Dear community,
I am struggling with statistics for price comparison.
I would like to check if the mean market price of a given product A differs over two consecutive time periods, namely from December till January and from February till March.
My H_0 would be that means are equal and H_1 that from Feb till March the mean is lower.
For this I have all necessary data as time series, sampled at the same frequency.
I thought of using the paired t-test, yet price distribution is not normal (extremely low p-value of Shapiro-Wilk test).
I guess that the two random samples of two groups cannot be treated as independent, as my intuition is that price in February would depend on price in January.
Do you know any test that would fit here? Given the nature of the problem?
Thanks in advance
Also it depends on why you need to compare those means. If you just want to see if there's a trend, I would recommend the Mann-Kendall test.
Thanks Andrey for your answer.
I collect the data continuously, every hour. The idea is to show that one particular market mechanism introduced on a given day influenced the price of the product, causing it to drop and that this drop was not observed before i.e. it was most likely due to this mechanism introduced
Then it becomes a bit more difficult, but still you can use some maths to prove that.
I recommend you the following:
1) Take the history of weekly observations (means) collected before the moment your mechanism was introduced.
2) Use a forecasting method to prepare 95% prediction intervals (PI) for the next two months.
3) If it happens that many weekly observations collected for the period after the introduction of the mechanism lie outside the PIs obtained in Step 2, it is likely that the mechanism really affected the price.
Dear Mariusz. I recommend using the t-statistics of the Student Criterion. I attach an example of this use to several other data. I hope you'll be interested.
Since you want to study price differences before and after an event, what you need is called an event study in the finance/accounting literature. See the attached for an introduction to that literature . Best wishes, David Booth PS this is similar to @Andrey Davydenko solution. (added 3/31/20).
- Badges
- Science topic
- Similar topics
- Mathematics
- Applied Mathematics