
This is additional evidence that the trend relationship changed._ However, note that the post-crisis trend is positive, compared to a downward trend in the pre-crisis period. _Explanation from IMF Staff: Once again, the regression results imply a highly significant trend term. Which of the specifications is most appropriate?

Which of the specifications appears to be most appropriate?Įnter the resulting p-values in the corresponding yellow-shaded cells in the Excel file. Repeat the unit root/stationarity tests, for the pre-Global Crisis period (from **2000:04 to 2009:05**), and enter the p-values you obtain in the corresponding yellow-shaded cells in the Excel file. Mutate( str_break = ifelse( pe_aus > 2 * mean( pe_aus), "true ", "false ")) % >%Īnswer: The structural break is likely to have occured in the period: `Late 2009 - Mid 2010`.
Kpss test eviews series#
# Estimate of structural break = 2 times the mean of a time series _Note: See Module 7 for a more detailed treatment of structural breaks._ Based on the graph of `pe_aus`, when is the structural break likely to occur? However, there may be a structural break in the series that is distorting the tests. _Hint: Based on the specification you selected in Q3.44, check the table summarizing the p-values of the different tests (first row of M3B_Table_unit_root_tests.xlsx) in order to reach a conclusion._ What conclusion can you draw about `pe_aus` for the **2000:04 - 2015:02** period (Use the command `smpl 2000M4 2015M2`)? Note that the p-values for the KPSS test should be included as ranges, such `p > 0.10`, `0.01 % Also, make sure you change the sample before running the test._Įnter the p-values of your results in the corresponding yellow shaded area in the Excel file.


_Hint: As in previous questions adapt the command `pe_aus.uroot(adf, exog = trend, lagmethod = aic)` where we added the option `lagmethod = aic` to make sure EViews uses the Aikeke criterion instead of the Schwarz criterion to determine the number of lags in the test. For the sample period **2000M4 - 2015M2**, conduct the three unit root/stationarity tests covered in the lecture (ADF, PP, and KPSS) for all specifications (Intercept, Intercept and Trend, and None), using the AIC to determine the maximum lag included. Open the series `pe_aus`, the price-earnings ratio for Australia. Also open the Excel file `M3B_Table_unit_root_tests.xlsx`, which you can fill in to summarize your results. Open the EViews workfile `Module3B_data.wf1`, pagefile `PE_ratios`. It appears that in first differences the Malaysian real effective exchange rate is stationary. However, it appears to be stationary in the second half of the time period (after the Asian chrisis). ))Ĭoncluding on the basis on visual inspection of Malaysian time series (real effective exchange rate) it appears that it is nonstationary. Tsdisplay( reer_mys $ reer_mys % >% diff(. # print the results of stationarity testingĪccording to the visual inspection and formal stationarity testing the **South African time series appears to be stationary**. Tsdisplay( my_pe_df $ pe_saf, las = 1, col = "blue ") # Module 3B: Statistical Properties of Time Series Data # IMF Online Course: Macroeconomic forecasting
