Averaging values/MEAN function

[Tanja Gabriele Baudson]

Hi all,

the MEAN.1 function allows to compute an average value of several
values even if only one variable is available. Is there any way to
realize the reverse -- computing the arithmetical mean if only one
variable is missing, else not? I think such a function would make more
sense. A brief "yes, there is" (preferably with a short mention of the
command) or "no, there isn't" would be perfectly sufficient as an
answer :)

Thanks to you all
Tanja
--
Tanja Gabriele Baudson
Universität Trier
FB I Psychologie
Hochbegabtenforschung und -förderung
54286 Trier
Fon 0651/201-4558
Fax [phone]
Email [hidden email]
Web http://www.uni-trier.de/index.php?id=9492

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

[Garry Gelade]

Tanja

The number follwowing the dot represents the minimum number of variables
that must be present for the mean to be calculated.
So if you are averaging four variables, MEAN.3(var1, var2, var3, var4) will
compute the case mean if any three (or all four) of the variables are
non-missing.  If two or more variables are missing for a case, the result
will be missing.

Garry Gelade


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Tanja Gabriele Baudson
Sent: 07 May 2011 10:15
To: [hidden email]
Subject: Averaging values/MEAN function

Hi all,

the MEAN.1 function allows to compute an average value of several
values even if only one variable is available. Is there any way to
realize the reverse -- computing the arithmetical mean if only one
variable is missing, else not? I think such a function would make more
sense. A brief "yes, there is" (preferably with a short mention of the
command) or "no, there isn't" would be perfectly sufficient as an
answer :)

Thanks to you all
Tanja
--
Tanja Gabriele Baudson
Universität Trier
FB I Psychologie
Hochbegabtenforschung und -förderung
54286 Trier
Fon 0651/201-4558
Fax [phone]
Email [hidden email]
Web http://www.uni-trier.de/index.php?id=9492

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

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

[Mike]

I think the following accomplishes what the OP wanted:

* Calculate the Number of missing values for N variables.
* V5 is used as the last variable but it should be set to
* whatever the relevant variable is.
count Nmissing= V1 to V5 (missing).

Do if (Nmissing eq 1).
compute mean.minus.one=mean(V1 to V5).
end if.

The above should allow one to calculate a mean for any
fixed number of missing values (though one should have
good reasons for why they are doing so).

-Mike Palij
New York University
[hidden email]



----- Original Message -----
From: "Garry Gelade" <[hidden email]>
To: <[hidden email]>
Sent: Saturday, May 07, 2011 5:53 AM
Subject: Re: Averaging values/MEAN function

> Tanja
>
> The number follwowing the dot represents the minimum number of variables
> that must be present for the mean to be calculated.
> So if you are averaging four variables, MEAN.3(var1, var2, var3, var4) will
> compute the case mean if any three (or all four) of the variables are
> non-missing.  If two or more variables are missing for a case, the result
> will be missing.
>
> Garry Gelade
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> Tanja Gabriele Baudson
> Sent: 07 May 2011 10:15
> To: [hidden email]
> Subject: Averaging values/MEAN function
>
> Hi all,
>
> the MEAN.1 function allows to compute an average value of several
> values even if only one variable is available. Is there any way to
> realize the reverse -- computing the arithmetical mean if only one
> variable is missing, else not? I think such a function would make more
> sense. A brief "yes, there is" (preferably with a short mention of the
> command) or "no, there isn't" would be perfectly sufficient as an
> answer :)
>
> Thanks to you all
> Tanja
> --
> Tanja Gabriele Baudson
> Universität Trier
> FB I Psychologie
> Hochbegabtenforschung und -förderung
> 54286 Trier
> Fon 0651/201-4558
> Fax [phone]
> Email [hidden email]
> Web http://www.uni-trier.de/index.php?id=9492

=====================
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]

Alternatively, one could use the NMISS function.

if (NMISS(v1 to v5) EQ 1) mean.minus.one=mean(V1 to V5).

Mike Palij wrote

I think the following accomplishes what the OP wanted:

* Calculate the Number of missing values for N variables.
* V5 is used as the last variable but it should be set to
* whatever the relevant variable is.
count Nmissing= V1 to V5 (missing).

Do if (Nmissing eq 1).
compute mean.minus.one=mean(V1 to V5).
end if.

The above should allow one to calculate a mean for any
fixed number of missing values (though one should have
good reasons for why they are doing so).

-Mike Palij
New York University
[hidden email]



----- Original Message -----
From: "Garry Gelade" <[hidden email]>
To: <[hidden email]>
Sent: Saturday, May 07, 2011 5:53 AM
Subject: Re: Averaging values/MEAN function


> Tanja
>
> The number follwowing the dot represents the minimum number of variables
> that must be present for the mean to be calculated.
> So if you are averaging four variables, MEAN.3(var1, var2, var3, var4) will
> compute the case mean if any three (or all four) of the variables are
> non-missing.  If two or more variables are missing for a case, the result
> will be missing.
>
> Garry Gelade
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> Tanja Gabriele Baudson
> Sent: 07 May 2011 10:15
> To: [hidden email]
> Subject: Averaging values/MEAN function
>
> Hi all,
>
> the MEAN.1 function allows to compute an average value of several
> values even if only one variable is available. Is there any way to
> realize the reverse -- computing the arithmetical mean if only one
> variable is missing, else not? I think such a function would make more
> sense. A brief "yes, there is" (preferably with a short mention of the
> command) or "no, there isn't" would be perfectly sufficient as an
> answer :)
>
> Thanks to you all
> Tanja
> --
> Tanja Gabriele Baudson
> Universität Trier
> FB I Psychologie
> Hochbegabtenforschung und -förderung
> 54286 Trier
> Fon 0651/201-4558
> Fax [phone]
> Email [hidden email]
> Web http://www.uni-trier.de/index.php?id=9492

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