Hi!
Suppose I have a dataset as follows
pd = c(10,7,10,11,7,11,7,6,8,3,12,7,7,10,10)
I wish to calculate the mean, standard deviation, median, skewness and kurtosis
i.e. regular standard statistical measures.
average = mean(pd)
stdev = sd(pd)
median = median(pd)
skew = skewness(pd)
kurt = kurtosis(pd)
Q. No (1)
How do I get these at a stretch using some R package? I came across moments and
e1071 package, but I am not sure which one to use and how?
Q. No. (2)
Many times I came across the command
set.seed(1234)
What is the significance of this command. I understand this is related to random
number generation. But what does it do?
Thanking in advance
Amelia
[[alternative HTML version deleted]]
On 12/23/2009 10:24 PM, Amelia Livington wrote:> Hi! > > Suppose I have a dataset as follows > > pd = c(10,7,10,11,7,11,7,6,8,3,12,7,7,10,10) > > I wish to calculate the mean, standard deviation, median, skewness and kurtosis i.e. regular standard statistical measures. > > average = mean(pd) > stdev = sd(pd) > median = median(pd) > skew = skewness(pd) > kurt = kurtosis(pd) > > Q. No (1) > > How do I get these at a stretch using some R package? I came across moments and e1071 package, but I am not sure which one to use and how? > > Q. No. (2) > Many times I came across the command > > set.seed(1234) > > What is the significance of this command. I understand this is related to random number generation. But what does it do? > >Hi Amelia, For 1) library(prettyR) library(timeDate) describe(pd, num.desc=c("mean","sd","median","kurtosis","skewness")) although there are many other ways to do this. for 2) set.seed() starts the random number generator at a particular place, allowing you to generate the same set of "random" numbers repeatedly. This can be useful for things like examples for which the particular set of numbers should be repeated when anyone runs the example. Jim
An answer to your second question:
Random number generated by your computer are not truly random, they are pseduo
random meaning that if your computer is it the exact same state at two
movements, it will produce the same string of "random" numbers.
Set.seed effectively puts your machine in a given state - it primes the pseudo
random number generator. If you set the seed before requesting a set of random
numbers, you will always get the same set of numbers. If you don't use
set.seed, the machine primes the generator using some other source, which may be
the system clock. Thus, if you don't use set.seed, it would be very, very,
unlikely that you would get the same string of random numbers.
John
John David Sorkin M.D., Ph.D.
Chief, Biostatistics and Informatics
University of Maryland School of Medicine Division of Gerontology
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)>>>
Amelia Livington <amelia_livington at yahoo.com> 12/23/2009 6:24 AM
>>>
Hi!
Suppose I have a dataset as follows
pd = c(10,7,10,11,7,11,7,6,8,3,12,7,7,10,10)
I wish to calculate the mean, standard deviation, median, skewness and kurtosis
i.e. regular standard statistical measures.
average = mean(pd)
stdev = sd(pd)
median = median(pd)
skew = skewness(pd)
kurt = kurtosis(pd)
Q. No (1)
How do I get these at a stretch using some R package? I came across moments and
e1071 package, but I am not sure which one to use and how?
Q. No. (2)
Many times I came across the command
set.seed(1234)
What is the significance of this command. I understand this is related to random
number generation. But what does it do?
Thanking in advance
Amelia
[[alternative HTML version deleted]]
Confidentiality Statement:
This email message, including any attachments, is for th...{{dropped:6}}