Inverse normal distribution function in MATRIX

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

Inverse normal distribution function in MATRIX

Beckstead, Jason

Hi All,

 

I am working with the MATRIX-ENDMATRIX procedure. I have a square matrix of probabilities and need to transform each value into a z-score. I note that there is a matrix function: CDFNORM referenced in the syntax guide (this takes z-scores and returns probabilities) but I do not see what I would guess I need, something like “IDFNORM”. Any help would be appreciated.

 

Jason

 

_____________________________________________________________

 Jason W. Beckstead, Ph.D.       

  Associate Professor/Quantitative Methodologist

  University of South Florida College of Public Health

  13201 Bruce B. Downs Blvd., MDC56, Tampa, FL 33612, USA

  Statistical Editor, International Journal of Nursing Studies

  phone: +1.813.974.7667  fax: +1.813.974.4719          

  personal website:  http://personal.health.usf.edu/jbeckste/

  International Journal of Nursing Studies  http://www.elsevier.com/ijns

 

===================== 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: Inverse normal distribution function in MATRIX

Jon Peck
 From the Syntax Reference Guide under MATRIX...

IDF.NORMAL. IDF.NORMAL(prob, mean, stddev). Numeric. Returns the value from the normal
distribution, with specified mean and standard deviation, for which the cumulative probability is prob.

The cdf and idf functions mimic the corresponding functions in the regular transformation system.  There is also a PROBIT function that is a special case of IDF.NORMAL.

You might have missed this, because there is also a CDFNORMAL function that doesn't follow the pattern.

I see this in the 25.0.0.2 SRG.  It is also in the Subscription version, I think, but would not be in 25.0.0.0 or earlier versions.  If you haven't installed fixpack 2, you can find it here

On Sat, Dec 1, 2018 at 1:19 PM Beckstead, Jason <[hidden email]> wrote:

Hi All,

 

I am working with the MATRIX-ENDMATRIX procedure. I have a square matrix of probabilities and need to transform each value into a z-score. I note that there is a matrix function: CDFNORM referenced in the syntax guide (this takes z-scores and returns probabilities) but I do not see what I would guess I need, something like “IDFNORM”. Any help would be appreciated.

 

Jason

 

_____________________________________________________________

 Jason W. Beckstead, Ph.D.       

  Associate Professor/Quantitative Methodologist

  University of South Florida College of Public Health

  13201 Bruce B. Downs Blvd., MDC56, Tampa, FL 33612, USA

  Statistical Editor, International Journal of Nursing Studies

  phone: +1.813.974.7667  fax: +1.813.974.4719          

  personal website:  http://personal.health.usf.edu/jbeckste/

  International Journal of Nursing Studies  http://www.elsevier.com/ijns

 

===================== 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


--
Jon K Peck
[hidden email]

===================== 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: Inverse normal distribution function in MATRIX

Bruce Weaver
Administrator
Thanks Jon.  Indeed, I was not seeing that in a PDF of the CSR manual for
SPSS 25.0.0.0; nor is it showing up in the online (html) version of the CSR
manual here:

https://www.ibm.com/support/knowledgecenter/en/SSLVMB_25.0.0/statistics_reference_project_ddita/spss/base/syn_matrix_matrix_functions.html

But if I open the CSR manual for SPSS 25.0.0.2 via the menu (Help > CSR), I
do see that info.  Here is the full path to finding it, for those who may be
interested.

MATRIX - END MATRIX > COMPUTE statement > MATRIX Functions

And under MATRIX functions, there are two branches:
> MATRIX cumulative distribution functions
> MATRIX inverse distribution functions

HTH.



Jon Peck wrote

> From the Syntax Reference Guide under MATRIX...
>
> IDF.NORMAL. IDF.NORMAL(prob, mean, stddev). Numeric. Returns the value
> from
> the normal
> distribution, with specified mean and standard deviation, for which the
> cumulative probability is prob.
>
> The cdf and idf functions mimic the corresponding functions in the regular
> transformation system.  There is also a PROBIT function that is a special
> case of IDF.NORMAL.
>
> You might have missed this, because there is also a CDFNORMAL function
> that
> doesn't follow the pattern.
>
> I see this in the 25.0.0.2 SRG.  It is also in the Subscription version, I
> think, but would not be in 25.0.0.0 or earlier versions.  If you haven't
> installed fixpack 2, you can find it here
> https://www-945.ibm.com/support/fixcentral/
>
> On Sat, Dec 1, 2018 at 1:19 PM Beckstead, Jason &lt;

> jbeckste@.usf

> &gt;
> wrote:
>
>> Hi All,
>>
>>
>>
>> I am working with the MATRIX-ENDMATRIX procedure. I have a square matrix
>> of probabilities and need to transform each value into a z-score. I note
>> that there is a matrix function: CDFNORM referenced in the syntax guide
>> (this takes z-scores and returns probabilities) but I do not see what I
>> would guess I need, something like “IDFNORM”. Any help would be
>> appreciated.
>>
>>
>>
>> Jason
>>
>>
>>
>> _____________________________________________________________
>>
>>  Jason W. Beckstead, Ph.D.
>>
>>   Associate Professor/Quantitative Methodologist
>>
>>   University of South Florida College of Public Health
>>
>>   13201 Bruce B. Downs Blvd., MDC56, Tampa, FL 33612, USA
>>
>>   Statistical Editor, International Journal of Nursing Studies
>>
>>   phone: +1.813.974.7667  fax: +1.813.974.4719
>>
>>   personal website:  http://personal.health.usf.edu/jbeckste/
>>
>>   International Journal of Nursing Studies  http://www.elsevier.com/ijns
>>
>>
>> ===================== To manage your subscription to SPSSX-L, send a
>> message to

> LISTSERV@.UGA

>  (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
>
>
>
> --
> Jon K Peck

> jkpeck@

>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (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





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: Inverse normal distribution function in MATRIX

Jon Peck
I have reported this to the Pubs folks.  They have been pretty good about promptly fixing problems in the online doc.  As Bruce says, the installed 25.0.0.2 CSR does document these functions, but the Command History section for MATRIX was missed.

On Mon, Dec 3, 2018 at 12:55 PM Bruce Weaver <[hidden email]> wrote:
Thanks Jon.  Indeed, I was not seeing that in a PDF of the CSR manual for
SPSS 25.0.0.0; nor is it showing up in the online (html) version of the CSR
manual here:

https://www.ibm.com/support/knowledgecenter/en/SSLVMB_25.0.0/statistics_reference_project_ddita/spss/base/syn_matrix_matrix_functions.html

But if I open the CSR manual for SPSS 25.0.0.2 via the menu (Help > CSR), I
do see that info.  Here is the full path to finding it, for those who may be
interested.

MATRIX - END MATRIX > COMPUTE statement > MATRIX Functions

And under MATRIX functions, there are two branches:
> MATRIX cumulative distribution functions
> MATRIX inverse distribution functions

HTH.



Jon Peck wrote
> From the Syntax Reference Guide under MATRIX...
>
> IDF.NORMAL. IDF.NORMAL(prob, mean, stddev). Numeric. Returns the value
> from
> the normal
> distribution, with specified mean and standard deviation, for which the
> cumulative probability is prob.
>
> The cdf and idf functions mimic the corresponding functions in the regular
> transformation system.  There is also a PROBIT function that is a special
> case of IDF.NORMAL.
>
> You might have missed this, because there is also a CDFNORMAL function
> that
> doesn't follow the pattern.
>
> I see this in the 25.0.0.2 SRG.  It is also in the Subscription version, I
> think, but would not be in 25.0.0.0 or earlier versions.  If you haven't
> installed fixpack 2, you can find it here
> https://www-945.ibm.com/support/fixcentral/
>
> On Sat, Dec 1, 2018 at 1:19 PM Beckstead, Jason &lt;

> jbeckste@.usf

> &gt;
> wrote:
>
>> Hi All,
>>
>>
>>
>> I am working with the MATRIX-ENDMATRIX procedure. I have a square matrix
>> of probabilities and need to transform each value into a z-score. I note
>> that there is a matrix function: CDFNORM referenced in the syntax guide
>> (this takes z-scores and returns probabilities) but I do not see what I
>> would guess I need, something like “IDFNORM”. Any help would be
>> appreciated.
>>
>>
>>
>> Jason
>>
>>
>>
>> _____________________________________________________________
>>
>>  Jason W. Beckstead, Ph.D.
>>
>>   Associate Professor/Quantitative Methodologist
>>
>>   University of South Florida College of Public Health
>>
>>   13201 Bruce B. Downs Blvd., MDC56, Tampa, FL 33612, USA
>>
>>   Statistical Editor, International Journal of Nursing Studies
>>
>>   phone: +1.813.974.7667  fax: +1.813.974.4719
>>
>>   personal website:  http://personal.health.usf.edu/jbeckste/
>>
>>   International Journal of Nursing Studies  http://www.elsevier.com/ijns
>>
>>
>> ===================== To manage your subscription to SPSSX-L, send a
>> message to

> LISTSERV@.UGA

>  (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
>
>
>
> --
> Jon K Peck

> jkpeck@

>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (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





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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


--
Jon K Peck
[hidden email]

===================== 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: Inverse normal distribution function in MATRIX

Jon Peck
Correction: although the CSR installed with fixpack2 for 25 documents the new CDF and IDF functions, they are not actually in 25.0.0.2.  Currently they are only in Subscription.  Presumably they will eventually show up in the non-Subscription version.

On Mon, Dec 3, 2018 at 1:10 PM Jon Peck <[hidden email]> wrote:
I have reported this to the Pubs folks.  They have been pretty good about promptly fixing problems in the online doc.  As Bruce says, the installed 25.0.0.2 CSR does document these functions, but the Command History section for MATRIX was missed.

On Mon, Dec 3, 2018 at 12:55 PM Bruce Weaver <[hidden email]> wrote:
Thanks Jon.  Indeed, I was not seeing that in a PDF of the CSR manual for
SPSS 25.0.0.0; nor is it showing up in the online (html) version of the CSR
manual here:

https://www.ibm.com/support/knowledgecenter/en/SSLVMB_25.0.0/statistics_reference_project_ddita/spss/base/syn_matrix_matrix_functions.html

But if I open the CSR manual for SPSS 25.0.0.2 via the menu (Help > CSR), I
do see that info.  Here is the full path to finding it, for those who may be
interested.

MATRIX - END MATRIX > COMPUTE statement > MATRIX Functions

And under MATRIX functions, there are two branches:
> MATRIX cumulative distribution functions
> MATRIX inverse distribution functions

HTH.



Jon Peck wrote
> From the Syntax Reference Guide under MATRIX...
>
> IDF.NORMAL. IDF.NORMAL(prob, mean, stddev). Numeric. Returns the value
> from
> the normal
> distribution, with specified mean and standard deviation, for which the
> cumulative probability is prob.
>
> The cdf and idf functions mimic the corresponding functions in the regular
> transformation system.  There is also a PROBIT function that is a special
> case of IDF.NORMAL.
>
> You might have missed this, because there is also a CDFNORMAL function
> that
> doesn't follow the pattern.
>
> I see this in the 25.0.0.2 SRG.  It is also in the Subscription version, I
> think, but would not be in 25.0.0.0 or earlier versions.  If you haven't
> installed fixpack 2, you can find it here
> https://www-945.ibm.com/support/fixcentral/
>
> On Sat, Dec 1, 2018 at 1:19 PM Beckstead, Jason &lt;

> jbeckste@.usf

> &gt;
> wrote:
>
>> Hi All,
>>
>>
>>
>> I am working with the MATRIX-ENDMATRIX procedure. I have a square matrix
>> of probabilities and need to transform each value into a z-score. I note
>> that there is a matrix function: CDFNORM referenced in the syntax guide
>> (this takes z-scores and returns probabilities) but I do not see what I
>> would guess I need, something like “IDFNORM”. Any help would be
>> appreciated.
>>
>>
>>
>> Jason
>>
>>
>>
>> _____________________________________________________________
>>
>>  Jason W. Beckstead, Ph.D.
>>
>>   Associate Professor/Quantitative Methodologist
>>
>>   University of South Florida College of Public Health
>>
>>   13201 Bruce B. Downs Blvd., MDC56, Tampa, FL 33612, USA
>>
>>   Statistical Editor, International Journal of Nursing Studies
>>
>>   phone: +1.813.974.7667  fax: +1.813.974.4719
>>
>>   personal website:  http://personal.health.usf.edu/jbeckste/
>>
>>   International Journal of Nursing Studies  http://www.elsevier.com/ijns
>>
>>
>> ===================== To manage your subscription to SPSSX-L, send a
>> message to

> LISTSERV@.UGA

>  (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
>
>
>
> --
> Jon K Peck

> jkpeck@

>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (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





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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


--
Jon K Peck
[hidden email]

--
Jon K Peck
[hidden email]

===================== 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