# [R] Conditional Statistics

Simon Blomberg s.blomberg1 at uq.edu.au
Tue Jan 8 05:30:30 CET 2013

```You can use the tapply function to do this. You can't type a line into
the mean statement. (See ?mean for what you can type in there). The
general approach is to have a vector of data (stock prices) and a
categorical variable (day of week). Then break up the data vector
according to the levels in the categorical variable, and calculate the
mean values:

Weekmeans <- tapply(data.vector, catvariable, mean)

This will give you the means for all days. If you really just want one
mean (just monday), you could do:

Monmean <- mean(data.vector[catvariable=="Monday"])

Similarly, if you want the standard deviation for each day of the week,
you would use:

WeekSD <- tapply(data.vector, catvariable, sd)
MonSD <- sd(data.vector[catvariable=="Monday"])

You will find that some things that are easy in SAS require a little
more thought in R, and vice versa. Certainly, the philosophical approach
to data analysis in R is different to that in SAS. There are a couple of

Cheers,

Simon.

On 08/01/13 11:17, Joseph Norman Thomson wrote:
> Hello,
>
> I am a new user of R. I am coming from SAS and do statistics on stock
> market data, economic data, and social data. My question is this: How
> can you get the mean, standard dev, etc. of a variable based on a
> conditional statement on either the same variable or a different
> variable in the same data set? So if I had the closing prices of the
> S&P from 01/01/1990-12/31/1990, how could I get the average price of
> the S&P from 02/01/1990-03/15/1990? Or the average price of the S&P on
> Mondays (assuming a dummy var is created for 1 = Monday, 0 = else). I
> understand that you can create subsets and new data sets based on the
> conditional statements; but is there an easier way to do this by
> typing a line into the mean() statement? That was extremely easy in
> SAS where you could say:
>
> proc means data=sp500;
> var price;
> where monday = 1;
>
> Thank you for your help.
>
> Joe
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> and provide commented, minimal, self-contained, reproducible code.

--
Simon Blomberg, BSc (Hons), PhD, MAppStat, AStat.
Lecturer and Consultant Statistician
School of Biological Sciences
The University of Queensland
St. Lucia Queensland 4072
Australia
T: +61 7 3365 2506
email: S.Blomberg1_at_uq.edu.au
http://www.evolutionarystatistics.org

Policies:
1.  I will NOT analyse your data for you.