Shareware Super Platinum 8/Shareware Super Platinum 8.iso/mac/DATABASE/KSTAT33C.ZIP;1/LATENEWS.DOC

Text File | 1993-10-01 | 9.8 KB | 195 lines

KWIKSTAT 3.3 LATENEWS

To determine the release number, look at the time stamp on this file's
directory. The hour and minute are version number and second is release
number. For example 3:35 means version 3.3 release 5.

Corrections to manual:

p 1-13,14: The figure 1.7 should show a pick (menu) list of field names.
Use up and down arrow keys to highlight field/variable to choose, then
press Enter, or point to the field name with the mouse pointer
and click once. Throughout the manual, when you choose one field for
an analysis, a pick list is used rather than typing in the number
of the field name. (see note 2 below)

p. 4-26: The table should be:

Gp1     Gp2     Gp3     Gp4
60.8    78.7    92.6    86.9
67.0    77.7    84.1    82.2
54.6    76.3    90.5    83.7
61.7    79.8            90.3

The only difference is that the 90.3 is in Gp4 instead of Gp3.

The formula on page 4-43 should read:

U = n1n2 - [n1(n1+1)]/2 - S

Reference:See Zar (1984), pages 139-142 (He uses R sub 1 instead of S in
the formula).

1. Loading KWIKSTAT in a subdirectory that had a previous version of
KWIKSTAT will not overwrite any of your DBF files. To save space on disk,
erase old Kwikstat programs prior to ver 3. (ERASE *.EXE), or load
Kwikstat in a different directory (e.g., \KS33).

2. Some actual screens may differ from the ones in the manual, since some do
not reflect changes made for mouse support. An important difference is
when you are asked to choose a field for analysis. In the manual, and
in some of the examples, you are told to press 2, for example, to choose
the second field name. Now, in many instances, fields appear in a menu-like
list. In this case, instead of pressing 2, you use the up and down arrow
keys to highlight your choice, then press Enter, or use the mouse pointer
to choose the field by name.

3. In several analyses, a late change has been made to give you more support
in viewing and printing the results of an analysis. In most cases, you will
be asked if you want to view/print results. If you answer Yes, a viewer will
be used to display the results of an analysis. Using the button bar commands
at the bottom of the screen, you can press function keys or click with a
mouse to output the report (to a file or printer), add a title to the report,
set the left margin, choose a printer code, or exit from the viewer.

If you save the contents of the viewer to a file, you can merge the
information into your word processor, or view/print the information
at a later time. To use the viewer from the DOS prompt, enter TXVIEW and
the name of the file to view. The viewer works on all ASCII text files.
For example, if you want to view a file named REPORT.TXT, you would enter
the command

        TXVIEW REPORT.TXT

4. Hercules graphics are supported on all modules except Simulations. Use a
Hercules/CGA Simulator such as SIMCGA or HGCIBM (both shareware programs)
to allow you to run the simulations module on a Hercules monitor. If you
use a simulator, specify a CGA monitor in the setup routine. Printing
graphics screens in the simulations module is not supported.

5. When displaying some graphs in EGA or VGA mode, you can change colors
using the following keys

F1, F2, F3 - change display colors
F5 - go to black and white
F6 - white on black
F8,F9,F10 - change background in VGA mode (gradual changes)

6. Version 3.3 supports display and printing of graphs in EGA and VGA modes
on Epson and HP Laserjet compatible printers. This allows much nicer results
in the printout of graphs. Not all combinations of printers and monitors are
supported when printing graphs. If you have problems printing graphics, try
another selection in the setup routine (Helps menu) For example, if you are
unable to print using the high resolution Epson or Laserjet options, try the
low resolution options. The high resolution options ONLY work for EGA and VGA
monitors and high-res Epson or Laserjet printers.

7. You can capture an EGA or VGA graphic screen into a PCX file. Display a
captured PCX graph by using the command SHOW from the DOS prompt. For
example, if you capture the file named GRAPH.PCX, enter

        SHOW GRAPH.PCX EGA

if captured in EGA mode. Use VGA in the command if captured in VGA mode.
Captured graphs can be imported into programs such as word processors,
slideshow programs, publishing programs, etc. that support the PCX
standard. When you import into WordPerect, you usually need to choose
to change the graph to black and white, invert the colors and scale
the graph to get the best detail.

8. Because it caused so many questions, a plot now usually does not ask
you what monitor type to use -- it uses only the one you specified in
the setup. This (hopefully) means that the program will be able to
handle printing graphs more consistently. If you miss this feature, you
can bring it back by copying the file SHOW.BAT to MCHOICE.INI (i.e.
COPY SHOW.BAT MCHOICE.INI). If you want a plot displayed in a different
monitor type, or if you like the way it prints using a different monitor
type (some people like the CGA/Laserjet printout better than the
VGA/Laserjet printout), you can choose a different monitor/printer by
choosing the Setup option from the Helps menu or by running the KSETUP
program from the DOS prompt.

9. In crosstabulations, you are given the option to choose what numbers
will appear in the table - Expected values, Contribution to Chi-Square
and Row/Col/Total Percents. The new entry not descibed in the manual is
called CONTRIB. This number is the "contribution to Chi-Square". That
is, the number shows how much a particular cell contributed to the
size of the Chi-Square statistic. This often comes in handy when you
are trying to discover what may have caused a table to result in a
low p-value (a high Chi-Square statistic).

10. Copy/Backup option in Data menu - this option allows you to copy a
database to a new filename or destination or to make a backup copy of
your database. If you are going to be doing manipulation of a database,
it is a good idea to make a backup first, in case a problem occurs that
effects data in your original database.

11. Multiple regression now allows 20 variables. However, if you push the
program to the limit with many variables and hundreds of records, you may
run into an out-of-memory problem.

12. The maximum length of a path for Kwikstat is 30 characters.

13. Beginning with release 3, there are two additional functions available
in the database. AVE(list) and SD(list), which calculates an average of the
listed fields and SD calculates the standard deviation. For example, If you
have fields named REP1, REP2 and REP3, doing a Field Replace with
=AVE(REP1,REP2,REP3) will place the average in the field. Doing a Field
replace with =STD(REP1,REP2,REP3) will place the standard deviation of the
three numbers in the field. Add the Math Calculator functions to the table
on page 2-51.

14. To support network use, Release 3 causes all temporary files to be
stored on the defined default path (you specified in setup). This means
that if you are running Kwikstat on a network, using your local machine as
the default Kwikstat path, all temporary files used by Kwikstat will be
stored on your local disk. This prevents problems caused by more than two
people trying to access the same temporary file at the same time.

15. When you choose edit from the Data menu, it goes directly to record 1
for editing. Use the Goto (F5) to move to a specific record once you are in
editing mode.

16. The Old TRANSFORMATION option in the data menu has been replaced by a
two step procedure. See manual pages 2-43 and 2-44. Briefly, you can now
create a new field without having to enter some number in the field. To
create a new field containing a value calculated from other field, first
create a new field, then replace the contents of the new field. These
options are easiest in the spreadsheet edit mode.

When entering a transformation (replace) or a subset equation, you must
be careful to enter it correctly. Here are some potential problems:

1. If you incorrectly spell a field name, the value for that field in
the equation will probably be evaluated as 0.
2. Do not use field names that have blanks in the names - or field names
that contain the characters /*+-^. Of course, field names SHOULD consist
only of numbers, letters and the underscore "_".

17. If you create a new variable by transformation (replace), be sure to
set missing values for all variables in that database -- the default missing
values are set at 0 (zero), so if you do not set new ones, any record
that contains a 0 in a field to be calculated will cause the result
to me a missing value (0).

18. (release 6) - New options have been added to the Delete option in the
data editor. When you choose Delete (F3), you can then choose to

 - Mark the current record for delete (or Unmark)
 - Mark or Unmark all records in the current field that match the current
   record field value.
 - Mark or Unmark a range of records.

This option allows you to easily perform an analysis on a portion of the
data without having to perform a subset. When records are marked for
deletion they will not be used in an analysis. For example, if you have
data that has a record called SEX, which contains the values F or M, and
you want to perform an analysis only on M, you could highlight the SEX
field in a record containing a F, then choose to mark for delete all
records where SEX = "F". After performing the analysis, you can
undelete the records to being your data set back to normal.

19. (release 7) - In edit there is now an Er/Ins option as F4. This
option now allows you to ERASE a record or INSERT one or more a blanks
record at the cursor position.