We look at a few forecasts for the year 2011 that we’ve run across, and compare them with the prediction distributions presented in Revised market prediction distributions.

FTSE 100

There is a “range forecast” on an Interactive Investor page of 5350 to 6565.  It isn’t clear (to me at least) what this means, but I find it fascinating that it is ever so close to a 95% confidence interval  assuming no market movement via my technology.  The quantiles of that range are 3.2% and 97.6%.

Table 1: Some 2011 predictions for the FTSE 100.

Figure 1: FTSE 100 (UK) 2011 prediction distribution with predictions.

Dow Jones Industrials

A range for the Dow Jones of 10,300 to 12,750 is predicted by tradersir. That corresponds to quantiles of 1.4% to 97.3% in my distribution.  Ranges are also given for the S&P 500: 1100 (0.9%) to 1400 (98.0%).

Table 2: Some 2011 predictions for the Dow Jones Industrials.

Figure 2: Dow Jones Industrial Average (USA) 2011 prediction distribution with predictions.

S&P 500

Table 3: Some 2011 predictions for the S&P 500.

Figure 3: S&P 500 (USA) 2011 prediction distribution with predictions.

Hang Seng

Table 4: Some 2011 predictions for the Hang Seng.

Figure 4: Hang Seng (Hong Kong) 2011 prediction distribution with predictions.

Shanghai Composite

Table 5: Some 2011 predictions for the Shanghai Composite.

Figure 5: Shanghai Composite (China) 2011 prediction distribution with predictions.

Sensex

Table 6: Some 2011 predictions for the Sensex.

Figure 6: Sensex (India) 2011 prediction distribution with predictions.

Oil price

Table 7: Some 2011 predictions for oil price.

Figure 7: Cushing OK contract 1 (US dollar) 2011 prediction distribution with predictions.

Epilogue

Figures may be reproduced with attribution.

Appendix R

The tables are created automatically by R from the data frames that hold the data for the predictions.  I just copy the R output and paste it into the html editing window.  The xtable package is almost suitable for that, but (as far as I can tell) it doesn’t allow the html commands to go through unaltered.  So I wrote a little function (pp.htmltable) to do what I wanted.

Yet again you can get the R functions that are used via the R command:

> source('http://www.portfolioprobe.com/R/blog/prediction_dist_funs.R')

On one use of this command, I received:

Error in file(file, "r", encoding = encoding) :
cannot open the connection
In addition: Warning message:
In file(file, "r", encoding = encoding) :
unable to resolve 'www.portfolioprobe.com'

However, that was just a temporary glitch.