Revised model for S&P 500 from 1992-01-01 to 2016-12-31

don't use "2016-10-01" to indicate 2016Q3 as data starts from 2016-10-03 in the designated period.

in order to extend data period of GDPC96, incorporate data from GDPnow. It suggest 2.8% annual GDP growth for 4th quarter, therefore adding another 0.7% will be the forecast of Q4.

> GDPC96 <- c(GDPC96,xts(as.numeric(last(GDPC96)*1.007),as.Date("2016-10-01")))
> start_date <- "1992-01-01"
> end_date <- "2016-12-31"
> start_date; end_date
[1] "1992-01-01"
[1] "2016-12-31"
> G <- GDPC96
> PA <- PAYEMS
> UC <- UNDCONTSA
> kikan <- paste(start_date,end_date,sep='::')

don't do "C <- UNDCONTSA", it will destroy the precious c() function.

> (summary(lm(to.quarterly(SP5[kikan])[,4] ~ to.quarterly(PA[kikan])[,4] * to.quarterly(UC[kikan])[,4] * G[kikan])))

Call:
lm(formula = to.quarterly(SP5[kikan])[, 4] ~ to.quarterly(PA[kikan])[,
    4] * to.quarterly(UC[kikan])[, 4] * G[kikan])

Residuals:
     Min       1Q   Median       3Q      Max
-308.451  -66.658    9.279   83.037  216.776

Coefficients:
                                                                     Estimate Std. Error t value Pr(>|t|)
(Intercept)                                                         2.752e+04  7.082e+03   3.886 0.000192 ***
to.quarterly(PA[kikan])[, 4]                                       -2.924e-01  6.109e-02  -4.786 6.46e-06 ***
to.quarterly(UC[kikan])[, 4]                                       -1.005e+01  9.216e+00  -1.090 0.278529
G[kikan]                                                           -1.970e+00  5.688e-01  -3.463 0.000813 ***
to.quarterly(PA[kikan])[, 4]:to.quarterly(UC[kikan])[, 4]           1.945e-04  7.119e-05   2.732 0.007551 **
to.quarterly(PA[kikan])[, 4]:G[kikan]                               2.139e-05  4.288e-06   4.989 2.86e-06 ***
to.quarterly(UC[kikan])[, 4]:G[kikan]                              -2.774e-04  7.493e-04  -0.370 0.712028
to.quarterly(PA[kikan])[, 4]:to.quarterly(UC[kikan])[, 4]:G[kikan] -6.310e-09  5.209e-09  -1.211 0.228875
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 126.8 on 92 degrees of freedom
Multiple R-squared:  0.9313, Adjusted R-squared:  0.9261
F-statistic: 178.2 on 7 and 92 DF,  p-value: < 2.2e-16