I keep replying to this...it's shown in the video and linked in the description. The same data as the authors of the plot!

Yep, the GDP growth variable's historical values and calculations to forecast it's future values.

No, I used the same data as the IMF and my model more closely matches the actual growth. My model is also very simple and illustrates the concept of reversion to the mean.

@@econ_eric what IMF data is that specifically?

@@user-yz9bu6rx7b Check out 9:39.

@@user-yz9bu6rx7b Please watch the video. I visit the actual website for data. I've also linked my data in the description.

You're welcome! Thank you!

You're welcome!

You're welcome!

You're welcome!

You're welcome!

That's a great question! I assume you mean a distance scale..I'm actually not familiar with adding these elements, but you may find some help at the Stata forums or simply through internet searches. Thanks!

Excellent news! I'm glad you got it. I find youtube to be a great resource for programming, so easy to see examples worked out.

Hey Emily, check out this website for the different color palettes: repec.sowi.unibe.ch/stata/palettes/colors.html. The author gives you the code and examples. You can do a search for "heat" or just pick out the scheme that you think looks best. Thanks!

Haha, I knew that might happen when I posted this. I hope you are well!

Hello Duhamel, you're welcome. I'm not certain that the spmap command has this functionality, but if you send me the files and code, then I can take a look at it. Alternatively, you can search online for more documentation and there is a forum where you can post the question for others: statalist.org. Thanks!

@@econ_eric Hello, thank you for your answer. I got the solution to my problem and I was able to put the names of the departments on the map.

Another concern of mine is to be able to visualise more than one variable at a time on the map with legends of each variable.

You're welcome!

You're welcome!

If you dfuller shows stationarity (reject Ho), then however you set up the dfuller test should be your base model. Then you adjust things. Check out p.2 of the tsdfuller pdf. If you're trying to determine which model is the best model to forecast with, then I would generate a new dependent variable series, delete some of the most recent observations, and forecast with each model. Some models may forecast a recovery from recession better and others will forecast the growth before a downturn better. Which is more important to you? There are also the indicators of model fit to consider. Also, I'm not sure if you mean the optimal lag # or the optimal lag. Check out the tsdfuller pdf for details on the output of dfuller and what you're actually testing.

Also, you can test whether a model is stationary by predicting residuals (postestimation in Stata). Predict the residuals and then use dfuller to determine if the residuals are stationary. Do this for each variation of your model. Also, If you find that the first difference of your variable is stationary, then try including a one-period lag of the variable on the right side of the equation (as an independent variable). Predict the residuals and determine if they are stationary. This can be a viable alternative to using your first difference model from dfuller as your main model.

You're welcome, Yuqing! Do I refer to squared deviation in the video or the program code? I'm not quite sure what you're referring to.

@@econ_eric hi Eric, you mentioned squared deviation from mean in the video and say there is much deviation from mean corresponding to the crisis, I am not sure if the squared deviation here referring to the variance

@@yuqingwu1011 I'm not sure where I said squared deviation in the video, but the GDP growth associated with a crisis will be a large deviation from the mean of the GDP growth series.

Of course, you're welcome, Patricia!

Of course! You're welcome!

Glad you liked it!

Glad it was helpful!

Yes! It was a simple autoregressive model without any error terms. Thanks!

You may not have saved coefficient estimates from the regression model.

Same issue here. I saved the coefficient estimate from regression model. But the error still states "Missing values were encountered while attempting to solve the model at time 2023. Variable NUTHIV evaluates to missing." What might I be doing wrong? Thank you beforehand!

Interesting! I'm not too familiar with these empirical models, but I'll consider it for a future video!

@@econ_eric that would be awesome, although I hope to beat you to it 😅😅. I couldn’t find any youtube videos, so I’ve decided to take the plunge myself

@@Beygent Good for you! Maybe we can collaborate for a video. Let me know how it turns out! :)

Yes, it is in the description of the video. Thanks!

Very welcome!

Hello Duong, thank you for your comment. I think your solution is to store the estimates from the new model with worldgdpgrowth and then use the forecast command. For instance, include worldgdpgrowth in the model on line 79, store the estimates, and then create a new forecast model on line 96 (call it something different than ericmodel). Please let me know if that works.

Hi dougie ws, did you perhaps make a change to the data? This program should work since I uploaded it to the Google drive. I would try to download and run again. Let me know if that works.

You are very welcome, Ali.

Glad it was helpful!

Thank you, Zaeem, you are welcome!

You're welcome!

Yes! It is still meaningful to regress gdp growth on l.gdp growth if it produces accurate forecasts. I would argue that the relationship is not spurious - a good year of growth is likely to spur another good year. Consider the alternatives and determine which model produces more accurate forecasts. I was thinking about making another video about lag specification or checking the accuracy of forecasts. There are several ways to check the accuracy of your forecasts - one easy way is to compare the actual data to the forecast. The Stata manual for the forecast command explains this well beginning on page 6: www.stata.com/manuals13/tsforecast.pdf If the coefficient on the lag of GDP growth is not significantly different from zero with 0.05 level of significance, we can try another model with only the regression constant or perhaps another variable or two. Then, plot and compare the forecasts between models, compare r-squared values, etc. In any case, if a model accurately forecasts, then it is hard to argue that it is not meaningful because a p-value for a coefficient is 0.054 rather than <0.05. It is true that the relationship may be spurious; however, the theoretical justification is not a stretch. Also, this model is probably sensitive to the selection of the sample. For instance, if we drop a recent outlier in GDP growth, the q-value and p-value may change.

@@econ_eric thanks for the comprehensive comment! A lot to digest and yes a video regarding lag specification and forecasting accuracy sound like good content! Thanks for the reply :)

Thank you, Chris, I have some more to come.

You're welcome!

Samia, what is your panel variable? If it identifies countries, then do you want real GDP growth plotted for each country in your data set? The variable f_realgdpgrowth includes a forecast of GDP growth, also. Therefore, many options are possible for an estimation and plot.

Hello Samia, you're welcome. However, I don't understand what you're asking with "the second 0.04". There is no panel data here.

@@econ_eric Yes I know there is no panel data in your video. I ask if you have the command to do this graph that figures in your video at the second 0.04 and also at the time 8.48 minute (forcasting graph) but with panel data case. I need to get this graph for my paper using panel data approach.

@@econ_eric I must to do a panel GMM forcasting study that's why.

Thank you, Giovanni!

Hello! The link to my program code and data is in the description - thank you!

@@econ_eric Hi Eric, thank you very much. Any idea about Covariate Augmented Dickey Full test? Thanks.

@@businessleadershipandmanag522 I've done a quick search and found a good post in the Stata forums by Andrew Musau: www.statalist.org/forums/forum/general-stata-discussion/general/1361250-determining-optional-lag-length-using-varsoc-for-panel-data According to Andrew in 2016, the topic isn't addressed well in the Stata forums. However, there have been some updates to Stata since 2016 and maybe they address it in Stata 17. You could also try contacting some of the Stata staff.

@@econ_eric Thanks Eric.

@@econ_eric Im using Stata 15.

Thank you, Hermanus!

Thank you, Lord of Fraternity!

You're welcome, Johanna! I'm glad you've found it useful!

Glad you enjoyed it!

You're welcome!