Search found 24 matches
- Thu Jun 22, 2017 11:13 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
One suggestion I made earlier was to include month dummies. But I suspect the most important advice is to look carefully about Gareth's comment on something being wrong with the data, both the large number of 1s for some skus and the data not matching the Excel file. Startz, These are particular SK...
- Thu Jun 22, 2017 11:11 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
EViews Gareth wrote:Unfortunately, I do not give econometric advice.
Thank you anyway!
- Thu Jun 22, 2017 9:04 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
Before delving too deeply into this, I'll point out a couple of things. First you might want to structure your workfile as a dated workfile. Going on the information you gave (it starts in 2014, the series "mes" is month, and "salida_del_mes" is day of the month), you can use th...
- Tue Jun 20, 2017 9:35 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
It's nice of you to share all this information. Can you explain the word "quasivariation?" I'm not familiar with it. http://www.uv.es/webgid/Descriptiva/Imagen17.jpg A measure that minimizes the square of the error minus the average error. Remember that the error in my model is given by E...
- Tue Jun 20, 2017 9:20 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
One small addition to Gareth's points. I think the "day of the month" variable" is just a sequence number within the month. In other words, "1" might sometimes be the first observation but the second day of the month. Since you know the day of the week, you could probably m...
- Tue Jun 20, 2017 9:18 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
Before delving too deeply into this, I'll point out a couple of things. First you might want to structure your workfile as a dated workfile. Going on the information you gave (it starts in 2014, the series "mes" is month, and "salida_del_mes" is day of the month), you can use th...
- Sat Jun 17, 2017 3:17 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
By the way, this is an interesting example. Perhaps it's something I could use in my undergraduate econometrics class. If you wouldn't mind, can you say a little more about where the data is from and what the objective of the forecast is? This attachment also has the series: 1. Stock of each sku pe...
- Sat Jun 17, 2017 3:15 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
By the way, this is an interesting example. Perhaps it's something I could use in my undergraduate econometrics class. If you wouldn't mind, can you say a little more about where the data is from and what the objective of the forecast is? This attachment also has the series: 1. Stock of each sku pe...
- Sat Jun 17, 2017 3:12 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
By the way, this is an interesting example. Perhaps it's something I could use in my undergraduate econometrics class. If you wouldn't mind, can you say a little more about where the data is from and what the objective of the forecast is? The data come from the sales made in the region of Valparaís...
- Sat Jun 17, 2017 1:38 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
I messed around a little with sku1, just as an example. You can get some improvement in forecasting by including a lagged value of the sku and also a time trend. I am pretty sure you could also get improvement by including month dummies, but you'd need to create a dated workfile for that. Thank you...
- Sat Jun 17, 2017 1:07 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
Is this data you can post? salida_del_mes : Corresponds to the day of the month that there was sale (it is different from 30 or 31 always smaller since it is not sold on Sundays or holidays). Lunes : Corresponds 1 if it is Monday, 0 if it is another day Martes : Corresponds 1 if it is Tuesday, 0 if...
- Sat Jun 17, 2017 12:58 pm
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Re: Coca cola demand forecast (models)
startz wrote:Is this data you can post?
- Sat Jun 17, 2017 10:21 am
- Forum: Data Manipulation
- Topic: basic problem
- Replies: 6
- Views: 4934
Re: basic problem
EViews Matt wrote:Oops, when testing I used a series instead of a matrix and forgot to change the syntax back. Replace "@elem(__best_model, @str(!c))" with what you had originally, "__best model(!c, 1)".
Thanks Matt
The difference was clear to me!
- Sat Jun 17, 2017 10:09 am
- Forum: Econometric Discussions
- Topic: Coca cola demand forecast (models)
- Replies: 24
- Views: 14926
Coca cola demand forecast (models)
Hello, I have a database of 84 different products (sku's from a Coca-Cola bottler). The database consists of the demand for each product from 01/01/2014 to 04/30/2017 day per day. What types of models could you use to predict next day demand? I have used moving averages and exponential smoothing (al...
- Sat Jun 17, 2017 8:57 am
- Forum: Data Manipulation
- Topic: basic problem
- Replies: 6
- Views: 4934
Re: basic problem
You've got the right idea. Here are a few changes: matrix __resultados = @sort(@uniquevals(__best_model),"a") matrix(__resultados.@rows, 2) __resultados for !i = 1 to __resultados.@rows !iden = 0 for !c = 1 to @obsrange if @elem(__best_model, @str(!c)) = __resultados(!i, 1) then !iden = 1...