Research Design and Analysis, Emporia State Univ.

Directions for using SigmaStat
Basic Statistics
To start the program: Click on Start, then Programs, then Jandel Scientific, then SigmaStat 2.0. This opens several windows, of which the active one is for entering data.

To enter data: Enter the following numbers from problem 6.1. Note that you will have 2 4.0s and 3 4.3s, etc. because SigmaStat can not read data as a frequency distribution. 4.0, 4.0, 4.3, 4.3, 4.3, 4.5, 4.5, 4.5, 4.5, 4.5, 4.6, 4.6, 4.6, 4.6, 4.6, 4.6, 4.6, 4.6, 4.7, 4.7, 4.7, 4.7, 4.7, 4.7, 4.8, 4.8, 4.8, 4.8, 4.8, 4.9, 4.9, 4.9, 4.9, 5.0, 5.0, 5.0, 5.1. Once the numbers are entered in column 1, label the column. Put the pointer in the gray area at the top of the column and click on the right mouse button, then click on Column Titles and enter a label (I used body weight). Click on Finish when you are done. Go back and check your numbers to be sure that the data were entered correctly.

To get basic statistics: Click on Statistics from the menu at the top, then click on Describe Data. This brings up a smaller window and on the right side is a box and it should say Data: body weight. If it does not, then click on Column 1. You can run basic statistics on several sets of data, if each set is in a different column. Once you have the column designated, then click on Finish and this will produce your output of basic statistics.

To save output: If you want to use the output in another program, for example WordPerfect, you will need to export it. Go to File on the top menu, then Export. This will bring up a window so that you can direct the output to the A:\ drive. This saves the file in rich text format, so that it can be read by other programs.

The output:

Descriptive Statistics:           Monday, August 28, 2000 9:01:12

Column         Size  Missing   Mean   Std Dev  Std. Error   Range    Max     Min
body weight     37      0      4.651   0.252     0.0415     1.100   5.100   4.000

Column       Median    25%     75%    Sum    Sum of Squares   CI   Skewness  Kurtosis
body weight   4.700   4.500   4.800  172.100    802.790     0.0841   -0.740     0.896

Column          K-S Distance  P Value
body weight       0.149        0.037

Explanation of the output: First Row:

Size is the sample size or number of observations (n).
Missing tells you the number of cells in your column that did not have entries.
Mean is the sample mean (Xbar): Sum divided by Size
Std Dev is the sample standard deviation (s).
Std Error is the sample standard error (SEM): Std Dev divided by the square root of Size.
Range is the largest value minus the smallest value: Max - Min.
Max is the largest value.
Min is the smallest value.

Second Row:

Median is the median
25% is the first quartile
75% is the second quartile
Sum is the sum of the observations
Sum of Squares is the sum of the squared observations: This is NOT the sum of squares as we have used this term, however it is used in the "machine" formula for the calculation of the sum of squares.
CI (originally labeled Confidence) is the quantity added and subtracted from the sample mean to get the upper and lower confidence limits:
Std error multiplied by t_0.05(2),36 = 0.0415 * 2.028.
Thus the lower confidence limit (L₁) = mean - CI = 4.651 - 0.0841 = 4.5670
The upper confidence limit (L₂) = mean - CI = 4.651 + 0.0841 = 4.735.
Skewness is g₁
Kurtosis is g₂

Third Row:

K-S Distance is the Kmolgorov-Smirnoff Goodness of Fit statistic
P Value is the value used to test the hypothesis that the data come from a normal distribution (we will cover this part later).

While in SigmaStat, if you click on Help on the top menu, and then Index, this will also give you a summary of the output. The glossary also contains some very useful information.

To save your work: Click on File, then Save As, then in the smaller window give you work a name and save it to the A:\ drive. This will save your original data plus your output in a SigmaStat file.

Return to Chapter 6.