| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 1 | % Generated by roxygen2: do not edit by hand | 
|  | 2 | % Please edit documentation in R/ci.R | 
|  | 3 | \name{ci} | 
|  | 4 | \alias{ci} | 
|  | 5 | \title{Add confidence interval and relative frequency variables} | 
|  | 6 | \usage{ | 
| Marc Kupietz | 71d6e05 | 2019-11-22 18:42:10 +0100 | [diff] [blame] | 7 | ci(df, x = totalResults, N = total, conf.level = 0.95) | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 8 | } | 
|  | 9 | \arguments{ | 
|  | 10 | \item{df}{table with columns for absolute and total frequencies.} | 
|  | 11 |  | 
|  | 12 | \item{x}{column with the observed absolute frequency.} | 
|  | 13 |  | 
| Marc Kupietz | 43a6ade | 2020-02-18 17:01:44 +0100 | [diff] [blame] | 14 | \item{N}{column with the total frequencies} | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 15 |  | 
|  | 16 | \item{conf.level}{confidence level of the returned confidence interval. Must | 
|  | 17 | be a single number between 0 and 1.} | 
|  | 18 | } | 
|  | 19 | \description{ | 
|  | 20 | Using \code{\link{prop.test}}, \code{ci} adds three columns to a data frame: | 
| Marc Kupietz | 3f57528 | 2019-10-04 14:46:04 +0200 | [diff] [blame] | 21 | 1. relative frequency (\code{f}) | 
|  | 22 | 2. lower bound of a confidence interval (\code{ci.low}) | 
|  | 23 | 3. upper bound of a confidence interval | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 24 | } | 
|  | 25 | \examples{ | 
| Marc Kupietz | 05b2277 | 2020-02-18 21:58:42 +0100 | [diff] [blame] | 26 | \donttest{ | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 27 | library(ggplot2) | 
|  | 28 | kco <- new("KorAPConnection", verbose=TRUE) | 
|  | 29 | expand_grid(year=2015:2018, alternatives=c("Hate Speech", "Hatespeech")) \%>\% | 
|  | 30 | bind_cols(corpusQuery(kco, .$alternatives, sprintf("pubDate in \%d", .$year))) \%>\% | 
| Marc Kupietz | 71d6e05 | 2019-11-22 18:42:10 +0100 | [diff] [blame] | 31 | mutate(total=corpusStats(kco, vc=vc)$tokens) \%>\% | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 32 | ci() \%>\% | 
|  | 33 | ggplot(aes(x=year, y=f, fill=query, color=query, ymin=conf.low, ymax=conf.high)) + | 
|  | 34 | geom_point() + geom_line() + geom_ribbon(alpha=.3) | 
| Marc Kupietz | 05b2277 | 2020-02-18 21:58:42 +0100 | [diff] [blame] | 35 | } | 
| Marc Kupietz | dcc1de6 | 2019-10-04 09:10:36 +0200 | [diff] [blame] | 36 | } | 
| Marc Kupietz | 3f57528 | 2019-10-04 14:46:04 +0200 | [diff] [blame] | 37 | \seealso{ | 
| Marc Kupietz | 43a6ade | 2020-02-18 17:01:44 +0100 | [diff] [blame] | 38 | \code{ci} is already included in \code{\link{frequencyQuery}} | 
| Marc Kupietz | 3f57528 | 2019-10-04 14:46:04 +0200 | [diff] [blame] | 39 | } |