Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: entering data


From   kusi@yorku.ca
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: entering data
Date   Sun, 21 Jul 2002 17:47:21 -0400

Dear listers,
can anyone help me with the following awkward task.
I have generated variables a and b  ,so as to form a triangular 
distribution,hence a  non -normal one.I saved the data as clt.dta  and then I 
ran the following commands for 100 times and ended up with the following,(I am 
only using the commands associated with sample of 32,to save space.But I ran 
the 100 commands for a sample of 2 ,to get the feel of the resulting 
distribution,)
.What I tried to do then was to enter the means of a and b for each run of the 
commands,but soon enough I discovered that it was an awkward task.I believe 
that in nc151 there was a part which dealt with zeroing on specific columns to 
retrieve returned data.Can anyone help me with that,thus saving me from going 
through all that work of rewriting and then reentering the specific data in 
edit.
Thanks 
. use clt ,clear

. sample 32
(68 observations deleted)

. summarize

Variable |     Obs        Mean   Std. Dev.       Min        Max
---------+-----------------------------------------------------
       a |      32    55.03125   30.70619          5        100  
       b |      32    18.34375    10.2354   1.666667   33.33333  

. 
. use clt ,clear

. sample 32
(68 observations deleted)

. summarize

Variable |     Obs        Mean   Std. Dev.       Min        Max
---------+-----------------------------------------------------
       a |      32    51.34375   30.83736          2         99  
       b |      32    17.11458   10.27912   .6666667         33  

. 

one hab dATA  iAfter generating a triangular distribution ,so as I trtQuoting 
David Greenberg <dg4@nyu.edu>:

> Look for discussions of the Central Limit Theorem. Depending on the 
> text, you will find formal mathematical demonstrations of the result, or 
> mathematically undemanding discussions that make the theorem plausible 
> even if, at first sight, it seems counter-intuitive. David Greenberg
> 
> ----- Original Message -----
> From: kusi@yorku.ca
> Date: Sunday, July 21, 2002 3:27 pm
> Subject: Re: st: Re: normal distributions
> 
> > Thanks,but that is why I am concerned about my inability to get 
> > its 
> > intuition.It seems contradictory to me,that an inherently 
> > negatively or 
> > positively skewed population distribution,could be normalised,by 
> > enlarging the 
> > sample size.If anything,that should retrace the skewness and not 
> > normalize the 
> > skewness.
> > Victor
> > 
> > 
> > Quoting David Greenberg <dg4@nyu.edu>:
> > 
> > > This topic is discussed in virtually every introductory 
> > statistics 
> > > textbook. David Greenberg, Sociology Department, New York 
> > University. 
> > > 
> > > ----- Original Message -----
> > > From: kusi@yorku.ca
> > > Date: Sunday, July 21, 2002 1:33 pm
> > > Subject: st: Re: normal distributions
> > > 
> > > > Dear subscribers,
> > > > can anyone help me understand how is it that for types of 
> > > > population 
> > > > distributions that are non-normal the sampling distribution of 
> > > > Xbar is 
> > > > approximately normal for sufficiently large samples.
> > > > Thanks Victor Michael Zammit
> > > > *
> > > > *   For searches and help try:
> > > > *   http://www.stata.com/support/faqs/res/findit.html
> > > > *   http://www.stata.com/support/statalist/faq
> > > > *   http://www.ats.ucla.edu/stat/stata/
> > > > 
> > > 
> > > *
> > > *   For searches and help try:
> > > *   http://www.stata.com/support/faqs/res/findit.html
> > > *   http://www.stata.com/support/statalist/faq
> > > *   http://www.ats.ucla.edu/stat/stata/
> > > 
> > 
> > 
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/support/faqs/res/findit.html
> > *   http://www.stata.com/support/statalist/faq
> > *   http://www.ats.ucla.edu/stat/stata/
> > 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index