Stat 518 - Fall 2000 - S-Plus Templates

Class Notes from 9/13/00
Copy, Paste, or Print

The Basics of S-plus:

Unlike SAS where you have to hit a key to run the program, S-Plus runs what you tell it to immediately. It is therefore important to keep a copy of the code you will be running in some other file, in general some word processor when using a PC.

Another difference between S-Plus and SAS is that S-Plus is run from the various Sun Sparcs in the department of mathematics and statistics. To use them from a PC you must thus remote login using the program X-Win32. When you start up X-Win32, nothing at first will happen except for the bar appearing at the bottom of the screen. Selecting one of the sessions there will call up an X-window into which you need to answer the prompt for your login name and password. These will generally NOT be the same as the login and password for the PC.

At the heart of S-Plus are the various objects that you enter. At any time (when you are in S-Plus) you can type in the function objects() to see which ones you have entered previously. Presumably there aren't any there right now. Splus also has many built in objects, most of which are functions. It saves these objects permanently (until you erase them). For this to work though, you need to create a .Data directory in UNIX. This can be done (before starting S-Plus), by typing:

mkdir .Data

Once we have done that, we can now start S-Plus. Simply type Splus at the unix prompt. You can now type objects() to see if anything is already there or not. One of the simplest types of objects to enter is simply a vector. Try typing:

x<-c(5,4,3,2)

The <- is the command that assigns what ever is on the left to the name that is on the right. The c indicates that an array or vector is going to be entered. Simply typing x now will return those four values. Typing x[3] will return the third value, mean(x) will return the mean, and objects() will show you that you now have an object called x.

Say we wished to enter the data set we used last time into S-Plus. We would use the line: 


satdata<-scan("",what=list(state="",verbal=0,math=0,pct=0))
S-Plus then comes back with a prompt to enter the data. We can now just cut and paste the block into it. Because UNIX tends to be unhappy if you try to cut and paste a whole bunch at one time, it is probably better to do it in to chunks. Paste the first chunk in by clicking with both mouse buttons, make sure there is a prompt showing, and then paste the second half in and hit return until it gets out of scan mode. Now, typing satdata will show you that the data set is in there.

The SAT data presented in the August 31st, 1999 New York Times: 


        Ala.    561  555    9

        Alaska  516  514   50

        Ariz.   524  525   34

        Ark.    563  556    6

        Calif.  497  514   49

        Colo.   536  540   32

        Conn.   510  509   80

        Dela.   503  497   67

        D.C.    494  478   77

        Fla.    499  498   53

        Ga.     487  482   63

        Hawaii  482  513   52

        Idaho   542  540   16

        Ill.    569  585   12

        Ind.    496  498   60

        Iowa    594  598    5

        Kan.    578  576    9

        Ky.     547  547   12

        La.     561  558    8

        Maine   507  507   68

        Md.     507  511   65

        Mass.   511  511   78

        Mich.   557  565   11

        Minn.   586  598    9

        Miss.   563  548    4

        Mo.     572  572    8

        Mont.   545  546   21

        Neb.    568  571    8

        Nev.    512  517   34

        N.H.    520  518   72

        N.J.    498  510   80

        N.M.    549  542   12

        N.Y.    495  502   76

        N.C.    493  493   61

        N.D.    594  605    5

        Ohio    534  538   25

        Okla.   576  560    8

        Ore.    525  525   53

        Pa.     498  495   70

        R.I.    504  499   70

        S.C.    479  475   61

        S.D.    585  588    4

        Tenn.   559  553   13

        Texas   494  499   50

        Utah    570  565    5

        Vt.     514  506   70

        Va.     508  499   65

        Wash.   525  526   52

        W.Va.   527  512   18

        Wis.    584  595    7

        Wyo.    546  551   10

We have now made a "data-frame" where each of the four columns goes with a different variable. We can refer to the four columns by using satdata$state, satdata$verbal, satdata$math, or satdata$pct. The following code will give us many of the results we got looking at this data set in SAS. But first we'll begin by giving all of the variables shorter names. 


v<-satdata$verbal

m<-satdata$math

p<-satdata$pct



summary(p) 



hist(p)



qqnorm(p)

qqline(p)
Unfortunately S-Plus removed the interactive help menus, but you can still find out more about changing the histogram for example by typing help(hist). The code below performs a linear regression to predict v from m. It is often best to put the regression output into an object though instead of simply running it.



vmregress<-lm(v~m)



vmregress



attributes(vmregress)



vmregress$residuals



qqnorm(vmregress$residuals)

qqline(vmregress$residuals)
Finally, this is the code that would be used for making the confidence interval for the variance of the verbal scores. 

alpha<-.05

df<-length(v)-1

clow <- df*var(v)/qchisq(1-alpha/2,df)

chi <- df*var(v)/qchisq(alpha/2,df)

c(clow,chi)

Notes on Copying, Pasting, and Printing Graphics:

In general, you will want to type your programs in MS Word or notepad, and then copy and paste them into the X-window. To copy from the X-window, simply highlight the text you want with the left mouse button. To paste into the X-window, simply hit both mouse buttons simultaneously.

To print a graphic, you need to set it to the right printer. Otherwise the default is the printer that the SUN machine is actually in. (Probably 310 LeConte.) To print to the printer LEX-3 in 303A, you would need to go to the "Options" menu, and choose "Printing..." In the command box, make it say lp -dlex3  Now simply click the "Print" button, and note that it should say at the bottom of the graphic window that it has printed. Simply hit close to make that window go away. Note that you can't view or print the graphics if you are using telnet instead of X-windows.