There will be US/XXX currency data of a short-window on the left side and at the right side, there will be Beta0 + Beta1*Surprise*Dummy1 + Beta2*Surprise*Dummy2 + Error Term where Dummy1 states whether it has price stability target and Dummy2 indicates whether it has any other targets or not. Therefore my regression will be as follows. I will then classify these central banks in a way that whether each of them has only price stability (inflation) objective in its legal objectives or any other objectives such as growth, unemployment etc. I am choosing 4 central banks of developed countries together with 4 developing countries with 'fragile' economies. I will examine the effect of monetary policy surprises of FED ( only the interest rate surprises of FOMC) on currencies with countries of different central banks with different legal objectives: Bank of Canada, Reserve Bank of Australia, ECB, Bank of England and a suitable four countries of 'Fragile Five'. This is a project of event study methodology. I briefly tell what I am doing in my project. Is it possible to compare the results of two different tests? If the model for Bitcoin included indeed also stationary I(0) variables, I would apply an ARDL model to the Bitcoin data and a VECM to Ethereum (the variables are cointegrated). Which result of the ADF-test regarding Bitcoin is more reliable/ should be considered? Should the number of lagged differences be chosen according to the AIC? 2.
#STATA DEDLETE XLIST SERIES#
Moreover the results for Ethereum suggest that the time series is non-stationary.
#STATA DEDLETE XLIST CODE#
For the "Bitcoin views on Wikipedia" the ADF-test shows different results depending on the lag-order (stationary for low lag order nonstationary for a high lag-order). Could you post a code example of the estout call here (Hint: you can use the wrappersxxx
to highlight code, but remove the ). One of the variables I use is "views on Wikipedia" as a proxy for public recognition respectively attractiveness.
![stata dedlete xlist stata dedlete xlist](https://newssrc.onlinedown.net/d/file/20201022/2344e66688a32a143468dd6e3794914a.jpg)
As i am comparing the price formation of Bitcoin and Ethereum, I assume, that the same model should be applied to both of the cryptocurrencies for the sake of comparability.
![stata dedlete xlist stata dedlete xlist](http://www.maartenbuis.nl/example_faq/dofile_11.jpg)
Generally it shouldn't be a problem if some variables are stationary whereas others are integrated of order one, as an ARDL model could be applied. However, i am facing some problems regarding the stationarity of some of my variables. Therefore i am conducting a time series analysis (either VECM or ARDL). I am currently writing my bachelor thesis on the price formation of cryptocurrencies.