm sure there is a year (1938-P?)that meets both the depression era and pre WW2 era, at a time when the "frenzy" was highest for hoarding coins right?
Consequently, those coins would probably not be taken care of, just thrown into a coffee can or some pottery jug, for "emergency" use. Thereby reducing the higher quality coins of that year even further.
The 1938-P was plentiful, but because a much lower mintage for that year than the year before could indicate Copper was again in demand, could have been the coin that was hoarded, and finding high grade versions of these might just be worth wild, right now! :)
|
|
Bedrock of the Community
United States
20753 Posts |
Quote:
But Carl, that's precisely the point of the work drdave is doing. If you analyze these numbers, you should be able to back-calculate current populations (IF the market forces are working correctly). Again, the main problem with coin statistics is no one, absolutely no one, knows how many of any coin still exists even if only few years old. So very many have been melted lately and those doing the melting really do not keep track of the dates. Yes many 31S's were saved in the 30's but how many are there today? No one knows. That is why price guides are only guides. There can not be a real price list since all prices are guesstamates. For all anyone knows even a 1975 Cent could now be non existant. |
|
Pillar of the Community
United States
1903 Posts |
statistics don't tell you what is ABSOLUTELY going on, statistic just give you a "best guess". No one has that crystal ball, but statistics is a way to "see" what is happening around you and make good guesses based on it. Statistics are never facts, just a reference. I think we lose sight when we think of statistics as an absolute when it really is just an "educated guess". When we look at statistics in that light, it can be very interesting, rewarding, and sometimes profitable to heed them. We all live our lives every day through statistics....that "gut" feeling you get about something is just your brain using you life experiences as a "statistic" and making a judgement based on them. Usually it is right, but not always. Doing these statistics on coins is just the same....usually...it is right, but we can always find exceptions. The wealthiest people in the world live and die by statistics....if it is good enough for them...it is good enough for me! I say.....soldier on and see what interesting statistics we can derive from poking at the data we have
|
|
Pillar of the Community
 United States
721 Posts |
Interesting discussion to this thread lately. Unholyroller, I started doing the analysis of different grade types, and didn't finish, frankly. What I remember is that the data started becoming more scattered, which is to be expected when considering population reports instead of mintage values. I agree that there is something interesting here with these statistics and the anomolies I believe can shed light on which ones are either more available or less available than expected. Might get back to this sometime.
|
|
Pillar of the Community
United States
764 Posts |
Is converting to z-scores entirely necessary? The mintages of each issue would not be normally distributed. I was thinking about this for the past half hour or so and came up with a suggestion: Consider dividing the mintage of each issue by the average mintage of that type. Then take a logarithm (I would recommend log base 2 so the values are not all so close to zero). This would make the average mintage coin have a value of zero and a difference of one would mean the more common coin is twice as common as the other. It also eliminates the need for the standard deviation which really does not seem very meaningful with a distribution like mintages. My work is in algebra and number theory, not statistics so this is just an opinion from another kind of numbers person. It may be helpful. Anyway, I think your analysis is pretty interesting.
AHHHHH, now it has me thinking about different kinds of ways to analyze wheat cents: Record the constants for either a power or exponential distribution of a price vs grade scatter plot for each coin. Then you can determine the probable circulation rate each issue had.
|
|
Pillar of the Community
United States
4132 Posts |
After reading this thread, I decided to do something similar with Mercury dimes, with some interesting conclusions. Here are the top 10 dates by mintage: 1916 D -3.08 1921 D -2.03 1921 P -1.93 1931 D -1.92 1926 S -1.78 1931 S -1.65 1930 S -1.63 1931 P -1.23 1928 D -1.02 1929 S -0.93 By analogy with drdave's numbers, 1916-D is the only true "key" and an almost exact match for the 1909-S VDB. But it really stands alone. The semi-keys by mintage are 1921-D, 1921-P, 1931-D, 1926-S, 1931-S and 1930-S, and they're closely clustered. the '21s are much closer to this group than they are to '16-D. Interestingly, mintage numbers don't correspond that strongly to prices for many dates. If you just went by mintage, 1931-D would seem very under-priced right now, followed closely by '31-S and '30-S. In lower grades they're only slightly off, but the anomaly becomes large at higher grades. There are other examples. 1938-D, believe it or not, is a lower mintage issue than 1923-S! '23-S is a tough date in nicer grades - $74 at XF40, the 6th most expensive date in that grade, while '38-D is a common date, worth about $5 in XF40 and can be had for just $68 in gem MS65 with full bands. It does start to make sense if there is a correlation by date. It's a pretty strong correlation, dates from the early 20s are considerably more expensive than similar mintage dates in the late 20s. Silver is soft and wears fast, so few early dates were still in nice shape when people started pulling them out of circulation as coin collecting took off in the 30s, 40s and 50s. There are some other explanations that may apply to specific dates. 1916 (and to a lesser extent 1916-S) are not low mintage, but they are a bit lower price than expected. But this is easily explained by the fact that they were saved in significant numbers because everybody liked the new design. The early 1930s issues weren't entirely released into circulation immediately because of the depression. By the time they did start appearing in the mid '30s, collectors and dealers were aware of their low mintage and scarcity and took care to set them aside. The trend of setting aside roll-quantities of coins as an investment also started around this time. I'm gonna try to teach myself multivariate analysis so I can come up with a model for this that takes into account mintage and date and maybe some other variables like geography. |
|
Pillar of the Community
United States
721 Posts |
The reason I chose z-scores is so that I could compare between different coins. One thought I had was to look at the break point (horizontal price to increasing price), and the slope values and group them into different categories. You can just plot the log(mintage) as well, but can't compare well between different coins.
|
|
Rest in Peace
United States
9104 Posts |
 , TrashyTrucker! |
|
Rest in Peace
United States
9104 Posts |
Quote: Anyone can say a 1931S Lincoln Cent had so many minted but no one on Earth knows how many are left. How many are in AU grades. The biggest problem with such charts is too many uncharted variables, like the 31s. Everyone knew the 31s was the second lowest mintage, and held them. Compare to the commoner 14d, or even the twice as common 09s, both of which are worth more. Now compare the prices:
Grade G VG F VF XF AU50 AU53 AU55 AU58 MS60
1909 S 79.35 88.55 105.60 122.40 198.00 234.00 246.00 264.00 288.00 300.00
1914 D 162.00 204.00 282.00 408.00 900.00 1,380. 1,530. 1,770. 2,040. 2,100.
1931 S 78.20 87.40 92.00 96.60 106.95 117.30 126.50 141.60 150.00 162.00
Notes: - the 31s, rarest of the three, is cheapest.
- the 09s, twice as common, is only slightly higher, due to the squirrel effect.
- the 31s barely doubles between good and ms60, a sure sign of hoarding.
- the 14d goes up 13 times, very close to Sheldon's pricing scale.*
*For Clewless Gnubees™, the familiar 1-70 Sheldon Pricing Scale was never intended for grading. A 12 was worth 3x as much as a 4, a 30 half as much as a 60, etc. Edited by biggfredd
02/14/2012 2:34 pm
|
|
Rest in Peace
United States
9104 Posts |
, paddy murphy! |
|
Pillar of the Community
United States
4132 Posts |
I did a multi-variable linear regression to try to relate log(mintage) to log(price) and year for Mercury dimes and came up with a much better model than one that just used mintage. However, it still wasn't a very good predictor of price at the grades I tried it at. It suggested that certain mid-20s dates like 1925-D were overpriced by more than twice, and some teen dates and late-20s/early-30s dates were under-priced by similar factors (interestingly, 1.8ish million mintage '30-S and '31-S were much more under-priced than 1.5ish million mintage '31-D). The under-priced dates seem to correspond to recessions, so I may try plugging in an economic-activity factor into the model to see if that will improve the fit at all. E.g. something like GDP over the 5 years following the release of each issue. I may also get a better fit by only looking at very low grades or only looking at uncirculated grades, which would be less dependent on amount of circulation. |
|
Pillar of the Community
United States
2295 Posts |
@biggfredd, pretty interesting analysis among those 3 cents.
I remember when I started collecting in the 1970s that I read that the ones with the lowest mintage were the most expensive, but it is really all about supply and demand. There are other denominations that are much lower in mintage than the Lincoln keys, but sell for way less. I wish I could remember a few off of the top of my head.
|
|
Pillar of the Community
United States
2295 Posts |
And this is a great thread. I really like the idea.
Is there a way to compare keys from one denomination to another?
Mainly to see what keys of what denominations are more rare than the other?
|
| |
Replies: 72 / Views: 10,975 |
First Page
Previous Page
Posted 02/10/2012 1:44 pm
