area under the curve

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

area under the curve

juanreynel
hi, how can I graph (step by step) a two tailed probability test under the normal gaussian curve. For example, find and graph the the probability that a subject's cholesterol level will be lower than one standard deviation below the mean and higher than two standard deviation above the mean. thanks reydeniro.
Reply | Threaded
Open this post in threaded view
|

Re: area under the curve

Richard Ristow
At 12:09 AM 3/20/2008, reydeniro wrote:

>hi, how can I graph (step by step) a two tailed probability test under the
>normal gaussian curve. For example, find and graph the the probability that
>a subject's cholesterol level will be lower than one  standard deviation
>below  the mean and higher than two standard deviation above the mean.
>thanks reydeniro.

No need. Look in the Command Syntax Reference, section Universals,
sub-section "Random Variable and Distribution Functions." Cumulative
distribution functions are available for many standard distributions,
including the normal.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Reply | Threaded
Open this post in threaded view
|

Re: area under the curve

Richard Ristow
At 01:48 PM 3/20/2008, juan reynel suarez la O wrote, off-list:

>I am not satisfied with your answer, I definetely want to
>graphycally represent the two tailed area based on the problem that I wrote.

I'm posting back to the list, because others may have better ideas
how to help you.

If you want a graph of a Gaussian, it's easy to generate a lot of
points (probably in an INPUT PROGRAM) and graph them. If you want to
numerically integrate that or any other function, most
numerical-integration methods are sequential, and should work across
SPSS cases with a little use of LAG.

And for details on how to get particular graphs, others will know
better than I.

-Good luck to you,
  Richard Ristow

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD