This repository was initiated by SST to share easy-to-use resources for the application of various statistical analysis methods and techniques. We have included resources that provide a good introduction to data analysis, covering key concepts, examples of how to interpret results and code to implement various approaches. However, if a more in-depth understanding is required, we recommend that you consult a traditional statistics textbook.
We organize this repository by datatype and assumption not met, that migh guide which approach is most addequate to use. All the resources include code written in R.
.
| Data type | Assumption | Modelling approach |
|---|---|---|
| Time series | Change point detection | |
| Time series | Looking at time series | |
| Continuos variable~difference between groups | ANOVA | |
| Continuos variable~difference between groups | non-independent observations | Mixed ANOVA |
| Continuos variable~ continuos or catagorical covariables | non-independent observations | Introduction to linear mixed models |
| Continuos variable~ continuos or catagorical covariables | non-independent observations | Mixed linear models definitions |
| Continuos variable~ continuos or catagorical covariables | non-independent observations | Fitting mixed linear models |
| Binary data/ Count data | non-normal distribution | Generalized linear models -GLM |
| Binary data/ Count data | non-normal distribution | Confidence Intervals for GLMs |
| Binary data/ Count data | zero inflated | Zero inflated models |
| Binary data/ Count data | zero inflated | Hurdle models |
| Binary data/ Count data | zero inflated | Visualizing zero inflated models |
| Continuos / Binary data/ Count data | non-linear relationships | Generalized Additive Models-GAMs |
| Bounded data / proportions | Beta regression models | |
| Bounded data / proportions | zero inflated | Zero inflated beta regression |
| Catagorical variables ~ multiple categories classes | Multinomial logistic regression | |
| Catagorical variables ~ multiple categories classes | Multinomial regression/Classifier algorithms | |
| Test models assumptions and plot residuals | DHARMa: residual diagnostics | |
| Test models assumptions and plot residuals | DHARMa for unsupported models | |
| General linear regression course | Linear Regression | |
| Advance regression modelling | Advance regression analysis | |
| Continuos variable~ continuos or catagorical covariables | Quantile regression | |
| Guidelines for mathemetical notation in ecology | Edwards & Auger-Méthé 2018 |