Additional Statistical Functions

I am new to numbers and working on a dissertation. I have 24 subjects that answered a pre and post test to measure perception. I have assigned all questions and potential answers with numerical values.
Has anyone used the statistical additional functions doing linear regression? I know there has to be a
way to run it across one row and 24 columns, I just can't seem to figure out how. Can anyone help?

webster212 wrote:
Has anyone used the statistical additional functions doing linear regression? I know there has to be a
way to run it across one row and 24 columns, I just can't seem to figure out how. Can anyone help?
You know a wrong info.
If you need to do linear regression in Numbers, you must use the mathematical formulas defining the property.
Yvan KOENIG (from FRANCE mercredi 23 avril 2008 08:58:06)

Similar Messages

BAPI to add additional partner functions in customer master(KNA1)

Hello All,
I wanted to add additional partner functions(2) to the list of partner functions which gets added by default while creating a customer. I am currently using BAPI_CUSTOMER_CREATEDATA1 to create the customer master. There i do not find any option to add my partner functions.
NOTE: I need to update KUNN2 field as well while adding my partner functions.
Could anyone please help here?
Regards,
Jay

Hi,
No you should not feel confident with SD_CUSTOMER_MAINTAIN_ALL.
It is used for only one very special case. The maintenance of consumer. And this should only be true from the transaction itself.
There exists other cases, one of the oldest one is the BAPI_CUSTOMER_CREATEFROMDATA1. But is is exclusively reserved for SAP Online store.
Despite the fact CMD_EI_API is quite difficult to use, it has the main benefit that is it supported if being triggered directly.
For the maintenance of customers, there is NO BAPI and NO direct function module.
There are some functions modules like the one above where the name is looking nice. But these should not be used.
The only valid solutions are :
Below ECC 2005 (6.00), the only solution was batch input and DEBMAS idocs. See note 384462
Starting with ECC 2005 (6.00) and above: a synchronisation tool has been introduce. See class CMD_EI_API and VMD_EI_API
Hope this helps
BR
Alain

Using advanced statistical functions in BO or creating your own ones

Hello,
Can someone tell me if it is possible to use more advanced statistical functions in BO (webi or deski f.i.) like the possibility to extrapolate figures. I only see a limited functions in Webi (mean, intrapolate, percentiles, ...).
If not is it then possible to add own functions in the available functions?
many regards

I believe there are more possibilities in WEbi 4.O

I purchased an additional audio function for the apps ＂baby monitor＂today, but this function didn't work on my ipad. Grateful if you would let me know how to refund the cost.

I purchased an additional audio function for the apps ＂baby monitor＂today， but this function didn't work on my ipad. Grateful if you would let me know how to refund the cost.

Refund
http://www.apple.com/emea/support/itunes/contact.html

Add statistical function to this?

I have this SQL which aggregate quantity per week.
WITH weeks_vw AS
    ( SELECT DISTINCT TO_CHAR(fill_year_day,'IYYYIW') AS fill_year_week
            FROM
           ( SELECT to_date('2012-11-01','yyyy-mm-dd') + (ROWNUM-1) AS fill_year_day
                    FROM    DUAL
                    CONNECT BY      LEVEL <= TRUNC(to_date('2012-12-10','yyyy-mm-dd') - to_date('2012-11-01','yyyy-mm-dd') ) + 1)
SELECT a.material, a.plant, sum(NVL(quantity,0)) AS sales_qty_sum
    FROM
SELECT t.material, t.plant, t.quantity, TO_CHAR(t.posting_date,'IYYYIW') AS posting_week
         FROM    tblTotalCom t
         Where     t.plant = '1900'
         AND     t.Posting_date >= to_date('2012-11-01','yyyy-mm-dd')
         AND     t.Posting_date <= to_date('2012-12-10','yyyy-mm-dd')
         AND     t.material = 'Label1' ) A
    PARTITION BY (a.material,a.plant) RIGHT OUTER JOIN weeks_vw ON weeks_vw.fill_year_week = A.posting_week
    GROUP BY a.material, a.plant, fill_year_weekNow I want to add a statistical function as below in this SQL to remove outliers.
WITH     got_analytics     AS
     SELECT       deptno
     ,       ename
     ,       sal
     ,       AVG (sal)    OVER (PARTITION BY deptno)     AS avg_sal
     ,       STDDEV (sal) OVER (PARTITION BY deptno)     AS stddev_sal
     FROM       scott.emp
SELECT       a.*
,       CASE
           WHEN ABS (sal - avg_sal)     > stddev_sal * 1.0   -- Change this number
           THEN '*** Outlier ***'
       END     AS outlier
FROM       got_analytics a
ORDER BY deptno
,            sal
;Do not know how to do it ...?

Why did you answer that as a question? Are you not sure which approach you need? Is my question unclear? Obviously, it's hard to provide something that helps you if we're not sure exactly what you are trying to accomplish...
WITH weeks_vw AS
    ( SELECT DISTINCT TO_CHAR(fill_year_day,'IYYYIW') AS fill_year_week
            FROM
           ( SELECT to_date('2012-11-01','yyyy-mm-dd') + (ROWNUM-1) AS fill_year_day
                    FROM    DUAL
                    CONNECT BY      LEVEL <= TRUNC(to_date('2012-12-10','yyyy-mm-dd') - to_date('2012-11-01','yyyy-mm-dd') ) + 1)
SELECT material,
      plant,
      sales_qty_sum,
      avg(sales_qty_sum) over () avg_sum,
      stddev(sales_qty_sum) over () std_dev_sum,
      abs((sales_qty_sum - avg(sales_qty_sum) over ())/ stddev(sales_qty_sum) over ()) stddevs_away
FROM (
      SELECT a.material, a.plant, sum(NVL(quantity,0)) AS sales_qty_sum
          FROM
            SELECT t.material, t.plant, t.quantity, TO_CHAR(t.posting_date,'IYYYIW') AS posting_week
              FROM    tblTotalCom t
             Where     t.plant = '1900'
              AND     t.Posting_date >= to_date('2012-11-01','yyyy-mm-dd')
              AND     t.Posting_date <= to_date('2012-12-10','yyyy-mm-dd')
              AND     t.material = 'Label1' ) A
       PARTITION BY (a.material,a.plant) RIGHT OUTER JOIN weeks_vw ON weeks_vw.fill_year_week = A.posting_week
       GROUP BY a.material, a.plant, fill_year_week)should compute the average sum, the standard deviation of the sum, and the number of standard deviations a particular row is from the mean. You can then filter out those rows that are more than 1 standard deviation from the mean
WITH weeks_vw AS
    ( SELECT DISTINCT TO_CHAR(fill_year_day,'IYYYIW') AS fill_year_week
            FROM
           ( SELECT to_date('2012-11-01','yyyy-mm-dd') + (ROWNUM-1) AS fill_year_day
                    FROM    DUAL
                    CONNECT BY      LEVEL <= TRUNC(to_date('2012-12-10','yyyy-mm-dd') - to_date('2012-11-01','yyyy-mm-dd') ) + 1)
SELECT *
FROM (
SELECT material,
      plant,
      sales_qty_sum,
      avg(sales_qty_sum) over () avg_sum,
      stddev(sales_qty_sum) over () std_dev_sum,
      abs((sales_qty_sum - avg(sales_qty_sum) over ())/ stddev(sales_qty_sum) over ()) stddevs_away
FROM (
      SELECT a.material, a.plant, sum(NVL(quantity,0)) AS sales_qty_sum
          FROM
            SELECT t.material, t.plant, t.quantity, TO_CHAR(t.posting_date,'IYYYIW') AS posting_week
              FROM    tblTotalCom t
             Where     t.plant = '1900'
              AND     t.Posting_date >= to_date('2012-11-01','yyyy-mm-dd')
              AND     t.Posting_date <= to_date('2012-12-10','yyyy-mm-dd')
              AND     t.material = 'Label1' ) A
       PARTITION BY (a.material,a.plant) RIGHT OUTER JOIN weeks_vw ON weeks_vw.fill_year_week = A.posting_week
       GROUP BY a.material, a.plant, fill_year_week))
WHERE stddevs_away <= 1Note that this will generally filter out ~33% of your data if you assume a normal distribution so this is a rather odd definition of "outlier". I believe in the earlier question you asked, it was suggested that you would probably want to pick cutoff of more than 1 standard deviation
Also, it would be very helpful if you posted the DDL to create the table, the DML to populate some sample data, and the expected results. Obviously, since I don't have your tables, I can't test the queries I posted which makes it very possible that I introduced an inadvertent syntax error.
Justin
Edited by: Justin Cave on Dec 11, 2012 5:15 PM

Additional laptop function keys and KDE

Hello everybody. If I install all KDE packages with:
sudo pacman -S kde
I got native support for all my laptop function keys (like volume control, mute, etc...) with also graphic icons showing up when I choose a function. Of course I also get a ton of other software which I don't need. Sadly to say, installing only kde-base (which of course is the way I want to proceed in order to fully configure my system only with what I need) doesn't provide this functionality. I spent some time looking at all KDE packages with:
pacman -Ss kde | less
to find out the one I need, without success. Has anyone any idea about the packages I may need to install? Thank you.
Last edited by Y3k (2011-10-03 01:12:05)

Moderator comment:
Perhaps the lack of response means there is no one out here with an answer. Maybe you should provide more information, or tell us what you learned in half day since the first post.
For example, do you think that telling us the type of laptop might be useful?
Please read our policy

SQL Statistical functions?

Trying to execute from ttisql to my readonly cache group:
Var_samp, Var_pop, stddev_samp, stddev_pop, median, and stats_mode all failed in TT. Is there no support for these statistics functions? If not, when can I expect to see them supported?
regards,
Henri

No, I'm afraid that we don't currently support any of those functions, sorry. I'm not sure yet what is planned for the next release so I can't say if they will be in that or not.
Chris

Inverse Normal Distribution function SAP Bex Query

Hi All
In BEx Query designer there are different aggregation types available i.e. min, max,average, standard deviation etc. for
formula or calculated key figure.There are not any additional statistical functions such normal distribution, inverse normal distribution available in Bex query designer. How to achieve normal distribution, inverse normal distribution as aggregation
type in Bex Query designer? Your help is appreciated.
Thanks

Hi Dennis,
We have done the similar thing recently but performance of crystal reports is very poor on bex query. Did you face the same thing? Any suggestions/ideas to improve performance..
Thanks,

SQL User Defined Functions for performing statistical calculations

Hi!
   I hope you can help. I just wasn’t sure where to go with this question, so I’m hoping you can at least point me in the right direction.
   I’m writing a SQL Server stored procedure that returns information for a facility-wide scorecard-type report. The row and columns are going to be displayed in a SQL Server Reporting Services report.
   Each row of information contains “Current Month” and “Previous Month” numbers and a variance column. Some rows may compare percentages, others whole numbers, others ratios, depending on the metric they’re measuring. For each row/metric the company has specified whether they want to see a t-test or a chi-squared statistical test to determine whether or not there was a statistically significant difference between the current month and the previous month.
   My question is this: Do you know where I can find a set of already-written user defined functions to perform statistical calculations beyond the basic ones provided in SQL Server 2005? I’m not using Analysis Services, so what I’m looking for are real SQL User Defined Functions where I can just pass my data to the function and have it return the result within a stored procedure.
   I’m aware that there may be some third-party statistical packages out there we could purchase, but that’s not what I’m looking for. And I’m not able to do anything like call Excel’s analysis pack functions from within my stored procedure. I’ve asked. They won’t let me do that.   I just need to perform the calculation within the stored procedure and return the result.
   Any suggestions? Is there a site where people are posting their SQL Server UDF’s to perform statistical functions? Or are you perhaps aware of something like a free add-in for SQL that will add statistical functions to those available in SQL? I just don’t want to have to write my own t-test function or my own chi-squared function if someone has already done it.
Thanks for your help in advance! Oh, and please let me know if this should have been posted in the TSQL forum instead.  I wasn't entirely sure.
Karen Grube

STATS_T_TEST_
docs.oracle.com/cd/B19306_01/server.102/b14200/functions157.htm
STATS_T_TEST_ONE: A one-sample t-test
STATS_T_TEST_PAIRED: A two-sample, paired t-test (also known as a crossed t-test)
STATS_T_TEST_INDEP: A t-test of two independent groups with the same variance (pooled variances)
STATS_T_TEST_INDEPU: A t-test of two independent groups with unequal variance (unpooled variances)

Statistical calc with MDX question (Mode function as an excel)

Hi All,
I need to create an MDX Calc to Returns the most frequently occurring, or repetitive, value in an array or range of data.
For example, the mode of 2, 3, 3, 5, 7, 10 is 3.
In Excel I use the MODE() function but I don't know how to do this in MDX and add it as a measure in Universe.
I can't do the formula in WEBI because we have big data volume and I can't retrieve all the customers in WEBI.
We have SAP BW 7.0 and SAP BusinessObjects XI 3.1 fix pack 1.3
Thanks in advance.

Hi,
it looks like you created the entry twice so I would suggest you close on of them:
Statistical calc with MDX question (Mode function as an excel)
I don't think that those kind of statistical functions are available in MDX. you can always go to se37 and use the bapi_get_functions to see the list of supported functions.
Ingo

Is it possible to extend Numbers' function list?

Hi,
I like Numbers, but, sadly, can't use it that much for my options trading because it lacks some important statistical functions like normdist().
Is it at all possible to extend Numbers myself to add this function? Its not hard to compute, but isn't the sort of thing you can do in a single expression.
Please advise.

Hello
This would require a single addition: the MACRO() function which is available in AppleWorks.
From my point of view it's a pity that they dropped it but *maybe I am in the 20% users which need it*
Yvan KOENIG (from FRANCE lundi 25 février 2008 19:00:56)

Create Support Message via BAPI with additional partners

Hi all,
i need to create a support message (slfn) via bapi / function module. The basic creation is no problem with BAPI_NOTIFICATION_CREATE.
But i need to set additional partner(functions) like "approved by" in the support message. With this bapi i can only set the processor and creator of the message.
How can i add additional partners via BAPI call?
Any help would be much appreciated.
Daniel

Hi Daniel,
i do not think there is a standard functionality for this.
you can use function module CRM_DNO_UPDATE_PARTNER to set partner functions to a message. You will have to build your own RFC enabled function module around this, though.
Then you can use it to add your partners after the message was created.
Regards,
Christoph

Is there a limitation on the no. of digits for constant function

hi
I want to compare a value of a certain field with a Constant with 89999999999 and pass the value only if it is less than this . I am using the less standard function and comparing the value .If it less than that only then I can pass the value however it is not able to compare more 7 digits.
Is this a limitation in the Constant Function?

Hi,
I know what is your problem coz I faced similar issue with Arithmetic function. So in order to solve the problem I added the paramter com.sap.aii.mappingtool.flib3.bigdecimalarithmetic in Exchange Profile as mentioned in the blog.
/people/thorsten.nordholmsbirk/blog/2006/08/25/new-arithmetic-and-statistical-functions-in-message-mappings-in-sp18
Note: After doing the changes you need to restart the JAVA server.
It works for me coz I have implemented the same in my system.
Regards,
Sarvesh

Digital Signature and workflow functionality in Enh Pack

We are working in ECC 6.0 environment. Recentaly we have activated Enh Pack 3 and 4 in our system. After that I can couple of additional QM functionality in system. SAP has provided few more settings in SPRO to activate digital signature in QN and workflow in standard peace.
I would be wonder if anyone has used those function in standard system without any custom development.
How can we use/ activate those (digital signature for QN and workflow) functionality? Reply appreciated.

SAP IMG > Quality Management> Quality Notifications> Notification processing> Specify Digital Signature
Give details like
Level -Header /Task Notification Type
Business
   Transaction
Signature Type
Strategy
Enter the Business Transaction: like PMM2 for Put notification in process,PMM4 for Complete notification,     QN40 for Release Task etc
Depending on your configuration systems asks for digital signature when you set header level status or Task level status
Means if u set Digital signature for PMM2 for Put notification in process system prompts for Digital siganture.
Regards
Nitin

Labview Executable with VISA functions in Run Time Engine

Hi Everybody
I designed a gui to communicate using VISA GPIB. I created an executable for the gui. I also installed LabView Run Time Engine on the desired machine. I recieved couple of errors, for which I copied the files visa32.dll, NIVISV32.dll and serpdrv to the folder with the executable.
I recieved the following error, ' Initialization of NIVISV32.dll failed. The process interminating abnormally.'
Are there any drivers I should install in addition to the Run Time Engine? If so, where can I find these drivers?
Thank you
Jackie

I installed NI-VISA with similar version as my development installation, and LV runtime engine. Labview still crashed.
I noticed certain library functions in full labview that is not present in the NI-VISA + LV run time directory, such as _visa.llb etc.
Do I need to copy these additional library functions too? Will Run Time Engine read these library functions?

Additional Statistical Functions

Similar Messages

Maybe you are looking for