I am not sure if this is the right place to ask this question (if not, please refer me to the right place), but it would be nice if someone could help me:
Description of the Data/the Scenario:
I have access to a huge amount of secondary data (>10000 cases) from a sourcing department of a company in the time-span from 2006-2012.
The dataset consists of the ID of the part that has been sourced, the year of price-negotiation, the price resulting from the negotiation and the participating companies in the negotiation. In this data, I want to test, whether the participation of low-cost competitors (in price-negotiation) had an effect on the price-trend/level over the (following) years.
Therefore, I plan to identify all parts that got negotiated (every year) from 2006-2012, then I want to split them into 2 groups, group 1 has low-cost country participation in negation after 2009 and group 2 has no low-cost country participation in negotiations at all (from 2006-2012). (Additional groups may be possible, but first I want to know how to do this with only two groups.)
In essence, I have a longitudinal design with control group (respectively, I have a multiple group short interrupted time series quasi-experiment or Interrupted Time Series Design with Comparison Group)
Has the participation of low-cost countries (long-term) effects on the price levels?
Year: 06 07 08 09 10 10 11 12 Group1: O O O O X O O O Group2: O O O O - O O O
ID Time Price group 1 2006 1,5$ 1 1 2007 1,5$ 1 1 2008 1,5$ 1 1 2009 1,3$ 1 1 2010 1,2$ 1 1 2011 1,2$ 1 1 2012 1,1$ 1 2 2006 10$ 2 2 2007 9,9$ 2 . . . .
A) Which analyses-approaches do I need to perform (e.g.LGM, HLM, PS--> see Braver & Braham 2005)?
B) Which programs (I have SPSS, otherwise preferable open source) do I need?
C) How to code my data that they fit in the program/ fit the analysis-approach (long format or wide format, dummies)?