Education Technology


Statistics: Why np Min?

by Texas Instruments

Objectives

  • Students will understand that normal distributions can be used to approximate binomial distributions whenever both np and n(1 – p) are sufficiently large.
  • Students will understand that when either np or n(1 – p) is small, the normal distribution probabilities for impossible numbers of successes (less than 0 or greater than n) are unreasonable.
  • Students will formulate guidelines to determine what they mean by sufficiently large for good approximations.

 

Vocabulary

  • binomial random variable
  • mean
  • normal random variable
  • number of trials, n
  • probability distribution function
  • probability of success, p
  • standard deviation

 

About the Lesson

This lesson involves examining the general shape of binomial distributions for a variety of values of n and p.
As a result, students will:

  • Compare the shapes of binomial distributions to those of related normal distributions, recognizing the distinction between discrete and continuous random variables.
  • Recognize that normal approximations of binomial probabilities become less and less accurate as either np or n(1–p) falls below 5 (or 10 or 15) by examining the probabilities calculated from the normal distribution for having the "number of successes" be less than 0 or greater than n.