I am pleased to announce Release 2.14 of the Real Statistics Resource Pack. The new release is available for free download (Download Resource Pack) and is compatible with all Windows versions of Excel. The Excel 2010/2013 versions are available now. The Excel 2007 version will be available later today,
The website and the Real Statistics Examples Workbook has been updated to reflect the new release. You can also download this file for free (Download Examples).
This release is a combination of some bug fixes and some new capabilities, including the following:
An option is now available to use either the QUARTILE or QUARTILE.EXC version of the quartile function. This results in the following changes:
- A Use exclusive version of quartile checkbox has been added to the Descriptive Statistics data analysis tool. If checked the QUARTILE.EXC version of the quartile function is used to calculate the inter-quartile range (IQR) and to produce the Box Plots.
- The IQR function has also been revised in a similar fashion. IQR(R1, R2, b) uses the QUARTILE.EXC function when b = TRUE and the QUARTILE function when b = FALSE.
The T Tests and Non-parametric equivalents data analysis tool has been revised as follows:
- A bug has been fixed which occurs when the t test with Two independent samples options are chosen with unequal sample sizes. The format of the output is also revised in this case.
- A second input range field has been added to the dialog box for this data analysis tool. When the Two independent samples or Two paired samples option is chosen, you have a choice of specifying both samples in the first input field (as in previous releases) or specifying each sample separately, one in each input range. In the first case the two samples must consist of two contiguous columns. In the second case, if the Two paired samples option is chosen then the samples must consist of two column ranges, while if the Two independent samples option is chosen then the two samples can be ranges of any shape.
- When the One sample option is chosen then only the first Input Range is used, but the range can be of any shape.
The STDERR_POOLED function has also been revised as follows:
- STDERR_POOLED(R1,R2,TRUE) is the pooled standard error of samples in ranges R1 and R2 assuming that we are using the t test with equal variances
- STDERR_POOLED(R1,R2,FALSE) is the pooled standard error of samples in ranges R1 and R2 assuming that we are using the t test with unequal variances