1
2
3
4
5
#

Name:

Description:

Michael Florent van Langren (1598-1675) was a Dutch mathematician and astronomer, who served as a royal mathematician to King Phillip IV of Spain, and who worked on one of the most significant problems of his time— the accurate determination of longitude, particularly for navigation at sea.

In order to convince the Spanish court of the seriousness of the problem (often resulting in great losses through ship wrecks), he prepared a 1-dimensional line graph, showing all the available estimates of the distance in longitude between Toledo and Rome, which showed large errors, for even this modest distance. This 1D line graph, from Langren (1644), is believed to be the first known graph of statistical data (Friendly etal., 2010). It provides a compelling example of the notions of statistical variability and bias.

The data frame Langren1644 gives the estimates and other information derived from the previously known 1644 graph. It turns out that van Langren produced other versions of this graph, as early as 1628. The data frame Langren.all gives the estimates derived from all known versions of this graph.

Variables:

Langren1644: A data frame with 12 observations on the following 10 variables, giving determinations of the distance in longitude between Toledo and Rome, from the 1644 graph.

Name

The name of the person giving a determination, a factor with levels A. Argelius ... T. Brahe

Longitude

Estimated value of the longitude distance between Toledo and Rome

Year

Year associated with this determination

Longname

A longer version of the Name, where appropriate; a factor with levels Andrea Argoli Christoph Clavius Tycho Brahe

City

The principal city where this person worked; a factor with levels Alexandria Amsterdam Bamberg Bologna Frankfurt Hven Leuven Middelburg Nuremberg Padua Paris Rome

Country

The country where this person worked; a factor with levels Belgium Denmark Egypt Flanders France Germany Italy Italy

Latitude

Latitude of this City; a numeric vector

Source

Likely source for this determination of Longitude; a factor with levels Astron Map

Gap

A numeric vector indicating whether the Longitude value is below or above the median

Langren.all: A data frame with 61 observations on the following 4 variables, giving determinations of Longitude between Toledo and Rome from all known versions of van Langren's graph.

Author

Author of the graph, a factor with levels Langren Lelewel

Year

Year of publication

Name

The name of the person giving a determination, a factor with levels Algunos1 Algunos2 Apianus ... Schonerus

Longitude

Estimated value of the longitude distance between Toledo and Rome

Details

In all the graphs, Toledo is implicitly at the origin and Rome is located relatively at the value of Longitude To judge correspondence with an actual map, the positions in (lat, long) are

toledo <- c(39.86, -4.03); rome <- c(41.89, 12.5)

Link To Google Sheets:

Rows:

Columns:

License Type:

References/Notes/Attributions:

Source

The longitude values were digitized from images of the various graphs, which may be found on the Supplementary materials page for Friendly etal. (2009).

References

Friendly, M., Valero-Mora, P. and Ulargui, J. I. (2010). The First (Known) Statistical Graph: Michael Florent van Langren and the "Secret" of Longitude. The American Statistician, 64 (2), 185-191. Supplementary materials: http://datavis.ca/gallery/langren/.

Langren, M. F. van. (1644). La Verdadera Longitud por Mar y Tierra. Antwerp: (n.p.), 1644. English translation available at http://datavis.ca/gallery/langren/verdadera.pdf.

Lelewel, J. (1851). Geographie du Moyen Age. Paris: Pilliet, 1851.

R Dataset Upload:

Use the following R code to directly access this dataset in R.

d <- read.csv("https://www.key2stats.com/van_Langren_s_Data_on_Longitude_Distance_between_Toledo_and_Rome_893_19.csv")

R Coding Interface:


Datasets Tag Questions & Instructional Blocks

NumberContentType
No results found.