How do I 'reverse engineer' the standard deviation? My problem is fairly concrete and direct. My company loves to do major business decisions based on many reports available on the media. These reports relates how our products are fairing in comparison to the competitor's offerings. The latest report had these scores (as percentages): Input values (%) 73.5, 16.34, 1.2, 1.15, 0.97, 0.94, 0.9, 0.89, 0.81, 0.31 Our product in the 'long' tail of this list. I argued with them that besides spots #2 and #1 all the other following the tail are on a 'stand', since, probably, the standard deviation will be much bigger that the points that separates everyone in the tail. So the question is: How may I calculate the standard deviation having only these percentual values available?

kjukks1234531 2022-09-23 Answered
How do I 'reverse engineer' the standard deviation?
My problem is fairly concrete and direct.
My company loves to do major business decisions based on many reports available on the media. These reports relates how our products are fairing in comparison to the competitor's offerings.
The latest report had these scores (as percentages):
Input values (%) 73.5, 16.34, 1.2, 1.15, 0.97, 0.94, 0.9, 0.89, 0.81, 0.31
Our product in the 'long' tail of this list. I argued with them that besides spots #2 and #1 all the other following the tail are on a 'stand', since, probably, the standard deviation will be much bigger that the points that separates everyone in the tail.
So the question is: How may I calculate the standard deviation having only these percentual values available?
You can still ask an expert for help

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

Solve your problem for the price of one coffee

  • Available 24/7
  • Math expert for every subject
  • Pay only if we can solve it
Ask Question

Answers (1)

xjiaminhoxy4
Answered 2022-09-24 Author has 9 answers
Without more information, you can't say much. Suppose you knew there was a survey question "Which product do you like best?" and the above numbers are the shares of products named.
If, in addition, you knew the sample size, e.g., N=1000, then you could compute the standard deviation of the mean (and consequently standard errors and confidence intervals):
s d ( x is best ) = 1 N # + 1 i = 1 N ( x i x ¯ ) 2 ,
where you have x ¯ N times x i = 1 and ( 1 x ¯ ) N times 100 x ¯ is the percentage from the survey, # the number of percentages computed from the data).
Without N, there's nothing you can say. Indeed, if they asked the whole population, then even a 0.01 difference is meaningful. But you are right, for small sample sizes the difference is likely not significantly different from zero.
Did you like this example?
Subscribe for all access

Expert Community at Your Service

  • Live experts 24/7
  • Questions are typically answered in as fast as 30 minutes
  • Personalized clear answers
Learn more

You might be interested in

asked 2022-09-26
Question : In a road traffic survey the number of cars passing a marker at a road was counted. The streams of cars in the two directions were a priori modelled as independent Poisson processes of intensities 2 per minute and 3 per minute, respectively. It was decided to stop the counting once 400 cars had passed. Let T 400 be that (random) time point and compute, using appropriate approximations, a time α such that P ( T 400 α ) = 0.90
Claimed Answer 85.1 minutes.
My Attempt : Since 400 cars passing with a rate of 5 cars/minute to pass in approximately 400 5 = 80 min. However this is not correct.
asked 2022-09-17
I have a bag of toys. 10% of the toys are balls. 10% of the toys are blue.
If I draw one toy at random, what're the odds I'll draw a blue ball?
asked 2022-09-11
Question about random samplings and estimations.
100 students were selected to participate in a survey by the school in May 2013. The next month, another 100 students were randomly selected to participate in the same survey, out of which 2 had already participate in the survey the previous month. If the number of students did not change from May to June then what is the approximate number of students in the school?
Came across this question. Is the question weird or am I just dumb? Can anyone suggest a way to solve this or an approach on how it can be solved. Thank you.
asked 2022-09-25
I had this question when I was shopping for some rates to refinance my house: how do know if I have found the lowest rates after searching through a bunch of offers with a reasonable amount of confidence, in a mathematical/statistical term. For example, if found "x" offers from different vendors, is the amount of "x" large enough to represent the bigger population i.e. all offers out there?
The reason I am asking is that I vaguely remember there are statistical sampling techniques from college days that survey companies used to represent the bigger populations. For instance, after surveying 2000 people, they can conclude something for the U.S. population. In other words, they "know" 2000 people can represent the U.S. population with some scientific backing.
Just curious, if there is a way to figure out the magical number "x", then I can go with the lowest rate after browsing through "x" vendors as well. The question is purely theoretical in this simple case: the lowest rate wins. Any leads or ideas are appreciated.
asked 2022-09-20
Which summary statistic and hypothesis test should be used?
A survey is conducted on 398 people that are either of type A (198) or type B (200) and answer 1 question on a 5 point scale 1=strongly agree, 2= agree,...5=strongly disagree.
What is the correct summary statistic and what hypothesis test should be used in answering: if the 2 types of people have differing opinions regarding the question?
attempt
Summarize using a 2 way table of type vs response (1,2,...,5), with a vector p ^ = ( p 1 p 2 p 3 p 4 p 5 ) as the summary statistic
This seems like a test of homogeneity is appropriate to answer the question but these people are drawn from the same population and cross-classified (right?) so then a test of independence (however a test of indep is unrelated to the question?)
asked 2022-09-25
A problem of Set Theory The question is :
In a market survey,a manufacturer obtained the following data :
Did you use our brand? Percentage answering yes
1. April 59
2. May 62
3. June 62
4. April and May 35
5. May and June 33
6. April and June 31
7. April,May and June 22
Is this correct?
That is the question.Now I don't really understand how to determine yes or not.Please help me.
asked 2022-09-30
A space X is unicoherent if whenever A,B are closed connected subsets of X such that A B = X, their intersection A Bis connected. The survey "A Survey on Unicoherence and Related Properties" by Garcia-Maynez and Illanes says that intuitively, a unicoherent space is a space with no "holes". For example, the closed disk in the plane is unicoherent, but the circle S 1 is not. This sounds like simple connectedness. For simple connectedness, by van Kampen's theorem, we have the following: if a space X has simply connected open subsets U,V such that U V = X and U V is nonempty and path-connected, then X is simply connected. It is then natural to ask a similar question for unicoherence. So, my question is: if a space X has closed unicoherent subsets A,B such that A B = X and 𝐴 𝐵 is connected, is X necessarily unicoherent? If necessary, you can assume that A,B are open rather than closed, or replace unicoherence conditions with open unicoherence conditions. Also, you can assume that 𝐴 𝐵 is nonempty if needed. Thank you in advance!

New questions