Chapter 11

Rolling the Dice on Predictions and Probability

In This Chapter

arrow Understanding linear and exponential trends

arrow Predicting future data from existing data

arrow Working with normal and Poisson distributions

When you’re analyzing data, one of the most important steps is usually to determine what model fits the data. No, I'm not talking about a model car or model plane! This is a mathematical model or, put another way, a formula that describes the data. The question of a model is applicable to all data that comes in X-Y pairs, such as the following:

  • Comparisons of weight and height measurements
  • Data on salary versus educational level
  • Number of fish feeding in a river by time of day
  • Number of employees calling in sick as related to day of the week


Suppose now that you plot all the data points on a chart — a scatter chart, in Excel terminology. What does the pattern look like? If the data is linear, the data points fall more or less along a straight line. If they fall along a curve rather than a straight line, they aren’t linear and are likely to be exponential. These two models — linear and exponential — are the two most commonly used models, and Excel provides functions ...

Get Excel Formulas and Functions For Dummies, 4th Edition now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.