The briefing (from German to English via Google Translate):
Measurement of direct elasticity and cannibalization At the beginning of the season, the responsible Category Manager (CM) has adapted its prices for lawnmowers. He has lowered some prices of robot lawn mowers and then adapted constantly. At the end of the season, he then tries to make an assessment of his pricing measures. In doing so, he wants to understand the effects of his price changes and measure the volume effects induced by the price change. However, he quickly encounters a number of challenges in his calculations and asks you for help. Now he describes what he has already tried:
A pre-conversion-to-conversion comparison has not provided any plausible values, as the weeks before the price change were still before the start of the season and hardly any lawn mowers (in both segments) were sold here
A comparison with the previous year also delivered unrealistic figures, as the season started much earlier last year. This year, however, the start of spring is yet to come It also complicates the assessment that Easter will be at a different time this year than last year
Finally, a big promotion (VAT Day), which takes place once a year, came to a day shortly after the changeover
The search for a suitable comparison assortment (for the measurement test vs. control group) has so far also been unsuccessful. For example, plants have responded much more strongly to the temperature fluctuations, other garden tools significantly less Now he asks you to do the analysis for him. As an additional challenge, he would also like to understand whether it is through the price cuts to cannibalization (customers change from others Products on the price lowered) within the product group. The main focus should be on the volume effects.
!TASK: Describe your procedure for determining direct elasticity, and (subordinate) for estimating cannibalization for price changes made. Take a detailed look at the analysis method you have selected and demonstrate the application to the existing data set. Describe why you choose which input variables from this dataset. Finally, consider the pros and cons of your procedure. Note: The main focus of the discussion will be on the analysis method you selected and the justification of your approach. Results are an advantage, but please do not despair if you can draw no or only implausible results from the record. Then explain why the results do not seem plausible to you and how you can change your analysis.
reg. the columns: umsatz in german = sales, niederschlag = rain, soll_vk = normal price in the shelf, brutto price, ist_vk = real price (incl. ads + give reduction)
1. Please use preferably Python ( However, R is also ok)
2. For reproducibility all source code must be attached
3. Please make comments in your code – the more, the better
6 freelancers are bidding on average €30 for this job
Is it possible for you to put the column headers in English? so that I can understand it better...I can finish the analysis within 2 days post your approval.