Counting Statistics

Table of Contents

Steps for Geiger-Mueller counter

# Import the python data analysis module
import pandas as pd

# Read your data into a DataFrame construct, and assign names to
# the columns. The column t1 is the times between each count, and 
# t2 is just the same as t1, but shifted one row upwards

df = pd.read_csv('path_to_your_data.txt', delim_whitespace = True,
                  names = ['Index', 't1', 't2', index_col = 'index']

# Print the first five rows of the dataframe so we know what our
# data looks like!


# Create a new column, 't3', which is simply the sum of t1 and t2 - 
# That is, t3 contains the times between every two counts.

df['t3'] = df['t1']+df['t2']
df.hist(column = 't1', bins = 100)

Your resulting histogram should look something like this:

However, don’t stop here! You should make the histogram of the distribution between every count as well, and compare it to the theoretical distribution that you would expect from your knowledge of counting statistics. Plot the theoretical function and estimate how good the experimental data matches the theory. If you see some discrepancies, try to reason about why they might arise.

Things I am looking for in particular - an intelligent discussion of why we see the distributions of ‘time between counts’ and ‘time between every 2 counts’ look the way they do.