What does 'F2.0' mean?

[Ruben Geert van den Berg]

Dear all,

Until this morning, I always believed that 'F2.0' refers to a numeric field for which '2' is the total number of bytes (including any decimals but not the decimal separator) and '.0' is the number of decimals. So 1 and 11 can have an f2.0 format but '1.1' (f2.1) and '111' (f3.0) don't fit into f2.0.

However, in data view, I see '4511' for a numeric variable with f2.0 format. Apparently, my beliefs on numeric formats seem erratic. Could anyone please explain what 'f2.0' exactly means?

TIA,

Ruben van den Berg
Consultant Models & Methods
TNS NIPO
Email: [hidden email]
Mobiel: [phone]
Telefoon: [phone]
Internet: www.tns-nipo.com

---

New Windows 7: Find the right PC for you. Learn more.

[Jarrod Teo-2]

Hi Ruben,

Let me just start with the newly created numeric variables. All newly created numeric variables unless altered by syntax and option setting, will be width 8 dec 2.

A width 8 dec 2 means it is 12345.67 not 123456.78 so '1.1' (f2.1) should be (f3.1) instead.

Somehow I feel that numeric format seems to bother syntax users more than non-syntax users cause Ruben you are right, in data view, I see '4511' for a numeric variable with f2.0 format is quite normal for a data entry person who do not use syntax.

regards
Dorraj Oet

---

Date: Tue, 15 Jun 2010 06:46:28 +0000
From: [hidden email]
Subject: What does 'F2.0' mean?
To: [hidden email]

Dear all,

Until this morning, I always believed that 'F2.0' refers to a numeric field for which '2' is the total number of bytes (including any decimals but not the decimal separator) and '.0' is the number of decimals. So 1 and 11 can have an f2.0 format but '1.1' (f2.1) and '111' (f3.0) don't fit into f2.0.

However, in data view, I see '4511' for a numeric variable with f2.0 format. Apparently, my beliefs on numeric formats seem erratic. Could anyone please explain what 'f2.0' exactly means?

TIA,

Ruben van den Berg
Consultant Models & Methods
TNS NIPO
Email: [hidden email]
Mobiel: [phone]
Telefoon: [phone]
Internet: www.tns-nipo.com

---

New Windows 7: Find the right PC for you. Learn more.

---

Hotmail: Trusted email with Microsoft’s powerful SPAM protection. Sign up now.

[Albert-Jan Roskam]

It refers to the display and print format, not to the way the numerical values are stored internally.

F2.0 means that the 2 digits are displayed, of which 0 digits are behind the dot.

 

Internally all numerical values use 8 bytes. They are stored as double precision floating point values.

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

--- On Tue, 6/15/10, Ruben van den Berg <[hidden email]> wrote:

From: Ruben van den Berg <[hidden email]>
Subject: [SPSSX-L] What does 'F2.0' mean?
To: [hidden email]
Date: Tuesday, June 15, 2010, 8:46 AM

Dear all,

Until this morning, I always believed that 'F2.0' refers to a numeric field for which '2' is the total number of bytes (including any decimals but not the decimal separator) and '.0' is the number of decimals. So 1 and 11 can have an f2.0 format but '1.1' (f2.1) and '111' (f3.0) don't fit into f2.0.

However, in data view, I see '4511' for a numeric variable with f2.0 format. Apparently, my beliefs on numeric formats seem erratic. Could anyone please explain what 'f2.0' exactly means?

TIA,

Ruben van den Berg
Consultant Models & Methods
TNS NIPO
Email: [hidden email]
Mobiel: [phone]
Telefoon: [phone]
Internet: www.tns-nipo.com

---

New Windows 7: Find the right PC for you. Learn more.

[Jarrod Teo-2]

Hi All,

I have questions regarding the Conjoint Utilities table as pasted below.

I know that in our case, the difference between the utility estimates for the two delivery methods, internet and local machine, which is (1.180 �C (-1.180), or 2.36) is much greater than twice the standard error (2 * .169, or .338), indicating that they are significantly different.

1. Then how do you do a similar calculation for question which has 3 attributes?
2. How large must be the utility estimates and the standard error as in example (1.180 �C (-1.180), or 2.36) and twice the standard error (2 * .169, or .338), to be considered significantly large? Is there a rule of thumb or guideline to follow?
   

Thanks for answering my questions.

Regards
Dorraj Oet

Utilities
		Utility Estimate	Std. Error
method	Internet	1.180	.169
	Local Machine	-1.180	.169
video	Video	2.176	.169
	No Video	-2.176	.169
question	Instant Message (9-5)	.922	.225
	Email (<1 Day Wait)	.911	.264
	No Support	-1.833	.264
price	$300	3.392	.225
	$400	-.192	.264
	$500	-3.200	.264
test	Test	.227	.169
	No Test	-.227	.169
example	Industry Specific	.354	.169
	Generic	-.354	.169
(Constant)		7.422	.187

---

Hotmail: Powerful Free email with security by Microsoft. Get it now.

[Ruben Geert van den Berg]

Thanks Albert-Jan and Dorraj!
 
'double precision floating point values' means that each byte can hold two digits? When I tried
 
data list free/id(f1).
begin data
11111111111111111111
end data.
 
(8*2)=16 digits survived.
 
So when I use a GET DATA command, SPSS will always try to read 16 digits for each numeric variable, regardless of the format (f2.0)? I previously had the trouble that string formats were too short since the first 200(?) cases didn't contain the longest string values present in the original data.
 
Well, this was another interesting discovery!
 
Best,

Ruben van den Berg
Consultant Models & Methods
TNS NIPO
Email: [hidden email]
Mobiel: [phone]
Telefoon: [phone]
Internet: www.tns-nipo.com



 

---

Date: Tue, 15 Jun 2010 02:03:12 -0700
From: [hidden email]
Subject: Re: What does 'F2.0' mean?
To: [hidden email]

It refers to the display and print format, not to the way the numerical values are stored internally.

F2.0 means that the 2 digits are displayed, of which 0 digits are behind the dot.

 

Internally all numerical values use 8 bytes. They are stored as double precision floating point values.

Cheers!!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine, public order, irrigation, roads, a fresh water system, and public health, what have the Romans ever done for us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

--- On Tue, 6/15/10, Ruben van den Berg <[hidden email]> wrote:

From: Ruben van den Berg <[hidden email]>
Subject: [SPSSX-L] What does 'F2.0' mean?
To: [hidden email]
Date: Tuesday, June 15, 2010, 8:46 AM

Dear all,

Until this morning, I always believed that 'F2.0' refers to a numeric field for which '2' is the total number of bytes (including any decimals but not the decimal separator) and '.0' is the number of decimals. So 1 and 11 can have an f2.0 format but '1.1' (f2.1) and '111' (f3.0) don't fit into f2.0.

However, in data view, I see '4511' for a numeric variable with f2.0 format. Apparently, my beliefs on numeric formats seem erratic. Could anyone please explain what 'f2.0' exactly means?

TIA,

Ruben van den Berg
Consultant Models & Methods
TNS NIPO
Email: [hidden email]
Mobiel: [phone]
Telefoon: [phone]
Internet: www.tns-nipo.com

---

New Windows 7: Find the right PC for you. Learn more.

---

New Windows 7: Find the right PC for you. Learn more.