1. ## Which test

This is a very basic question, but if its simplicity does not offend you it may amuse you

I have been playing the lottery (the UK National Lottery) since 1994. We chose 6 numbers between 1 and 49 and we can either let a lottery machine generate the random numbers for us, which is called "lucky dip" or enter our own numbers. I played 293 times, letting the machines generate random numbers 50 times and entering my own (random and each time different) combinations the remaining 243 times.
I want to know if my guessing is better than the random guesses generated by machines and I am not sure what statistical test to chose to answer the question.
Here are the data:

"Guessed by", 0, 1, 2, 3, 4
"Machine", 21, 19, 9, 1, 0
"Human", 102, 93, 41, 6, 1

Sorry about the clumpsy format, this is actually a 6 x 3 table. First Row contains headings for the columns. The numbers in the first row correspond to the number of matched lottery numbers. (i.e. I managed to guess 3 numbers correctly 6 times whereas the machines managed to do it only 1 time.)
Second and the third line contain the actual data: number of lottery draws where the guesses matched 0, 1, 2, 3 or 4 drawn lottery numbers. The line starting with "Machine" are the counts of the correct guesses by the machines and the last line, starting with "Human" are the counts of my correct guesses.

I would be most grateful if someone could point me in the right direction.

Christian

2. These a bit better represented numbers and the graph. Visually there is only very little difference between these curves, but I wonder if that little difference is statistically significant.
Christian

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts