Help for uderstanding a sentence

English translation: 5% level= alpha (type I error) is 0.05 / / 90% power= 1- beta (type II error) is 0.10

GLOSSARY ENTRY (DERIVED FROM QUESTION BELOW)
English term or phrase:difference between groups at the 5% level and with a power of 90%,
Selected answer:5% level= alpha (type I error) is 0.05 / / 90% power= 1- beta (type II error) is 0.10
Entered by: Elena Sgarbo (X)

11:13 May 19, 2004
English language (monolingual) [PRO]
Medical - Medical: Pharmaceuticals
English term or phrase: Help for uderstanding a sentence
The sentence is from an article on Type 2 diabetes:

It was estimated that a sample size of 500 patients was required to show a significant difference between the groups in mean change in body weight at the 5% level and with a power of 90%, providing that the true difference of the expectations in the population is at least 0.3-fold that of the standard deviation.
Empty Whiskey Glass
Local time: 11:08
Statistics: 5% level= alpha (type I error) is 0.05 / 90% power= 1- beta (type II error) is 0.10
Explanation:
Hi Svetozar

These percentages most likely refer to the type I error (alpha) and type II error (beta), respectively, that the investigators have set beforehand for the statistical analysis of their study.

By setting a statistical Alpha error at 5%, all analyzed variables that have a P value equal or lower to .05 will be "statistically significant".

In this case, for the beta error, Beta= 1 - 0.90= 0.10. This means that the investigators have decided that they will accept a 10% chance (100-90) of missing an association between the variable of interest and the other variables. That is, there is a 90% chance of finding an association of that size.

Hope this helps

Elena

--------------------------------------------------
Note added at 59 mins (2004-05-19 12:12:56 GMT)
--------------------------------------------------

Svetozar,

The interpretation of the sentence is what I wrote above.... it\'s a rather complex statistical concept. The way I understood it when I first studied it was by reading about type I and type II errors (and alpha and beta) in several books on Statistics. There\'s also info on the Internet...

Best wishes,
Elena
Selected response from:

Elena Sgarbo (X)
Grading comment
4 KudoZ points were awarded for this answer



SUMMARY OF ALL EXPLANATIONS PROVIDED
5 +1Statistics: 5% level= alpha (type I error) is 0.05 / 90% power= 1- beta (type II error) is 0.10
Elena Sgarbo (X)
4ref. for 'power'
David Sirett


Discussion entries: 3





  

Answers


43 mins   confidence: Answerer confidence 4/5Answerer confidence 4/5
help for uderstanding a sentence
ref. for 'power'


Explanation:
The ref. explains 'power' in the context of detecing small differences.

--------------------------------------------------
Note added at 45 mins (2004-05-19 11:58:32 GMT)
--------------------------------------------------

detecTing

--------------------------------------------------
Note added at 54 mins (2004-05-19 12:07:56 GMT)
--------------------------------------------------

detecTing


    Reference: http://www.army-itam.com/public/lm/lcta/scenar3/power.htm
David Sirett
Local time: 10:08
Specializes in field
Native speaker of: Native in EnglishEnglish
PRO pts in category: 20
Login to enter a peer comment (or grade)

43 mins   confidence: Answerer confidence 5/5 peer agreement (net): +1
help for uderstanding a sentence
Statistics: 5% level= alpha (type I error) is 0.05 / 90% power= 1- beta (type II error) is 0.10


Explanation:
Hi Svetozar

These percentages most likely refer to the type I error (alpha) and type II error (beta), respectively, that the investigators have set beforehand for the statistical analysis of their study.

By setting a statistical Alpha error at 5%, all analyzed variables that have a P value equal or lower to .05 will be "statistically significant".

In this case, for the beta error, Beta= 1 - 0.90= 0.10. This means that the investigators have decided that they will accept a 10% chance (100-90) of missing an association between the variable of interest and the other variables. That is, there is a 90% chance of finding an association of that size.

Hope this helps

Elena

--------------------------------------------------
Note added at 59 mins (2004-05-19 12:12:56 GMT)
--------------------------------------------------

Svetozar,

The interpretation of the sentence is what I wrote above.... it\'s a rather complex statistical concept. The way I understood it when I first studied it was by reading about type I and type II errors (and alpha and beta) in several books on Statistics. There\'s also info on the Internet...

Best wishes,
Elena

Elena Sgarbo (X)
Specializes in field
Native speaker of: Native in SpanishSpanish
PRO pts in category: 12

Peer comments on this answer (and responses from the answerer)
agree  David Sirett: wot she said...
1 min
  -> Thanks, David :-)
Login to enter a peer comment (or grade)



Login or register (free and only takes a few minutes) to participate in this question.

You will also have access to many other tools and opportunities designed for those who have language-related jobs (or are passionate about them). Participation is free and the site has a strict confidentiality policy.

KudoZ™ translation help

The KudoZ network provides a framework for translators and others to assist each other with translations or explanations of terms and short phrases.


See also:
Term search
  • All of ProZ.com
  • Term search
  • Jobs
  • Forums
  • Multiple search