Re: st: standard normal distribution

[Nick Cox <njcoxstata@gmail.com>]

Yes; this is a radical misunderstanding.

You appear to be averaging densities. Densities can't be negative and  
so their mean can't be zero. Their SD depends on the sample taken but  
as the range of density for a standard normal is less than 0.4 (as  
shown by these results) the SD will be even smaller.

Nick


On 27 Aug 2012, at 16:56, tashi lama <ltashi32@hotmail.com> wrote:

> Hello all,
>   This might be more of a statistical question than stata but I  
> would really appreciate if someone explain me this. I thought I  
> understood normal distribution until I see this. I have a standard  
> normal distribution table with N(mean=0,standard deviation=1) which  
> gives me the following
>
>      x          y
>  |---------------|
>  | -9   1.03e-18 |
>  | -8   5.05e-15 |
>  | -7   9.14e-12 |
>  | -6   6.08e-09 |
>  | -5   1.49e-06 |
>  |---------------|
>  | -4   .0001339 |
>  | -3    .004433 |
>  | -2   .0540047 |
>  | -1   .2420321 |
>  |  0   .3990434 |
>  |---------------|
>  |  1   .2420321 |
>  |  2   .0540047 |
>  |  3    .004433 |
>  |  4   .0001339 |
>  |  5   1.49e-06 |
>  |---------------|
>  |  6   6.08e-09 |
>  |  7   9.14e-12 |
>  |  8   5.05e-15 |
>  |  9   1.03e-18 |
>  | 10   7.70e-23 |
>  +---------------+
>
> summ y
> Variable |       Obs        Mean    Std. Dev.       Min        Max
> -------------+--------------------------------------------------------
>           y |        20    .0500127    .1105588   7.70e-23   .3990434
>
> Do I not must get mean of  y to be 0 and standard deviation to be 1  
> since it is a normal distribution N(0,1). Am I misunderstanding  
> something
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/