rockchalk (version 1.8.111)

outreg0: Creates a publication quality result table for regression models. outreg0 is the last version in the last development stream.

Description

outreg0 writes its output directly to the terminal, but does not create an output object. The new version of this function--which I wish you would try instead--does the same work, but it also creates an output object that can be transformed for other purposes.

Usage

outreg0(modelList, title, label, modelLabels = NULL, varLabels = NULL,
  tight = TRUE, showAIC = FALSE, float = FALSE, request, runFuns,
  digits = 3, alpha = 0.05)

Arguments

modelList

A regression model or an R list of regression models. If this is a named list, the names will be used as column labels, unless the argument modelLabels is supplied separately, which will override the names of modelList.

title

A title to be displayed on the top of the LaTeX regression table.

label

A string to be used as a LaTeX label in the table to be created.

modelLabels

A vector of charater string variables, one for each element in modelList. Will override the names in modelList.

varLabels

To beautify the parameter names printed. Must be a named vector in the format c(parmname = "displayName", parmname = "displayName"). Include as many parameters as desired, it is not necessary to supply new labels for all of the parameters. "displayName" must be valid laTeX. This feature is useful if your variable names have any illegal LaTeX characters, such as "$" or "_".

tight

If TRUE, parameter estimates and standard errors are printed in a single column. If FALSE, parameter estimates and standard errors are printed side by side.

showAIC

If TRUE, the AIC estimate is included with the diagnostic values

float

Include boilerplate for a table float, with the tabular markup inside it.

request

Extra information to be retrieved from the summary(model) and displayed. This must be a vector of named arguments, such as c(adj.r.squared = "adj $R^2$", fstatistic = "F"). The name must be a valid name of the output object, the value should be the label the user wants printed in the table. See details.

runFuns

A list of functions

digits

Default = 3. How many digits after decimal sign are to be displayed.

alpha

Default = 0.05. I think stars are dumb, but enough people have asked me for more stars that I'm caving in. Enter c(0.05, 0.01, 0.001) to see what happens.

Value

None

Details

This provides "markup" that the user is will copy into a LaTeX document. The table is a LaTeX tabular environment, which can be enclosed in a table to obtain a "floating," automatically numbered LaTeX document environment. The default will create the tabular-inside-a-table, but if only the tabular is needed, use the argument float = FALSE. This can be called within Sweave documents. The markup generated by the basic usage will generally be presentable as is, while user requests for additional details may cause output that needs some hand-editing.

A LaTeX tabular object is created, with the floating table markup around it if requested (float = TRUE).

The table include a minimally sufficient (in my opinion) model summary. For any fitted model, outreg0() will present the parameter estimates and standard errors, and it will also scan the summary of the object for some summary values and goodness of fit indicators. Some users may want more information. lm fits will not include output for the "fstatistic" that is reported in the lm's summary object, but users can ask for it with the argument request. Similarly, the argument runFuns can ask for additional diagnostic functions to be reported.

While outreg0() originally designed for models fitted by lm() and glm(), it will now work for any kind of regression model that has methods summary(), coef(), vcov() and nobs(). This will not succeed, however, if the regression model's summary function does not create an object that holds values in a workable structure (in the same way that lm() and glm() do). Please pressure people who write R packages that claim to "do regression" to supply methods to do the basic work that we need to compile tables.

Two types of customization arguments were introduced with rockchalk version 1.7.3. The new arguments are request and runFuns. Beta test reports are welcome!

The request argument supplies a list of names of summary output elements that are desired. The format is a pair, a value to be retrieved and a name to be printed for it. With the lm() regression, for example, one might want the output of the F test and the adjusted R-square. An example usage might be request = c(adj.r.squared = "adj. $R^2", fstatistic = "F"). The names may be included in quotation marks if the user desires to do so: request = c("adj.r.squared" = "adj. $R^2", "fstatistic" = "F"). The value on the left is the name of the desired information in the summary object, while the value on the right is any valid LaTeX markup that the user desires to display in the first column of the table. request terms that generate a single numerical value will generally work fine, while requests that ask for more structured information, such as the F test (including the 2 degrees of freedom values) are still a work in progress.

The runFuns argument is inspired by a user request: could this include the BIC or other summaries that some models report? We have to run the BIC function, and divert the result into the correct column of the result table. Any R function, whether supplied with and R package or in the user's own code, may be used. This is a two-part specification, one representing the function to be run, the other representing the name that is desired in the output. For example, it might be runFuns = c("AIC" = "Akaike Criterion", "BIC" = "Schwartz Criterion", "logLik" = "LL").

Examples

# NOT RUN {
set.seed(2134234)
dat <- data.frame(x1 = rnorm(100), x2 = rnorm(100))
dat$y1 <- 30 + 5 * rnorm(100) + 3 * dat$x1 + 4 * dat$x2
dat$y2 <- rnorm(100) + 5 * dat$x2
m1 <- lm(y1 ~ x1, data = dat)
m2 <- lm(y1 ~ x2, data = dat)
m3 <- lm(y1 ~ x1 + x2, data = dat)
gm1 <- glm(y1 ~ x1, family = Gamma, data = dat)

outreg0(list("Model 1" = m1), title = "My One Tightly Printed Regression")

outreg0(list("Model 1" = m1), title = "My One Tightly Printed Regression in a
Float", float = TRUE, label = "outreg1")

outreg0(list("Fingers" = m1), tight = FALSE, title = "My Only
Spread Out Regression", float = TRUE, alpha = c(0.05, 0.01,
0.001))

outreg0(list(ModelA = m1, "Model B label with Spaces" = m2),
      varLabels = list(x1 = "Billie"),
      title = "My Two Linear Regressions",
      request = c(fstatistic = "F"))

outreg0(list(ModelA = m1, ModelB = m2),
    modelLabels = c("Overrides ModelA", "Overrides ModelB"),
    varLabels = list(x1 = "Billie"),
    title = "Note modelLabels Overrides model names")

outreg0(list(m1, m2), modelLabels = c("Whatever", "Whichever"),
    title = "Still have showAIC argument, as in previous versions",
    showAIC = TRUE, float = TRUE)

outreg0(list(m1, m2), modelLabels = c("Whatever", "Whichever"),
    title = "Another way to get AIC output",
    runFuns = c("AIC" = "Akaike IC"))

outreg0(list("Amod" = m1, "Bmod" = m2, "Gmod" = m3),
    title = "My Three Linear Regressions", float = FALSE)

outreg0(list(m1, m2, m3), tight = FALSE,
    modelLabels = c("I Love really long titles", "Hate Long", "Medium"),
    float = FALSE)

outreg0(list(gm1), modelLabels = c("GLM"), float = TRUE)

outreg0(list(m1, gm1), modelLabels = c("OLS", "GLM"),
    float = TRUE, alpha = c(0.05, 0.01))

outreg0(list(OLS = m1, GLM = gm1), float = TRUE,
    request = c(fstatistic = "F"), runFuns = c("BIC" = "BIC"))

outreg0(list(OLS = m1, GLM = gm1), float = TRUE,
    request = c(fstatistic = "F"), runFuns = c("BIC" = "BIC"),
    digits = 5, alpha = 0.01)

outreg0(list("OLS 1" = m1, "OLS 2" = m2,  GLM = gm1), float = TRUE,
    request = c(fstatistic = "F"),
    runFuns = c("BIC" = "BIC", logLik = "ll"),
    digits = 5, alpha = c(0.05, 0.01, 0.001))

outreg0(list(ModelA = gm1, "Model B label with Spaces" = m2),
    request = c(fstatistic = "F"),
    runFuns = c("BIC" = "Schwarz IC", "AIC" = "Akaike IC",
         "nobs" = "N Again?"))
# }