We may operate from a place with quite a nice climate, plenty of sunny beaches and all that, but from time to time we take a break and do a bit of actual work.
Here are some of the things we've been up to most recently.
•Doubled the data-record limit in the Mini version
The Mini version is the default installation; it's not necessary for users to purchase a license to run Mini.
This version was formerly limited to just 50 data records -- that's now gone up to 100. As before, there is no limit on the number of items that may be processed. The installer for the Mini version (free) is available here.
•Reduced the price of a Student license to $0.00
Yes, true! From 1 April 2017 students may now get a one-year license for free. Find out how by visiting the e-store.
•Made improvements to the Pearson VUE Exam Developer macro
The number of Lertap 5 users who also make use of Pearson VUE's Exam Developer platform is not quite approaching infinity yet, but the in-built macro continues to make it truly easy to "port" Lertap's item and test statistics over to Exam Developer, especially after a couple of recent modifications and minor enhancements. Read about it.
•Added support for omega reliability estimation
There's now a special macro in Lertap 5 to support those interested in deriving McDonald's estimates of test and scale reliability and internal consistency. Read about it.
•Quantile plot trace lines cleaned up a bit
The line markers used in quantile plot trace lines are now off by default, resulting in cleaner, easier-to-read displays. Read about this change towards the bottom of this topic.
•An empirical comparison of two reliability measures
Coefficient alpha, or "Cronbach's alpha", has been to go-to measure of test reliability for eons. Some authors have suggested that another reliability index, omega, is better. Research findings comparing alpha and omega, and related references to current literature, are now available here.
•A new importer for scanner csv files
OMR scanners, such as Scantrons, will readily output results in "csv" format. A new whiz-bang macro makes it quite simple to convert csv files so that they're Lertap ready. It's called ImportCSV.
•Another look at Lertap's cheat checker
RSA, response similarity analysis, is the procedure used in Lertap 5 to investigate the possibility of cheating on multiple-choice tests. It's been available since the year 2005. A new paper compares RSA to two other programs, "SCheck" and "Iteman 4".
This work prompted some enhancements to RSA; read about them here.
Two new workbooks have been added to the Sample Datasets website exemplifying the application of RSA in a practical university setting.
•An alternative operating mode for the Interpret option
Version 126.96.36.199 is now available for download (as of 15 March 2016). A "user run mode" setting has been added which significantly alters the way the Interpret option works. In normal mode, whenever the Interpret option is selected after it has already been used at least once, all secondary worksheets are deleted as the option gets underway. At times this can be inconvenient as it effectively wipes out any work users may have done to make their Scores report and quantile plots look exactly as wanted (for example). With large datasets this can be more than inconvenient: it can substantially add to the time it takes for Interpret to do its job.
Changing the user run mode from normal to the new "Elmillon direct" mode provides a solution to these issues.
•Improved performance for users with Excel 2013 and Excel 2016 (Windows)
Version 5.10.7 is now available for download (as of 10 January 2016). Improvements in Lertap 5's VBA coding have resulted in much better response and processing times, especially for Windows users with Excel 2013 of Excel 2016. How much better? As an example, the "M.Nursing" dataset with 1,769 student results and a 60-item test could take almost 9 minutes to process before, depending on the computer in use of course. Now it takes under a minute. A new "TimeTrials" summary is here.
Users with Excel 2010 will also note better speed. "M.Nursing" could take a bit over a minute to process before; now it's well under 30 seconds.
Some of these improvements have also been applied to the Excel 2011 (Macintosh) version, bringing it to version 188.8.131.52. The Mac version is now noticeably faster than before, although it's still much slower than the Windows versions. The "TimeTrials" summary mentioned above has details. Work continues on the Excel 2016 (Macintosh) version; this is going slowly as Microsoft is still updating the Mac version of Excel 2016. (Write to firstname.lastname@example.org if interested in the Mac version.)
•Added a new sample dataset with items having multiple responses
Multiple-response items are multiple-choice questions where it's necessary for students to pick out all the correct responses to an item, and there will be more than one. For example, to get item "I1" correct, students must select both options B and D. This is a type of the "multiple-mark" item format discussed in Haladyna & Rodriguez (2013, p.121).
Click here to be transported to the "Zmed" sample dataset.
•Excel 2016 capability added
This is the latest version of Excel from Microsoft, released in November 2015. Assuming you're using a Windows computer, not a Macintosh, when you download the Lertap installer from this page you'll get Lertap 5.10.6, a version capable of functioning with three versions of Excel for Windows: Excel 2010, Excel 2013, and Excel 2016.
What's different in Excel 2016? Try these links:
How well does the Windows version of Excel 2016 run Lertap 5? Initial time trials indicate it's about the same as Excel 2013. That is, it's slow, especially when compared with Excel 2010 (our favourite version). See the comments found towards the end of this document:
•Chapter 2 update (<--click here)
The manual for Lertap 5 was printed in the year 2001. It's not only a manual, you know. It has numerous references, and is particularly strong in its treatment and review of the application of classical test theory, including testing for subject mastery.
We recently updated Chapter 2, making it more useful to users with Excel 2010, 2013, and 2016. Expect more chapter updates in coming months. A complete link to the manual and all of its chapters is here.
•New output (<--click here)
This is quite a substantial change; a lot of work has gone into it: now Lertap 5 will produce a report for a cognitive subtest which combines quantile plots of response trace lines with data taken from the "brief" and "full" statistical summaries, resulting in an "all-in-one" summary of item performance having both graphs and tables.
Fix yourself up with a cup of a favorite brew, click on the link above, sit back, and take it in -- and note: you'll be treated to an extensive tour of new features and corresponding options. We suggest a quick look of all of the document's sections, followed by a closer look at the areas which most attract you. (In other words, some parts of the document are boring and tedious, but they're followed by good stuff.)
This might be an appropriate spot to remind you of the "production mode" capability. With production mode on, you can set things up so that the new report will be automatic output.
•IRT with EIRT (<--click here)
"EIRT" originated in 2006 as a counterpart to "RIRT", a package of item response theory routines for use in the R environment, put together by French-speaking colleagues in France and Canada. The E in EIRT stands for Excel -- this is a package designed for use with Excel, and it goes very well with Lertap 5, making it a reasonably straightforward process to have IRT parameter and theta estimates written as another worksheet within a user's Lertap 5 workbook. Very handy; give it a burl. It works tres bien.
•IRT with SAS (<--click here)
The SAS University Edition is a powerful data analysis system, and it's free. Late last year, 2014, SAS' IRT routines moved from beta testing to production, and they're potent indeed. Now there's support for SAS IRT in Lertap 5 -- take it for a spin.
•VUE Exam Developer (<--click here)
Those people at Pearson VUE keeping improving their game, adding new features and capabilities. We've added a new macro which will take Lertap 5 results, massage them, and churn out an Excel workbook for use with VUE Exam Developer
This isn't the first special macro we've written for Lertap 5 users who dabble in Pearson VUE stuff. See here. Write to us at email@example.com for more about Lertap and VUE, or, if you have the Excel 2010 / 2013 version of Lertap, download and install the latest version and take the ExamDeveloper1 macro for a spin.
•Oh Master! (<--click here)
We've changed the way the Mastery= setting works for all of you who work with tests having a cutoff score of some sort. Now (yes, we hear you saying "at last!") it's possible to set the cutoff at an actual test score as opposed to percentage of maximum possible.
•"Time trials" (<--click here)
Small computers keep getting more powerful. Now even a computer with an Intel Atom processor, such as the Surface 3, can be used to get some real Lertap work done. (Note that it helps to have Excel 2010 instead of Excel 2013 -- wonder how the coming Excel 2016 will fare.)
A link to the complete "updates summary" page is here.