Difference between revisions of "Fifteen-unit rule for rounding numerical results"
From Testiwiki
(justification added) |
m (→Result) |
||
| (4 intermediate revisions by 2 users not shown) | |||
| Line 19: | Line 19: | ||
* in the average value, the uncertainty of the least significant digit (LSD) must not exceed 15 units, | * in the average value, the uncertainty of the least significant digit (LSD) must not exceed 15 units, | ||
| − | * the probable uncertainty | + | * and the probable uncertainty is always rounded upwards, to the same decimal position as the average value. |
| − | + | {{todo|Tämähän on hyvä ohje. Voisitko tehdä koodin, jossa R:llä tehdään tuo pyöristys automaattisesti? Varmaan toimisi helpoiten funktiona, jolle annetaan 2 parametria eli ''estimate'' ja ''uncertainty''. --[[User:Jouni|Jouni]] 13:46, 10 August 2011 (EEST)|Erkki Kuusisto|project=Opasnet}} | |
Please see the following examples: | Please see the following examples: | ||
| − | * <font color=red>(1062 ± 41) meters</font> is '''incorrect''', because the LSD of the average value (2) is associated with an uncertainty of 41 units (and the uncertainty is | + | * <font color=red>(1062 ± 41) meters</font> is '''incorrect''', because the LSD of the average value (2) is associated with an uncertainty of 41 units (and the uncertainty is also 41 units) |
| − | * <font color=green>(1060 ± 50) meters</font> is '''correct''', because the LSD of the average value (6) is now associated with an uncertainty of 5 units only (and the uncertainty | + | * <font color=red>(1060 ± 41) meters</font> is also '''incorrect''', because the uncertainty contains a lower significant decimal position ("ones") than the average value ("tens") |
| + | * <font color=green>(1060 ± 50) meters</font> is '''correct''', because the LSD of the average value (6) is now associated with an uncertainty of 5 units only (and the uncertainty has been rounded to the same decimal position as the average value) | ||
:: - Note that the original uncertainty (41) has been rounded upwards (to 50). | :: - Note that the original uncertainty (41) has been rounded upwards (to 50). | ||
| − | * <font color=red>(0.8765 ± 0.0132) kg</font> is '''incorrect''', because the LSD of the average value (5) is associated with an uncertainty of 132 units | + | |
| − | * <font color=green>(0.876 ± 0.014) kg</font> is '''correct''', because the LSD of the average value (6) is now associated with an uncertainty of 14 units only (and the uncertainty | + | * <font color=red>(0.8765 ± 0.0132) kg</font> is '''incorrect''', because the LSD of the average value (5) is associated with an uncertainty of 132 units |
| + | * <font color=green>(0.876 ± 0.014) kg</font> is '''correct''', because the LSD of the average value (6) is now associated with an uncertainty of 14 units only (and the uncertainty has been rounded to the same decimal position as the average value) | ||
:: - Note that the original uncertainty (0.0132) has been rounded upwards (to 0.014). | :: - Note that the original uncertainty (0.0132) has been rounded upwards (to 0.014). | ||
| + | |||
| + | |||
| + | * <font color=red>(0.9765 ± 0.0172) kg</font> is '''incorrect''', because the LSD of the average value (5) is associated with an uncertainty of 172 units | ||
| + | * <font color=red>(0.976 ± 0.018) kg</font> is still '''incorrect''', because the LSD of the average value (6) is associated with an uncertainty of 18 units | ||
| + | * <font color=green>(0.98 ± 0.02) kg</font> is '''correct''', because the LSD of the average value (8) is now associated with an uncertainty of 2 units only (and the uncertainty has been rounded to the same decimal position as the average value). | ||
| + | |||
| + | |||
| + | [[Category:Publications]] | ||
Latest revision as of 12:27, 10 August 2011
This page is a method.
The page identifier is Op_en5327 |
|---|
| Moderator:Erkki Kuusisto (see all) |
|
Give your opinion to the peer rating of the content of this page. |
| Upload data
|
Scope
When presenting the final results of a study, what is a scientifically sound method for rounding numerical results of the form "average value ± probable uncertainty"?
Definition
Usually, from scientific studies (whether based on physical measurements or mathematical modelling), numerical results are obtained that consist of an average value or a best estimate (e.g. 4.5678 meters) and a measure of the probable uncertainty (e.g. ±0.2345 meters). However, as raw figures, either or both of these may be too precise (i.e. contain more digits than is justifiable or meaningful).
Thus, before publishing, a systematic method for rounding those results to a justifiable and meaningful precision is needed, in order to avoid a misconception of excessively (in)accurate results.
The 15-unit rule is a practical method (used in e.g. the teaching of university-level physics and engineering) that ensures that neither the average value nor the probable uncertainty will be expressed with a meaninglessly high precision.
Result
The 15-unit rule says that:
- in the average value, the uncertainty of the least significant digit (LSD) must not exceed 15 units,
- and the probable uncertainty is always rounded upwards, to the same decimal position as the average value.
TODO: {{#todo:Tämähän on hyvä ohje. Voisitko tehdä koodin, jossa R:llä tehdään tuo pyöristys automaattisesti? Varmaan toimisi helpoiten funktiona, jolle annetaan 2 parametria eli estimate ja uncertainty. --Jouni 13:46, 10 August 2011 (EEST)|Erkki Kuusisto|Opasnet}}
Please see the following examples:
- (1062 ± 41) meters is incorrect, because the LSD of the average value (2) is associated with an uncertainty of 41 units (and the uncertainty is also 41 units)
- (1060 ± 41) meters is also incorrect, because the uncertainty contains a lower significant decimal position ("ones") than the average value ("tens")
- (1060 ± 50) meters is correct, because the LSD of the average value (6) is now associated with an uncertainty of 5 units only (and the uncertainty has been rounded to the same decimal position as the average value)
- - Note that the original uncertainty (41) has been rounded upwards (to 50).
- (0.8765 ± 0.0132) kg is incorrect, because the LSD of the average value (5) is associated with an uncertainty of 132 units
- (0.876 ± 0.014) kg is correct, because the LSD of the average value (6) is now associated with an uncertainty of 14 units only (and the uncertainty has been rounded to the same decimal position as the average value)
- - Note that the original uncertainty (0.0132) has been rounded upwards (to 0.014).
- (0.9765 ± 0.0172) kg is incorrect, because the LSD of the average value (5) is associated with an uncertainty of 172 units
- (0.976 ± 0.018) kg is still incorrect, because the LSD of the average value (6) is associated with an uncertainty of 18 units
- (0.98 ± 0.02) kg is correct, because the LSD of the average value (8) is now associated with an uncertainty of 2 units only (and the uncertainty has been rounded to the same decimal position as the average value).
