Getting Started With the R Commander

John Fox Version 1.9-0 (27 August 2012)

Starting the R Commander

This document directly describes the use of the R Commander under the Windows version of R. There are small dierences in the appearance and use of the R Commander under Mac OS X and on Linux and Unix systems. Information about installing the R Commander on these platforms is available by following the link to the installation notes at the R Commander web page http://socserv.socsci.mcmaster.ca/ jfox/Misc/Rcmdr/index.html, or directly at tinyurl.com/Rcmdr. Once R is running, simply loading the Rcmdr package by typing the command library(Rcmdr) into the R Console starts the R Commander graphical user interface (GUI). To function optimally under Windows, the R Commander requires the single-document interface (SDI) to R.1 After loading the package, R Console and R Commander windows should appear more or less as in Figures 1 and 2. These and other screen images in this document were created under Windows Vista; if you use another version of Windows (or, of course, another computing platform), then the appearance of the screen may dier.2 The R Commander and R Console windows oat freely on the desktop. You will normally use the menus and dialog boxes of the R Commander to read, manipulate, and analyze data. R commands generated by the R Commander GUI appear in the upper text window (labelled Script Window ) within the main R Commander window. You can also type R commands directly into the script window or at the (greater-than) prompt in the R Console ; the main purpose of the R Commander, however, is to avoid having to type commands. Printed output appears by default in the second text window (labelled Output Window ). The lower, gray window (labelled Messages ) displays error messages, warnings, and some other information (notes), such as the start-up message in Figure 2. When you create graphs, these will appear in a separate Graphics Device window.
manual is adapted and updated from Fox (2005). Please address correspondence to [email protected]. Windows version of R is normally run from a multiple-document interface (MDI), which contains the R Console window, Graphical Device windows created during the session, and any other windows related to the R process. In contrast, under the single-document interface (SDI), the R Console and Graphical Device windows are not contained within a master window. There are several ways to run R in SDI mode for example, by selecting the SDI when R is installed, by editing the Rconsole le in R s etc subdirectory, or by adding --sdi to the Target eld in the Shortcut tab of the R desktop icons Properties. This limitation of the Rcmdr package is inherited from the tcltk package, on which Rcmdr depends. 2 Notice that Rcmdr requires some packages in addition to several of the recommended packages that are normally distributed with R . Rcmdr, the required packages, and many other contributed packages are available for download from the Comprehensive R Archive Network (CRAN) at http://cran.r-project.org/. If these packages are not installed, the Rcmdr will oer to install them from the Internet or from local les (e.g., on a CD/ROM). If you install the Rcmdr package via the Windows R GUI, not all of the packages on which the Rcmdr depends will be installed. You can install the Rcmdr package and all of the packages on which it depends via the install.packages function, setting the argument dependencies = TRUE. Thanks to Dirk Eddelbuettel, Debian Linux users need only issue the command $ apt-get install r-cran-rcmdr to install the Rcmdr package along with all of the packages that it requires. In any event, building and installing the Rcmdr package on Linux systems is typically straightforward. The task can be more formidible under Mac OS X , since the tcltk package on which the Rcmdr depends requires that Tcl/Tk be installed and that R is running under X-Windows.
1 The This

Figure 1: The R Console window after loading the Rcmdr package.

Figure 2: The R Commander window at start-up.

There are several menus along the top of the R Commander window: File Menu items for loading and saving script les; for saving output and the R workspace; and for exiting. Edit Menu items (Cut, Copy, Paste, etc.) for editing the contents of the script and output windows. Right clicking in the script or output window also brings up an edit context menu. Data Submenus containing menu items for reading and manipulating data. Statistics Submenus containing menu items for a variety of basic statistical analyses. Graphs Menu items for creating simple statistical graphs. Models Menu items and submenus for obtaining numerical summaries, condence intervals, hypothesis tests, diagnostics, and graphs for a statistical model, and for adding diagnostic quantities, such as residuals, to the data set. Distributions Cumulative probabilities, probability densities or masses, quantiles, and graphs of standard statistical distributions (to be used, for example, as a substitute for statistical tables) and samples from these distributions. Tools Menu items for loading R packages unrelated to the Rcmdr package (e.g., to access data saved in another package), for loading Rcmdr plug-in packages (see Fox, 2007, and Fox and Carvalho, 2012), and for setting some options. Help Menu items to obtain information about the R Commander (including this manual). As well, each R Commander dialog box has a Help button (see below).

The complete menu tree for the R Commander (version 1.9-0) is shown below. Most menu items lead to dialog boxes, as illustrated later in this manual. Menu items are inactive (grayed out) if they are inapplicable to the current context. File ||||||||Edit ||||||||Data |||| | | | | | || || | | | | | | | | | | |Change working directory Open script file Save script Save script as Save output Save output as Save R workspace Save R workspace as Exit - from Commander |- from Commander and R Cut Copy Paste Delete Find Select all Undo Redo Clear Window New data set Load data set Merge data sets Import data - from text file, clipboard, or URL |- from SPSS data set |- from SAS xport file |- from Minitab data set |- from STATA data set |- from Excel, Access, or dBase data set [32-bit Windows only] |- from Excel file [currently 64-bit Windows only] Data in packages - List data sets in packages |- Read data set from attached package Active data set - Select active data set |- Refresh active data set |- Help on active data set (if available) |- Variables in active data set |- Set case names |- Subset active data set |- Aggregate variables in active data set |- Remove row(s) from active data set |- Stack variables in active data set |- Remove cases with missing data |- Save active data set |- Export active data set Manage variables in active data set - Recode variable |- Compute new variable |- Add observation numbers to data set |- Standardize variables |- Convert numeric variables to factors |- Bin numeric variable |- Reorder factor levels |- Define contrasts for a factor 5

|- Rename variables |- Delete variables from data set Statistics | | | | | | | || | || | | | || || | || | | || | | | | | | |Active data set Numerical summaries Frequency distributions Count missing observations Table of statistics Correlation matrix Correlation test Shapiro-Wilk test of normality Tables - Two-way table |- Multi-way table |- Enter and analyze two-way table Means - Single-sample t-test |- Independent-samples t-test |- Paired t-test |- One-way ANOVA |- Multi-way ANOVA Proportions - Single-sample proportion test |- Two-sample proportions test Variances - Two-variances F-test |- Bartletts test |- Levenes test Nonparametric tests - Two-sample Wilcoxon test |- Paired-samples Wilcoxon test |- Kruskal-Wallis test |- Friedman rank-sum test Dimensional analysis - Scale reliability |- Principal-components analysis |- Factor analysis |- Confirmatory factor analysis |- Cluster analysis - k-means cluster analysis |- Hierarchical cluster analysis |- Summarize hierarchical clustering |- Add hierarchical clustering to data set Fit models - Linear regression |- Linear model |- Generalized linear model |- Multinomial logit model |- Ordinal regression model Color palette Index plot Histogram Stem-and-leaf display Boxplot Quantile-comparison plot Scatterplot Scatterplot matrix Line graph XY conditioning plot Plot of means Strip chart Bar graph Pie chart 6 Summaries |||||||Contingency

Graphs |||||||||||||-

3D scatterplot Identify observations with mouse Save graph to file to file - as bitmap |- as PDF/Postscript/EPS |- 3D RGL graph Models - Select active model |- Summarize model |- Add observation statistics to data |- Confidence intervals |- Akaike Information Criterion (AIC) |- Bayesian Information Criterion (BIC) |- Stepwise model selection |- Subset model selection |- Hypothesis tests - ANOVA table | |- Compare two models | |- Linear hypothesis |- Numerical diagnostics - Variance-inflation factors | |- Breusch-Pagan test for heteroscedasticity | |- Durbin-Watson test for autocorrelation | |- RESET test for nonlinearity | |- Bonferroni outlier test |- Graphs - Basic diagnostic plots |- Residual quantile-comparison plot |- Component+residual plots |- Added-variable plots |- Influence plot |- Effect plots Distributions - Continuous distributions - Normal distribution - Normal quantiles | | |- Normal probabilities | | |- Plot normal distribution | | |- Sample from normal distribution | |- t distribution - t quantiles | | |- t probabilities | | |- Plot t distribution | | |- Sample from t distribution | |- Chi-squared distribution - Chi-squared quantiles | | |- Chi-squared probabilities | | |- Plot chi-squared distribution | | |- Sample from chi-squared distribution | |- F distribution - F quantiles | | |- F probabilities | | |- Plot F distribution | | |- Sample from F distribution | |- Exponential distribution - Exponential quantiles | | |- Exponential probabilities | | |- Plot exponential distribution | | |- Sample from exponential distribution | |- Uniform distribution - Uniform quantiles | | |- Uniform probabilities | | |- Plot uniform distribution | | |- Sample from uniform distribution | |- Beta distribution - Beta quantiles | | |- Beta probabilities 7

|- 3D graph | || ||- Save graph

| | |- Plot beta distribution | | |- Sample from beta distribution | |- Cauchy distribution - Cauchy quantiles | | |- Cauchy probabilities | | |- Plot Cauchy distribution | | |- Sample from Cauchy distribution | |- Logistic distribution - Logistic quantiles | | |- Logistic probabilities | | |- Plot logistic distribution | | |- Sample from logistic distribution | |- Lognormal distribution - Lognormal quantiles | | |- Lognormal probabilities | | |- Plot lognormal distribution | | |- Sample from lognormal distribution | |- Gamma distribution - Gamma quantiles | | |- Gamma probabilities | | |- Plot gamma distribution | | |- Sample from gamma distribution | |- Weibull distribution - Weibull quantiles | | |- Weibull probabilities | | |- Sample from Weibull distribution | |- Gumbel distribution - Gumbel quantiles | |- Gumbel probabilities | |- Plot Gumbel distribution | |- Sample from Gumbel distribution |- Discrete distributions - Binomial distribution - Binomial quantiles | |- Binomial tail probabilities | |- Binomial probabilities | |- Plot binomial distribution | |- Sample from binomial distribution |- Poisson distribution - Poisson quantiles | |- Poisson tail probabilities | |- Poisson probabilities | |- Plot Poisson distribution | |- Sample from Poisson distribution |- Geometric distribution - Geometric quantiles | |- Geometric tail probabilities | |- Geometric probabilities | |- Plot geometric distribution | |- Sample from geometric distribution |- Hypergeometric distribution - Hypergeometric quantiles | |- Hypergeometric tail probabilities | |- Hypergeometric probabilities | |- Plot hypergeometric distribution | |- Sample from hypergeometric distribution |- Negative binomial distribution - Negative binomial quantiles |- Negative binomial tail probabilities |- Negative binomial probabilities |- Plot negative binomial distribution |- Sample from negative binomial distribution Tools - Load package(s) |- Load Rcmdr plug-in(s) |- Options Help - Commander help 8

||||-

Introduction to the R Commander Help on active data set (if available) About Rcmdr Start R help system

The R Commander interface includes a few elements in addition to the menus and dialogs: Below the menus is a toolbar with a row of buttons. The left-most (at) button shows the name of the active data set. Initially there is no active data set. If you press this button, you will be able to choose among data sets currently in memory (if there is more than one). Most of the menus and dialogs in the R Commander reference the active data set. (The File, Edit, and Distributions menus are exceptions.) Two buttons allow you to open the R data editor to modify the active data set or a viewer to examine it. The data-set viewer can remain open while other operations are performed.3 A at button indicates the name of the active statistical model a linear model (such as a linearregression model), a generalized linear model, a multinomial logit model, or an ordinal regression model.4 Initially there is no active model. If there is more than one model in memory, you can choose among them by pressing the button. Immediately below the toolbar is the script window (so labelled), a large scrollable text window. As mentioned, commands generated by the GUI are copied into this window. You can edit the text in the script window or even type your own R commands into the window. Pressing the Submit button, which is at the right below the script window (or, alternatively, the key combination Ctrl-r, for run, or Ctrl-Tab ), causes the line containing the cursor to be submitted (or resubmitted) for execution. If several lines are selected (e.g., by left-clicking and dragging the mouse over them), then pressing Submit will cause all of them to be executed. Commands entered into the script window can extend over more than one line, but all lines must be submitted simultaneously. The key combination Ctrl-a selects all of the text in the script window, and Ctrl-s brings up a dialog box to save the contents of the window. Below the script window is a large scrollable and editable text window for output. Commands echoed to this window appear in red, output in dark blue (as in the R Console ). At the bottom is a small gray text window for messages. Error messages are displayed in red text, warnings in green, and other messages in dark blue. Errors and warnings also provide an audible cue by ringing a bell. Once you have loaded the Rcmdr package, you can minimize the R Console. The R Commander window can also be resized or maximized in the normal manner. If you resize the R Commander, the width of subsequent R output is automatically adjusted to t the output window. The R Commander is highly congurable: I have described the default conguration here. Changes to the conguration can be made via the Tools Options. . . menu, or much more extensively by setting options in R.5 See the Rcmdr help les for details.

3 The data viewer, provided by the showData function from David Firths relimp package, can be slow for data sets with large numbers of variables. When the number of variables exceeds a threshold (initially set to 100), the less aesthetically pleasing R View command is used instead to display the data set. To use View regardless of the number of variables, set the threshold to 0. See the R Commander help le for details. 4 R Commander plug-in packages (Fox, 2007; Fox and Carvalho, 2012) may provide additional classes of models. 5 A menu item that terminates in ellipses (i.e., three dots, ...) leads to a dialog box; this is a standard GUI convention. In this document, represents selecting a menu item or submenu from a menu.

10

Data Input

Most of the procedures in the R Commander assume that there is an active data set.6 If there are several data sets in memory, you can choose among them, but only one is active. When the R Commander starts up, there is no active data set. The R Commander provides several ways to get data into R:7 On platforms other than Mac OS X, you can enter data directly via Data New data set.... This is a reasonable choice for a very small data set. You can import data from a plain-text (ascii) le or the clipboard, over the Internet from a URL, from another statistical package (Minitab, SPSS, SAS, or Stata), or (under Windows) from an Excel, Access, or dBase data set. You can read a data set that is included in an R package, either typing the name of the data set (if you know it), or selecting the data set in a dialog box.

2.1

Reading Data From a Text File

For example, consider the data le Nations.txt.8 The rst few lines of the le are as follows: TFR contraception Afghanistan Albania Algeria American-Samoa Andorra Angola Antigua Argentina Armenia Australia . . . Asia Europe Africa Oceania Europe Africa Americas Americas Europe Oceania

The rst line of the le contains variable names: TFR (the total fertility rate, expressed as number of children per woman), contraception (the rate of contraceptive use among married women, in percent), infant.mortality (the infant-mortality rate per 1000 live births), GDP (gross domestic product per capita, in U.S. dollars), and region. Subsequent lines contain the data values themselves, one line per country. The data values are separated by white space one or more blanks or tabs. Although it is helpful to make the data values line up vertically, it is not necessary to do so. Notice that the data lines begin with the country names. Because we want these to be the row names for the data set, there is no corresponding variable name: That is, there are ve variable names but six data values on each line. When this happens, R will interpret the rst value on each line as the row name. Some of the data values are missing. In R, it is most convenient to use NA (representing not available) to encode missing data, as I have done here. The variables TFR, contraception, infant.mortality, and GDP are numeric (quantitative) variables; in contrast, region contains region names. When the data are read, R will treat region as a factor that is, as a categorical variable. In most contexts, the R Commander distinguishes between numerical variables and factors.
6 Procedures selected under via the Distributions menu are exceptions, as is Enter and analyze two-way table... under the Statistics Contingency tables menu. 7 Not all of these data sources may be available on all platforms. 8 This le resides in the etc subdirectory of the Rcmdr package.

11

To read the data le into R, select Data Import data from text le, clipboard, or URL... from the R Commander menus. This operation brings up a Read Text Data dialog, as shown in Figure 3. The default name of the data set is Dataset. I have changed the name to Nations. Valid R names begin with an upper- or lower-case letter (or a period, .) and consist entirely of letters, periods, underscores (_), and numerals (i.e., 09); in particular, do not include any embedded blanks in a data-set name. You should also know that R is case-sensitive, and so, for example, nations, Nations, and NATIONS are distinguished, and could be used to represent dierent data sets. Clicking the OK button in the Read Text Data dialog brings up an Open le dialog, shown in Figure 4. Here I navigated to the le Nations.txt. Clicking the Open button in the dialog will cause the data le to be read. Once the data le is read, it becomes the active data set in the R Commander. As a consequence, in Figure 5, the name of the data set appears in the data set button near the top left of the R Commander window. I clicked the View data set button to bring up the data viewer window, also shown in Figure 5. Notice that the commands to read and view the Nations data set (the R read.table and showData commands) appear, partially obscured by the display of the data set, in the script and output windows. When the data set is read and becomes the active data set, a note appears in the messages window. The R Commander also issued a library command to load the relimp package, which was used to display the data set; here, as in general, packages are loaded automatically by the R Commander as they are needed. The read.table command creates an R data frame, which is an object containing a rectangular casesby-variables data set: The rows of the data set represent cases or observations and the columns represent variables. Data sets in the R Commander are R data frames.

2.2

Entering Data Directly

To enter data directly into the R basic spreadsheet-like data editor you can proceed as follows.9 As an example, I use a very small data set from Problem 2.44 in Moore (2000): Select Data New data set... from the R Commander menus. Optionally enter a name for the data set, such as Problem2.44, in the resulting dialog box, and click the OK button. (Remember that R names cannot include intervening blanks.) This will bring up a Data Editor window with an empty data set. Enter the data from the problem into the rst two columns of the data editor. You can move from one cell to another by using the arrow keys on your keyboard, by tabbing, by pressing the Enter key, or by pointing with the mouse and left-clicking. When you are nished entering the data, the window should look like Figure 6. Next, click on the name var1 above the rst column. This will bring up a Variable editor dialog box, as in Figure 7. Type the variable name age in the box, just as I have, and click the X button at the upper-right corner of the Variable editor window, or press the Enter key, to close the window. Repeat this procedure to name the second column height. The Data Editor should now look like Figure 8. Select File Close from the Data Editor menus or click the X at the upper-right of the Data Editor window. The data set that you entered is now the active data set in the R Commander.

9 Because of limitations in the R data editor for that platform, data sets cannot be entered directly under Mac OS X , and the corresponding menu item consequently is suppressed.

12

Figure 3: Reading data from a text le.

13

Figure 4: Open-le dialog for reading a text data le.

2.3

Reading Data from a Package

Many R packages include data. Data sets in packages can be listed in a pop-up window via Data Data in packages List data sets in packages, and can be read into the R Commander via Data Data in packages Read data set from an attached package.10 The resulting dialog box is shown in Figure 9. If you know the name of a data set in a package then you can enter its name directly; otherwise double-clicking on the name of a package displays its data sets in the right list box; and double-clicking on a data set name copies the name to the data-set entry eld in the dialog.11 Pressing a letter key in the Data set scroll box will move to the next data set whose name begins with that letter. You can access additional R packages by Tools Load packages.

Creating Numerical Summaries and Graphs

Once there is an active data set, you can use the R Commander menus to produce a variety of numerical summaries and graphs. I will describe just a few basic examples here. A good GUI should be largely selfexplanatory: I hope that once you see how the R Commander works, you will have little trouble using it, assisted perhaps by the on-line help les. In the initial examples below, I assume that the active data set is the Nations data set, read from a text le in the previous section. If you typed in the ve-observation data set from Moore (2000), or read in the Prestige data set from the car package operations that were also described in the previous section then one of these is the active data set. Recall that you can change the active data set by clicking on the
1 0 Not all data in packages are data frames, and only data frames are suitable for use in the R Commander . If you try to read data that are not a data frame, an error message will appear in the messages window. 1 1 In general in the R Commander , when it is necessary to copy an item from a list box to another location in a dialog, a double-click is required.

14

Figure 5: Displaying the active data set.

15

Figure 6: Data editor after the data are entered.

Figure 7: Dialog box for changing the name of a variable in the data editor.

16

Figure 8: The Data Editor window after both variable names have been changed.

Figure 9: Reading data from an attached package in this case the Prestige data set from the car package.

17

at button with the active data sets name near the top left of the R Commander window, selecting from among a list of data sets currently resident in memory. Selecting Statistics Summaries Active data set produces the results shown in Figure 10. For each numerical variable in the data set (TFR, contraception, infant.mortality, and GDP), R reports the minimum and maximum values, the rst and third quartiles, the median, and the mean, along with the number of missing values. For the categorical variable region, we get the number of observations at each level of the factor. Had the data set included more than ten variables, the R Commander would have asked us whether we really want to proceed potentially protecting us from producing unwanted voluminous output. Similarly, selecting Statistics Summaries Numerical summaries... brings up the dialog box shown in Figure 11. Only numerical variables are shown in the variable list in this dialog; the factor region is missing, because it is not sensible to compute numerical summaries for a factor. Clicking on infant.mortality, and then clicking OK, produces the following output (in the output window):12 > numSummary(Nations[,"infant.mortality"], statistics=c("mean", "sd", "IQR", + "quantiles"), quantiles=c(0,.25,.5,.75,1)) mean sd IQR 0% 25% 50% 75% 100% n NA 43.47761 38.75604 54 2 12 30 66 169 201 6 By default, the R command that is executed prints out the mean, standard deviation (sd), and interquartile range (IQR) of the variable, along with quantiles (percentiles) corresponding to the minimum, the rst quartile, the median, the third quartile, and the maximum; n is the number of valid obserations, and NA the number of missing values. As is typical of R Commander dialogs, the Numerical Summaries dialog box in Figure 11 includes OK, Cancel, Reset, and Help buttons. The Help button leads to a help page (which appears in your web browser) either for the dialog itself or (as here) for an R function that the dialog invokes. The Reset button, which is present in most R Commander dialogs, resets the dialog to its original state; otherwise, the dialog retains selections from the previous invocation. Dialog state is also reset when the active data set changes. The Numerical Summaries dialog box also makes provision for computing summaries within groups dened by the levels of a factor. Clicking on the Summarize by groups... button brings up the Groups dialog, as shown in Figure 12. Because there is only one factor in the Nations data set, only the variable region appears in the variable list, and it is pre-selected; clicking OK changes the Summarize by groups... button to Summarize by region (see Figure 13); clicking OK again produces the following results: > numSummary(Nations[,c("GDP", "infant.mortality")], groups=Nations$region, + statistics=c("mean", "sd", "IQR", "quantiles"), quantiles=c(0,.25,.5,.75,1)) Variable: GDP mean sd IQR 0% 25% 50% 75% 100% Africa 1196.000 2089.614 795.50 36 209.00 389.5 1004.50 11854 Americas 5398.000 6083.311 5268.50 386 1749.25 2765.5 7017.75 26037 Asia 4505.051 6277.738 6062.50 122 345.00 1079.0 6407.50 22898 Europe 13698.909 13165.412 24582.25 271 1643.75 9222.5 26226.00 42416 Oceania 8732.600 11328.708 16409.25 654 1102.75 2348.5 17512.00 41718 Variable: infant.mortality mean sd Africa 85.27273 35.188095 Americas 25.60000 17.439713 Asia 45.65854 32.980001 Europe 11.85366 7.122363 Oceania 27.79167 29.622229 n NA 54 1 40 1 39 2 44 1 20 5

IQR 0% 25% 50% 75% 100% n NA 50.0 7 61.00 85.0 111.00 169 55 0 24.0 6 12.00 21.5 36.00 82 40 1 50.0 5 22.00 37.0 72.00 154 41 0 10.0 5 6.00 8.0 16.00 32 41 4 26.5 2 9.25 20.0 35.75 135 24 1

1 2 To select a single variable in a variable-list box, simply left-click on its name. In some contexts, you will have to (or want to) select more than one variable. In these cases, the usual Windows conventions apply: Left-clicking on a variable selects it and de-selects any variables that have previously been selected; Shift-left-click extends the selection; and Ctrl-left-click toggles the selection for an individual variable.

18

Figure 10: Getting variable summaries for the active data set.

19

Figure 11: The Numerical Summaries dialog box. Several other R Commander dialogs allow you to select a grouping variable in this manner. Making graphs with the R Commander is also straightforward. For example, selecting Graphs Histogram... from the R Commander menus brings up the Histogram dialog box in Figure 14; and clicking on infant.mortality followed by OK, opens a Graphics Device window with the histogram shown in Figure 15. If you make several graphs in a session, then only the most recent normally appears in the Graphics Device window. You can recall previous graphs using the Page Up and Page Down keys on your keyboard.13

1 3 At start-up, the R Commander turns on the graph history mechanism; this feature is available only on Windows systems. Dynamic three-dimensional scatterplots created by Graphs 3D graph 3D scatterplot... appear in a special RGL device window; likewise, eect displays created for statistical models (Fox, 2003; Fox and Hong, 2009) via Models Graphs E ect plots appear in individual graphics-device windows.

20

Figure 12: Selecting a grouping variable in the Groups dialog box.

21

Figure 13: The Numerical Summaries dialog box after the grouping variable region has been selected and with two numeric variables selected.

Figure 14: The Histogram dialog.

22

Figure 15: A graphics window containing the histogram for infant mortality in the Nations data set.

23

Figure 16: The Linear Model dialog box, with Prestige from the car package as the active data set.

Statistical Models

Several kinds of statistical models can be t in the R Commander using menu items under Statistics Fit models : linear models (by both Linear regression and Linear model ), generalized linear models, multinomial logit models, and ordinal regression models such as the proportional-odds model [the latter two from Venables and Ripleys (2002) nnet and MASS packages, respectively]. Although the resulting dialog boxes dier in certain details (for example, the generalized linear model dialog makes provision for selecting a distributional family and corresponding link function), they share a common general structure, as illustrated in the Linear Model dialog in Figure 16.14 Double-clicking on a variable in the variable-list box copies it to the model formula to the left-hand side of the formula, if it is empty, otherwise to the right-hand side (with a preceding + sign if the context requires it). Note that factors (categorical variables) are parenthetically labelled as such in the variable list. The row of buttons above the formula can be used to enter operators and parentheses into the righthand side of the formula. You can also type directly into the formula elds, and indeed may have to do so, for example, to put a term such as log(income) into the formula. The name of the model, here LinearModel.1, is automatically generated, but you can substitute any valid R name. You can type an R expression into the box labelled Subset expression ; if supplied, this is passed to the subset argument of the lm function, and is used to t the model to a subset of the observations in the data set. One form of subset expression is a logical expression that evaluates to TRUE or FALSE for each observation, such as type != "prof" (which would select all non-professional occupations from the Prestige data set).

1 4 An exception is the Linear Regression dialog in which the response variable and explanatory variables are simply selected by name from list boxes containing the numeric variables in the current data set. The explanation below assumes familiarity with R model formulas; see, for example, the Introduction to R manual that comes with R , which may be accessed from the Help menu in the R Console .

24

Clicking the OK button produces the following output (in the output window), and makes LinearModel.1 the active model, with its name displayed in the Model button: > LinearModel.1 <- lm(prestige ~ (education + income)*type, data=Prestige) > summary(LinearModel.1) Call: lm(formula = prestige ~ (education + income) * type, data = Prestige) Residuals: Min 1Q -13.462 -4.225 Coefficients: Estimate Std. Error t value (Intercept) 2.276e+00 7.057e+00 0.323 education 1.713e+00 9.572e-01 1.790 income 3.522e-03 5.563e-04 6.332 type[T.prof] 1.535e+01 1.372e+01 1.119 type[T.wc] -3.354e+01 1.765e+01 -1.900 education:type[T.prof] 1.388e+00 1.289e+00 1.077 education:type[T.wc] 4.291e+00 1.757e+00 2.442 income:type[T.prof] -2.903e-03 5.989e-04 -4.847 income:type[T.wc] -2.072e-03 8.940e-04 -2.318 --Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . Pr(>|t|) 0.7478 0.0769 9.62e-09 0.2660 0.0607 0.2844 0.0166 5.28e-06 0.0228

Median 1.346

3Q 3.826

Max 19.631

. *** . * *** *

0.1 1

Residual standard error: 6.318 on 89 degrees of freedom (4 observations deleted due to missingness) Multiple R-squared: 0.8747, Adjusted R-squared: 0.8634 F-statistic: 77.64 on 8 and 89 DF, p-value: < 2.2e-16 Operations on the active model may be selected from the Models menu. For example, Models Hypothesis tests Anova table..., followed by selecting the default Type-II tests, produces the following output: > Anova(LinearModel.1, type="II") Anova Table (Type II tests) Response: prestige Sum Sq Df F value Pr(>F) education 1068.0 1 26.7532 1.413e-06 *** income 1131.9 1 28.3544 7.511e-07 *** type 591.2 2 7.4044 0.001060 ** education:type 238.4 2 2.9859 0.055574 . income:type 951.8 2 11.9210 2.588e-05 *** Residuals 3552.9 89 --Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1

25

5
5.1

Odds and Ends

You can save text output directly from the File menu in the R Commander ; likewise you can save or print a graph from the File menu in an R Graphics Device window. It is generally more convenient, however, to collect the text output and graphs that you want to keep in a word-processor document. In this manner, you can intersperse R output with your typed notes and explanations. Open a word processor such as Word, OpenOce Writer, or even Windows WordPad. To copy text from the output window, block the text with the mouse, select Copy from the Edit menu (or press the key combination Ctrl-c, or right-click in the window and select Copy from the context menu), and then paste the text into the word-processor window via Edit Paste (or Ctrl-v ), as you would for any Windows application. One point worth mentioning is that you should use a mono-spaced (typewriter) font, such as Courier New, for text output from R; otherwise the output will not line up neatly. Likewise to copy a graph, select File Copy to the clipboard as a Metale from the R Graphics Device menus; then paste the graph into the word-processor document via Edit Paste (or Ctrl-v ). Alternatively, you can use Ctrl-w to copy the graph from the R Graphics Device, or right-click on the graph to bring up a context menu, from which you can select Copy as metale.15 At the end of your R session, you can save or print the document that you have created, providing an annotated record of your work. Alternative routes to saving text and graphical output may be found respectively under the R Commander File and Graphs Save graph to le menus. Saving the R Commander script window, via File Save script, allows you to reproduce your work on a future occasion.

5.2

Terminating the R Session

There are several ways to terminate your session. For example, you can select File Exit From Commander and R from the R Commander menus. You will be asked to conrm, and then asked whether you want to save the contents of the script and output windows. Likewise, you can select File Exit from the R Console ; in this case, you will be asked whether you want to save the R workspace (i.e., the data that R keeps in memory); you would normally answer No.

5.3

Entering Commands in the Script Window

The script window provides a simple facility for editing, entering, and executing commands. Commands generated by the R Commander appear in the script window, and you can type and edit commands in the window more or less as in any editor. The R Commander does not provide a true console for R, however, and the script window has some limitations. For example, all lines of a multiline command must be submitted simultaneously for execution. For serious R programming, it is preferable to use the script editors provided by the Windows and Mac OS X versions of R, or even better a programming editor or interactive development environment, such as RStudio www.rstudio.org.16

References
Fox, J. (2003). Eect displays in R for generalised linear models. Journal of Statistical Software, 8(15):127. Fox, J. (2005). The R Commander: A basic-statistics graphical user interface to R. Journal of Statistical Software, 19(9):142. Fox, J. (2007). Extending the R Commander by plug in packages. R News, 7(3):4652. Fox, J. and Carvalho, Marilia S. (2012). The RcmdrPlugin.survival package: Extending the R Commander interface to survival analysis. Journal of Statistical Software, 49(7):132.
1 5 As you will see when you examine these menus, you can save graphs in a variety of formats, and to les as well as to the clipboard. The procedure suggested here is straightforward, however, and generally results in high-quality graphs. Once again, this description applies to Windows systems. 1 6 The R Commander will run under RStudio , in which case by default R Commander output and messages are directed to the R console within RStudio, but there are some issues, such as instability and incompatibility with the RStudio graphics device.

26

Fox, J. and Hong, J. (2009). Eect displays in R for multinomial and proportional-odds logit models: Extensions to the eects package. Journal of Statistical Software, 32(1):124. Moore, D. S. (2000). The Basic Practice of Statistics, Second Edition. Freeman, New York. Venables, W. N. and Ripley, B. D. (2002). Modern Applied Statistics with S, Fourth Edition. Springer, New York.

27