Delve into modern statistical analysis with R. Gain insights into data description, linear modeling, advanced techniques, and GLMs. Discover how to effectively interpret and analyze real-world models.

r_img.tar.gz

rscript

r_stat

R is a widely used programming language for statistical computing. It features robust libraries that cover everything from basic data analytics to visualization functions for presentation. R is used by professional data scientists, researchers, and marketers.

This course is a comprehensive introduction to modern statistical analysis using R, particularly for researchers in life and environmental sciences. You’ll review R and cover its functionality with its various packages. You'll review essential statistical functions including data description, linear modeling, regression analysis, and more. You’ll also cover advanced analytical techniques looking at analysis of variance, factorial designs, and non-normal data distributions. You’ll also discuss generalized linear models, including binomial GLMs and GLMs for binary data. 

By the end of this course, you’ll be prepared to apply statistical methods to real-world problems and interpret and analyze various models in an effective contemporary manner.

Performing Modern Statistical Analysis with R

**(True or False.)** In a GLM analysis of count data, the use of the log link function ensures that all predicted counts are positive by taking the exponential of the values generated by the linear predictor.

(True or False.) In a GLM analysis of count data, the use of the log link function ensures that all predicted counts are positive by taking the exponential of the values generated by the linear predictor.

the model overestimating the true level of variation in the data

the model underestimating the true level of variation in the data

the model estimating overdispersion of data

**(Fill in the blank.)** If the residual deviance is larger than the residual degrees of freedom (more than an order of 1.2), using the Poisson distribution in a GLM analysis will result in ________.

(Fill in the blank.) If the residual deviance is larger than the residual degrees of freedom (more than an order of 1.2), using the Poisson distribution in a GLM analysis will result in ________.

Quasi-maximum likelihood, maximum likelihood

Maximum likelihood, quasi-maximum likelihood

**(Fill in the blank.)** ________ assumes that the level of variability in data is approximately as predicted for the distribution being used in the GLM, but _______ instead estimates the observed level of variation in the data.

(Fill in the blank.) ________ assumes that the level of variability in data is approximately as predicted for the distribution being used in the GLM, but _______ instead estimates the observed level of variation in the data.

Test your knowledge of generalized linear models for count data.

Introduction

Description

Estimation

Linear Models

Regression

Prediction

Testing

Intervals

Analysis of Variance

Factorial Designs

Analysis of Covariance

Linear Model Complexities

Generalized Linear Models

GLMs for Count Data

Binomial GLMs

GLMs for Binary Data

Conclusion

Appendix

Quiz: GLMs for Count Data