cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
emmablue
Level II

how to calculate standard deviation across multiple columns?

Is it possible to use JMP to calculate standard deviation across multiple columns? I could only figure out how to do the calculation in the same column. 

 

firstsecondthirdCV
2.4507122.4411282.430674 
1.2671391.2584291.260132 
2053.4592062.3412067.839 
1.7522831.7619821.763598 
1.1081771.1137781.115453 
1.2322381.2252361.232238 
2.4711462.4654442.456794 
3 ACCEPTED SOLUTIONS

Accepted Solutions

Re: how to calculate standard deviation across multiple columns?

You're looking for the "Std Dev" function.

 

Jordan_Hiller_0-1719513951606.png

 

https://www.jmp.com/support/help/en/18.0/#page/jmp/statistical-functions.shtml#

 

See attached data table as well.

View solution in original post

jthi
Super User

Re: how to calculate standard deviation across multiple columns?

Do you mean by row? You can for example use Std Dev function and list the columns

Std Dev(:first, :second, third)
-Jarmo

View solution in original post

txnelson
Super User

Re: how to calculate standard deviation across multiple columns?

If you are attempting to calculate the Coefficient of Variation for each row, it would be:

txnelson_0-1719514502263.png

names default to here(1);
dt=
New Table( "example",
	Add Rows( 7 ),
	New Column( "first",
		Numeric,
		Set Values(
			[2.4507119999999998, 1.267139, 2053.4589999999998, 1.752283, 1.108177,
			1.2322379999999999, 2.4711460000000001]
		)
	),
	New Column( "second",
		Numeric,
		Set Values(
			[2.441128, 1.258429, 2062.3409999999999, 1.7619819999999999,
			1.1137779999999999, 1.225236, 2.4654440000000002]
		)
	),
	New Column( "third",
		Numeric,
		Set Values(
			[2.4306739999999998, 1.260132, 2067.8389999999999, 1.763598, 1.115453,
			1.2322379999999999, 2.4567939999999999]
		)
	)
);

dt << new column("CV", formula( stddev(:first,:second,:third)/mean(:first,:second,:third)));

If you want to calculate the STD for the complete data table matrix it would be

names default to here(1);
dt=
New Table( "example",
	Add Rows( 7 ),
	New Column( "first",
		Numeric,
		Set Values(
			[2.4507119999999998, 1.267139, 2053.4589999999998, 1.752283, 1.108177,
			1.2322379999999999, 2.4711460000000001]
		)
	),
	New Column( "second",
		Numeric,
		Set Values(
			[2.441128, 1.258429, 2062.3409999999999, 1.7619819999999999,
			1.1137779999999999, 1.225236, 2.4654440000000002]
		)
	),
	New Column( "third",
		Numeric,
		Set Values(
			[2.4306739999999998, 1.260132, 2067.8389999999999, 1.763598, 1.115453,
			1.2322379999999999, 2.4567939999999999]
		)
	)
);

totalSTD = stddev(dt[0,0]);
show(totalSTD);
)
Jim

View solution in original post

3 REPLIES 3

Re: how to calculate standard deviation across multiple columns?

You're looking for the "Std Dev" function.

 

Jordan_Hiller_0-1719513951606.png

 

https://www.jmp.com/support/help/en/18.0/#page/jmp/statistical-functions.shtml#

 

See attached data table as well.

jthi
Super User

Re: how to calculate standard deviation across multiple columns?

Do you mean by row? You can for example use Std Dev function and list the columns

Std Dev(:first, :second, third)
-Jarmo
txnelson
Super User

Re: how to calculate standard deviation across multiple columns?

If you are attempting to calculate the Coefficient of Variation for each row, it would be:

txnelson_0-1719514502263.png

names default to here(1);
dt=
New Table( "example",
	Add Rows( 7 ),
	New Column( "first",
		Numeric,
		Set Values(
			[2.4507119999999998, 1.267139, 2053.4589999999998, 1.752283, 1.108177,
			1.2322379999999999, 2.4711460000000001]
		)
	),
	New Column( "second",
		Numeric,
		Set Values(
			[2.441128, 1.258429, 2062.3409999999999, 1.7619819999999999,
			1.1137779999999999, 1.225236, 2.4654440000000002]
		)
	),
	New Column( "third",
		Numeric,
		Set Values(
			[2.4306739999999998, 1.260132, 2067.8389999999999, 1.763598, 1.115453,
			1.2322379999999999, 2.4567939999999999]
		)
	)
);

dt << new column("CV", formula( stddev(:first,:second,:third)/mean(:first,:second,:third)));

If you want to calculate the STD for the complete data table matrix it would be

names default to here(1);
dt=
New Table( "example",
	Add Rows( 7 ),
	New Column( "first",
		Numeric,
		Set Values(
			[2.4507119999999998, 1.267139, 2053.4589999999998, 1.752283, 1.108177,
			1.2322379999999999, 2.4711460000000001]
		)
	),
	New Column( "second",
		Numeric,
		Set Values(
			[2.441128, 1.258429, 2062.3409999999999, 1.7619819999999999,
			1.1137779999999999, 1.225236, 2.4654440000000002]
		)
	),
	New Column( "third",
		Numeric,
		Set Values(
			[2.4306739999999998, 1.260132, 2067.8389999999999, 1.763598, 1.115453,
			1.2322379999999999, 2.4567939999999999]
		)
	)
);

totalSTD = stddev(dt[0,0]);
show(totalSTD);
)
Jim