# Basic Time-Series Analysis: Model Choice Cookbook

This post is the sixth and final in a series explaining Basic Time Series Analysis. Click the link to check out the first post which focused on stationarity versus non-stationarity, and to find a list of other topics covered. As a reminder, this post is intended to be a very applied example of how use certain tests and models in a time-sereis analysis, either to get someone started learning about time-series techniques or to provide a big-picture perspective to someone taking a formal time-series class where the stats are coming fast and furious.

This post concludes the sequence of posts on time series basics. It certainly doesn’t replace the need for a good course in time-series econometrics/statistics; there are a lot of complicating factors and model extensions I didn’t touch upon. But, I hope beginners can use it to get started poking at their own questions, or reading others’ research based on little more than what is covered in these posts.

So with that, the final post in this series provides a ‘cookbook’ approach, or series of questions along a decision tree to guide you toward what kind of model you should be thinking about for your own analysis.

# Cookbook for Model Selection

One minor detail. After deciding that you have one series you want to explore, you determine if the series is stationary or not. This flows into the Mean/Variance? box because whether or not the series are stationary partially determines the form the ARIMA or GARCH will take.

# That’s It!

Well, that’s it for this sequence of posts on the Basics of Time Series econometrics. Thanks for reading along!

### Reposts

• Suman Kumar
• F. Bethke
• Geraldo Costa Júnior
• Economic Sense
• Mohammed Ohiul Islam
• Tobias Dalhaus
• Rstats
• Ramaele Moshoeshoe

### Mentions

• Levi Russell 📈

1. What advice would you give someone with 5 variables, one of which is trend stationary and the rest are nonstationary? The research question regards the effects of 4 of the vbls on the other. That is, I’m interested in the marginal effects, not forecasts.

2. Difference the non-stationary ones. Interpretation gets weird.

### Webmentions

• READ ALL OF THESE, ESPECIALLY PHD STUDENTS!!!!