Skip to content
Prev 295726 / 398503 Next

how to check given number seq. is time series or not?

On May 26, 2012, at 7:50 AM, R. Michael Weylandt wrote:

            
After I stopped chuckling at Michael's response, I copied that list to  
my clipboard, clicked once on my Rconsole window, and typed:

vec <- scan()  # and hit return

I then pasted the clipboard contents to the console, watched as 100  
numeric values were passed on to 'vec' and hit enter to cause a double  
<cr> to signal to scan() to stop entry. I then typed:

plot(vec)

And one can then see that most of the numbers lie between 0 and 1.5. I  
thought I saw a "hard ceiling" at around 1.5 and looking at the data I  
wondered if the several values of 1.442... were the same:

 > vec[vec==1.4424189950435]
  [1] 1.442419 1.442419 1.442419 1.442419 1.442419 1.442419 1.442419  
1.442419 1.442419 1.442419
[11] 1.442419 1.442419 1.442419

There does seem to be a discrete process underlying this. There are  
only 32 discrete values, and here at the 10 most common:

 > rev(table(vec)[order(table(vec))] )[1:10]
vec
   1.4424189950435  1.22726162946495  1.35785109728356  
0.970883941918588 0.774234247460432
                13                11                 7                  
7                 6
  1.10704609982913   0.9670580678417 0.889046409368551  
0.822170913920467  4.91679981837699
                 5                 5                 5                  
5                 3

Four values stand out as materially different. Three of them appear to  
have hit some sort of "secondary ceiling" at a value of 5 and another  
is sitting all alone at 2.3 (roughly).

Now as Michael asked .... what WAS the question?