[SciPy-User] Time Series Analysis in SciPy
Mon Oct 10 10:23:48 CDT 2011
On Mon, Oct 10, 2011 at 11:22 AM, <firstname.lastname@example.org> wrote:
> On Mon, Oct 10, 2011 at 11:14 AM, Haq, Salman <Salman.Haq@neustar.biz> wrote:
>> Hi All,
>> I'm dipping my feet in statistical analysis after a long time could use some high-level guidance.
>> I have several historical time series and I want to be able to answer questions about them like:
>> - how well does series A track series B?
>> - is there causality between series A and B?
>> - etc....
>> I think these are common questions about time series data that I'd like to answer.
>> How do I go about doing this?
>> - which set of libraries/functions should I most likely explore?
> short answer: pandas and scikits.statsmodels.
too short: and nitime if you are more interested in frequency domain
>> - which type of visualizations will be most intuitive to understand the results?
>> - implementation-wise, which is the most efficient way to store/load the data if the series are typically under 1000 samples?
>> - other things or resources I should keep in mind?
>> SciPy-User mailing list
More information about the SciPy-User