Re: [R] simulation study using R

From: Paul Gilbert <pgilbert_at_bank-banque-canada.ca>
Date: Wed, 05 Mar 2008 10:44:16 -0500

Davood Tofighi wrote:
> Thanks for your reply. For each condition, I will have a matrix or data
> frames of 1000 rows and 4 columns. I also have a total of 64 conditions for
> now. So, in total, I will have 64 matrices or data frames of 1000 rows and 4
> columns. The format of data I would like to store would be data frames or
> matrices. I also would like to store the data for later use,
I generally find it is better to store the seed and other data you need to reproduce the experiment, rather than trying to store the data (see, for example, package setRNG). If you save only the summary statistics you need, then you can usually do it in memory. (Be sure to assign variables for the statistics to their full size first and then populate them, rather than extending them at each step.) If you write things to files then it will slow down your simulation a lot. In fact, in most cases it will be quicker to re-run the experiment than it will be to read the data from disk.

Paul
> e.g., a plot of
> the empirical distribution of the chi^2, or to compute the power of Chi^2
> across 1000 reps for each condition.
>
> On Mon, Mar 3, 2008 at 7:03 PM, jim holtman <jholtman_at_gmail.com> wrote:
>
>
>> What is the format of the data you are storing (single value,
>> multivalued vector, matrix, dataframe, ...)? This will help formulate
>> a solution. What do you plan to do with the data? Are you going to
>> do further analysis, write it to flat files, store it in a data base,
>> etc.? How big are the data objects you are manipulating?
>>
>> On Mon, Mar 3, 2008 at 7:05 PM, Davood Tofighi <dtofighi_at_asu.edu> wrote:
>>
>>> Dear All,
>>>
>>> I am running a Monte Carlo simulation study and have some questions on
>>>
>> how
>>
>>> to manage data storage efficiently at the end of each 1000 replication
>>>
>> loop.
>>
>>> I have three conditions coded using the FOR {} loops and a FOR loop that
>>> generates data for each condition, performs analysis, and computes a
>>> statistic 1000 times. Therefore, for each condition, I will have 1000
>>> statistic values. My question is what's the best way to store the 1000
>>> statistic for each condition. Any suggestion on how to manage such
>>> simulation studies is greatly appreciated.
>>> Thanks,
>>>
>>> --
>>> Davood Tofighi
>>> Department of Psychology
>>> Arizona State University
>>>
>>> [[alternative HTML version deleted]]
>>>
>>> ______________________________________________
>>> R-help_at_r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide
>>>
>> http://www.R-project.org/posting-guide.html
>>
>>> and provide commented, minimal, self-contained, reproducible code.
>>>
>>>
>>
>> --
>> Jim Holtman
>> Cincinnati, OH
>> +1 513 646 9390
>>
>> What is the problem you are trying to solve?
>>
>>
>
>
>
>


La version franšaise suit le texte anglais.


This email may contain privileged and/or confidential in...{{dropped:26}}



R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Wed 05 Mar 2008 - 15:51:30 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Wed 05 Mar 2008 - 19:30:37 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive