Any FM to calculate Standard Deviation .. ?

Hi All,
My requirement is to calculate the standard deviation for the work hours in a task list.Please let me know if there is any FM available to achieve this.
Cheers
Nishanth

Hi,
Check out using these two FM to calculate the standard deviation which is used for the track of a quality control chart, if you want to use the standard deviation as a control value for a quantitative characteristic in order to detect the dispersion changes for a characteristic. The second one uses the multiplicative factor for the chi-square distribution required for the calculation of the control limits is estimated on the basis of the total dispersion of all original values.
1)QRKT_STD_DEVIATION_SHEWHART
2)QRKT_STD_DEVIATION_SHEWHART_2
Regards,
Jagath

Similar Messages

How to calculate standard deviation of a certain number of points?

Hi, I have an application that I acquire force signals and pu then on a array.
I need to calculate the standard deviation and the mean each a certain number of points, 1000 for example.
I'm having problems with this, if you can help me I'd be thankful.
Thanks
Douglas
Solved!
Go to Solution.

So you need something like this?
There are only two ways to tell somebody thanks: Kudos and Marked Solutions
Unofficial Forum Rules and Guidelines
Attachments:
Std_Deviation.png ‏12 KB

Standard deviation in abap

Dear Freinds,
I want to calculate standard deviation of my internal table columns in abap code , please help me how to calculate it .
Thanks,
Naveen

hi,
try this code for calculating it:-
REPORT abc.
DATA : BEGIN OF itab OCCURS 0,
num TYPE i,
END OF itab.
data : std type p decimals 2.
itab-num = 8. APPEND itab.
itab-num = 25. APPEND itab.
itab-num = 7. APPEND itab.
itab-num = 5. APPEND itab.
itab-num = 8. APPEND itab.
itab-num = 3. APPEND itab.
itab-num = 10. APPEND itab.
itab-num = 12. APPEND itab.
itab-num = 9. APPEND itab.
PERFORM stdev changing std..
write :/ std.
FORM stdev CHANGING std.
DATA : mn TYPE p DECIMALS 2.
DATA : sm TYPE i.
DATA : sm2 TYPE i.
DATA : dev TYPE p DECIMALS 2.
DATA : cnt TYPE i.
LOOP AT itab.
sm = sm + itab-num.
cnt = cnt + 1.
sm2 = sm2 + ( itab-num * itab-num ).
ENDLOOP.
mn = sm / cnt.
dev = ( sm2 - ( ( ( sm * sm ) / cnt ) ) ) / ( cnt - 1 ) .
dev = SQRT( dev ).
std = dev.
ENDFORM. "stdev
Edited by: ricx .s on May 2, 2009 1:50 PM
Edited by: ricx .s on May 2, 2009 1:51 PM

Is there any bapi for standard deviation

is there any bapi for standard deviation

You can use the function module
1. 'QRKT_STD_DEVIATION_SHEWHART'-Algorithms for Shewhart chart for s with internal dispersion and mean line
2.'QRKT_STD_DEVIATION_SHEWHART_2'- Algorithms for Shewhart chart for s with overall dispersion and mean line.
You could also calculate it yourself of course - standard deviation is the square root of the sum of the square of the differences between the mean and each value divided by the number of values you have less one.
Reward points..

Query designer and Standard deviation result rows

Hello everyone,
Here is my problem.
I have a key figure for which I do not want any decimals. So in the Number Format : Number of Decimal Places = 0.
I thought the result rows would follow the same rules by not displaying any decimals.
But using the Calculate Result as ... "Standard Deviation", even though my key figure is define with no decimals, the result row displays 5 decimals anyway !
Why? and is there any way I can suppress the decimals of my results rows with a Standard Deviation
Thx
JBF
Edited by: Jean-Baptiste Faubert on Jan 16, 2008 2:56 PM

Hello Jean,
First I would try to unmark flag 'Use default Settings' below Number of Decimal Places in Query Designer.
If this doesn't help you could set Decimal Places in the Provider specific Properties in Key Figure of the MultiProvider used from 'Not defined' to 0.
Also you could change the number of decimals in InfoObject maintainance of used Key Figure (in RSA1).
But then you have to check other queries where this Key Figure is used.
Kind regards
Klaus

How to calculate standard error in Numbers

How to calculate standard error in Numbers?

Urbinan,
STDEV will estimate the stardard deviation based on your sample and STDEVP will calculate the standard deviation of your entire population.
Jerry

Function module to calculate standrad deviation

Hi everybody...
gud morning
please do tell mei the standard function module for calculating standard deviation.

Hi,
You can use the function module
1. 'QRKT_STD_DEVIATION_SHEWHART'-Algorithms for Shewhart chart for s with internal dispersion and mean line
2.'QRKT_STD_DEVIATION_SHEWHART_2'- Algorithms for Shewhart chart for s with overall dispersion and mean line.
You could also calculate it yourself of course - standard deviation is the square root of the sum of the square of the differences between the mean and each value divided by the number of values you have less one.
Hope this helps.
Regards,
Sophia Xavier

Help on standard deviation please

I am writing a program to find standard deviation. Below is what I have so far "not much I know" but I have tried so don't get flame happy. It errors out and I have tried to fix it. I know the formula for standard deviaition but I can't seem to program it right. I also need to program the code to have three methods the main, an Average method, and a standard deviation method. I know how to make a method but I am having trouble on how to call them. Any help would be appreciated. I am not asking anyone to do my work for me just give me some tips. I would rather take a 0 on the assignement and learn later than turn in someone else's work becaue I will never pass my final if I do that.
import java.text.*;
import javax.swing.*;
class StandardDeviation{
     public static void main(String [] args){
     DecimalFormat df = new DecimalFormat("0.00");
     //Average Code Segment
          double [] values = {10,20,30,4,2}; //Assigns numbers to values
          double valueAverage,square, sum = 0;
          for(int i = 0; i < values.length; i ++){
               sum += values;
          valueAverage = sum / 5; //Computes Average
          System.out.println("Average is: " +valueAverage); //Displays average of values to test to see if it worked
//Deviation Code Segment
for (int i = 0; i < values.length; ++i)
double diff = values - valueAverage;
sum+= diff*diff;
System.out.println(+ Math.sqrt(sum/(values.length - 1))); // here I was trying to test to see if my formula worked
I get the following error
java:20: operator - cannot be applied to double[],double
double diff = values - valueAverage;

Okay this code works. Duffymo can you give me some pointers of writing this code using multiple methods? I can write the methods. I just have a hard time grasping the concept of calling them. I have had a hard time learning this in java. I also looked at some of your past posts on Standard Deviation I see what you are saying about the multiple methods. I know that I need a main method that would probably include the values. Then I would have a average method which would call the values to compute the average. Then I would have the StdDev method to compute the Standard deviation method. Any tips on where to begin on this?
mport java.text.*;
import javax.swing.*;
class StandardDeviation{
     public static void main(String [] args){
     DecimalFormat df = new DecimalFormat("0.00");
     //Average Code Segment
          double [] values = {10,20,30,4,2}; //Assigns numbers to values
          double valueAverage,square, sum = 0;
          for(int i = 0; i < values.length; i ++){
               sum += values;
          valueAverage = sum / 5; //Computes Average
          System.out.println("Average is: " +valueAverage); //Displays average of values
          //return valueAverage;
     //Deviation Code Segment
for (int i = 0; i < values.length; ++i)
double diff = values[i]- valueAverage;
sum+= diff*diff;
System.out.println("The Standard deviation is: "+ df.format(Math.sqrt(sum/(values.length - 1))));

Standard Deviation

I was wondering how you get the standard deviation to show up on the graph. I know where the button is to activate the standard deviation for a simple bar chart, however it doesn't show the actual deviation, it gave me uniform for each bar in the chart. How can I fix this? Also I know that the standard deviation isn't the same because I have seen what the chart I am making is supposed to look like.

cgord wrote:
... I know that the standard deviation isn't the same because I have seen what the chart I am making is supposed to look like.
cgord,
The problem is that Numbers doesn't know what your chart is supposed to look like. It's doing the best it can. There is no such thing as a standard deviation for a single point. Numbers considers that your series is a data set and calculates a mean and standard deviation for the set. It then applies this mean and deviation to the error bars, in a proper way, the same for each member of the set.
If your data set is actually a collection of dataset averages, each with a standard deviation of its own, then it might be appropriate to show each bar with it's own custom error bar, calculated elsewhere.
To make this work, you would display each bar's corresponding StdDev in the same row as the mean you are charting and then you would indicate to Numbers which column this custom error bar data is located.
Hope this helps.
Jerry

Standard Deviation Calculation

I'm trying to calculate a standard deviation using the following formula, @STDEVRANGE (SKIPBOTH, "nibt", @CURRMBRRANGE (TIME, GEN, 5, -24,0)); but I keep getting an error..."@currmbrrange must be used as a range parameter"Did anyone ever get this before, and if so, how did you resolve it?Thanks!

Why not separate methods for each?
The suggestion from the previous poster is a good one. Your problem is probably due to roundoff. Donald Knuth did some work on this:
While this method is correct in theory and will often work well enough, it is extremely vulnerable to the effects of roundoff error in computer floating point operations. It is possible to end up taking the square root of a negative number! The problem, together with a better solution, is described in Donald Knuth's "The Art of Computer Programming, Volume 2: Seminumerical Algorithms", section 4.2.2. The solution is to compute mean and standard deviation using a recurrence relation, like this:
M(1) = x(1), M(k) = M(k-1) + (x(k) - M(k-1) / k
S(1) = 0, S(k) = S(k-1) + (x(k) - M(k-1)) * (x(k) - M(k))
for 2 <= k <= n, then
sigma = sqrt(S(n) / (n - 1))
Knuth attributes this method to B.P. Welford, Technometrics, 4,(1962), 419-420.
%

Standard deviation in VaR

Dear SAP people,
how do the system calculate the standard deviation in VaR with
historical simulation assuming normal distribution?
In the documentation I can read: "the standard deviation is determined
using a statistical estimation".
Can you give me further information about the statistical procedure
used?
Gianmaria Basile

Dear lwo,
You can add two more channels.
One with mittelwert+standardabweichung/2
and one with mittelwert-standardabweichung/2 .
Then configure them to show only symbols and no line.
Color them red and choose a cross as symbol.
Be sure, the mittelwert channel is the first one in the array,
or the bars will hide the crosses.
Best regards,
Stefan Heinzl
Message Edited by Stefan Heinzl on 03-09-2009 09:56 AM
Attachments:
Block Diagram.jpg ‏17 KB
Front Panel.jpg ‏40 KB

Standard deviation in Diadem - Population or Sample formula?

Hi all,
I am an Applications Engineer here at NI and I have been working with a customer on the following issue:
DIAdem-Idea-Exchange/DIAdem-Standard-Deviation-Weighting
Essentially you are unable to specify which formula the standard deviation function uses. Attached to this post is an example VBScript that reads data from a column in Excel and calculates the standard deviation using the Population formula. I hope this serves as a useful starting point to anyone looking to add this functionality.
Kind regards

I've just noticed the URL doesn't link correctly, here is a working one:
DIAdem-Idea-Exchange/DIAdem-Standard-Deviation-Weighting

Reg.Standard Deviation

Hi,
I am having following scnario of limits for the MICs
Char Lower Limit Upper Limit s/d-0.02
C 0.08 0.12
in the result recording if the user enters more than the specification system should check with standard deviation and valuation should happen according to standard deviation.
which field i have to use in the quantitative tab,how to solve this.
this varies material to material.
Regards,
Selva.

Hi Selva,
You can use following functionality, which may serve your purpose.
Variable Inspection
Use
In a variable inspection, you must specify at least one tolerance limit in the inspection plan for the quantitative characteristic in question. ISO 3951 serves as a standard for a variable inspection. The Quality Management application component has two valuation procedures for variable inspections:
S-method, single-sided tolerance range
S-method, double-sided tolerance range
When you perform a variable inspection according to the s-method for normally distributed characteristic values, the sample size, mean value (x-bar), and standard deviation (s) of the characteristic values are required as inspection results. Depending on the recording form used, you either enter the statistics, or the system calculates them from the single values.
Depending on whether there is an upper specification value (USL) or a lower specification value (LSL) for the characteristic values, the inspection characteristic is rejected if the following conditions are met:
Mean > USL - k * s
or
Mean < LSL + k * s
The value k is the acceptance factor defined in the sampling plan. The mean value and standard deviation must be known.
If the tolerance range is limited on both sides (double-sided), there are two variants for conducting the s-method valuation. You define which variant is used in the function module for the valuation rule. The variants differ in their acceptance range.
When the s-method uses the double-sided tolerance range, both limits of the tolerance range are treated together. The share above the tolerance range and the share below are estimated and compared with a critical value that is calculated from the sample size and acceptance factor. This form of variable inspection leads to the same decision as the graphical procedure described in the ISO 3951 standard (see the figure below). Given the same sampling plan, the acceptance range is smaller than for the variant of the s-method in which the two limit values are handled separately. In this case, the upper and lower specification values are checked separately. The characteristic is rejected when one of the two rejection conditions is met.
Regards
Suhas

Calculate standard composition via EH&S Expert

I'm having a hard time finding out how EH&S expert is use to calculate standard composition on the real sub.
It would be greatly appreciated if someone could answer the following questions:
What are the prerequisites?
What is the process for maintaining the master data?
Best regards / Gustav

Expert can only be used to drill down into the components of another composition that has already been filled out. Typically, Exact Composition by Product will have your raw/real sub composition filled in by some other process (BOMBOS, manually, I believe recipe management can do it... there may be other options). After Exact Comp is filled with a composition, only then expert run a rule that can drill down into each component to get the pure sub base components and fill out your standard comp.
I'm not sure if you've used Expert before, but Expert can't perform any logic on it's own, you must have a ruleset set up for it to run. Assuming you don't have Expert already set up, you first need to setup Expert on a Windows Server. Expert can be obtained from SAP Service MarketPlace. Instructions can be found in customizing (SPRO) under EHS->Basic Data and Tools->Tools-> EH&S Expert. You then have to develop or purchase a rule to do what you need. Documentation for developing Expert Rules can be found at http://help.sap.com/saphelp_erp60_sp/helpdata/en/c1/eda0f591ec12408b25e7a1b369ca45/frameset.htm under Specification Management->Specification Editing->Secondary Data Determination->EH&S Expert. I assume that most companies (including SAP) that have a content and rule package would have a standard composition rule that they could sell you if developing one doesn't seem to be a good option.

Standard Deviation In Oracle

Hi,
I have a set of values with me which is retrieved using a query.
I have to calculate mean,median and standard deviation of these values.
Please help me how to implement this in the query.
How do I find standard deviation with these values?
Thanks
Priya

How do I find standard deviation with these values?read about STDDEV in the documentation
oops, ... way too late

Any FM to calculate Standard Deviation .. ?

Similar Messages

Maybe you are looking for