Explore
 The Explore procedure provides a variety of visual and numerical summaries of the data, either for all cases or
separately for groups of cases. The dependent variable must be  ratio, while the grouping variables
may be interval or nominal.

With the Explore procedure, you can:
Screen data
Identify outliers
Check assumptions
Characterize differences among groups of cases

1. Move the dependent variable over to the right

2. Move the grouping variable into the factor box

3. Click on the appropriate radial button for what you would like to display in the output
    Both- Statistics and Plots (not worth doing)
    Statistics: displays the following (you may have to click the statistics button and activate these)
            Descriptives- include the mean, median, 5% trimmed mean, standard error, variance,
                            standard deviation, minimum, maximum, range, and interquartile range, shape
                            of the distribution; skewness, kurtosis, and 95% confidence interval for the mean.
            M-Estimaters- Robust alternatives to the sample mean and median for estimating the center of location.
                            (not worth doing)
            Outliers- (NOTE: not real outliers) Displays the five largest and five smallest values
            Percentiles- displays various percentiles
    Plots: displays the following (you may have to click the plots button and activate these)
                Plots include Stem and Leaf displays and boxplots (not worth doing)

4. The output gives you boxes, depending upon what you selected, the information.  
    1. Case Processing Summary: Gives you the Sample Size (N), amount of missing cases and
                        the percentages of valid and missing cases.
    2. Descriptives: Gives you all the information you asked for in Descriptives
                    The first variable name in the upper left corner is the dependent variable measured.
                    The second is the grouping variable that the discriptives will be sorted by.
                        Measures of central tendency include the mean, median, and 5% trimmed mean.
                        Measures of dispersion include standard error, variance, standard deviation, minimum,
                                maximum, range, and interquartile range.
                        The descriptive statistics also include measures of the shape of the distribution; skewness    
                                and kurtosis are displayed with their standard errors.    
                        The 95% level confidence interval for the mean is also displayed.

    3. Percentiles: Gives the value for the 5th, 10th, 25th, 50th, 75th, 90th, and 95th percentiles

    4. Extreme Values: Gives the five lowest and five highest value as well as the case number for it
       

page created by Ryan Pohlig