Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Estimate 95th percentile of a highly skewed distribution from summary stats?


From   "Feiveson, Alan H. (JSC-SK311)" <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: st: Estimate 95th percentile of a highly skewed distribution from summary stats?
Date   Wed, 7 Aug 2013 18:53:12 +0000

Jordan - Using only the information you have given, here's three possible distributions assuming yours is a mixture of a mass at zero with probability PZ, and a gamma(la, al) with probability 1- PZ. Since the median is still zero and the 75th percentile is 7, this bonds PZ between .50 and 0.75. As you can see, using this model produces values of the 95th percentile between 9.01 and 13.6


P(zero)    alpha     lamda      mean       75th      95th 
.74       2.3958     8.0270     5.0000     7.0005    13.6025
.60       2.4631     5.0750     5.0000     7.0003     9.7534
.51       1.7765     5.7440     5.0000     7.0001     9.0110


p.s. This was fun!

Al Feiveson

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Jordan Silberman
Sent: Wednesday, August 07, 2013 10:58 AM
To: [email protected]
Subject: Re: st: Estimate 95th percentile of a highly skewed distribution from summary stats?

Thank you Nick. Yes, unfortunately I know nothing about the distribution other than what I posted, so a simple summarize command won't work. Jordan

On Wed, Aug 7, 2013 at 7:42 AM, Nick Cox <[email protected]> wrote:
> Evidently the point of this is that _you know nothing except what you 
> have shown us_.
>
> Otherwise -summarize, detail- would do this for you, without even 
> needing to look up the more specialised commands it cross-references.
>
> The flip answer is somewhere in [7, 50]. I don't know how to improve 
> on that flip answer without making very strong assumptions about the 
> distribution. You don't even know what the fraction of zeros is.
>
> If this were my problem I would use the maximum, knowing that it is biased.
> Nick
> [email protected]
>
>
> On 7 August 2013 12:23, Jordan Silberman <[email protected]> wrote:
>> Hi Stata folks,
>>
>> I have some (but not all) descriptive stats for a highly skewed, 
>> zero-inflated distribution. I need to estimate the 95th percentile 
>> score for this distribution.
>>
>> Here's the info I have:
>>
>> min value: 0
>> max: 50
>> mean: 5
>> median: 0
>> 75th percentile: 7
>>
>> Obviously the distribution is highly skewed to the right. Does anyone 
>> know of a method through which I can estimate the 95th percentile 
>> score for this distribution?
>>
>> The background is that this is a distribution of estimation errors 
>> for an algorithm, and I need an estimate of a value that the error is 
>> equal to or less than in 95% of cases.
>>
>> Thanks,
>> Jordan
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>> *   http://www.ats.ucla.edu/stat/stata/
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index