Dear Stata users,
For my Project, I need the histogram of the intraday returns for each day and save the densities.
As far as I search, I am able to save the density with twoway__gen_histogram command.
However, I also need to assign the minimum and maximum numbers to the bins by myself.
I am not allowed the share the original data but let’s say I am working with the following fake data:
when I check the range with
the output is
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
return | 48 .0226268 .0122959 -.0100898 .0395165
As you can see , range of return is [-.0100898 .0395165]. But methodology that I followed requires that first bin should start with the -.01 and last bin should end with 0.035, and width of each bin should be 0.001. Consequently there should be (0.035 – (-0.01)) / 0.001 = 45 bins. And the values less than -0.01 and more than .035 should be counted as tails. In other words what I want is to have:
Lower tail : less than -.01
Bin-1: between -0.01 and -0.009
Bin-2: between -0.009 and -0.008
Bin-3: between -0.008 and -0.007
…
Bin-45: between 0.034 and 0.035
Upper tail: more than 0.035
There is a start option for twoway__gen_histogram command (and for histogram command as well) But I think these are not what I am looking for, because here https://www.stata.com/manuals13/rhistogram.pdf it is said start(#), if specified, must be less than or equal to m (minimum value of the variable), or else an error will be issued.
Do you have any suggestions? I think that there is an easy way to do it but I cannot figure it out. I appreciate any help or opinion.
Thank you in advance.
Best
Merve
For my Project, I need the histogram of the intraday returns for each day and save the densities.
As far as I search, I am able to save the density with twoway__gen_histogram command.
However, I also need to assign the minimum and maximum numbers to the bins by myself.
I am not allowed the share the original data but let’s say I am working with the following fake data:
Code:
* Example generated by -dataex-. To install: ssc install dataex clear input float(DATE_stata DAY MONTH YEAR TIME_stata HOUR MINUTE SECOND return) 21306 2 5 2018 3.57e+07 9 55 0 .004712995 21306 2 5 2018 3.60e+07 10 0 0 .03359007 21306 2 5 2018 3.63e+07 10 5 0 .0395165 21306 2 5 2018 3.66e+07 10 10 0 .021177117 21306 2 5 2018 3.69e+07 10 15 0 .02277919 21306 2 5 2018 3.72e+07 10 20 0 .033864293 21306 2 5 2018 3.75e+07 10 25 0 .020484 21306 2 5 2018 3.78e+07 10 30 0 .018225307 21306 2 5 2018 3.81e+07 10 35 0 .01916204 21306 2 5 2018 3.84e+07 10 40 0 .035961933 21306 2 5 2018 3.87e+07 10 45 0 .02108501 21306 2 5 2018 3.90e+07 10 50 0 .029303394 21306 2 5 2018 3.93e+07 10 55 0 .005171665 21306 2 5 2018 3.96e+07 11 0 0 .002619719 21306 2 5 2018 3.99e+07 11 5 0 .003468564 21306 2 5 2018 4.02e+07 11 10 0 .02528198 21306 2 5 2018 4.05e+07 11 15 0 .03248618 21306 2 5 2018 4.08e+07 11 20 0 .02698752 21306 2 5 2018 4.11e+07 11 25 0 .0193095 21306 2 5 2018 4.14e+07 11 30 0 .01664686 21306 2 5 2018 4.17e+07 11 35 0 .00985556 21306 2 5 2018 4.20e+07 11 40 0 .031419493 21306 2 5 2018 4.23e+07 11 45 0 .008919027 21306 2 5 2018 4.26e+07 11 50 0 -.0100898 21306 2 5 2018 4.29e+07 11 55 0 .03562382 21306 2 5 2018 4.32e+07 12 0 0 .01907039 21306 2 5 2018 4.35e+07 12 5 0 .03053173 21306 2 5 2018 4.38e+07 12 10 0 .02947596 21306 2 5 2018 4.41e+07 12 15 0 .003836877 21306 2 5 2018 4.44e+07 12 20 0 .032339774 21306 2 5 2018 4.47e+07 12 25 0 .022225296 21306 2 5 2018 4.50e+07 12 30 0 .03634135 21306 2 5 2018 4.53e+07 12 35 0 .005161573 21306 2 5 2018 4.56e+07 12 40 0 .036354125 21306 2 5 2018 4.59e+07 12 45 0 .007547986 21306 2 5 2018 4.62e+07 12 50 0 .03292318 21306 2 5 2018 4.65e+07 12 55 0 .03106813 21306 2 5 2018 4.68e+07 13 0 0 .020866474 21306 2 5 2018 4.71e+07 13 5 0 .001889656 21306 2 5 2018 4.74e+07 13 10 0 .03760757 21306 2 5 2018 4.77e+07 13 15 0 .032291573 21306 2 5 2018 4.80e+07 13 20 0 .03772156 21306 2 5 2018 4.83e+07 13 25 0 .017582364 21306 2 5 2018 4.86e+07 13 30 0 .03873967 21306 2 5 2018 4.89e+07 13 35 0 .01911121 21306 2 5 2018 4.92e+07 13 40 0 .03079806 21306 2 5 2018 4.95e+07 13 45 0 .031644672 21306 2 5 2018 4.98e+07 13 50 0 .02339589 21306 2 5 2018 5.01e+07 13 55 0 . 21306 2 5 2018 5.04e+07 14 0 0 . end format %tdDD/NN/CCYY DATE_stata format %tc TIME_stata
Code:
sum return
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
return | 48 .0226268 .0122959 -.0100898 .0395165
As you can see , range of return is [-.0100898 .0395165]. But methodology that I followed requires that first bin should start with the -.01 and last bin should end with 0.035, and width of each bin should be 0.001. Consequently there should be (0.035 – (-0.01)) / 0.001 = 45 bins. And the values less than -0.01 and more than .035 should be counted as tails. In other words what I want is to have:
Lower tail : less than -.01
Bin-1: between -0.01 and -0.009
Bin-2: between -0.009 and -0.008
Bin-3: between -0.008 and -0.007
…
Bin-45: between 0.034 and 0.035
Upper tail: more than 0.035
There is a start option for twoway__gen_histogram command (and for histogram command as well) But I think these are not what I am looking for, because here https://www.stata.com/manuals13/rhistogram.pdf it is said start(#), if specified, must be less than or equal to m (minimum value of the variable), or else an error will be issued.
Do you have any suggestions? I think that there is an easy way to do it but I cannot figure it out. I appreciate any help or opinion.
Thank you in advance.
Best
Merve
Comment