Lines, models, and errors: Regression in the field

By Brian McArdle. 2003

101 citations recorded by the source corpus.

Subfields: Global and Planetary Change, Nature and Landscape Conservation, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/ac2942730ba84888677a8ad5eb1077ae25b18ffc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Global and Planetary Change

1. William K. Cornwell
2. Elena Litchman
3. Shinichi Nakagawa
4. A. Green
5. J. Peig
6. Richard J. Smith
7. P. Hurd
8. David D. Ackerly

In Nature and Landscape Conservation

1. L. Garamszegi
2. Shinichi Nakagawa
3. William K. Cornwell
4. J. Peig
5. David D. Ackerly
6. Richard J. Smith
7. H. Schielzeth
8. Roger Mundry

In Water Science and Technology

1. Shinichi Nakagawa
2. A. Green
3. J. Peig
4. Richard J. Smith
5. Elena Litchman
6. David D. Ackerly
7. William K. Cornwell
8. L. Garamszegi

Citations in the corpus

• Trait-Based Community Ecology of Phytoplankton (2008, background): “Three statistical issues need to be considered for future studies of this kind: (a) Because both variables are measured with error, a regression model such as reduced major axis regression is more appropriate than ordinary least squares (McArdle 2003, Warton et al. 2006).”
• Knowing when to draw the line: designing more informative ecological experiments (2005, unknown): “McArdle BH. 2003.”
• Beyond the ‘3/4‐power law’: variation in the intra‐and interspecific scaling of metabolic rate in animals (2005, unknown): “Further discussion of the relative merits of using LSR, RMA and other regression techniques in scaling studies can be found in Gould (1966), LaBarbera (1989), Harvey & Pagel (1991), Niklas (1994, 2004), Sokal & Rohlf (1995), McArdle (2003) and Kaitaniemi (2004).”
• Changing philosophies and tools for statistical inferences in behavioral ecology (2009, methodology): “37, we can interpret aspects of niche breadth as having around 40% probability that they may indeed play a role in determining patterns on abundance in these birds. Notice also that the averaged slope estimates are different than those obtained in the single model that Symonds and Johnson (2006)prod”
• The paradigm of body condition: a critical reappraisal of current methods based on mass and length (2010, methodology): “…two interdependent variables, the true slope will lie somewhere between the extreme slopes fitted by OLS regression of lnM on lnL and the reverse regression of lnL on lnM (McArdle 2003), the exact position depending on the relative importance of each variable as a descriptor of true body size.”
• A trait-based approach to community assembly: partitioning of species trait values into within- and among-community components. (2007, background): “The plot level trait means are measured with error, due to sampling error in the individual trait values, which will result in attenuation (underestimation) of regression slopes (McArdle 2003; Warton et al. 2006); we estimate that this attenuation error is < 1%.”
• Use and misuse of the reduced major axis for line-fitting. (2009, methodology): “These will be discussed in detail later, but it is virtually always the case with biological data that some error is present in both the X-axis and Y-axis variables (McArdle, 2003).”
• Information-theoretic approaches to statistical analysis in behavioural ecology: an introduction (2010, background): “2009), which can cause a downward bias in parameter estimations (McArdle 2003; Adolph and Hardin 2007).”