sampling distribution of the mean

[Salbod]

I'm looking for a class demonstration of the sampling distribution of the mean.

I thought I ran across this some time back. But when I checked the list I couldn't find it.

I have a population of 20 heights. I want to randomly select with replacement four heights and compute their mean. I want to do this a 1000 times. At the end I want a file with 1000 means.

Any help or suggestions will be greatly appreciated.

TIA, Steve (Pace University, NYC)

 

[David Marso]

Here is a QAD I wrote in 5 minutes ;-)
--
DATA LIST FREE / X.
BEGIN DATA
1 2 4 3 7 6 8 7 9 6 5 4 5
END DATA.
SET MXLOOPS=100000000.

MATRIX.
GET DATA /VARIABLES x.
COMPUTE means=MAKE(1000,1,0).
COMPUTE N=NROW(data).
LOOP #=1 TO 1000.
+  LOOP i=1 TO 4.
+    COMPUTE means(#,1)=Means(#,1) + data((TRUNC(UNIFORM(1,1)*N)+1),1).
+  END LOOP.
END LOOP.
COMPUTE Means=Means/4.
SAVE Means / OUTFILE */VARIABLES=Mean.


END MATRIX.

Salbod wrote

I'm looking for a class demonstration of the sampling distribution of the mean.

I thought I ran across this some time back. But when I checked the list I couldn't find it.

I have a population of 20 heights. I want to randomly select with replacement four heights and compute their mean. I want to do this a 1000 times. At the end I want a file with 1000 means.

Any help or suggestions will be greatly appreciated.

TIA, Steve (Pace University, NYC)

[Salbod]

David, THANK YOU.

I will definitely put this in the vault.

I now understand why I couldn't solve it with plain syntax. Your solution is neat and informative.

Warm regards, Steve  

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso
Sent: Thursday, February 25, 2016 11:57 PM
To: [hidden email]
Subject: Re: sampling distribution of the mean

Here is a QAD I wrote in 5 minutes ;-)
--
DATA LIST FREE / X.
BEGIN DATA
1 2 4 3 7 6 8 7 9 6 5 4 5
END DATA.
SET MXLOOPS=100000000.

MATRIX.
GET DATA /VARIABLES x.
COMPUTE means=MAKE(1000,1,0).
COMPUTE N=NROW(data).
LOOP #=1 TO 1000.
+  LOOP i=1 TO 4.
+    COMPUTE means(#,1)=Means(#,1) + data((TRUNC(UNIFORM(1,1)*N)+1),1).
+  END LOOP.
END LOOP.
COMPUTE Means=Means/4.
SAVE Means / OUTFILE */VARIABLES=Mean.


END MATRIX.
Salbod wrote

> I'm looking for a class demonstration of the sampling distribution of
> the mean.
>
> I thought I ran across this some time back. But when I checked the
> list I couldn't find it.
>
> I have a population of 20 heights. I want to randomly select with
> replacement four heights and compute their mean. I want to do this a
> 1000 times. At the end I want a file with 1000 means.
>
> Any help or suggestions will be greatly appreciated.
>
> TIA, Steve (Pace University, NYC)

-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/sampling-distribution-of-the-mean-tp5731618p5731619.html
Sent from the SPSSX Discussion mailing list archive at 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

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

[David Marso]

Here is a plain syntax version.  I prefer the MATRIX solution for a number of reasons (no need to flip the data, no external file, no need to hack the N ) for starters.
--
DATA LIST FREE / X.
BEGIN DATA
1 2 4 3 7 6 8 7 9 6 5 4 5
END DATA.

FLIP.
DATASET Name Source.
COMPUTE @=$SYSMIS.
COMPUTE N=NVALID(var001 TO @).
VECTOR V=var001 TO @.
LOOP Sample=1 TO 1000.
+  COMPUTE M=0.
+  LOOP #=1 TO 4.
+    COMPUTE #draw=TRUNC(RV.UNIFORM(1,N+1)).
+    COMPUTE M=M+V(#draw).
+  END LOOP.
+  COMPUTE Mean=M/4.
+  XSAVE OUTFILE 'C:\TEMP\temp.sav' / KEEP Sample Mean.
END LOOP.
EXECUTE.
GET FILE 'C:\TEMP\temp.sav' .

Salbod wrote

David, THANK YOU.

I will definitely put this in the vault.

I now understand why I couldn't solve it with plain syntax. Your solution is neat and informative.

Warm regards, Steve  

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Marso
Sent: Thursday, February 25, 2016 11:57 PM
To: [hidden email]
Subject: Re: sampling distribution of the mean

Here is a QAD I wrote in 5 minutes ;-)
--
DATA LIST FREE / X.
BEGIN DATA
1 2 4 3 7 6 8 7 9 6 5 4 5
END DATA.
SET MXLOOPS=100000000.

MATRIX.
GET DATA /VARIABLES x.
COMPUTE means=MAKE(1000,1,0).
COMPUTE N=NROW(data).
LOOP #=1 TO 1000.
+  LOOP i=1 TO 4.
+    COMPUTE means(#,1)=Means(#,1) + data((TRUNC(UNIFORM(1,1)*N)+1),1).
+  END LOOP.
END LOOP.
COMPUTE Means=Means/4.
SAVE Means / OUTFILE */VARIABLES=Mean.


END MATRIX.
Salbod wrote
> I'm looking for a class demonstration of the sampling distribution of
> the mean.
>
> I thought I ran across this some time back. But when I checked the
> list I couldn't find it.
>
> I have a population of 20 heights. I want to randomly select with
> replacement four heights and compute their mean. I want to do this a
> 1000 times. At the end I want a file with 1000 means.
>
> Any help or suggestions will be greatly appreciated.
>
> TIA, Steve (Pace University, NYC)





-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/sampling-distribution-of-the-mean-tp5731618p5731619.html
Sent from the SPSSX Discussion mailing list archive at 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

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