DISCLAIMER: The information on this site is presented on an "as is" basis, and does not claim to present definitive information, make recommendation or to represent such official bodies such as the Standard Celeration Society. Users of this site agree that the owner of the site or authors of pages and articles are indemnified against legal liability
To view/save page as pdf
To return to Charting Templates page
Notes from Stuart Harder on SCCFB_dcpm_v7_2a
Stu Harder has given permission for users to email him questions.
Date 6/21/07
About the SCCRB_dcpm_v7_2a: This is a beta-version.
1. When first opening a template, the user can now go to the Set-up
page, click an Update button, and have Excel identify the operating
system it is running under and find the version of Excel. This permits
formulas to change automatically to accommodate newer versions of Excel,
like Excel 2007 for Windows. I just had an opportunity to play around
with 2007. Can't say I'm a fan of it yet, but I'll give it a chance.
2. There is now a user option to set the vertical axis scale, changing
it from 0.1 to 1 and back again. This precludes having to maintain two
separate templates and the modification applies to
- daily count per day
- weekly count per week
- monthly count per month
- yearly count per year,
doesn't think of that need to be linked to this one feature to make it
work right. I think I got it.
3. I added an option to impose celeration lines on the Accuracy Ratio
chart of the yearly count per year template. This option shows up in
the Celeration Finder dialog box. I'll add the same feature to the
other templates (daily count per minute has it too) when I get time.
4. This week I worked on adding a new feature to the daily count per
minute template. This may be of greater interest to researchers, but I
felt compelled to add it after reading Johnston and Pennypacker's
'Strategies' again. Several versions back I added the computational
routines for the Absolute Mean Ratio (AMR) measure of variability. I
really like this measure because it utilizes all pairwise ratios in
determining the extent of variation among the data points in a series.
Presently, the Summary Table page gives a new value for the AMR with
each new celeration line. This same table reports the relative change
in the AMR from present phase to preceding phase and also provides a
relative comparison of the AMR for acceleration and deceleration series
with conditions. These descriptive statistics offer a straightforward
method for comparing changes in variability given changes in context.
I've now taken this analysis a graphical step further. I've added a
chart plot for a Moving Absolute Mean Ratio. The user can determine how
many points get factored into the calculation of the AMR, so by example,
if a 5-term moving AMR is needed, the program computes the AMR for the
first 5 points, plots the result, slides ahead one day, and computes the
AMR for the next 5 points. By plotting the acceleration, deceleration,
and accuracy ratio series on the same chart, one can see the how
variability changes over time using a standard measure of variation.
Followup note
Date: 6/22/07
Dear Friends,
Here is the latest evolution in the 'daily count per minute' SCC.
As I mentioned in the announcement sent yesterday, this template contains a
new chart used to display the Absolute Mean Ratio (AMR). The mAMR Chart
displays this descriptive measure of movement cycle variability over
time using a moving 'window'. If the window is set to 5 data points,
then the routine grabs the first five points, calculates the absolute
mean ratio, plots its, and then slides ahead one notch and grabs the
next 5 points.
Please keep in mind that this particular chart does not refer to
frequency level or celeration. It is a measure of variability over
time. What you see in this chart when the graph lines increase is an
indication of rising variability. When the lines decrease, variability
also decreases. It is also important to look carefully at the SCC
itself and compare what the SCC shows by way of bounce with that shown
on the mAMR chart. You will often see patterns in which the absolute
mean ratio is stable even though the celeration line is rising at x2.
You can change the value of the 'window' on the Moving AMR page. Go to
cell E3 and enter the value you want. Small values result in lower
values of the AMR in general; larger window values result in larger AMR
values, especially when the movement cycle is accelerating or decelerating.
I think this is an import descriptive measure of variation, but we are
going to have to study it's properties to learn what it tells us.
Consider this template a beta version. Let me know if you have
questions. Thanks.
Stu Harder
2/8/08
Page Information
|
Wiki Information |
Recent PBwiki Blog Posts |
Create your own educational wiki!