DPChallenge: A Digital Photography Contest You are not logged in. (log in or register) 
 

DPChallenge Forums >> Current Challenge >> Interesting Statistical Analysis (an oxymoron?)
Pages:  
Showing posts 1 - 11 of 11, (reverse)
AuthorThread
 04/23/2005 05:46:22 PM · #1
After having read numerous postings questioning the low scores that appear in almost every challenge on entries that otherwise "rock", I decided to do a little sleuthing to better understand what is happening.

Last night I wrote a program to browse through the member profile section and analyze voting averages. I am happy to say that I found very few long-term chronic low voters.

I created a handful of graphs.

Graph 1 illustrates the frequency of each average vote. As you can see, this is a classical bell curve peaking at 5.0. No surprise here.



Graph 2 is a bit more interesting - it looks at the relative average score someone gets vs the score they give. A negative score indicates they vote others lower than themselves, a positive score indicates they vote others higher. What I did find is that there is a tendency to vote others lower, and almost nobody votes others equal to their own average. Not sure what to make of that.


The final graph compares the average score a person gives to the number of challenges they have entered. This to me was the most telling and promising, because it clearly shows that people's average scoring increases as they enter more challenges.

I would interpret this to say that

My interpretation of these results is that, as people participate more, they become appreciative of other's efforts and the quality of their work. Rather than people trying to stick it to others, they just need some time to mature.

04/23/2005 05:52:59 PM · #2
Very nice bit of work Sam, interesting indeed!
 04/23/2005 05:53:09 PM · #3
WOW better show this to laurielblack she loves statistics and everything Mathematic.

PS: You got too much time on your hands! ;o) LOL
 04/23/2005 05:59:16 PM · #4
Yep, no surprises in graph 1. Actually, I might have expected a "split" between 5.0 & 5.5 for the "average of averages" since the true midpoint of the 1-10 scale is 5.5. That is apparently not the case, however. Interesting.
In graph 2 there may be a problem with either the binning or the plotting. Look at your X scale, the values -0.6, -0.1, +0.3 are plotted equidistantly, but they are certainly not equidistant. This may be causing or contributing to the central dip.
I agree with your conclusion on the last graph. It certainly reflects my own experience, and others have reported that their own voting behavior has followed this trend.

Message edited by author 2005-04-23 18:00:49.
 04/23/2005 06:26:18 PM · #5
Originally posted by northrop3:
After having read numerous postings questioning the low scores that appear in almost every challenge on entries that otherwise "rock", I decided to do a little sleuthing to better understand what is happening.

Last night I wrote a program to browse through the member profile section and analyze voting averages. I am happy to say that I found very few long-term chronic low voters.

I created a handful of graphs.

Graph 1 illustrates the frequency of each average vote. As you can see, this is a classical bell curve peaking at 5.0. No surprise here.



Wow
some 30 people have a voting average of 9.9

Message edited by author 2005-04-23 18:26:58.
 04/23/2005 06:55:56 PM · #6
Yikes! Thanks, this is interesting. We were going to do the same thing
Friday night but ended up having a naked dance party instead ;) We're glad someone has the patience for that kind of thing, we've often looked at the average vote cast statistic and wondered the same thing thatlead you to do this research, nice work!

04/23/2005 08:21:36 PM · #7
Originally posted by northrop3:
After having read numerous postings questioning the low scores that appear in almost every challenge on entries that otherwise "rock", I decided to do a little sleuthing to better understand what is happening.

Last night I wrote a program to browse through the member profile section and analyze voting averages. I am happy to say that I found very few long-term chronic low voters.

I created a handful of graphs.

Graph 1 illustrates the frequency of each average vote. As you can see, this is a classical bell curve peaking at 5.0. No surprise here.



Graph 2 is a bit more interesting - it looks at the relative average score someone gets vs the score they give. A negative score indicates they vote others lower than themselves, a positive score indicates they vote others higher. What I did find is that there is a tendency to vote others lower, and almost nobody votes others equal to their own average. Not sure what to make of that.


The final graph compares the average score a person gives to the number of challenges they have entered. This to me was the most telling and promising, because it clearly shows that people's average scoring increases as they enter more challenges.

I would interpret this to say that

My interpretation of these results is that, as people participate more, they become appreciative of other's efforts and the quality of their work. Rather than people trying to stick it to others, they just need some time to mature.


Wonderful analyais, Sam. I hereby convey upon you the honorary title "The Math Guy - 2nd Degree."

With Love and Affection -- The (Original) Math Guy
 04/23/2005 08:48:48 PM · #8
wow, you must love numbers. interesting graph on the last one I would think that the more challenges a person enters the lower their scoring might be because they are improving in their own photography, but hey I was wrong.
 04/24/2005 12:16:21 PM · #9
Or the last graph could mean that the grumpy people go away and the nice people stay?
 04/24/2005 12:35:51 PM · #10
Very interesting analysis.
 04/25/2005 09:32:55 PM · #11
Geez, I can barely balance my checkbook, and you did THIS? Will you do my taxes?? LOL
Pages:  
Current Server Time: 06/25/2025 11:31:20 AM

Please log in or register to post to the forums.


Home - Challenges - Community - League - Photos - Cameras - Lenses - Learn - Help - Terms of Use - Privacy - Top ^
DPChallenge, and website content and design, Copyright © 2001-2025 Challenging Technologies, LLC.
All digital photo copyrights belong to the photographers and may not be used without permission.
Current Server Time: 06/25/2025 11:31:20 AM EDT.