Statistics Terms to Know when Using Excel 2007 Data Analysis Tools

By Stephen L. Nelson

Part of Excel 2007 Data Analysis For Dummies Cheat Sheet

With the data analysis tools available in Excel 2007, you can create spreadsheets that show the details of any statistic you can create a formula to find — and you can find any number. It helps to know what you’re looking for and what to expect, and the terms in the following list help you understand what kinds of statistics you can produce.

  • average: Typically, an average is the arithmetic mean for a set of values. Excel supplies several average functions.

  • chi-square: Use chi-squares to compare observed values with expected values, returning the level of significance, or probability (also called a p-value). A p-value helps you to assess whether differences between the observed and expected values represent chance.

  • cross-tabulation: This is an analysis technique that summarizes data in two or more ways. Summarizing sales information both by customer and product is a cross-tabulation.

  • descriptive statistics: Descriptive statistics just describe the values in a set. For example, if you sum a set of values, that sum is a descriptive statistic. Finding the biggest value or the smallest value in a set of numbers is also a descriptive statistic.

  • exponential smoothing: Exponential smoothing calculates the moving average but weights the values included in the moving average calculations so that more recent values have a bigger effect.

  • inferential statistics: Inferential statistics are based on the very useful, intuitive idea that if you look at a sample of values from a population and the sample is representative and large enough, you can draw conclusions about the population based on characteristics of the sample.

  • kurtosis: This is a measure of the tails in a distribution of values.

  • median: The median is the middle value in a set of values. Half of the values fall below the median, and half of the values fall above the median.

  • mode: Mode is the most common value in a set.

  • moving average: A moving average is calculated using only a specified set of values, such as an average based on just the last three values.

  • normal distribution: Also known as a Gaussian distribution, normal distribution is the infamous bell curve.

  • p-value: A p-value is the level of significance, or probability.

  • regression analysis: Regression analysis involves plotting pairs of independent and dependent variables in an XY chart and then finding a linear or exponential equation that best describes the plotted data.

  • skewness: This is a measure of the symmetry of a distribution of values.

  • standard deviation: A standard deviation describes dispersion about the data set’s mean. You can kind of think of a standard deviation as an average deviation from the mean.

  • variance: A variance describes dispersion about the data set’s mean. The variance is the square of the standard deviation; the standard deviation is the square root of the variance.

  • z-value: This is the distance between a value and the mean in terms of standard deviations.