Updated with data: Error in Diff…must be factors

Question

I hope you all can help me.

I have a list with two data frames -- contests and expvar. In the data frame contests, each row is a match with the first column being the winner of the match, and the second column being the loser of the match. In the data frame expvar I have player-specific predictor variables. These are all numbers. I am trying to use the BradleyTerry2 package to analyze my data. Here is the code I am using:

a <- data.frame(read.csv(file.choose()))
b <- data.frame(read.csv(file.choose()))
ablist <- list(contests=a, expvar=b)  
Model <- BTm(1, winner, loser, ~level2[..]+(1|..), data=ablist)

This is the error I get:

Error in Diff(player1, player2, formula, id, data, separate.ability, refcat,  : 
'player1$..' and 'player2$..' must be factors with the same levels

My question is, what am I doing wrong? I have tried many things, but I am not sure what this error means. Should I change my variables into factors? Why/how? The winners and losers all have the same categories of predictor variables.

Here is my output for dput(a)

structure(list(winner = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 
9L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 11L, 
11L, 11L, 11L, 11L, 11L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 
13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 14L, 14L, 
14L, 14L, 14L, 15L, 15L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 
16L, 16L, 16L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 
18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 
20L, 20L, 20L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 22L, 
22L, 22L, 22L, 22L, 23L, 23L, 23L, 23L, 23L, 23L, 23L, 23L, 23L, 
24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 25L, 
25L, 25L, 25L, 25L, 25L, 25L, 25L, 26L, 26L, 26L, 26L, 26L, 26L, 
26L, 27L, 27L, 27L, 27L, 28L, 28L, 29L, 29L, 29L, 29L, 29L, 29L, 
29L, 29L, 29L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 
30L, 30L, 30L, 31L, 31L, 31L, 31L, 31L, 31L, 31L, 31L, 23L, 13L, 
20L, 20L), .Label = c("Arizona Cardinals", "Atlanta Falcons", 
"Baltimore Ravens", "Buffalo Bills", "Carolina Panthers", "Chicago Bears", 
"Cincinnati Bengals", "Cleveland Browns", "Dallas Cowboys", "Denver Broncos", 
"Green Bay Packers", "Houston Texans", "Indianapolis Colts", 
"Jacksonville Jaguars", "Kansas City Chiefs", "Miami Dolphins", 
"Minnesota Vikings", "New England Patriots", "New Orleans Saints", 
"New York Giants", "New York Jets", "Oakland Raiders", "Philadelphia Eagles", 
"Pittsburgh Steelers", "San Diego Chargers", "San Francisco 49ers", 
"Seattle Seahawks", "St. Louis Rams", "Tampa Bay Buccaneers", 
"Tennessee Titans", "Washington Redskins"), class = "factor"), 
    loser = structure(c(4L, 9L, 17L, 27L, 27L, 28L, 28L, 29L, 
    29L, 5L, 6L, 11L, 12L, 16L, 18L, 20L, 23L, 26L, 29L, 30L, 
    7L, 7L, 8L, 8L, 9L, 13L, 15L, 17L, 23L, 24L, 32L, 10L, 15L, 
    16L, 23L, 26L, 28L, 29L, 1L, 2L, 6L, 10L, 11L, 12L, 16L, 
    20L, 20L, 23L, 26L, 30L, 11L, 11L, 12L, 14L, 15L, 18L, 20L, 
    24L, 29L, 8L, 15L, 16L, 32L, 4L, 7L, 15L, 21L, 7L, 8L, 12L, 
    21L, 24L, 27L, 28L, 30L, 32L, 2L, 8L, 16L, 20L, 22L, 23L, 
    26L, 30L, 6L, 11L, 11L, 14L, 18L, 28L, 6L, 7L, 8L, 11L, 12L, 
    15L, 17L, 31L, 3L, 7L, 8L, 11L, 13L, 13L, 15L, 19L, 25L, 
    26L, 31L, 10L, 11L, 12L, 13L, 14L, 10L, 23L, 4L, 4L, 10L, 
    16L, 19L, 22L, 23L, 26L, 27L, 28L, 29L, 1L, 5L, 6L, 11L, 
    11L, 12L, 13L, 15L, 20L, 21L, 1L, 4L, 4L, 10L, 16L, 17L, 
    22L, 23L, 27L, 28L, 29L, 2L, 11L, 12L, 16L, 23L, 26L, 27L, 
    30L, 1L, 3L, 5L, 7L, 9L, 24L, 25L, 27L, 28L, 32L, 1L, 4L, 
    4L, 7L, 16L, 17L, 19L, 29L, 31L, 10L, 13L, 16L, 22L, 30L, 
    1L, 2L, 8L, 9L, 21L, 25L, 27L, 28L, 29L, 3L, 3L, 7L, 7L, 
    8L, 8L, 9L, 13L, 15L, 19L, 26L, 32L, 10L, 16L, 16L, 19L, 
    22L, 23L, 23L, 30L, 4L, 11L, 22L, 28L, 29L, 29L, 32L, 22L, 
    27L, 29L, 29L, 9L, 32L, 2L, 5L, 6L, 11L, 12L, 16L, 18L, 20L, 
    28L, 3L, 6L, 7L, 8L, 11L, 12L, 13L, 14L, 15L, 15L, 16L, 18L, 
    25L, 1L, 8L, 9L, 11L, 20L, 24L, 24L, 28L, 7L, 18L, 29L, 32L
    ), .Label = c("Arizona Cardinals", "Atlanta Falcons", "Baltimore Ravens", 
    "Buffalo Bills", "Carolina Panthers", "Chicago Bears", "Cincinnati Bengals", 
    "Cleveland Browns", "Dallas Cowboys", "Denver Broncos", "Detroit Lions", 
    "Green Bay Packers", "Houston Texans", "Indianapolis Colts", 
    "Jacksonville Jaguars", "Kansas City Chiefs", "Miami Dolphins", 
    "Minnesota Vikings", "New England Patriots", "New Orleans Saints", 
    "New York Giants", "New York Jets", "Oakland Raiders", "Philadelphia Eagles", 
    "Pittsburgh Steelers", "San Diego Chargers", "San Francisco 49ers", 
    "Seattle Seahawks", "St. Louis Rams", "Tampa Bay Buccaneers", 
    "Tennessee Titans", "Washington Redskins"), class = "factor")), .Names = c("winner", 
"loser"), row.names = c(NA, -256L), class = "data.frame")

Here it is for dput(b)

structure(list(X = structure(1:32, .Label = c("Arizona Cardinals", 
"Atlanta Falcons", "Baltimore Ravens", "Buffalo Bills", "Carolina Panthers", 
"Chicago Bears", "Cincinnati Bengals", "Cleveland Browns", "Dallas Cowboys", 
"Denver Broncos", "Detroit Lions", "Green Bay Packers", "Houston Texans", 
"Indianapolis Colts", "Jacksonville Jaguars", "Kansas City Chiefs", 
"Miami Dolphins", "Minnesota Vikings", "New England Patriots", 
"New Orleans Saints", "New York Giants", "New York Jets", "Oakland Raiders", 
"Philadelphia Eagles", "Pittsburgh Steelers", "San Diego Chargers", 
"San Francisco 49ers", "Seattle Seahawks", "St. Louis Rams", 
"Tampa Bay Buccaneers", "Tennessee Titans", "Washington Redskins"
), class = "factor"), id = 1:32, high = c(0L, 0L, 0L, 0L, 0L, 
1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), level2 = c(0, 0.67, 
0, 0.33, 0.25, 0, 0, 0.25, 0.33, 0, 0.25, 0, 0, 0.5, 0, 0, 0.25, 
0.33, 0, 0, 0, 0, 0, 0, 0, 0.67, 0.25, 0, 0.2, 0, 0, 0.6), level3 = c(0.25, 
0.4, 0.36, 0.3, 0.11, 0.56, 0.38, 0.5, 0.22, 0.33, 0.6, 0.3, 
0.57, 0.38, 0.29, 0.43, 0.3, 0.33, 0.29, 0.14, 0.2, 0.22, 0.33, 
0.22, 0.5, 0.27, 0.4, 0.2, 0.43, 0.43, 0.33, 0.44)), .Names = c("X", 
"id", "high", "level2", "level3"), row.names = c(NA, -32L), class = "data.frame"

Thank you

Answer 1

I also got stuck with this error message for the 'BTm' function. The problem can be resolved by defining the levels. (levels are a definable attribute for functions of type factor). Try setting levels for player1 & player2:

    levels(contests[,1]) <- unique(c(contests[,1], contests[,2]))
    levels(contests[,2]) <- unique(c(contests[,1], contests[,2]))

Sorry I couldn't help 3 years ago ;)