Statistical models for categorical data: Brief review for applications in ecology

Ramos, Maria do Rosário; Oliveira, Manuela; Borges, José G.; McDill, Marc E.

doi:10.1063/1.4913055

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where linear regression is discouraged for the analysis of contingency tables, logistic regression is widely recommended as an ideal means of modelling binomial data (Dunn & Smyth, 2018; Lever et al., 2016; Orme & Combs‐Orme, 2009; Ramos et al., 2015; Tutz, 2012). While a binomial GLM analysis does not directly return inference of differences in probabilities, the conversion of predictions to the probability scale is reasonably commonplace.…”

Section: Discussionmentioning

confidence: 99%

“…Using a linear regression is thus regarded by some as 'unsatisfactory' (Tutz, 2012) at best and 'completely unreliable' (Seltman, 2018) at worst. By contrast, the logistic regression is largely accepted as an appropriate method to estimate probabilities of categorical explanatory variables, compensating for the aforementioned problems with linear regressions (Dunn & Smyth, 2018;Fagerland et al, 2017;Lever et al, 2016;Orme & Combs-Orme, 2009;Ramos et al, 2015;Tutz, 2012). Nonetheless, a clear advantage of linear over logistic regression is the often more straightforward interpretation of model coefficients (without requiring conversion).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classical tests, linear models and their extensions for the analysis of 2 × 2 contingency tables

Nagel,

Ruxton,

Morrissey

2024

Methods Ecol Evol

View full text Add to dashboard Cite

Ecologists and evolutionary biologists are regularly tasked with the comparison of binary data across groups. There is, however, some discussion in the biostatistics literature about the best methodology for the analysis of data comprising binary explanatory and response variables forming a 2 × 2 contingency table. We assess several methodologies for the analysis of 2 × 2 contingency tables using a simulation scheme of different sample sizes with outcomes evenly or unevenly distributed between groups. Specifically, we assess the commonly recommended logistic (generalised linear model [GLM]) regression analysis, the classical Pearson chi‐squared test and four conventional alternatives (Yates' correction, Fisher's exact, exact unconditional and mid‐p), as well as the widely discouraged linear model (LM) regression. We found that both LM and GLM analyses provided unbiased estimates of the difference in proportions between groups. LM and GLM analyses also provided accurate standard errors and confidence intervals when the experimental design was balanced. When the experimental design was unbalanced, sample size was small, and one of the two groups had a probability close to 1 or 0, LM analysis could substantially over‐ or under‐represent statistical uncertainty. For null hypothesis significance testing, the performance of the chi‐squared test and LM analysis were almost identical. Across all scenarios, both had high power to detect non‐null effects and reject false positives. By contrast, the GLM analysis was underpowered when using z‐based p‐values, in particular when one of the two groups had a probability near 1 or 0. The GLM using the LRT had better power to detect non‐null results. Our simulation results suggest that, wherever a chi‐squared test would be recommended, a linear regression is a suitable alternative for the analysis of 2 × 2 contingency table data. When researchers opt for more sophisticated procedures, we provide R functions to calculate the standard error of a difference between two probabilities from a Bernoulli GLM output using the delta method. We also explore approaches to compliment GLM analysis of 2 × 2 contingency tables with credible intervals on the probability scale. These additional operations should support researchers to make valid assessments of both statistical and practical significances.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classical tests, linear models and their extensions for the analysis of 2 × 2 contingency tables

Nagel,

Ruxton,

Morrissey

2024

Methods Ecol Evol

View full text Add to dashboard Cite

show abstract

“…The metrics chosen were Compensation method, Project performance criteria, Species targeted, Habitat targeted, and Credit/ debit calculation method. Each metric information was assigned to simple categorical scores to allow for a comparison between qualitative and quantitative data and make use of information that is normally deemed unsuited for empirical modeling [ 45 , 46 ]. For instance, a bank targeting a single habitat aspect was assigned a score of 1 for habitat targeted, a 2 when targeting multiple aspects, and a 3 when targeting whole ecosystems.…”

Section: Methodsmentioning

confidence: 99%

Mitigation bank applications for freshwater systems: Control mechanisms, project complexity, and caveats

Theis,

Poesch

2024

PLoS ONE

View full text Add to dashboard Cite

Biodiversity and mitigation banking has become a popular alternative offsetting mechanism, especially for freshwater species and systems. Central to this increase in popularity is the need for sound control mechanisms to ensure offset functionality. Two commonly used mechanisms are monitoring requirements and staggered release of bank credits over time. We used data from 47 banks in the United States, targeting freshwater systems and species. Based on the 47 banks meeting our criteria we showed that control mechanisms generally scale with increased project complexity and that banks release most of their total credit amount within the first 3 years. We further showed that advance credits are common and can increase the potential for credit release without providing tangible ecological benefits. Physical and biological assessment criteria commonly used by banks let us identify three main bank types focusing on connectivity, physical aspects, and habitat and species and their application possibilities and caveats to provide different ecosystem benefits for freshwater species and systems affected by anthropogenic development.

show abstract

Modeling Overdispersion, Autocorrelation, and Zero-Inflated Count Data Via Generalized Additive Models and Bayesian Statistics in an Aphid Population Study

2019

View full text Add to dashboard Cite

Statistical models for categorical data: Brief review for applications in ecology

Cited by 4 publications

References 0 publications

Classical tests, linear models and their extensions for the analysis of 2 × 2 contingency tables

Classical tests, linear models and their extensions for the analysis of 2 × 2 contingency tables

Mitigation bank applications for freshwater systems: Control mechanisms, project complexity, and caveats

Modeling Overdispersion, Autocorrelation, and Zero-Inflated Count Data Via Generalized Additive Models and Bayesian Statistics in an Aphid Population Study

Contact Info

Product

Resources

About