Message Boards Message Boards

0
|
7736 Views
|
5 Replies
|
1 Total Likes
View groups...
Share
Share this post:

Interpretation of strong peak at mean in Gaussian/Poisson histogram

Posted 10 years ago

Howdy all! My first posting since comp.soft-sys.math.mathematica days!

I recently acquired a data-logging Geiger counter and have been fitting the time-series data (total counts per 1 minute interval). Since the numbers well exceed 1, the Poisson distribution I expect will look quite Gaussian. I bin the count rates then fit the data. The distributions are as expected EXCEPT that I keep finding in finer-scale histograms of the counts-per-minute data a much-larger-than-expected narrow peak right at the peak of the histogram.
(In graphic attached: red=Poisson, green=Gaussian.) Being a naive theoretical non-nuclear physicist, I'm puzzled. Can someone explain my data to me? :) Perhaps I am regressing to the normal (a pun, not an interpretation)?

Thanks! DMW

Attachments:
POSTED BY: David Wood
5 Replies
Posted 10 years ago

What really counts is that you're satisfied with the rationale you've provided. But you've peaked my interest (no pun intended). The spread in the histogram is certainly about what you'd expect from a Poisson with mean around 50: 95% of the counts would fall between 36 and 64. The 60-minute moving average figure looks like what one would expect from 3500 1-minute counts from a Poisson distribution. But samples from a Poisson distribution would not have such a peak in a histogram. The observed histogram is consistent with a random samples from a Poisson distribution but "contaminated" with a set of values very close to the mean.

If you're willing to share one of the datasets (in the original time order) and/or your Mathematica code to get the histograms, I'd certainly like to see if I could see something in the data. (Daniel Lichtblau is absolutely correct: one can't say much without the raw data.) Also, it seems like your rationale could be validated with some additional lines of code.

POSTED BY: Jim Baldwin

It is possible that you just need narrower bins to see a tall thin peak. I confess the sides look a bit fat for that to happen though.

POSTED BY: Daniel Lichtblau
POSTED BY: David Wood

Thanks for your response, Daniel. Attached is what I hope is a salient graphical summary of the data (the log10 power spectrum of the DFT of moving average data may be spurious.) I believe the issue is one of physics or of some feature of statistics not known to me. The prominent peak at the mean count rate survives many binning choices. A radiation statistics or weak source astrophysicist might know?

Attachments:
POSTED BY: David Wood

Hard to say much without the raw data. Possibly an accident of where the bin boundaries are drawn?

POSTED BY: Daniel Lichtblau
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract