Aug 29, 2008 11:43
15 yrs ago
Dutch term
metrisch meetniveau
Dutch to English
Science
Mathematics & Statistics
Statistical analysis
I am translating a series of documents on statistical analysis. Most of the meterial is straightforward, bit I am stumped by this phrase. Context:
"Zowel predictor- als criteriumvariabelen dienen van *metrisch niveau* te zijn. Het is echter mogelijk om predictorvariabelen van een lager *meetniveau* in de analyse op te nemen."
"Er zijn drie situaties denkbaar bij het voorspellen van de waarde van een criteriumvariabele:
Voorspellen zonder predictoren.
Voorspellen met één predictor.
Voorspellen met meerdere predictoren.
In het eerste geval lijkt het gebruik van het rekenkundig gemiddelde de beste aanpak (onder de veronderstelling van een *metrisch meetniveau*)."
A literal translation does not really seem to fill the bill. Any statisticians out there?
"Zowel predictor- als criteriumvariabelen dienen van *metrisch niveau* te zijn. Het is echter mogelijk om predictorvariabelen van een lager *meetniveau* in de analyse op te nemen."
"Er zijn drie situaties denkbaar bij het voorspellen van de waarde van een criteriumvariabele:
Voorspellen zonder predictoren.
Voorspellen met één predictor.
Voorspellen met meerdere predictoren.
In het eerste geval lijkt het gebruik van het rekenkundig gemiddelde de beste aanpak (onder de veronderstelling van een *metrisch meetniveau*)."
A literal translation does not really seem to fill the bill. Any statisticians out there?
Proposed translations
(English)
| 3 +1 | of metric level / on a metric scale |
Harry Borsje
|
| 5 | measurement scale |
Adam Smith
|
Proposed translations
+1
24 mins
Harry Borsje
Netherlands
Netherlands
Native in Dutch
Works in field
Netherlands
Communicate technology with passion
Native in: Dutch 
Works in: German to Dutch, English to Dutch
Related KudoZ points
:
4
Dutch term (edited):
van metrisch niveau
Selected
of metric level / on a metric scale
See ref. for a dictinction of measurement levels, of which some (the lower two) are metric and others are not. Also interesting discussions related to Likert scales to be found.
Peer comment(s):
| agree |
Tina Vonhof (X)
: Nice ref.
1 hr
|
| neutral |
Adam Smith
: I agree with the reference, but not all variables are measured on a metric scale / level
1 day 21 hrs
|
4 KudoZ points awarded for this answer.
Comment: "BOTH contributions were good and helpful, but this one came closer to supplying the answer that I required. Thanks Harry, Adam and Tina."
1 day 22 hrs
Adam Smith
United Kingdom
United Kingdom
Native in English
Works in field
United Kingdom
Medical & legal expertise
Native in: English
Works in: Dutch to English, Flemish to English, Afrikaans to English, and 1 more.
Related KudoZ points
:
4
measurement scale
This not normally phrased like this within in English texts, i.e. a reference is usually made to the "level" of measurement (nominal, ordinal, interval or ratio) rather than stating that the criterion/predictor variables were one of the "scales of measurement / measurement scales". Since the text is (presumably) referring to a (logistic/linear/mulitple) regression analysis the level for the predictor may vary.
"However, it has been shown to be biased when predictor variables vary in their number of categories or scale of measurement [13], because the underlying Gini gain splitting criterion is a biased estimator and can be affected by multiple testing effects [14]."
ref. http://www.biomedcentral.com/1471-2105/9/307
There is a big debate in the literature about measurement theory (e.g. http://en.wikipedia.org/wiki/Rasch_model)
"However, it has been shown to be biased when predictor variables vary in their number of categories or scale of measurement [13], because the underlying Gini gain splitting criterion is a biased estimator and can be affected by multiple testing effects [14]."
ref. http://www.biomedcentral.com/1471-2105/9/307
There is a big debate in the literature about measurement theory (e.g. http://en.wikipedia.org/wiki/Rasch_model)
Discussion