Detailed instructions for use are in the User's Guide.
[. . . ] Guide to Using
StatTools
Statistics Add-In for Microsoft Excel
®
Version 5. 5 May, 2009
Palisade Corporation 798 Cascadilla St Ithaca, NY 14850 (607) 277-8000 http://www. palisade. com
Copyright Notice
Copyright © 2009, Palisade Corporation.
Trademark Acknowledgments
Microsoft, Excel and Windows are registered trademarks of Microsoft, Inc. IBM is a registered trademark of International Business Machines, Inc. Palisade, TopRank, BestFit and RISKview are registered trademarks of Palisade Corporation.
Welcome to StatTools for Excel
Welcome
StatTools gives Microsoft Excel - the industry-standard data analysis and modeling tool - a new, powerful statistics toolset!StatTools is a Microsoft Excel statistics add-in, allowing you to analyze data in Excel worksheets and work in the familiar Microsoft Office environment. [. . . ] Link to Data The histogram and all formulas for the test are linked to the original data. So if the data change, the histogram and the test results change automatically.
Reference: StatTools Menu Commands
104
Lilliefors Test Command
Tests if observed data for a variable is normally distributed The Lilliefors Test procedure provides a more powerful test for normality than the more familiar chi-square goodness-of-fit test. (More powerful means that it is more likely to detect non-normality if it exists. ) It is based on a comparison of the "empirical cdf" and a normal cdf, where "cdf" stands for cumulative distribution function, showing the probability of being less than or equal to any particular value. For example, if there are 100 observations and the 13th smallest is 137, then the empirical cdf, evaluated at 137, is 0. 13. The Lilliefors test finds the maximum vertical distance between the empirical cdf and the normal cdf, and it compares this maximum to tabulated values (that are based on sample size). If the observed maximum vertical distance is sufficiently large, then we have evidence that the data do not come from a normal distribution. Lilliefors Test Dialog Box This analysis is set up using the Lilliefors Test dialog box:
One or more variables can be selected for testing. Variables can be from different data sets.
Reference: StatTools Menu Commands
105
Lilliefors Test Report
The results of the test are shown in the report above. There is no pvalue (as in most hypothesis tests), but we see from the statement that the maximum vertical distance is sufficiently large to cast doubt on the normality assumption. More evidence to this effect appears in the cdf's in the included chart. Actually, the fit between the two curves appears to be "pretty good, " and it might be good enough for all practical purposes. That is, we might conclude that these data are "close enough" to being normally distributed for our purposes.
Reference: StatTools Menu Commands
106
Missing Data and Link to Data
· ·
Missing Data - Missing data are allowed. Link to Data The CDFs and all formulas for the test are linked to the original data. So if the data change, the graph and the test results change automatically.
Reference: StatTools Menu Commands
107
Q-Q Normal Plot Command
Tests if observed data for a variable is normally distributed The Q-Q Normal Plot command creates a quantile-quantile (Q-Q) plot for a single variable. Although the details are somewhat complex, the objective is fairly simple: to compare the quantiles (or percentiles) for the data to the quantiles from a normal distribution. If the data are essentially normal, then the points on the Q-Q plot should be close to a 45-degree line. However, obvious curvature in the plot is an indication of some form of non-normality (skewness, for example). Q-Q Normal Plot Dialog Box This analysis is set up using the Q-Q Normal Plot dialog box:
One variable can be selected for plotting. This options in the Q-Q Normal Plot dialog box include: · Plot Using Standardized Q-Values - Specifies to use a standardized Q-Value, instead of Q-Q data, on the Y-axis of the graph. This makes comparisons of the Y-axis values between Q-Q Normal plots possible.
Reference: StatTools Menu Commands
108
Q-Q Normal Plot Report
As stated earlier, this is an informal test of normality. It is difficult to say "how close" to a 45-degree line the plot should be to accept a normality assumption. Typically, we look for obvious curvature in the plot, and none is apparent in the plot here. [. . . ] StatStandardize(2, 1, 3) calculates a normalized value at the value 2 from a distribution with a mean of 1 and a standard deviation of 3. x is the value to be normalized mean is the arithmetic mean of the distribution. It must be > 0.
Examples
Guidelines
STDDEV
Description
STDDEV (Data1, Data2, . . . DataN) calculates the sample standard deviation of the data specified in Data1, Data2, . . . DataN. StatStdDev(A1:A10, {1;2;3;2. 4}) calculates the sample standard deviation of all value in the data set located in A1:A10 and the values 1, 2, 3 and 2. 4. [. . . ]