Sampling to figure most common color in M&M packet

Click For Summary
To determine the most common color in an M&M packet using sampling, multiple samples should be taken to ensure statistical significance. The initial approach was flawed due to the small sample size, which may not accurately represent the overall distribution of colors. To identify the two most common colors, additional samples should be collected and analyzed for frequency. Standard deviation cannot be calculated for categorical data like colors; it applies to numerical variables instead. For more accurate results, consider conducting hypothesis testing or consulting the manufacturer for color distribution data.
musicgold
Messages
303
Reaction score
19
Hi,

I am struggling with a problem and do not know how I should approach it.

I went to a baseball game with my son, where I bought him a packet of M&Ms. While eating the candy, my son asked me what color most of the M&Ms are. At first, I intended to tell him that there are equal numbers of M&Ms of every color, but then I decided to do an experiment. I asked him to randomly take out 10 M&Ms from the packet, without replacing them back. We had the following sample.

Br Br Br Br Y Y R O O G

Where, Br= Brown, Y=Yellow, R=Red, O=Orange, G= Green, B= Blue.
Altogether, there were six colors and about 150 M&Ms in that 150-gm packet.

Seeing this, I was not sure what answer to put forward. I asked him to draw one more sample. The second sample was as given below.
O O O O O O O Y R B

Now I was totally confused. I realized that I need to brush up on my Probability and Stats knowledge. Here are the questions I am struggling with.

1. How can I find the most common color using the sampling approach?
2. What was wrong with my approach to the problem?
3. What would I need to do if I wanted to find the two most common colors in a packet?
4. How can I calculate the standard deviation of a sample in this kind of experiment?

Thanks,

MG.
 
Physics news on Phys.org
There are many statistical tests you can do to decide if a sample is at all an indication that one should throw away a hypothesis. Just google hypothesis testing, for example. If you want to decide what the most common colour is, for example, you just need to make lots of tests, then decide if your results are significant enough to discard the hypothesis that all colours are equally likely. So also google significance testing.

Or you could call the manufacturers and ask them.

About the only error I can see is that you attempted to make a judgement about something from a way too small sample. Though you should make it clear if you mean that you want to think about one particular packet, or just a packet in general. And if you want to work out a 'standard deviation' then you need a numerical random variable: the most common colour isn't something that even has a standard deviation. The number of purple M&Ms in a packet is a random variable that has a standard deviation.
 
If there are an infinite number of natural numbers, and an infinite number of fractions in between any two natural numbers, and an infinite number of fractions in between any two of those fractions, and an infinite number of fractions in between any two of those fractions, and an infinite number of fractions in between any two of those fractions, and... then that must mean that there are not only infinite infinities, but an infinite number of those infinities. and an infinite number of those...

Similar threads

Replies
1
Views
4K
  • · Replies 23 ·
Replies
23
Views
4K
Replies
4
Views
1K
Replies
1
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 10 ·
Replies
10
Views
4K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 14 ·
Replies
14
Views
2K
  • · Replies 65 ·
3
Replies
65
Views
7K