Page 48 - FINAL CFA II SLIDES JUNE 2019 DAY 3
P. 48
READING 9: TIME SERIES ANALYSIS
The critical 2TT (5% SL and
t-statistic for Lag 2 = 100 df) = 1.98 > 0.851760; so?
0.0843368 / 0.099 = 0.8518.
Fail to Reject Ho and conclude that none of the autocorrelations of the residuals is statistically different from zero. Meaning?
There is sufficient reason to believe that the error terms from the AR(1) model are NOT serially correlated.
If t-tests indicate any correlation computed in Step 2 are statistically significant (i.e., t ≥ 1.98), the AR model is not specified correctly.
Additional lags are included and the correlations of the residuals (error terms) are checked again until all autocorrelations are insignificant.
