3
$\begingroup$

enter image description here link: https://research.stlouisfed.org/fred2/graph/?g=3big

I have watched this video where he explain this chart. Basically he shows high correlation between Monetary Base and the Stock Market. But I cannot understand why he multiply the Wilshire for 47 and the "Federal Funds Rate" for 250 ?

$\endgroup$
1
$\begingroup$

The multiplication factors are there so that they can be charted and be seen on the same axis as the St. Louis Adjusted Monetary Base.

The factor of 47 means that the closeness of the match between that and the Wilshire 5000 in 2000-2015 is easiest to see, by overlaying the curves in that period.

$\endgroup$
  • 1
    $\begingroup$ Ok, but which is the formula where you get 47 as result? It Came from a regression ? $\endgroup$ – sparkle Jan 30 '16 at 13:57
  • 1
    $\begingroup$ @sparkle you're over-thinking it: regression's an over-complication. Look at the chart. Look at the green line and the red line for 2010-2015. What do you notice? That's why they chose 47. $\endgroup$ – EnergyNumbers Jan 30 '16 at 17:09
0
$\begingroup$

I think you have to look at the concept of spurious regression.

A key idea useful to interpreting correlations like this is the idea of "spurious regression". Any two time series X and Y each of which has a trend (even if it's a "random trend" !) will appear to have a high negative or positive correlation. (This is because, if there's a trend, all the values above the mean and all the values below the mean will tend to be on opposite sides of the time series, for both series. A high correlation then tells you that the above the mean values of one series coincide with the above(or below) the mean values of the other series...which is not very surprising.) A high correlation in this setup is an interesting finding if it's a correlation of the 'de-trended' series, or of the 'differenced' series.

Also, plot the series since then. The stock market has gone through upturns and downturns that do not seem to be related to the monetary base in any way.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.