How to learn fitting models?

I am new to R(learned the basics)
In my current job I have to solve the following problem(the following is an example)
- Suppose we have 10, 000 users
- For each user we have his expected monthly spending(in dollars)(with some method that I don't know) for one year
- What we have to do it fit a model where if for that year we give two dates(Jan-1, March 16), the model should tell us the expected spending(in dollars) for this duration

Question:

How to go about and fit a model
How to see graphically that model fits correctly with the data points I have
How to predict and get answer

Please assist me
Thank you

asked Mar 23 '12 at 14:09

daydreamer
105●6●8●9

One Answer:

oldest newest most voted

This is a very narrow question regarding an application, but a very broad one regarding the field of statistical anlysis. A general answer is beyond the scope of this forum.

Depending on your mathematical and computational background you can consult a wide range of books -- e.g. 'Machine learning for hackers' or 'collective intelligence' by O'Reilly on the easier end of the spectrum. If you are not afraid of matrix algebra, probability theory, calculus and graph theory, I recommend David Barber's very recent 'Bayesian reasoning and machine learning'. It is very complete and has lots of examples (including code!).

answered Mar 23 '12 at 14:42

Justin Bayer
1706●9●30●45

Subscription:

Once you sign in you will be able to subscribe for any updates here

Tags:

regression ×101
data-mining ×64
statistics ×49
r ×27
modeling ×22

Asked: Mar 23 '12 at 14:09

Seen: 1,261 times

Last updated: Mar 23 '12 at 14:42

How to learn fitting models?

Subscription:

Related questions