statcheck (version 1.0.1)

checkPDFdir: Extract statistics and recompute p values from a directory with pdf files.

Description

Extracts statistical references from a directory with PDF files. The "pdftotext" program (http://www.foolabs.com/xpdf/download.html) is used to convert PDF files to plain text files. This must be installed and PATH variables must be properly set so that this program can be used from command line.

By default a GUI window is opened that allows you to choose the directory (using tcltk).

Usage

checkPDFdir(dir, subdir = TRUE, ...)

Arguments

dir

String indicating the directory to be used.

subdir

Logical indicating whether you also want to check subfolders. Defaults to TRUE

...

Arguments sent to statcheck.

Value

Source

Name of the file of which the statistic is extracted

Statistic

Character indicating the statistic that is extracted

df1

First degree of freedom

df2

Second degree of freedom (if applicable)

Test.Comparison

Reported comparison of the test statistic, when importing from pdf this will often not be converted properly

Value

Reported value of the statistic

Reported.Comparison

Reported comparison, when importing from pdf this might not be converted properly

Reported.P.Value

The reported p-value, or NA if the reported value was NS

Computed

The recomputed p-value

Raw

Raw string of the statistical reference that is extracted

Error

The computed p value is not congruent with the reported p value

DecisionError

The reported result is significant whereas the recomputed result is not, or vice versa.

OneTail

Logical. Is it likely that the reported p value resulted from a correction for one-sided testing?

OneTailedInTxt

Logical. Does the text contain the string "sided", "tailed", and/or "directional"?

CopyPaste

Logical. Does the exact string of the extracted raw results occur anywhere else in the article?

Details

See statcheck for more details. Use checkPDF to import individual PDF files. Currently only statistics in the form "stat (df1, df2) = value, p = value" are extracted. Because the Chi-square symbol can not be repressented in plain text it is often lost in the conversion. Because of this Chi-square values are extracted by finding all statistical references with one degree of freedom that do not follow the symbol "t" or "r". While this does extract most Chi-square values it is possible that other statistics, possibly due to unconventional notation, are also extracted and reported as chi-square values.

Depending on the PDF file the comparison operators can sometimes not be converted correctly, causing these to not be reported in the output. Using html versions of articles and the similar function checkHTMLdir is recommended for more stable results.

Note that the conversion to plain text and extraction of statistics can result in errors. Some statistical values can be missed, especially if the notation is unconventional. It is recommended to manually check some of the results.

See Also

statcheck, checkPDF, checkHTMLdir, checkHTML, checkdir

Examples

  # with this command a menu will pop up from which you can select the directory with PDF articles


# checkPDFdir()





# you could also specify the directory beforehand


# for instance:


# DIR <- "C:/mydocuments/articles"


# checkPDFdir(DIR)