2017MAY17 S&P500 forecast.

> as.xts(forecast(auto.arima(UC),h=10)$mean[1:10],as.Date(as.yearmon(seq(mondate(index(last(UC)))+1,by=1,length.out=10))))[(3-month(index(last(UC))) %% 3) + c(1,4,7)]  #arimaUC
               [,1]
2017-07-01 1070.704
2017-10-01 1067.531
2018-01-01 1065.085
> as.xts(forecast(auto.arima(PA),h=10)$mean[1:10],as.Date(as.yearmon(seq(mondate(index(last(PA)))+1,by=1,length.out=10))))[(3-month(index(last(PA))) %% 3) + c(1,4,7)]
               [,1]
2017-07-01 146533.6
2017-10-01 146980.6
2018-01-01 147405.9
> my_sp5(last(GDP) * 1.05**(2/4),146533.6,1070)
[1] "m_m params! apply.quarter - UC w/ nominal GDP"
                GDP
2017-01-01 2471.923
> my_sp5(last(GDP) * 1.05**(3/4),146980.6,1067.531)
[1] "m_m params! apply.quarter - UC w/ nominal GDP"
                GDP
2017-01-01 2557.749
> my_sp5(last(GDP) * 1.05**(4/4),147405.9,1065.085)
[1] "m_m params! apply.quarter - UC w/ nominal GDP"
                GDP
2017-01-01 2642.108
> last(UC)
           UNDCONTSA
2017-04-01      1074
> kikan
[1] "1992-01-01::2017-03-31"

Please see below. The result is not same the previous post even with completely same parameters. This is caused by UNDCONSTA before April is also revised at this time and it has an impact on the underlying economic model.

> my_sp5(19767.59,147405.9,1117.029)
[1] "m_m params! apply.quarter - UC w/ nominal GDP"
[1] 2537.074