Go to procedure (table input)

Go to procedure (read table)

Go to procedure (data input)

For table input type three or more means in the second column with for each mean the related standard deviation in the third column and number of cases in the fourth column. Numbers should all be positive and can have decimals, except for the number of cases, which should be an integer. Input a title for each groep in the first title column. This nominal factor variable can be a number or text identifying each group.

For data input concerning one case per row the means procedure will sumarize the data into a means table and the means procedure also allows you to use this table for a one-way anova test. Reading means tables from excel or csv is done with the meanst procedure. This procedure can also be used to make empty table rows by way of the "show rows" option.

For the analysis of the difference between two groups the t-test procedure and for the analysis of proportions the 2xr procedure is advised.

The Oneway Anova procedure tests if there is an overall statistically significant difference between three or more means. The procedure is comparable with the SPSS one-way procedure. After checking the ANOVA/F-value box the procedure outputs an anova table including the explained and unexplained Sum of Squares (or variation), the percentage of variation explained, the explained and unexplained Mean Sum of Squares (or variance), the F-value with degrees of freedom and the significance of F, and the standard error of the residuals.

For comparisons between sets of two means the t-test can be requested. The number of t-tests you get equals n.rows*(n.rows-1)/2. So for a seven row table you can get at most 7*6/2=21 comparisons. Beware of chance capitalization. In comparing all these differences in means you are bound to find some significant purely on the basis of chance fluctuation. Please read the Bonferroni help page for a discussion on this topic and maybe apply the Bonferroni procedure. Note that the means in this procedure are not correlated. Lastly a means table can be requested including the variance, standard errors of the means and significance intervals for each mean and a row with the totals for the table.

The procedure is meant for relatively small tables. Number of rows is in principle limited to 50, but might be less dependent on your browser and other settings.

This procedure is experimental!! Just give it a try and please let us know about your (negative) experiences and give us your suggestions @: