Title: | Example Datasets from Archaeological Research |
---|---|
Description: | The archdata package provides several types of data that are typically used in archaeological research. It provides all of the data sets used in "Quantitative Methods in Archaeology Using R" by David L Carlson, one of the Cambridge Manuals in Archaeology. |
Authors: | David L. Carlson [aut, cre], Georg Roth [ctb] |
Maintainer: | David L. Carlson <[email protected]> |
License: | GPL (>= 2) |
Version: | 1.2-1 |
Built: | 2024-11-27 05:40:33 UTC |
Source: | https://github.com/cran/archdata |
Includes archaeological data sets used in Quantitative Methods in Archaeology Using R by David L Carlson (Cambridge Manuals in Archaeology).
Package: | archdata |
Type: | Package |
Version: | 1.2 |
Date: | 2018-01-31 |
License: | GPL |
Acheulean
Seven African Acheulean Sites
Arnhofen
Point pattern of mining pits from the Neolithic chert mine at Arnhofen
BACups
Bronze Age Cups from Italy
BarmoseI.grid
Flakes per grid unit from Barmose I, South Zealand, Denmark
BarmoseI.pp
Piece plotted artifacts from Barmose I, South Zealand, Denmark
Bornholm
Female Iron Age Graves, Bornholm, Denmark
DartPoints
Five dart point types from Fort Hood, Texas, U.S.A.
EIAGraves
Early Iron Age Graves - Tell el-Far'ah, Palestine
EndScrapers
Upper Paleolithic End Scrapers from Castenet A and Ferrassie H, France
EngrBone
Upper Paleolithic Engraved Bone Design Elements - Spain
ESASites
Early Stone Age Sites - Norway
EWBurials
Ernest Witte Cemetery, Austin, County, Texas, U.S.A.
Fibulae
Bronze La Tène fibulae from Műnsingen, Switzerland
Handaxes
Lower Paleolithic handaxes from Furze Platt, Maidenhead, Berkshire, England
MaskSite
Mask Site, Alaska, USA
Mesolithic
British Mesolithic assemblages
Michelsberg
Younger Neolithic Pottery from Central Europe
Nelson
Prehistoric Ceramics at Pueblo San Cristobal, New Mexico, U.S.A.
Olorgesailie.maj
Major stone tool classes, Olorgesailie, Kenya
Olorgesailie.sub
Stone tool subclasses, Olorgesailie, Kenya
OxfordPots
Distribution of Late Romano-British Oxford Pottery
PitHouses
Late Stone Age and Early Sami Iron Age Pithouses in Arctic Norway
RBGlass1
Romano-British Glass, Major and Minor Elements
RBGlass2
Romano-British Glass, Trace Elements
RBPottery
Romano-British Pottery
Snodgrass
House pits at the Mississippian Snodgrass site in Butler County, Missouri, U.S.A.
TRBPottery
Neolithic TRB Pottery from Demark
David L. Carlson and Georg Roth
Maintainer: David L. Carlson <[email protected]>
See individual data sets for information on the source and publications illustrating their use.
Stone tool assemblage data from a paper by Lewis Binford (1972). The sites include Olorgesailie, Isimila, Kalambo Falls, Lochard, Kariandusi, Broken Hill, and Nsongezi. Data include approximate latitude and longitude for each site as well as the frequency for each of 12 stone tool types.
data(Acheulean)
data(Acheulean)
A data frame with 7 observations showing the site location and the number of specimens for each of 12 stone artifact types. The localities are identified by rownames
.
Lat
Latitude (approximate)
Long
Longitude (approximate)
HA
Number of handaxes
CL
Number of cleavers
KN
Number of knives
FS
Number of flake scrapers
D
Number of discoids
CS
Number of core scrapers
P
Number of picks
CH
Number of choppers
SP
Number of spheroids
OLT
Number of other large tools
SS
Number of small scrapers
OST
Number of other small tools
Binford (1972) presents the percentages for 12 tool types at 32 assemblages from 7 sites (including Olorgesailie) which was based on Maxine Kleindienst's analysis of Lower Paleolithic Acheulean sites in Africa (1961 and 1962). The data were also analyzed by Glynn Isaac (1977). To create the Acheulean data set, the percentages in the original publication have been converted back to counts by dividing by 100 and multiplying by the number of tools. The assemblages from each site are summed. The largest assemblage is Kalambo Falls with 1349 artifacts and the smallest is Broken Hill (Kabwe) with 94. The rownames
identify each site and an attribute named Variables
provides variable labels for each column.
Binford, L. R. 1972. Contemporary Model Building: Paradigms and the Current State of Paleolithic Research. In Models in Archaeology, edited by D. L. Clarke, pp 109–166. Methuen.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 304-314.
Isaac, Glynn Ll. 1977. Olorgesailie: Archeological Studies of a Middle Pleistocene Lake Basin in Kenya. University of Chicago.
Kleindienst, Maxine R. 1961. Variability within the Late Acheulian assemblage in East Africa. South African Archaeological Bulletin 16: 35–52.
Kleindienst, Maxine R. 1962. Components of the East African Acheulian assemblage: an analytic approach. In Actes du IVe Congrès Panafricain de Préhistoire et de l’Étude du Quaternaire, ed. C. Mortelmans and J. Nenquin, pp 81-105.
data(Acheulean) # Compute percentages for each assemblage Acheulean.pct <- prop.table(as.matrix(Acheulean[,3:14]), 1)*100 round(Acheulean.pct, 2) plot(OST~HA, Acheulean.pct) boxplot(Acheulean.pct)
data(Acheulean) # Compute percentages for each assemblage Acheulean.pct <- prop.table(as.matrix(Acheulean[,3:14]), 1)*100 round(Acheulean.pct, 2) plot(OST~HA, Acheulean.pct) boxplot(Acheulean.pct)
The list object contains two data tables of coordinates, one representing the centers of round mining pits, the other holding the vertices of the observed polygonal area. Data was generated by G. Roth in 2006 (Roth 2008). Spatial distance unit is meter. For converting the data to a point pattern see Examples.
data(Arnhofen)
data(Arnhofen)
A list with two entries. The first is a data frame, points
, with 216 observations of x
and y
coordinates. Each line represents the center of a round mining pit. The second is a data frame, window
, with 100 observations and 3 variables, x
, y
, and vertex ID
. Each line represents a vertex of the polygonal observation area.
points$x
(num) x coordinates of pit centers in m
points$y
(num) y coordinates of pit centers in m
window$x
(num) x coordinates of observation window vertices in m
window$y
(num) y coordinates of observation window vertices in m
window$id
(num) id for observation window vertices
The coordinates in dataframe points
represent the centres of 216 mining pits in the southeastern section of the 2001 excavation at the Neolithic chert mine of Abensberg-Arnhofen (Roth 2008). Direct dates for mining from the excavation place the site at 5300-4200 BC while use of mined material ends with the Bell Beaker Culture suggesting an end date for the mine of ca. 2200 BC. The regular pit pattern presented here dates to about 4200 BC, i.e. to the Münchshöfen Culture (4500-4000 BC). Arnhofen is the largest neolithic mine in Germany. The mining organization was analyzed by Roth (2008) using point pattern analysis (cf. Baddeley et al. 2016) which showed the neolithic mining to be conducted by farmers from surrounding villages (presumably on a seasonal basis).
The pit centers were located manually in a GIS using excavation maps from between 3 to 4 m below present surface. Mining pits were similar to vertical tubes with an average diameter of 1 m and a rounded horizontal section. A point therefore represents the center of such a vertical tube in the horizontal plane. A few of the pits reached a depth of nearly 8 m below surface. The vertices of the observation area polygon circumscribe a slightly smaller region than the excavated area. The list contains the additional attributes: reference for the data, short data description (site) and geographical coordinates (Lat/Lon) of the excavation.
Roth, G. 2008. Geben und Nehmen, Eine Wirtschaftshistorische Studie zum Neolithischen Hornsteinbergbau von Abensberg-Arnhofen, Kr. Kelheim (Niederbayern) [in 4 volumes]. online PhD-thesis, University of Cologne 2008. http://kups.ub.uni-koeln.de/4176.
Baddeley, A., E. Rubak and R. Turner. 2016. Spatial Point Patterns: Methodology and Applications with R. CRC Press. Boca Raton.
# data and package spatstat by A. Baddeley et al. 2016 for point pattern analysis # package spatstat is described and illustrated in Baddeley et al. (2016) if (requireNamespace("spatstat", quietly = TRUE)) { library(spatstat) data(Arnhofen) ap <- Arnhofen # to shorten the following code # generate observation window object; note the polygonal outline. arnwin <- owin(poly=ap$window[, 1:2]) # generate point process pattern object from points and owin object app <- ppp(ap$points$x, ap$points$y, arnwin) unitname(app) <- c("metre", "metres") # optional, asign unitnames # note that owin vertices traverse the polygon anticlockwise plot(arnwin) points(ap$window[, 1:2], pch=3, cex=.5) text(ap$window[, 1], ap$window[, 2], ap$window[, 3], pos=3, cex=.7) # visual inspection of the point process pattern plot(app) # Computing the summary function "centered Besag's L" assuming # homogeneous intensity. Centered Besag's L is just a conveniently # transformed Ripley's K. see references in ?Lest. set.seed(1) Lcentrd <- envelope(app, Lest, nsim=49, nrank=1, global=TRUE, r=seq(0,7, 0.01), correction="translate", transform=expression(.-r)) # for the arguments see ?Kest and ?envelope. tm <- "Centered Besags's L for Arnhofen-Southeast" # title plot(Lcentrd, legendpos="bottomright", legendargs=list(bg="white"), main=tm, las=1) # The deviations below envelopes suggest regular inter point distances # at the 1 percent level - deviations above would have suggested clustering # with r representing the radius of round clusters. plot(Lcentrd, xlim=c(.5,2), legendpos="topright", legendargs=list(bg="white"), las=1, main=tm) (inhibr <- Lcentrd$r[Lcentrd$obs<Lcentrd$lo]) # significant inhibition between pits with an average diameter of 1 m pits # were spaced at regular distances up to about 0.7 m apart: max(inhibr) - 1 citation("spatstat") # don't forget to reference the method. } else { cat("This example requires package spatstat.\n") }
# data and package spatstat by A. Baddeley et al. 2016 for point pattern analysis # package spatstat is described and illustrated in Baddeley et al. (2016) if (requireNamespace("spatstat", quietly = TRUE)) { library(spatstat) data(Arnhofen) ap <- Arnhofen # to shorten the following code # generate observation window object; note the polygonal outline. arnwin <- owin(poly=ap$window[, 1:2]) # generate point process pattern object from points and owin object app <- ppp(ap$points$x, ap$points$y, arnwin) unitname(app) <- c("metre", "metres") # optional, asign unitnames # note that owin vertices traverse the polygon anticlockwise plot(arnwin) points(ap$window[, 1:2], pch=3, cex=.5) text(ap$window[, 1], ap$window[, 2], ap$window[, 3], pos=3, cex=.7) # visual inspection of the point process pattern plot(app) # Computing the summary function "centered Besag's L" assuming # homogeneous intensity. Centered Besag's L is just a conveniently # transformed Ripley's K. see references in ?Lest. set.seed(1) Lcentrd <- envelope(app, Lest, nsim=49, nrank=1, global=TRUE, r=seq(0,7, 0.01), correction="translate", transform=expression(.-r)) # for the arguments see ?Kest and ?envelope. tm <- "Centered Besags's L for Arnhofen-Southeast" # title plot(Lcentrd, legendpos="bottomright", legendargs=list(bg="white"), main=tm, las=1) # The deviations below envelopes suggest regular inter point distances # at the 1 percent level - deviations above would have suggested clustering # with r representing the radius of round clusters. plot(Lcentrd, xlim=c(.5,2), legendpos="topright", legendargs=list(bg="white"), las=1, main=tm) (inhibr <- Lcentrd$r[Lcentrd$obs<Lcentrd$lo]) # significant inhibition between pits with an average diameter of 1 m pits # were spaced at regular distances up to about 0.7 m apart: max(inhibr) - 1 citation("spatstat") # don't forget to reference the method. } else { cat("This example requires package spatstat.\n") }
Measurements on Early and Late Bronze Age ceramic cups from Italy analyzed by Lukesh and Howe (1978).
data("BACups")
data("BACups")
A data frame with 60 observations on the following 6 variables.
RD
Rim Diameter
ND
Neck Diameter
SD
Shoulder Diameter
H
Total Height
NH
Neck Height
Phase
Chronological Phase: Protoapennine, Subapennine
These data on the dimensions of Bronze Age cups from Italy are a subset extracted from a set published by Lukesh and Howe (1978) of the specimens for which full data was available. The data were scanned from Table A4 (Appendix A) in Baxter (1994). The Protoapennine cups are Early Bronze Age while the Subapennine cups are Late Bronze Age.
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press. Edinburgh.
Lukesh S. S. and S. Howe 1978. Protoapennine vs. Subapennine: Mathematical Distinction Between Two Ceramic Phases. Journal of Field Archaeology 5: 339-47.
data(BACups) by(BACups[, -6], BACups$Phase, summary) plot(RD~H, BACups, pch=as.numeric(Phase)) legend("topleft", levels(BACups$Phase), pch=1:2)
data(BACups) by(BACups[, -6], BACups$Phase, summary) plot(RD~H, BACups, pch=as.numeric(Phase)) legend("topleft", levels(BACups$Phase), pch=1:2)
Flake counts for each of 107 contiguous grid units at the Barmose I Maglemosian site used by Blankholm (1991) to illustrate several spatial analysis methods.
data(BarmoseI.grid)
data(BarmoseI.grid)
A data frame with 107 observations on the following 3 variables.
North
North coordinate of southwest corner of unit
East
East coordinate of southwest corner of unit
Debitage
Number of flakes
Barmose I is an early Maglemosian (7500 - 6000 BCE) site located in Barmosen in South Zealand, Denmark. The site was excavated in 1967-1971 by Axel Johansson (Johansson 1971 and 1990). Flake counts and grid coordinates were taken from Figure 100 in Blankholm (1991) for BarmoseI.grid
. BarmoseI.pp
includes the locations of 473 artifacts from Appendix C of Blankholm's book.
Blankholm, Hans Peter. 1991. Intrasite Spatial Analysis in Theory and Practice. Aarhus University Press.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 358-367.
Johansson, Axel. 1971. Barmosegruppen. Præboreale Bopladsfund me Skiveøkser i Sydsjælland. Foreløbig Meddelelse. Historisk Samfund for Præstø Amt. Årbog 1968, pp. 101-170.
Johansson, Axel. 1990. Barmosegruppen. Præboreale Bopladsfund i Sydsjælland. Årbog. Aarhus University Press.
data(BarmoseI.grid) plot(North~East, BarmoseI.grid, xlim=c(0, 12), ylim=c(0, 14), type="n", asp=1) with(BarmoseI.grid, text(East+.5, North+.5, Debitage, cex=.8))
data(BarmoseI.grid) plot(North~East, BarmoseI.grid, xlim=c(0, 12), ylim=c(0, 14), type="n", asp=1) with(BarmoseI.grid, text(East+.5, North+.5, Debitage, cex=.8))
Two dimensional locations of 473 artifacts at the Barmose I Maglemosian site used by Blankholm (1991) to illustrate several spatial analysis methods.
data(BarmoseI.pp)
data(BarmoseI.pp)
A data frame with 473 observations on the following 4 variables.
North
North coordinate
East
East coordinate
Class
Numeric code used by Blankholm: 1
, 2
, 3
, 4
, 5
, 6
, 7
, 8
, 9
, 10
, 11
Label
Artifact type: Scrapers
, Burins
, Lanceolate Microliths
, Microburins
, Flake Axes
, Core Axes
, Square Knives
, Blade/Flake Knives
, Denticulated/Notched Pieces
, Cores
, Core Platforms
Barmose I is an early Maglemosian (7500 - 6000 BCE) site located in Barmosen in South Zealand, Denmark. The site was excavated in 1967-1971 by Axel Johansson (Johansson 1971 and 1990). Flake counts and grid coordinates were taken from Figure 100 in Blankholm (1991) for BarmoseI.grid
. BarmoseI.pp
includes the locations of 473 artifacts from Appendix C of Blankholm's book (1991).
Blankholm, Hans Peter. 1991. Intrasite Spatial Analysis in Theory and Practice. Aarhus University Press.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 367-377.
Johansson, Axel. 1971. Barmosegruppen. Præboreale Bopladsfund me Skiveøkser i Sydsjælland. Foreløbig Meddelelse. Historisk Samfund for Præstø Amt. Årbog 1968, pp. 101–170.
Johansson, Axel. 1990. Barmosegruppen. Præboreale Bopladsfund i Sydsjælland. Årbog. Aarhus University Press.
data(BarmoseI.pp) plot(North~East, BarmoseI.pp, asp=1, pch=as.numeric(Class)) legend("bottomleft", levels(BarmoseI.pp$Label), pch=1:11, cex=.75)
data(BarmoseI.pp) plot(North~East, BarmoseI.pp, asp=1, pch=as.numeric(Class)) legend("bottomleft", levels(BarmoseI.pp$Label), pch=1:11, cex=.75)
Data on the occurrence of 39 different types of ornamentation in 77 female graves at Iron age sites in in Bornholm, Denmark.
data("Bornholm")
data("Bornholm")
A data frame with 77 observations on the following 42 variables.
Number
Observation Number
Site
Site/Bural Number
Period
Chronological period: 1a
, 1b
, 2a
, 2b
, 2c
, 3a
, and 3b
N2c
count
R3d
count
N2a
count
Q3b
count
R3c
count
N1
count
Q3c
count
O1
count
O2
count
N2e
count
I3
count
R3b
count
K1a
count
Q3a
count
I2
count
K1c
count
K1b
count
H
count
Q3d
count
J1d
count
S1
count
D
count
Q2
count
S3
count
P2
count
P4
count
G3
count
E2a
count
P3
count
R3a
count
R1
count
E2b
count
G2
count
I1b
count
G1
count
F
count
P1
count
I1a
count
A2e
count
Nielsen used data on 39 different types of ornaments from Ørsnes (1966) to seriate a series of 77 Late Germanic Iron Age (CE 550 - 800) graves from Bornholm, Denmark (1988, Table 4 and Figure 7). Baxter re-analyzed the data to illustrate correspondence analysis (1994: 104-107, Table A6). These data were taken from Nielsen's Table 4 showing her seriation. Baxter's version is scrambled in order to evaluate different seriation methods and does not include the ornament types (illustrated in Nielson's Figure 7). The data include Ørsnes's period and subperiod designations (1966).
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press. Edinburgh.
Nielsen, K. H. 1988. Correspondence Analysis Applied to Hords and Graves of the Germanic Iron Age. In Multivariate Archaeology: Numerical Approaches in Scandinavian Archaeology, edited by Torsten Madsen, pp 37-54. Jutland Archaeological Society Publications XXI. Arahus University Press.
Ørsnes, M. 1966. Form og stil i Sydskandinaviens yngre germanske jernalder. Nationalmuseets skrifter. Arkæologisk-historisk række 11. Copenhagen.
if (requireNamespace("MASS", quietly = TRUE)) { data(Bornholm) Bornholm.ca <- MASS::corresp(Bornholm[, 4:42], nf=2) plot(Bornholm.ca$rscore, pch=substring(Bornholm$Period, 1, 1), cex=.75) boxplot(Bornholm.ca$rscore[, 1]~Bornholm$Period, main="First CA Axis by Period") } else { cat("This example requires the MASS package.\n") }
if (requireNamespace("MASS", quietly = TRUE)) { data(Bornholm) Bornholm.ca <- MASS::corresp(Bornholm[, 4:42], nf=2) plot(Bornholm.ca$rscore, pch=substring(Bornholm$Period, 1, 1), cex=.75) boxplot(Bornholm.ca$rscore[, 1]~Bornholm$Period, main="First CA Axis by Period") } else { cat("This example requires the MASS package.\n") }
Metric and categorical measurements on 91 Archaic dart points recovered during surface surveys at Fort Hood, Texas representing five types.
data(DartPoints)
data(DartPoints)
A data frame with 91 observations on the following 17 variables.
Name
Dart point type: Darl
, Ensor
, Pedernales
, Travis
, Wells
Catalog
Fort Hood catalog number
TARL
Texas Archeological Research Laboratory site number
Quad
Fort Hood Quad
Length
Maximum Length (mm)
Width
Maximum Width (mm)
Thickness
Maxmimum Thickness (mm)
B.Width
Basal width (mm)
J.Width
Juncture width (mm)
H.Length
Haft element length (mm)
Weight
Weight (gm)
Blade.Sh
Blade shape: E - Excurvate
, I - Incurvate
, R - Recurvate
, S - Straight
Base.Sh
Base shape: E - Excurvate
, I - Incurvate
, R - Recurvate
, S - Straight
Should.Sh
Shoulder shape: E - Excurvate
, I - Incurvate
, S - Straight
, X - None
Should.Or
Shoulder orientation: B - Barbed
, H - Horizontal
, T - Tapered
, X - None
Haft.Sh
Shape lateral haft element A - Angular
, E - Excurvate
, I - Incurvate
, R - Recurvate
, S - Straight
Haft.Or
Orientation lateral haft element: C - Concave
, E - Expanding
, P - Parallel
, T - Contracting
, V - Convex
Measurements on five types of dart points from Fort Hood in central Texas (Darl, Ensor, Pedernales, Travis, and Wells). The points were recovered during 10 different pedestrian survey projects during the 1980's and were classified and measured by H. Blaine Ensor using the system created by Futato (1983) as described in Carlson, S., et al 1987, pp 51-70 and Appendices 4 and 7.
Fort Hood Projectile Points. Electronic database compiling the results of multiple surface surveys at Fort Hood in the possession of David L. Carlson, Department of Anthropology, Texas A&M University, College Station, TX. The artifacts are curated at Fort Hood, TX by the Cultural Resources Branch of the Directorate of Public Works.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 52-60, 99-103, 106-107, 109-115, 148-157, 182-185, 198-211.
Carlson, S. B., H. B. Ensor, D. L. Carlson, E. A. Miller, and D E. Young. 1987. Archaeological Survey at Fort Hood, Texas Fiscal Year 1984. United States Army Fort Hood. Archaeological Resource Management Series, Research Report Number 14.
Futato, E. M. 1983. Projectile Point Morphology: Steps Toward a Formal Account. in Proceedings of the Thirty-fourth Southeastern Archaeological Conference, Lafayette, Louisiana, October 27-19, 1977. Southeastern Archaeological Conference. Bulletin 21: 38–81.
data(DartPoints) boxplot(Length~Name, DartPoints) plot(Width~Length, DartPoints, pch=as.numeric(Name), main="FOrt Hood Dart Points") legend("topleft", levels(DartPoints$Name), pch=1:5)
data(DartPoints) boxplot(Length~Name, DartPoints) plot(Width~Length, DartPoints, pch=as.numeric(Name), main="FOrt Hood Dart Points") legend("topleft", levels(DartPoints$Name), pch=1:5)
Counts of 52 different ceramic types in 6 large tombs and 10 broadly contemporaneous groups of tombs.
data("EIAGraves")
data("EIAGraves")
A data frame with 52 rows (ceramic types) found in 16 units (a grave or a group of graves).
Type
Ceramic type number
G100
19 broadly contemporaneous graves and tombs
G200B
30 broadly contemporaneous graves and tombs
G200C
28 broadly contemporaneous graves and tombs
G201
An indidivual tomb
G229
An indidivual tomb
G500N
19 broadly contemporaneous graves and tombs
G532
An indidivual tomb
G542
An indidivual tomb
G552
An indidivual tomb
G562
An indidivual tomb
G600
52 broadly contemporaneous graves and tombs
G800
39 broadly contemporaneous graves and tombs
G900B
41 broadly contemporaneous graves and tombs
G900L
3 broadly contemporaneous graves and tombs
G900S
5 broadly contemporaneous graves and tombs
G900U
7 broadly contemporaneous graves and tombs
The data on counts of 52 different ceramic types in 6 large tombs and 10 broadly contemporaneous groups of tombs come from Tell el-Far'ah (South), Palestine. They were originally published in McClellan (1979). The data were scanned from Table 2.5 in Baxter (2003, p. 25-6). The 52 rows correspond to different pottery types found in association with the burials.
Baxter, M. J. 2003. Statistics in Archaeology. Arnold, London.
McClellan, T. L. 1979. Chronology of the 'Philistine' Burials at Tell el-Farah (South). Journal of Field Archaeology 6: 57-73.
data(EIAGraves) # How many ceramics of each type? # Exclude the first column which is the ceramic type number rowSums(EIAGraves[, -1]) # How many tomb groups contain each type? rowSums(EIAGraves[, -1]>0) # How many ceramics in each tomb group? colSums(EIAGraves[, -1]) # How many types are found in each tomb group? colSums(EIAGraves[, -1]>0)
data(EIAGraves) # How many ceramics of each type? # Exclude the first column which is the ceramic type number rowSums(EIAGraves[, -1]) # How many tomb groups contain each type? rowSums(EIAGraves[, -1]>0) # How many ceramics in each tomb group? colSums(EIAGraves[, -1]) # How many types are found in each tomb group? colSums(EIAGraves[, -1]>0)
Data on 3000 Upper Paleolithic end scrapers from two sites analyzed by James Sackett (1966) and reanalyzed by Dwight Read (1974 and 2007).
data(EndScrapers)
data(EndScrapers)
A data frame with 48 observations on the following 6 variables.
Width
Width: Narrow
, Wide
Sides
Sides: Convergent
, Parallel
Curvature
End Curvature: Round
, Medium
, Shallow
Retouched
Retouching: Retouched
, Unretouched
Site
Site: Castenet A
, Ferrassie H
Freq
Number of end scrapers
The scrapers are grouped on 5 categorical variables into 48 groups. Sackett's analysis employed Chi square and the examination of residuals. Read used the data to illustrate loglinear modelling (1974, 2007). The data come from Tables IV and VIII (pp 373 and 380) in Sackett's original article
Sackett, James R. 1966. Quantitative Analysis of Upper Paleolithic Stone Tools. American Anthropologist 68(2): 356–394.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 72-77, 91-94.
Read, Dwight W. 1974. Some Comments on Typologies in Archaeology and an Outline of a Methodology. American Antiquity 39: 216-242.
Read, Dwight W. 2007. Artifact Classification: A Conceptual and Methodological Approach. Left Coast Press.
data(EndScrapers) xtabs(Freq~Site+Curvature, EndScrapers) xtabs(Freq~Curvature+Sides+Site, EndScrapers)
data(EndScrapers) xtabs(Freq~Site+Curvature, EndScrapers) xtabs(Freq~Curvature+Sides+Site, EndScrapers)
Counts of 44 engraved bone design elements at five Upper Paleolithic hunter-gatherer sites in Cantabrian, Spain.
data("EngrBone")
data("EngrBone")
A data frame with 44 types of engraved bone found at 5 sites.
A
Altamira
CM
Cueto de la Mina
EJ
El Juyo
EC
El Cierro
LP
La Paloma
Counts of 44 engraved bone design elements at five prehistoric hunter-gatherer sites in Cantabrian, Spain. The data were originally analyzed by Conkey (1980) and appear in this format in Kaufman (1998). Kintigh (1984) used these data to illustrate a method for comparing the diversity between samples. The data were scanned from Table 2.4 in Baxter (2003, p. 24).
Baxter, M. J. 2003. Statistics in Archaeology. Arnold, London.
Conkey, M. W. 1980. The Identification of Prehistoric Hunter-Gatherer Aggregation Sites: The Case of Altamira. Current Anthropology 21: 609-30.
Kaufman, D. 1998. Measuring Archaeological Diversity: An Application of the Jackknife Technique. American Antiquity 63: 73-85.
Kintigh, K. 1984. Measuring Archaeological Diversity by Comparison with Simulated Assemblages. American Antiquity 49: 44-54.
data(EngrBone) # Number of engraved bone specimens at each site NS <- colSums(EngrBone) # Number of kinds of engraved bone at each site NT <- colSums(EngrBone>0) plot(NS, NT, xlab="Number of Specimens", ylab="Number of Types", main="Engraved Bone", las=1) text(NS, NT, names(EngrBone), pos=c(1, 3, 3, 3, 3)) Key <- apply(attr(EngrBone, "Variables"), 1, paste, collapse=" - ") legend("topleft", legend=Key)
data(EngrBone) # Number of engraved bone specimens at each site NS <- colSums(EngrBone) # Number of kinds of engraved bone at each site NT <- colSums(EngrBone>0) plot(NS, NT, xlab="Number of Specimens", ylab="Number of Types", main="Engraved Bone", las=1) text(NS, NT, names(EngrBone), pos=c(1, 3, 3, 3, 3)) Key <- apply(attr(EngrBone, "Variables"), 1, paste, collapse=" - ") legend("topleft", legend=Key)
Data on 43 Early Stone Age assemblages in Norway come originally from Bølviken et al (1982).
data("ESASites")
data("ESASites")
A data frame with 43 observations on the following 16 variables.
TA
Tanged Arrows
BA
Blade Arrows
TOA
Transverse and Oblique Arrows
AA
Atypical Arrows
M
Microliths
FK
Flake Knives
BK
Blade Knives
NK
Notched Knives
CFS
Core and Flake Scrapers
BS
Blade Scrapers
DS
Disc Scrapers
Bu
Burins
Ax
Axes
Ch
Chisels
SAx
Slate Axes
Pf
Perforators
Data on 43 Early Stone Age (8000 - 4000 BCE) assemblages in Norway come originally from Bølviken et al (1982). The data were scanned from Table A5 (Appendix A) in Baxter (1994).
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press. Edinburgh.
Bølviken, E., E. Helskog, K. Helskog, I. M. Holm-Olsen, L. Solheim, and R. Bertelsen. 1982. Correspondence Analysis: An Alternative to Principal Components. World Archaeology 14: 41-60.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 398-410.
data(ESASites) NS <- rowSums(ESASites) NT <- rowSums(ESASites > 0) plot(NS, NT, xlab="Number of Artifacts", ylab="Number of Types", main="Early Stone Age Sites", las=1)
data(ESASites) NS <- rowSums(ESASites) NT <- rowSums(ESASites > 0) plot(NS, NT, xlab="Number of Artifacts", ylab="Number of Types", main="Early Stone Age Sites", las=1)
Sex, age, burial group, location, and burial orientation and direction facing from the Ernest Witte site, a Late Archaic cemetery in Texas (Hall 1981).
data(EWBurials)
data(EWBurials)
A data frame with 49 observations on the following 7 variables.
Group
Cemetery group, a factor with levels 1
, 2
North
North grid location of the burial in meters (excavation grid system)
West
East grid location of the burial in meters (excavation grid system)
Age
Age category, a factor with levels Fetus
, Infant
, Child
, Adolescent
, Young Adult
, Adult
, Middle Adult
, Old Adult
Sex
a factor with levels Female
, Male
Direction
circular data in degrees indicating the direction of the individual measured from the head along the vertebral column
Looking
circular data in degrees indication the direction the individual is facing
Goods
Presence or absence of grave goods
The Ernest Witte site in Austin County, Texas contains four burial groups from different time periods. Group 1 includes 60 interments and that occurred between about 2000 and 1200 BCE. Group 2 is the largest with 148 interments. The burials in this group were interred between about CE 200 and 500. Groups 3 and 4 include only 10 and 13 interments and date to CE 500 to 1500, but are not included in this data set which was taken from Appendix II (Hall 1981). Two of the variables, direction
and looking
, are circular data and require package circular
. Hall (2010) provides a summary of the site and its significance.
Hall, G. D. 1981. Allen's Creek: A Study in the Cultural Prehistory of the Lower Brazos River Valley. The University of Texas at Austin. Texas Archeological Survey. Texas. Research Report No. 61.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 350-357.
Hall, G. D. 2010. Ernest Witte site. Handbook of Texas Online https://www.tshaonline.org/handbook/entries/ernest-witte-site. Texas State Historical Association.
data(EWBurials) xtabs(~Age+Sex+Group, EWBurials) if (requireNamespace("circular", quietly = TRUE)) { plot(EWBurials$Direction) } else { cat("This example requires package circular.\n") }
data(EWBurials) xtabs(~Age+Sex+Group, EWBurials) if (requireNamespace("circular", quietly = TRUE)) { plot(EWBurials$Direction) } else { cat("This example requires package circular.\n") }
The La Tène fibulae from the Iron Age cemetery of Münsingen near Berne, Switzerland (100 - 500 BCE) described by F. R. Hodson (1968).
data("Fibulae")
data("Fibulae")
A data frame with 30 observations on the following 16 variables.
Grave
Grave number
Mno
Museum number
FL
Foot Length
BH
Bow Height
BFA
Bow Front Angle
FA
Foot Angle
CD
Coil Diameter
BRA
Bow Rear Angle
ED
Element Diameter
FEL
Foot Extension Length
C
Catchplate
BW
Bow Width
BT
Bow Thickness
FEW
Foot Extension Width
Coils
Number of Coils
Length
Total Length
The La Tène fibulae from the Iron Age cemetery of Münsingen near Berne, Switzerland were reported by F. R. Hodson (1968). They were featured in several papers by Hodson over the years and used to illustrate a variety of multivariate statistical techniques. The data here were taken from Doran and Hodson (1975), Table 9.1. These are the raw measurements including 5 missing values in foot extension thickness and 1 in foot extension length.
Doran, J. E. and F. R. Hodson. 1975. Mathematics and Computers in Archaeology. Harvard University Press, Cambridge, Massachusetts.
Hodson, F. R. 1968. The La Tène Cemetery at Műnsingen-Rain. Stampfli, Berne.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 88-91, 95-99, 103-109, 127-129, 132-138, 162-169.
Hodson, F. R., P. H. A. Sneath, J. E. Doran. 1966. Some Experiments in the Numerical Analysis of Archaeological Data. Biometrika 53: 311-324.
Hodson, F. R. 1969. Searching for Structure within Multivariate Archaeological Data. World Archaeology 1: 90-105.
Hodson, F. R. 1970. Cluster Analysis and Archaeology: some New Developments and Applications. World Archaeology 1: 299-320.
Hodson, F. R. 1971. Numerical Typology and Prehistoric Archaeology. In Mathematics int eh Archaeological and Historical Sciences, edited by F. R. Hodson, D. G. Kendall and P. Tautu, pp 30-45. Edinburgh University Press, Edinburgh.
Sneath, P. H. A. 1968. Goodness of Intuitive Arrangements into Time Trends Based on Complex Pattern. Systematic Zoology 17: 256-260.
data(Fibulae) t(sapply(Fibulae[, 3:16], quantile, na.rm=TRUE)) plot(density(Fibulae$Length, bw="SJ"), main="Kernel Density Plot of Length")
data(Fibulae) t(sapply(Fibulae[, 3:16], quantile, na.rm=TRUE)) plot(density(Fibulae$Length, bw="SJ"), main="Kernel Density Plot of Length")
Handaxes from the Furze Platt site stored at the Royal Ontario Museum.
data(Handaxes)
data(Handaxes)
A data frame with 600 observations on the following 8 variables.
Catalog
Specimen catalog number
L
Maximum Length
L1
Distance from the butt to the location of the maximum breadth measured along the length dimension
B
Maximum breadth
B1
Breadth measured at 1/5 of the length from the tip. Measured perpendicular to the length
B2
Breadth measured at 1/5 of the length from the butt. Measured perpendicular to the length
T
Maximum thickness, not necessarily measured at the maximum breadth
T1
Thickness measured at B1
The data consist of measurements on 600 handaxes from the Furze Platt site stored at the Royal Ontario Museum that were measured by William Fox. The measurements follow the system used by Derek Roe (Roe 1964, 1968, 1981). Fox's measurements were digitized by Tony Baker and uploaded to his website.
Fox, William and Tony Baker. 2006. Dimensions of 600 Acheulean Handaxes from Furze Platt, Maidenhead, Berkshire, England. Archived at https://web.archive.org/web/20080515113522/http://www.ele.net/acheulean/FPatROM.htm. 11 Accessed January 2021.
Baker, Tony. 2006. The Acheulean Handaxe. Archived article available at https://web.archive.org/web/20080831233847/http://www.ele.net:80/acheulean/handaxe.htm. Accessed 11 January 2021.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 221-231, 269-277, 321-330.
Fox, William. 1969. An Analysis of the R. O. M. Collection, Lower Paleolithic Implements: Furze Platt, Maidenhead, Berkshire, England. Unpublished paper and notes in the possession of the author.
Roe, D. A. 1964. The British Lower and Middle Paleolithic: some problems, methods of study and preliminary results. Proceedings of the Prehistoric Society 30: 245–267.
Roe, D. A. 1968. British Lower and Middle Paleolithic Handaxe groups. Proceedings of the Prehistoric Society 34: 1–82.
Roe, D. A. 1981. The Lower and Middle Paleolithic Periods in Britain. Routledge.
data(Handaxes) summary(Handaxes)
data(Handaxes) summary(Handaxes)
The distribution of five categories of artifacts at the Mask site, occupied by the Nunamiut (Binford 1978a).
data("MaskSite")
data("MaskSite")
A data frame with 494 observations on the following 3 variables.
X
horizontal coordinate
Y
vertical coordinate
Category
a factor with levels Artifacts
, Spent Cartridges
, Wood Shavings
, Bone Splinters
, and Large Bones
The Mask Site was reported by Binford (1978a) as an example of a hunting stand where Nunamiut men watched for game as part of a larger ethnoarchaeological study of the Nunamiut (Binford 1978b). The data from the site have been widely used to illustrate the utility of various methods of intra site spatial analysis (including Baxter 2003, Blankholm 1991, Kintigh 1990, and Whallon 1984). The data consist of 494 locations of five different classes (artifacts, spent cartridges, wood shavings, bone splinters, and large bones). The data were scanned from Appendix A (Blankholm 1991).
Binford, L. R. 1978a. Dimensional Analysis of Behavior and Site Structure: Learning from an Eskimo Hunting Stand. American Antiquity 43: 330 - 361.
Blankholm, Hans Peter. 1991. Intrasite Spatial Analysis in Theory and Practice. Aarhus University Press.
Baxter, M. 2003. Statistics in Archaeology. Arnold Applications in Statistics.
Binford, L. R. 1978b. Nunamiut Ethnoarchaeology. Academic Press.
Kintigh, K. 1990. Intrasite Spatial Analysis: A Commentary on Major Methods. In Mathematics and Information Science in Archaeology: A Flexible Framework, edited by A. Voorrips, pp 165-200. Studies in Modern Archaeology 3. Holos.
Whallon, R. 1984. Unconstrained Clustering for the Analysis of Spatial Distributions in Archaeology. In Intrasite Spatial Analysis in Archaeology, edited by H. Hietala, pp 242 - 277. Cambridge University Press.
data(MaskSite) plot(Y~X, MaskSite, main="Mask Site", asp=1, pch=as.numeric(Category), cex=.75) legend("bottomright", levels(MaskSite$Category), pch=1:5)
data(MaskSite) plot(Y~X, MaskSite, main="Mask Site", asp=1, pch=as.numeric(Category), cex=.75) legend("bottomright", levels(MaskSite$Category), pch=1:5)
Counts of 5 different stone artifact types from 33 Mesolithic sites in Britain.
data("Mesolithic")
data("Mesolithic")
A data frame with 33 observations on the following 5 variables.
Microliths
Number of microliths
Scrapers
Number of scrapers
Burins
Number of burins
Axes
Number of axes
Saws
Number of saws
Data on 33 Mesolithic (9000 - 4000 BCE) assemblages are a subset Pitts (1979) extracted from a set published by Mellars (1976). The data were scanned from Table A3 (Appendix A) in Baxter (1994).
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press. Edinburgh.
Mellars, P. 1976. Settlement Patterns and Industrial Variability in the British Mesolithic. In Problems in Economic and Social Archaeology, edited by Sieveking, G de G., I. H. Longworth, and K. E. Wilson, pp 375-99. Duckworth, London.
Pitts, M. W. 1979. Hides and Antlers: A New Look at the Gatherer-Hunter Site at Star Carr, North Yorkshire, England. World Archaeology 11: 32-44.
data(Mesolithic) Mesolithic.pct <- prop.table(as.matrix(Mesolithic), 1)*100 apply(Mesolithic.pct, 2, quantile) cor(Mesolithic.pct)
data(Mesolithic) Mesolithic.pct <- prop.table(as.matrix(Mesolithic), 1)*100 apply(Mesolithic.pct, 2, quantile) cor(Mesolithic.pct)
A sites by types table of abundance data on vessel types in archaeological features of the Younger Neolithic Michelsberg Culture from Belgium, France and Germany by Birgit Höhn (2002).
data(Michelsberg)
data(Michelsberg)
A data frame with 109 observations on the following 42 variables. Each line represents one feature. Some categorical variables are not converted to factors.
id
Unique identifier (categorical, integer)
site_name
Name of site (categorical, character)
catalogue_nr
Number in catalogue of Höhn (2002) (categorical, integer)
feature_nr
Number of the archaeological feature (categorical, numeric)
to3
Pot/vessel type 3 count
f4
Bottle type 4 count
b2
Beaker type 2 count
to2
Pot/vessel type 2 count
b3
Beaker type 3 count
b7
Beaker type 7 count
kw5
Carinated bowl type 5 count
vg1
Storage vessel type 1 count
vg2
Storage vessel type 2 count
t4a
Tulip beaker type 4a count
kw2
Carinated bowl type 2 count
kw4
Carinated bowl type 4 count
b5
Beaker type 5 count
t3b
Tulip beaker type 3b count
f3
Bottle type 3 count
kw3
Carinated bowl type 3 count
kw1
Carinated bowl type 1 count
b6
Beaker type 6 count
to1
Pot/vessel type 1 count
b1
Beaker type 1 count
t3a
Tulip beaker type 3a count
vg4
Storage vessel type 4 count
ks2
Conical bowl type 2 count
ks1
Conical bowl type 1 count
t2b
Tulip beaker type 2b count
f2
Bottle type 2 count
bs3
Globular bowl type 3 count
t2a
Tulip beaker type 2a count
bs2
Globular bowl type 2 count
b4
Beaker type 4 count
bs1
Globular bowl type 1 count
f1
Bottle type 1 count
t1b
Tulip beaker type 1b count
vg3
Storage vessel type 3 count
t1a
Tulip beaker type 1a count
mbk_phase
MBK phase according to Lüning (1967) as an ordered factor with levels I
< I/II
< II
< II/III
< III
< III-V
< III/IV
< IV
< IV/V
< Munz
< V
x_utm32n
x coordinate in m; projection UTM WGS 84, zone 32 nord
y_utm32n
y coordinate in m; projection UTM WGS 84, zone 32 nord
Höhn (2002) recorded pottery vessel shapes from 108 archaeological features (pits, ditches etc.) from 69 sites of the Central European Younger Neolithic Michelsberg Culture (MBK; 4350-3500 BC) following Lüning's (1967) typology. Her correspondence analysis of the abundance data (columns 5 to 39) exhibits a pronounced Guttman effect or arch, suggesting the data set is structured by a time gradient. Recently Mischka et al. (2015) projected an 109th Michelsberg assemblage, Flintbek LA48, a pit with Michelsberg pottery from a North German site of the Funnel Beaker Culture (TRB), as a supplementary row into the existing chronology thereby connecting the relative chronologies of TRB and MBK. The data frame contains as attributes the references for the data, a typological key and the map projection. Note that ambiguous fragments of conical bowls (ks1 and ks2) are assigned as 0.5 to each of the two types resulting also in positive entries suitable to analysis by CA.
Höhn, B. 2002. Die Michelsberger Kultur in der Wetterau. Universitätsforschungen zur prähistorischen Archäologie 87. Bonn: Habelt.
Mischka, D., Roth, G. and K. Struckmeyer 2015. Michelsberg and Oxie in contact next to the Baltic Sea. In: Neolithic Diversities. Perspectives from a conference in Lund, Sweden. Acta Archaeologica Lundensia Ser. 8, No. 65, edited by Kr. Brink et al., pp 241–250.
Lüning, J. 1967. Die Michelsberger Kultur: Ihre Funde in zeitlicher und räumlicher Gliederung. Berichte der Römisch-Germanischen Kommission 48, 1-350.
if (requireNamespace("ca", quietly = TRUE)) { data(Michelsberg) str(Michelsberg) names(Michelsberg)[5:39] attributes(Michelsberg)$typological_key # geographical distribution xy <- as.matrix(Michelsberg[,41:42])/1000 plot(xy, asp=1, pch=16, col=rgb(.3,.3,.3,.5)) text(xy[,1], xy[,2], Michelsberg$id, cex=.7, pos=2) # Note site 109 to the Northeast; # preparing the data set for CA abu <- Michelsberg[, 5:39] rownames(abu) <- Michelsberg$id # CA with site 109, Flintbek LA48, as supplementary row MBK.ca <- ca::ca(abu, ndim=min(dim(abu)-1), suprow=109 ) # asymmetric biplot with row quality and column contribution plot(MBK.ca, map="rowprincipal", contrib=c("relative", "absolute")) title(main="Row-isometric Biplot of Michelsberg CA", cex.sub=.7, sub="color intensity represents quality for sites and contributions for types") } else { cat("This example requires package ca to run.\n") }
if (requireNamespace("ca", quietly = TRUE)) { data(Michelsberg) str(Michelsberg) names(Michelsberg)[5:39] attributes(Michelsberg)$typological_key # geographical distribution xy <- as.matrix(Michelsberg[,41:42])/1000 plot(xy, asp=1, pch=16, col=rgb(.3,.3,.3,.5)) text(xy[,1], xy[,2], Michelsberg$id, cex=.7, pos=2) # Note site 109 to the Northeast; # preparing the data set for CA abu <- Michelsberg[, 5:39] rownames(abu) <- Michelsberg$id # CA with site 109, Flintbek LA48, as supplementary row MBK.ca <- ca::ca(abu, ndim=min(dim(abu)-1), suprow=109 ) # asymmetric biplot with row quality and column contribution plot(MBK.ca, map="rowprincipal", contrib=c("relative", "absolute")) title(main="Row-isometric Biplot of Michelsberg CA", cex.sub=.7, sub="color intensity represents quality for sites and contributions for types") } else { cat("This example requires package ca to run.\n") }
Ceramic distribution in a midden deposit at Pueblo San Cristobal reported by Nels Nelson in 1916.
data(Nelson)
data(Nelson)
A data frame with 10 observations on the following 8 variables.
Depth
Depth in feet from 1 to 10 for 1 foot arbitrary excavation levels
Corrugated
Number of corrugated ware ceramics
Biscuit
Number of Biscuit ware ceramics
Type_I
Number of two and three color painted ware ceramics
Type_II_Red
Number of two color glazed red ware ceramics
Type_II_Yellow
Number of two color glazed yellow ware ceramics
Type_II_Gray
Number of two color glazed gray ware ceramics
Type_III
Number of three color glazed ware ceramics
Data from a midden deposit at San Cristobal in the American Southwest. It has been used as a classic illustration of the potential for creating a relative chronology using frequency seriation of ceramic artifact types. The site was occupied approximately from CE 1350 to 1680. Ceramic artifact fragment counts are presented for each 1-foot (30 cm) arbitrary level excavated in the midden deposit. When converted to percentages (usually excluding the corrugated ware), the data illustrate a classical "battleship curve" like those described in Ford (1962).
Nelson, N. C. 1916. Chronology of the Tano Ruins, New Mexico. American Anthropologist 18(2): 159–180.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 381-386, 390-393.
Ford, J. A. (1962) A Quantitative Method for Deriving Cultural Chronology. Pan American Union, Technical Manual No 1.
data(Nelson) # Remove Depth and Corrugated and compute percentages Nelson.pct <- prop.table(as.matrix(Nelson[,3:7]), 1)*100 # Percentages for each type by level round(Nelson.pct, 2) # Battleship plot from plotrix package if (requireNamespace("plotrix", quietly = TRUE)) { plotrix::battleship.plot(Nelson.pct, col="gray") } else { cat("This example requires package plotrix.\n") }
data(Nelson) # Remove Depth and Corrugated and compute percentages Nelson.pct <- prop.table(as.matrix(Nelson[,3:7]), 1)*100 # Percentages for each type by level round(Nelson.pct, 2) # Battleship plot from plotrix package if (requireNamespace("plotrix", quietly = TRUE)) { plotrix::battleship.plot(Nelson.pct, col="gray") } else { cat("This example requires package plotrix.\n") }
The data represent the number of specimens in each of 6 major artifact classes recovered from 19 localities at the Lower Paleolithic site of Olorgesailie as described in Isaac (1977).
data(Olorgesailie.maj)
data(Olorgesailie.maj)
A data frame with 19 observations showing the number of specimens for each of 6 stone artifact types.
Large.cutting.tools
Number of large cutting tools
Heavy.duty.tools
Number of heavy duty tools
Large.scrapers
Number of large scrapers
Other.large.tools
Number of other large tools
Small.tools
Number of small tools
Spheroids
Number of spheroids
The data come from Table E1 in Isaac (1977: 239). The rownames
identify localities in the lower, middle and upper strata to provide relative chronological placement. They are in the same order as the columns in the table: LS1 (BBB), LS2 (BBA), LS3(FB), LS4(FB-HL), LS5(FB-I3), MS1a(DE/89 A-L), MS1b(DE/89 A-I), MS2a(DE/89 B-L), MS2b(DE/89 B-I), MS3(DE/89 C), MS4(H/6), MS5(H/9 A), MS6(H/9 AM), MS7(Mid), MS8(Meng), MS9(LHS), US1(TRTrM10), US2(Hog), US3(MFS). Potts (2011) provides updated information on the site complex.
Isaac, Glynn Ll. 1977. Olorgesailie: Archeological Studies of a Middle Pleistocene Lake Basin in Kenya. The University of Chicago Press.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 115-119, 138-142.
Potts, R. 2011. Olorgesailie–Retrospective and current synthesis. In Casting the net wide: papers in honor of Glynn Isaac and his approach to human origins research, edited by J. Sept and D. Pilbeam, pp 1–20. American School of Prehistoric Resarch Monographs in Archaeology and Paleoanthropology.
data(Olorgesailie.maj) # Chi square after removing the first two columns and simulating the p # value since there are a number of very small expected values chisq.test(Olorgesailie.maj, simulate.p.value=TRUE) # Compute percentages over the localities Olor.pct <- prop.table(as.matrix(Olorgesailie.maj), 1)*100 boxplot(Olor.pct)
data(Olorgesailie.maj) # Chi square after removing the first two columns and simulating the p # value since there are a number of very small expected values chisq.test(Olorgesailie.maj, simulate.p.value=TRUE) # Compute percentages over the localities Olor.pct <- prop.table(as.matrix(Olorgesailie.maj), 1)*100 boxplot(Olor.pct)
The data represent the number of specimens in each of 16 artifact subclasses recovered from 19 localities at the Lower Paleolithic site of Olorgesailie as described in Isaac (1977).
data(Olorgesailie.sub)
data(Olorgesailie.sub)
A data frame with 19 observations showing the stratum, locality and the number of specimens for each of 16 stone artifact types.
Strat
stratum: Lower
, Middle
, Upper
Locality
Locality
HA
Number of handaxes
PHA
Number of pick-like handaxes
CHA
Number of chisel handaxes
CL
Number of cleavers
KN
Number of knives
BLCT
Number of broken large cutting tools
PAT
Number of picks and trièdres
CH
Number of choppers
CS
Number of core scrapers
LFS
Number of large flake scrapers
CB
Number of core bifaces
OLT
Number of other large tools
SSS
Number of small scrapers simple
SSNP
Number of small scrapers nosed point
OST
Number of other small tools
SP
Number of spheroids
The data come from Table E1 in Isaac (1977: 239). The Locality
contains the column headings in the original table. The rownames
are the same as those in Olorgesailie.maj
. The attribute Variables
in the data frame includes the full variable names. Potts (2011) provides updated information on the site complex.
Isaac, Glynn Ll. 1977. Olorgesailie: Archeological Studies of a Middle Pleistocene Lake Basin in Kenya. The University of Chicago Press.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 280-293.
Potts, R. 2011. Olorgesailie–Retrospective and current synthesis. In Casting the net wide: papers in honor of Glynn Isaac and his approach to human origins research, edited by J. Sept and D. Pilbeam, pp 1–20. American School of Prehistoric Research Monographs in Archaeology and Paleoanthropology.
data(Olorgesailie.sub) # Chi square after removing the first two columns and simulating the p # value since there are a number of very small expected values chisq.test(Olorgesailie.sub[,3:18], simulate.p.value=TRUE) # Compute percentages over the localities Olor.pct <- prop.table(as.matrix(Olorgesailie.sub[,3:18]), 1)*100 boxplot(Olor.pct, cex.axis=.7)
data(Olorgesailie.sub) # Chi square after removing the first two columns and simulating the p # value since there are a number of very small expected values chisq.test(Olorgesailie.sub[,3:18], simulate.p.value=TRUE) # Compute percentages over the localities Olor.pct <- prop.table(as.matrix(Olorgesailie.sub[,3:18]), 1)*100 boxplot(Olor.pct, cex.axis=.7)
Percentages of Late Romano-British Oxford Pottery on 30 sites
data("OxfordPots")
data("OxfordPots")
A data frame with 30 observations on the following 7 variables.
Place
Site name
OxfordPct
Percentage of Oxford pottery
OxfordDst
Distance to Oxford in miles
NewForestPct
Percentage of New Forest pottery
NewForestDst
Distance to New Forest
WalledArea
Acreage of walled towns
WaterTrans
Availability of a water transportation link, 1=probable presence
In several publications Ian Hodder analyzed the spatial distribution of Late Romano-British pottery produced at Oxford as evidence of trade and marketing patterns. These data come from the article by Fulford and Hodder (1974). In addition to the percentage of Oxford pottery and the distance to Oxford for 30 sites, data on New Forest pottery was included and information on walled town size and the availability of water transportation.
Fulford, M. and I. Hodder. 1974. A Regression Analysis of Some Late Romano-British Pottery: A Case Study. Oxoniensia 39: 26-33.
Hodder, I. 1974. A Regression Analysis of Some Trade and Marketing Patterns. World Archaeology 6: 172-189.
Hodder, I. and C. Orton. 1976. Spatial Analysis in Archaeology, pp 117-119.
data(OxfordPots) # Construct Fulford and Hodder's Figure 3 Oxford.lm1 <- lm(log(OxfordPct)~OxfordDst, OxfordPots, subset=WaterTrans==0) Oxford.lm2 <- lm(log(OxfordPct)~OxfordDst, OxfordPots, subset=WaterTrans==1) plot(log(OxfordPct)~OxfordDst, OxfordPots, xlim=c(0, 160), yaxt="n", ylim=c(0, 3.25), ylab="Percentage of Oxford Pottery", xlab="Distance (miles)", pch=c(1, 16)[WaterTrans+1], cex=1.5, lwd=2) # Add log y-axis axis(2, log(c(1, 5, 10, 20)), c(1, 5, 10, 20), las=1) abline(Oxford.lm1, lwd=2) abline(Oxford.lm2, lwd=2)
data(OxfordPots) # Construct Fulford and Hodder's Figure 3 Oxford.lm1 <- lm(log(OxfordPct)~OxfordDst, OxfordPots, subset=WaterTrans==0) Oxford.lm2 <- lm(log(OxfordPct)~OxfordDst, OxfordPots, subset=WaterTrans==1) plot(log(OxfordPct)~OxfordDst, OxfordPots, xlim=c(0, 160), yaxt="n", ylim=c(0, 3.25), ylab="Percentage of Oxford Pottery", xlab="Distance (miles)", pch=c(1, 16)[WaterTrans+1], cex=1.5, lwd=2) # Add log y-axis axis(2, log(c(1, 5, 10, 20)), c(1, 5, 10, 20), las=1) abline(Oxford.lm1, lwd=2) abline(Oxford.lm2, lwd=2)
The morphology of 45 Arctic Norway pithouses is described in terms of 6 categorical variables.
data("PitHouses")
data("PitHouses")
A data frame with 45 observations on the following 6 variables.
Hearths
a factor with levels None
, One
, Two
, and Charcoal Conc
Depth
a factor with levels Deep
and Shallow
Size
a factor with levels Small
, Medium
, and Large
Form
a factor with levels Oval
and Rectangular
Orient
a factor with levels Parallel Coast
and Gabel Toward Coast
Entrance
a factor with levels One Side
, Front and One Side
, and None
Data on the morphology of pit houses from Arctic Norway described by Engelstad (1988). The data were scanned from Table A7 in Baxter (1994). The category labels are used rather than the numeric values listed in Table A7. The data represent the Group C pithouses as described in Engelstad (1988) which was more variable than groups A or B. The data were converted into an incidence matrix (Table A8 in Baxter (1994) and Table 3 in Englestad (1988)) and used in a multiple correspondence analysis.
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press.
Engelstad, E. 1988. Pit Houses in Arctic Norway - An Investigation of Their Typology Using Multiple Correspondence Analysis. In Multivariate Archaeology, edited by T. Madsen, pp. 71-84. Aarhus University Press.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 192-197.
data(PitHouses) # Crosstabulation of Hearths with Size PitHouses.tbl <- xtabs(~Hearths+Size, PitHouses) PitHouses.tbl barplot(PitHouses.tbl, ylab="Frequency", main="Arctic Norway Pithouses", beside=TRUE, legend.text=TRUE, args.legend=list(title="Hearths")) barplot(prop.table(PitHouses.tbl, 2)*100, ylim=c(0, 60), main="Arctic Norway Pithouses", ylab="Percent", beside=TRUE, legend.text=TRUE, args.legend=list(title="Hearths"))
data(PitHouses) # Crosstabulation of Hearths with Size PitHouses.tbl <- xtabs(~Hearths+Size, PitHouses) PitHouses.tbl barplot(PitHouses.tbl, ylab="Frequency", main="Arctic Norway Pithouses", beside=TRUE, legend.text=TRUE, args.legend=list(title="Hearths")) barplot(prop.table(PitHouses.tbl, 2)*100, ylim=c(0, 60), main="Arctic Norway Pithouses", ylab="Percent", beside=TRUE, legend.text=TRUE, args.legend=list(title="Hearths"))
The concentrations for 11 major and minor elements in 105 Romano-British waste glass specimens from two furnace sites (Leicester and Mancetter).
data("RBGlass1")
data("RBGlass1")
A data frame with 105 observations on the following 12 variables.
Site
a factor with levels Leicester
and Mancetter
Al
Percentage Aluminum
Fe
Percentage Iron
Mg
Percentage Magnesium
Ca
Percentage Calcium
Na
Percentage Sodium
K
Percentage Potassium
Ti
Percentage Titanium
P
Percentage Phosphorus
Mn
Percentage Manganese
Sb
Percentage Antinmony
Pb
Percentage Lead
The concentrations for 11 major and minor elements in 105 Romano-British waste glass specimens from two furnace sites (Leicester and Mancetter) come from Caroline Jackson's Ph. D. thesis at Bradford University. The data here were scanned from from Baxter (1994) Table A1. Measurements are percentage for each element.
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press.
Jackson, C. M. 1992. A Compositional Analysis of Roman and Early Post-Roman Glass and Glass Working Waste from Selected British Sites Towards an Understanding of the Technology of Glass-Making Through Analysis by Inductively-Coupled Plasma Spectrometry. Unpublished PhD thesis. Bradford University (BL: D214554).
Baxter, M. J., Cool H.E.M., Heyworth M.P. and Jackson, C.M. 1995. Compositional Variability in Colourless Roman Vessel Glass. Archaeometry 37(1), 129-141.
Baxter, M. J., Cool, H. E. M. and Jackson, C. M. (2005). Further Studies in the Compositional Variability of Colourless Romano-British Glass. Archaeometry 47, 47-68.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 245-247, 256-261.
Jackson, C M, J R Hunter, S E Warren, and H E M Cool. 1991. The Analysis of Blue-Green Glass and Glassy Waste from Two Romano-British Glass Working Sites. In Archaeometry 1990, edited by E. Pernicka and G. A. Wagner, pp 295-304. Birkhäuser Verlag.
data(RBGlass1) RBGlass1.pca <- prcomp(RBGlass1[, -1], scale.=TRUE) biplot(RBGlass1.pca, xlabs=abbreviate(RBGlass1$Site, 1), cex=.75)
data(RBGlass1) RBGlass1.pca <- prcomp(RBGlass1[, -1], scale.=TRUE) biplot(RBGlass1.pca, xlabs=abbreviate(RBGlass1$Site, 1), cex=.75)
The concentrations for 11 trace elements in 105 Romano-British waste glass specimens from two furnace sites (Leicester and Mancetter).
data("RBGlass2")
data("RBGlass2")
A data frame with 105 observations on the following 12 variables.
Site
a factor with levels Leicester
and Mancetter
Ba
Barium ppm
Co
Cobalt ppm
Cr
Chromium ppm
Cu
Copper ppm
Li
Lithium ppm
Ni
Nickel ppm
Sr
Strontium ppm
V
Vanadium ppm
Y
Yttrium ppm
Zn
Zinc ppm
Zr
Zirconium ppm
The concentrations for 11 trace elements in 105 Romano-British waste glass specimens from two furnace sites (Leicester and Mancetter) come from Caroline Jackson's Ph. D. thesis at Bradford University. The data here were scanned from from Baxter (1994) Table A2. Measurements are parts per million (ppm) for each of 11 elements.
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press.
Jackson, C. M. 1992. A Compositional Analysis of Roman and Early Post-Roman Glass and Glass Working Waste from Selected British Sites Towards an Understanding of the Technology of Glass-Making Through Analysis by Inductively-Coupled Plasma Spectrometry. Unpublished PhD thesis. Bradford University (BL: D214554).
Baxter, M. J., Cool H.E.M., Heyworth M.P. and Jackson, C.M. 1995. Compositional Variability in Colourless Roman Vessel Glass. Archaeometry 37(1), 129-141.
Baxter, M. J., Cool, H. E. M. and Jackson, C. M. (2005). Further Studies in the Compositional Variability of Colourless Romano-British Glass. Archaeometry 47, 47-68.
Jackson, C M, J R Hunter, S E Warren, and H E M Cool. 1991. The Analysis of Blue-Green Glass and Glassy Waste from Two Romano-British Glass Working Sites. In Archaeometry 1990, edited by E. Pernicka and G. A. Wagner, pp 295-304. Birkhäuser Verlag.
data(RBGlass2) RBGlass2.pca <- prcomp(RBGlass2[, -1], scale.=TRUE) biplot(RBGlass2.pca, xlabs=abbreviate(RBGlass2$Site, 1), cex=.75)
data(RBGlass2) RBGlass2.pca <- prcomp(RBGlass2[, -1], scale.=TRUE) biplot(RBGlass2.pca, xlabs=abbreviate(RBGlass2$Site, 1), cex=.75)
Results of chemical analyses of 48 specimens of Romano-British pottery from 5 sites in 3 regions.
data("RBPottery")
data("RBPottery")
A data frame with 48 observations on the following 12 variables.
ID
Sample ID
Kiln
Kiln: Gloucester
, Llanedeyrn
, Caldicot
, Islands Thorns
, and Ashley Rails
Region
Region: Gloucester
, Wales
, and New Forest
Al2O3
Percentage aluminum trioxide
Fe2O3
Percentage Iron trioxide
MgO
Percentage magnesium oxide
CaO
Percentage calcium oxide
Na2O
Percentage sodium oxide
K2O
Percentage potassium oxide
TiO2
Percentage titanium dioxide
MnO
Percentage manganese oxide
BaO
Percentage barium oxide
Results of chemical analyses of 48 specimens of Romano-British pottery published by Tubb, et al. (1980). The numbers are the percentage metal oxide. "Kiln" indicates at which kiln site the pottery was found. The kiln sites come from three regions (1=Gloucester, (2=Llanedeyrn, 3=Caldicot), (4=Islands Thorns, 5=Ashley Rails)). The data were scanned from Table 2.2 in Baxter (2003, p. 21) and preserve three probable typographical errors in the original publication. Those errors are the values for TiO2 in line 4 (sample GA4), for MnO in line 35 (sample C13), and for K2O in line 36 (sample C14). Versions of these data are also available as Pottery
in package car
, pottery
in package HSAUR
, and Pottery2
in package heplots
.
Baxter, M. J. 2003. Statistics in Archaeology. Arnold.
Tubb, A., A. J. Parker, and G. Nickless. 1980. The Analysis of Romano-British Pottery by Atomic Absorption Spectrophotometry. Archaeometry 22: 153-71.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 247-255, 335-342.
data(RBPottery) print(aggregate(RBPottery[, -c(1:3)], list(Region=RBPottery$Region), mean), digits=2) plot(Na2O~CaO, RBPottery, pch=as.numeric(Region)-1) legend("topright", levels(RBPottery$Region), title="Region", pch=0:2)
data(RBPottery) print(aggregate(RBPottery[, -c(1:3)], list(Region=RBPottery$Region), mean), digits=2) plot(Na2O~CaO, RBPottery, pch=as.numeric(Region)-1) legend("topright", levels(RBPottery$Region), title="Region", pch=0:2)
Information on the size, location and contents of 91 house pits at the Snodgrass site which was occupied between about CE 1325-1420.
data(Snodgrass)
data(Snodgrass)
A data frame with 91 observations on the following 15 variables.
East
East grid location of house in feet (excavation grid system)
South
East grid location of house in feet (excavation grid system)
Length
House length in feet
Width
House width in feet
Segment
Three areas within the site 1
, 2
, 3
Inside
Location within or outside the "white wall" Inside
, Outside
Area
Area in square feet
Points
Number of projectile points
Abraders
Number of abraders
Discs
Number of discs
Earplugs
Number of earplugs
Effigies
Number of effigies
Ceramics
Number of ceramics
Total
Total Number of artifacts listed above
Types
Number of kinds of artifacts listed above
The data from 91 house pits at the Snodgrass site were reported by Price and Giffin in 1979. The layout of the houses follows a grid pattern with the long axis oriented northeast surrounded by a fortification trench. There is also evidence of an interior wall that may have separated the houses inside that wall from those outside the wall. Price and Griffin use differences in house size and artifact composition to suggest that those differences may have reflected rank differences between the occupants of the two areas. That conclusion has been questioned on a number of grounds by Cogswell, et al (2001), but the data are still useful for illustrating a number of quantitative methods. The data come from the appendices except for the house locations which were estimated from the base map in Figure 10 (Price and Griffin 1979).
Price, J. E. and J. B. Griffin. 1979. The Snodgrass Site of the Powers Phase of Southeast Missouri. Anthropological Papers. Museum of Anthropology, University of Michigan, No. 66.
Carlson, David L. 2017. Quantitative Methods in Archaeology Using R. Cambridge University Press, pp 171-183, 232-242.
Cogswell, J. W., M. J. O'Brien, and D. S. Glover. 2001. The Artifactual Content of Selected House Floors at Turner and Snodgrass. In Mississippian Community Organization: The Powers Phase in Southeastern Missouri, edited by M. J. O'Brien, pp 181–229. Kluwer Academic/Plenum.
data(Snodgrass) plot(-South~East, Snodgrass, main="Snodgrass Site", pch=as.numeric(Inside)+4, asp=1) legend("topleft", levels(Snodgrass$Inside), pch=5:6) boxplot(Area~Inside, Snodgrass)
data(Snodgrass) plot(-South~East, Snodgrass, main="Snodgrass Site", pch=as.numeric(Inside)+4, asp=1) legend("topleft", levels(Snodgrass$Inside), pch=5:6) boxplot(Area~Inside, Snodgrass)
Measurements at 8 landmarks along one side of 118 Neolithic TRB (Trichterrandbecherkultur, Funnelneckbeaker culture) pottery vessels representing 3 different groups.
data("TRBPottery")
data("TRBPottery")
A data frame with 118 observations on the following 17 variables.
Form
a factor with levels Funnel beakers
, Bowls
, and Flasks
AX
Point 1, x
AY
Point 1, y
BX
Point 2, x
BY
Point 2, y
CX
Point 3, x
CY
Point 3, y
DX
Point 4, x
DY
Point 4, y
EX
Point 5, x
EY
Point 5, y
FX
Point 6, x
FY
Point 6, y
GX
Point 7, x
GY
Point 7, y
HX
Point 8, x
HY
Point 8, y
The data are based on a study by E. K. Nielsen (1983) of Neolithic Pottery of 135 complete pots. The measurements are taken at landmarks identified along the profile of each pot (see Madsen, 1988 Figure 5). The data were reanalyzed by Madsen (1988). Baxter (1994) reanalyzed the data using several different methods. The data were scanned from Table 1 in Madsen (1988, p. 18) which included only 118 pots.
Madsen, T. 1988. Multivariate Statistics and Archaeology. In Multivariate Archaeology: Numerical Approaches in Scandinavian Archaeology, edited by T. Madsen, pp 7 - 28.
Nielsen, E. K. 1983. Tidligneolitiske Keramikfund. Unpublished thesis. Institute of Archaeology, University of Copenhagen.
Baxter, M. J. 1994. Exploratory Multivariate Analysis in Archaeology. Edinburgh University Press, pp 128-132.
data(TRBPottery) TRBPottery.frm <- aggregate(TRBPottery[, -1], list(Form=TRBPottery$Form), mean) Xvals <- TRBPottery.frm[, seq(2, 16, by=2)] Yvals <- TRBPottery.frm[, seq(3, 17, by=2)] matplot(t(Xvals), t(Yvals), xlab="X", ylab="Y", type="l", asp=1, las=1, col="black", lwd=2) legend("topleft", levels(TRBPottery$Form), lty=1:3, col="black", lwd=2)
data(TRBPottery) TRBPottery.frm <- aggregate(TRBPottery[, -1], list(Form=TRBPottery$Form), mean) Xvals <- TRBPottery.frm[, seq(2, 16, by=2)] Yvals <- TRBPottery.frm[, seq(3, 17, by=2)] matplot(t(Xvals), t(Yvals), xlab="X", ylab="Y", type="l", asp=1, las=1, col="black", lwd=2) legend("topleft", levels(TRBPottery$Form), lty=1:3, col="black", lwd=2)