Conclusion

1. Conclusion

Good job on completing this course.

2. What you've learned

You've learned how GLMs extend the abilities of LMs. Count data can be included with Poisson error terms. Binary data can be included with Binomial error terms such as the logit and probit options. You've also seen how to plot and understand GLM outs. Last, you learned about extending GLMs to include multiple regression.

3. Where to from here?

So, where to from this course? If you missed it, DataCamp offers a course on multiple and logistic regression that covers topics related to this course. Also, the DataCamp course on Hierarchical and mixed-effects extends GLMs to include random-effects. This course covers what happens if you have groups inside of groups. For example, students inside of classrooms that are nested inside of schools. GLMs also extend to non-linear and additive models such as General Additive Models, known as GAMs. You can learn about how to choose variables using methods such as AIC. Logistic regression can be extended beyond binary outcomes to include multiple response variables using ordered logistic regression. Finally, many different types of regression exist. For example, quantile regression allows responses such as the median or 75% percentile to be used rather than the mean. To learn about these and other tools, you may need to search the web and read R packages documentation.

4. Happy coding!

Good job on completing this course! I hope you're able to keep expanding your regression tool box and grow as as data scientist. Happy coding!

Create Your Free Account

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.