Ambiguities in scientific terms: The use of "error" and "bias" in statistics
The proper use of statistics is key for professionals who answer questions from data, including ecologists. However, statistics is generally confusing for these professionals, in part due to difficulties related to its terminology. Many of these difficulties derive from the multiple meanings that a term has, both inside and outside the statistical scope. For Spanish-speaking professionals, the translation of English terms also contributes to this confusion. In this paper we show (and intend to clarify) some of these problems from two key terms of an introductory statistics course: error and bias. These terms are discussed in the different contexts that involve problem resolution using statistics: sampling, measurement, estimation, inference and prediction. Error is inherent to statistics and is used to quantify different types of variability or to indicate the possibility of making mistakes on decision making, depending on the context. On the other hand, bias reflects the tendency towards certain values and/or elements, and leads to erroneous conclusions if not avoided. We propose that the problems associated with lexical ambiguity should to be addressed from university teaching and based on this, we offer some recommendations. Thus, the present article not only offers a guide for professionals to make an adequate use of some statistical terms but also provides a contribution for teaching.https://doi.org/10.25260/EA.18.28.3.0.680
Main Authors: | , , , |
---|---|
Format: | Digital revista |
Language: | spa |
Published: |
Asociación Argentina de Ecología
2018
|
Online Access: | https://ojs.ecologiaaustral.com.ar/index.php/Ecologia_Austral/article/view/680 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|