Hi everyone,
I'm a total newbie in using stata. For my diploma I have a huge panel
dataset with about 4 million observations based on daily sales from a well
known Company. Within these dataset I have 29 different Variables (15
different marketing Variables). I'm trying to measure the influence and the
effects of these marketing variables on the amount of sales for the last 4
years.
The dataset looks like the following: (variables in order to their
appearance)
Date/ Customer - No./ Name/ Material/ Price/ Sales/ 15 different marketing
Variables/ Bonus/ 8 other not so important Variables
I have a few questions, and hope you can give me some good hints to bring
that analysis to an good end:
1.) In the dataset I have multiple observations. I tried to eliminate them
with a pivot table, but there are still duplicates in the dataset. Is there
any chance to work with them in the dataset? It would save me a lot of time
to leave them into the dataset.
2.) What kind of panel model should I use?
3.) My biggest problem is to manage the marketing Variables. These Marketing
payments are paid on a fix date for special marketing actions. The
difference on these marketing actions are the payments that are paid to
vendors and not to the end customers. The effects from these marketing
actions can start for e.g. 2 weeks in advance or 2 weeks later, because the
company and the vendors have made an agreement in advance.
My question is, how can I define my marketing variables that consider these
effects. I'm not sure if I can realize it with regular lags and leads.
I'm thankful for every help or suggestions. Thanks in advance.
Tobi
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
