# NTplot

##### Specify plots to illustrate Normal and t Hypothesis Tests or Confidence Intervals, including normal approximation to the binomial.

Specify plots to illustrate Normal and t Hypothesis Tests or Confidence Intervals, including normal approximation to the binomial.

##### Usage

```
NTplot(mean0, ...)
## S3 method for class 'default':
NTplot(mean0=0, ..., shiny=FALSE,
distribution.name = c("normal","z","t","binomial"))
## S3 method for class 'htest':
NTplot(mean0, ..., shiny=FALSE, NTmethod="htest")
## S3 method for class 'power.htest':
NTplot(mean0, ..., shiny=FALSE, xbar=NA, ## these input values are used
mean1, n, df, sd, distribution.name, sub, ## these input values ignored
alpha.left, alpha.right, number.vars) ## these input values ignored
## NTplot(NTplot(htest.object), n=20) ## allows override of arguments
## S3 method for class 'NormalAndTplot':
NTplot(mean0, ..., shiny=FALSE)
```

##### Arguments

- mean0
- For the default method,
`mean0`

is either missing or a numeric argument for the mean under the null hypothesis. For the`htest`

method,`mean0`

is an`htest`

object from the - xbar
- See
`NormalAndTplot`

. - ...
- Other arguments, selected from the options for the
default method
`NormalAndTplot`

. - shiny
- Logical. If
`TRUE`

, a`shiny`

app is started to provide an interactive graphics device in a web-browser. If`FALSE`

, a plot is drawn on the current graphics device. - htest
- logical.
`TRUE`

for`"htest"`

objects. - mean1, n, df, sd, sub, alpha.left, alpha.right, number.vars
- These variables are ignored here. They
are captured so they won't interfere with similarly named variables
that are generated in the
`power.htest`

method. - distribution.name
- Ignored by
`htest`

and`power.htest`

methods. Otherwise passed on to the next method. - NTmethod
- Character string used when
`shiny=TRUE`

. It is normally calculated by the methods.`NTmethod`

tells`shiny`

how to use or ignore the`df`

and`n`

sliders. See the extended discussion in

##### Details

The graphs produced by this single function cover most of the first semester
introductory Statistics course.
All options of the `t.test`

, `power.t.test`

, and `z.test`

are accepted and displayed.

`NTplot`

is built on `xyplot`

.
Most of the arguments detailed in `xyplot`

documentation work to
control the appearance of the plot.

The shiny app (called when the argument `shiny=TRUE`

)
provides animated sliders for the means, standard
deviation, xlimits, significance levels, df, and n. The df and n are
rounded to integers for the sliders (relevant for `htest`

and
`power.htest`

objects).

When you have a graph on the shiny window that you wish to keep, click on the "Display Options" tab, and then on the "Display Call" radio button. The main shiny window will show an R command which will reproduce the current plot. Pick it up with the mouse and drop it into an R console window.

To get out of the shiny window and return to an interactive R console,
move the cursor back to the console window and interrupt the shiny call, usually
by entering `Ctrl-C`

or `ESC`

.

##### Value

`"trellis"`

object. The object can be plotted or fed back into the`NTplot`

function with argument`shiny=TRUE`

to allow interactive graphical investigation of the hypothesis test or confidence interval. The attributes of the object\`NTobj <- NTplot()`

\`attr(NTobj, "scales")`

and`attr(NTobj, "prob")`

make the data values and probability values accessible for further R computations. The`"call"`

attribute`cat(attr(NT.object, "call"), "`

") displays a statement that can be copied back into R to reproduce the graph. The`cat()`

is needed to unescape embedded quotes. The`"call.list"`

attribute`attr(NT.object, "call.list")`

is a list that can be used with`do.call`

to reproduce the graph.`do.call(NTplot, attr(NT.object, "call.list"))`

. This is usually not needed by the user because the simpler statement`NTplot(NT.object)`

does it for you. [object Object]`NormalAndTplot`

,`print.NormalAndTplot`

.This function is built on lattice andlatticeExtra . It supersedes the similar function`normal.and.t.dist`

built on base graphics that is used in many displays in the book by Erich Neuwirth and me:*R through Excel*, Springer (2009).http://www.springer.com/978-1-4419-0051-7 . Many details, particularly the alternate color scheme and the concept of floating probability labels, grew out of discussions that Erich and I have had since the book was published. It incorporates ideas that Jay Kerns and I developed at the 2011 UseR! conference. This version incorporates some ideas suggested by Moritz Heene.hplot shiny x1 <- rnorm(12) x2 <- rnorm(12, mean=.5) NT.object <- NTplot(mean0=0, mean1=1) NT.object attr(NT.object, "scales") attr(NT.object, "prob") cat(attr(NT.object, "call"), "

") ## the cat() is needed to unescape embedded quotes. NTplot(t.test(x1, x2)) NTplot(power.t.test(power = .90, delta = 1, alternative = "one.sided"))

## 22 distinct calls are shown in demo(NTplot, ask=FALSE)

## these are interactive and do not work in static checking of the code NTplot(mean0=0, mean1=1, shiny=TRUE) NTplot(t.test(x1, x2), shiny=TRUE, mean1=1) NTplot(power.t.test(power = .90, delta = 1, alternative = "one.sided"), shiny=TRUE) NTplot(NT.object, shiny=TRUE)

*Documentation reproduced from package HH, version 3.1-23, License: GPL (>= 2)*