Another approach (still using the theory of sufficient statistics) is to generate data from a normal distribution that matches exactly the sizes, means, and standard deviations that you have, then analyze the simulated data.
The mvrnorm function in the MASS package can generate data with a given mean and standard deviation. If you don't want to use that, tools like rnorm, apply, sweep, scale, and ave can also be used to create data with the given means and sds. -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare [email protected] 801.408.8111 > -----Original Message----- > From: [email protected] [mailto:r-help-bounces@r- > project.org] On Behalf Of Rao, Niny > Sent: Monday, February 07, 2011 7:18 PM > To: David Winsemius > Cc: [email protected] > Subject: Re: [R] Perform one-way ANOVA using standard deviation and > mean > > > > On Monday2/7/11 9:09 PM, "David Winsemius" <[email protected]> > wrote: > > > > >On Feb 7, 2011, at 8:15 PM, Rao, Niny wrote: > > > >> Hi! I need to perform ANOVA on a couple of data sets. The only > >> information I have are N, Mean and Standard deviation. I am very new > >> to R, so can someone point me to the right direction on where to go? > > > >Here are my data > > ID Mean SD Coef of Var > 62L 121.60 6.21 5.10 > 94D 115.92 3.22 2.78 > 14F 86.51 3.17 3.66 > 11P 126.71 5.45 4.30 > 10L 116.67 2.17 1.86 > 96T 98.20 1.38 1.41 > 55U 125.93 3.69 2.93 > 79X 93.73 5.86 6.25 > 55L 84.24 2.52 2.99 > 59Q 128.72 0.74 0.58 > 56S 121.12 1.07 0.89 > > > > Sincerely > Niny Rao, PhD > Philadelphia University > > ______________________________________________ > [email protected] 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. ______________________________________________ [email protected] 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.
