## Keeping it random

You used an applet to randomly select the 10 grid segments. Why is it important to ** randomly** select segments to count?

It's something called "**experimenter’s bias**"! You can’t help but be a little biased. You as the sampler might have a tendency to choose the most conveniently located segment, or the fullest segment, or the least full segment, or the most interesting looking segment, or the segment the farthest from the beehive…..

BUT - for the random sample to be really, really, random, all members of the population need to have an ** equal chance** of being selected. To overcome experimenter’s bias, there are all sorts of different ways to generate a random selection. In the olden days, we used

**random number tables**(like the one on the left, titled "Ten Thousand Random Digits") to come up with numbers. The tables would be conveniently placed in the back of your text book, but using them was

**painful**.

Thankfully, in this modern age, **computers can efficiently generate random numbers** for us (like in the applet below) and we can now leave the random number tables with the abacuses and slide rules.

Copyright University of Maryland, 2007

You may link to this site for educational purposes.

Please do not copy without permission

requests/questions/feedback email: mathbench@umd.edu