Amber

From InterSciWiki
Jump to: navigation, search

Amber Johnson - Project_2013#New_List_of_Generalizations_from_Binford_2001

This first file has errors lgather & perwitg Screen Shot 2014-02-13 at 6.33.31 PM.png

April 27 2015

http://capone.mtsu.edu/eaeff/DEf_LRB.html
library (Hmisc)
library(mice)
library(foreign)
library(stringr)
library(AER)
library(spdep)
library(psych)
library(geosphere)
library(relaimpo)
library(linprog)
library(dismo)
library(forward)
library(pastecs)
library(classInt)
library(maps)
library(dismo)
library(plyr)
library(aod)
library(reshape)
library(RColorBrewer)
library(XML)
library(tm)
library(mlogit)
#The Dow-Eff functions, as well as the five ethnological datasets, are contained in an R-workspace, located in the cloud.
load(url("http://capone.mtsu.edu/eaeff/downloads/DEf01f.Rdata"))
#-show the objects contained in DEf01f.Rdata
data.frame(type=sapply(ls(),function(x) class(get(x))))
Dear Eric and Stu,
  • I have an important user request for a new option in CoSSci, which we might discuss first in today's phone call; it has highest priority and can be summarized for one of the datasets (LRB) as bolded below given the first few explanatory lines:
setDS("LRB") #lets say the user uses LRB and wants one or more subsamples defined by a table of variables; in this example:
table(dx$grppat,dx$subsp)  #maybe (2,2) n=30 won't work we know (1,2) n=5 certainly won't work because of too few cases
    1   2   3
1  75 112  48
2   5  30  69
  • say the user needs a CoSSci command to include all the subsamples except for (1,2) n=5, (2,2) n=30. so WE NEED TO DEFINE A NEW USER OPTION just above NEW VARIABLE that does exclusion of cases, and as one example:

SubSetExclusion #(e.g., for LRB) Goal: [IF dx$grppat=1 AND IF dx$subsp=1 then ] include these cases, e.g.,

IF dx$grppat>1 then dx$grppat=NA
IF dx$subsp>1 then dx$subsp=NA
  • but allow as many new SubSetExclusion statements as needed in the new window, as many windows will appear as needed by the user.
  • Thanks, Doug


setDS("LRB") #lets say the user uses LRB and wants to define subsamples of the table of variables
table(dx$grppat,dx$subsp)  #maybe 2,2 n=30 won't work (1,2) n=5 certainly won't work because of too few cases
     1   2   3
 1  75 112  48
 2   5  30  69
#say the user needs a CoSSci command to include subsamples except for (1,2) n=5, (2,2) n=30. DEFINE A USER OPTION  
SubSetExclusion  #(e.g., for LRB)    #Goal: [IF dx$grppat=1 AND IF dx$subsp=1 then ] include these cases, e.g.,
 IF dx$grppat>1 then dx$grppat=NA 
 IF dx$subsp>1 then dx$subsp=NA
but allow as many new SubSetExclusion statements as needed in the new window

2012 Amber

Yes, sure, Doug, send the data and I’ll do what I can as soon as I can.


Anthon


E. Anthon Eff Professor, Economics

Middle Tennessee State University

Mail: MTSU Box X050 Murfreesboro, TN 37132

http://frank.mtsu.edu/~eaeff

615.898.2387


Natura non facit saltum


From: Doug White [1] Sent: Sunday, March 11, 2012 7:05 PM To: Anthon Eff Subject: Fwd: Re: Binford forager coding guide


Tony, its amazing but I located the anthropologist wife of Binford who was earlier his research assistant and programmer for the 2001 book, and who teaches at Truman State University, Missouri in anthro. She has extended the Binford database to include new variables and has an extensive codebook; once I discovered her she was thrilled to join the SFI working group, send the Binford data in *.sav format, the codebook, etc., and agreed to collaborate on making it all web-accessable (probably open access) with her software joining all of yours and ours. Unbeknownst to her I also put her down for a chapter in the "Companion" handbook. The tinkering with here SPSS file is minor (see below) but just slightly out of my pay grade as yet. Might I send you the SPSS file to fix the glitch and create a more workable *.Rdata file? (nice thing is that it has factors but maybe thats what causes the glitch). I am working of creating the Vaux data file and making the whole ensemble compatible with your scripts and ours. This will make the Binford database comparable in quality of variables to SCCS, highly integrated in terms of the coding constructions, lots of worldwide environmental data, twice as large as SCCS (sample N=339), and amenable to Eff-Dow type regression software. I.e., a major advance for cross-cultural studies. As you know, half of our working group project is on foragers and the evolution of human cooperation. Say yes or find me a student to get me over this hump and I will send the Spss file. Best wishes. Doug


Original Message --------

Subject:

Re: Binford forager coding guide

Date: Sun, 11 Mar 2012 18:39:19 -0500

From:

Johnson, Amber <ajohnson@truman.edu>

To:

Doug White <drwhite@uci.edu>