Error in check.dataform(data) : Cannot handle columns with class matrix: #363

Jades1 · 2020-06-02T20:09:41Z

Jades1
Jun 2, 2020

Hi, I posted a longer question here: https://stackoverflow.com/questions/62136918/imputing-longitudinal-covariates-with-mice-using-2l-norm, but I'm not sure if you have time to answer it.

However, when I try to use the script remove.collinear = False, I get the following error:

Error in check.dataform(data) : 
  Cannot handle columns with class matrix: per.asianper.blackper.whiteno.grad.hshssome.collegebama.plus

Any help you could give would be appreciated!

Thanks much,
James

This is my prediction matrix

pm <- matrix(ncol = 24, nrow = 24)
rownames(pm) <- c("COUNTY_ID", "PLACE_ID", "year", "STATE", "state", "CITY", "EXPENDITURE_PER_STUDENT", "diff.dem", "cent.EXP_STUDENT", "cent.log.pop.dens", "cent.log.pop", "cent.schooldist.prop5.17.pov", "per_capita_income", "unemployment_rate", "cent.log.officers", "median.inc", 'per.asian', 'per.black',  'per.white', 'no.grad.hs', 'hs', 'some.college','ba', 'ma.plus') 
colnames(pm) <- c("COUNTY_ID", "PLACE_ID", "year", "STATE", "state", "CITY", "EXPENDITURE_PER_STUDENT", "diff.dem", "cent.EXP_STUDENT", "cent.log.pop.dens", "cent.log.pop", "cent.schooldist.prop5.17.pov", "per_capita_income", "unemployment_rate", "cent.log.officers", "median.inc", 'per.asian', 'per.black',  'per.white', 'no.grad.hs', 'hs', 'some.college','ba', 'ma.plus') 

total.years.final$PLACE_ID <- as.integer(total.years.final$PLACE_ID)

pm["COUNTY_ID",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["PLACE_ID",] <- -c(0,0,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["year",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["STATE",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["state",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["CITY",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["EXPENDITURE_PER_STUDENT",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["diff.dem", ] <- c(0,-2,0,0,0,0,0,0,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["cent.EXP_STUDENT",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["cent.log.pop.dens",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["cent.log.pop",] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,2)
pm["per_capita_income", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2)
pm["cent.schooldist.prop5.17.pov", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,0,2,2,2,2,2,2,2,2,2,2,2)
pm["unemployment_rate", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,0,2,2,2,2,2,2,2,2,2,2)
pm["cent.log.officers", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,0,2,2,2,2,2,2,2,2,2)
pm["median.inc", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,0,2,2,2,2,2,2,2,2)
pm["per.asian", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,0,2,2,2,2,2,2,2)
pm["per.black", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,0,2,2,2,2,2,2)
pm["per.white", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,0,2,2,2,2,2)
pm["no.grad.hs", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,0,2,2,2,2)
pm["hs", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,0,2,2,2)
pm["some.college", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,0,2,2)
pm["ba", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,0,2)
pm["ma.plus", ] <- c(0,-2,0,0,0,0,0,2,0,0,0,2,2,2,2,2,2,2,2,2,2,2,2,0)

impmethod <- character(ncol(total.years.final))
names(impmethod) <- colnames(total.years.final)
impmethod[c("diff.dem", "prop5.17.pov", "per_capita_income", "unemployment_rate", "log.officers", "median.inc", 'per.asian', 'per.black',  'per.white', 'no.grad.hs', 'hs', 'some.college','ba', 'ma.plus')] <- "2l.norm"
impmethod[c("COUNTY_ID", "PLACE_ID", "year", "STATE", "state", "CITY", "EXPENDITURE_PER_STUDENT", "cent.EXP_STUDENT", "cent.log.pop.dens", "cent.log.pop")] <- ""

mice.city <- mice(total.years.final, pred = pm,
                    method=impmethod, maxit=10, printFlag = FALSE, seed=123, remove.collinear = FALSE)

and a dput()

structure(list(COUNTY_ID = c("01067", "01067", "01067", "01067", 
"01067", "01067", "01067", "01067", "01067", "01067", "01067", 
"01067", "01067", "01067", "01067", "01067", "01073", "01073", 
"01073", "01073", "01073", "01073", "01073", "01073", "01073", 
"01073", "01073", "01073", "01073", "01073", "01073"), PLACE_ID = c(100124L, 
100124L, 100124L, 100124L, 100124L, 100124L, 100124L, 100124L, 
100124L, 100124L, 100124L, 100124L, 100124L, 100124L, 100124L, 
100124L, 100460L, 100460L, 100460L, 100460L, 100460L, 100460L, 
100460L, 100460L, 100460L, 100460L, 100460L, 100460L, 100460L, 
100460L, 100460L), year = c(2005, 2003, 2006, 2006, 2007, 2008, 
2009, 2010, 2013, 2011, 2012, 2017, 2014, 2018, 2015, 2016, 2005, 
2003, 2006, 2006, 2007, 2009, 2010, 2012, 2011, 2013, 2017, 2018, 
2014, 2015, 2016), STATE = c("alabama", "alabama", "alabama", 
"alabama", "alabama", "alabama", "alabama", "alabama", "alabama", 
"alabama", "alabama", "alabama", "alabama", "alabama", "alabama", 
"alabama", "alabama", "alabama", "alabama", "alabama", "alabama", 
"alabama", "alabama", "alabama", "alabama", "alabama", "alabama", 
"alabama", "alabama", "alabama", "alabama"), state = c("AL", 
"AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", 
"AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", 
"AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL"), CITY = c("abbeville", 
"abbeville", "abbeville", "abbeville", "abbeville", "abbeville", 
"abbeville", "abbeville", "abbeville", "abbeville", "abbeville", 
"abbeville", "abbeville", "abbeville", "abbeville", "abbeville", 
"adamsville", "adamsville", "adamsville", "adamsville", "adamsville", 
"adamsville", "adamsville", "adamsville", "adamsville", "adamsville", 
"adamsville", "adamsville", "adamsville", "adamsville", "adamsville"
), EXPENDITURE_PER_STUDENT = c(6.80427570954663, 6.91392685629849, 
7.42387732749179, 7.42387732749179, 7.80973129992738, 8.57273726639795, 
8.14466546112116, 7.91766361717101, 7.91607343574372, 7.57727272727273, 
7.50594166366583, 8.92486942547208, 8.26783670354826, 9.11440162271805, 
8.4435736677116, 8.48149606299213, 6.31827864279556, 5.93085371942087, 
7.21194954512474, 7.21194954512474, 7.96307522733535, 8.61417039862885, 
9.07166232181485, 8.53174161987882, 8.87169548243168, 8.67074218858299, 
9.10707472837356, 9.26178618857902, 8.80355219180731, 8.79260061661528, 
8.79535631164801), diff.dem = c(-0.329982339356066, -0.329982339356066, 
-0.329982339356066, -0.329982339356066, -0.329982339356066, -0.296831637372803, 
-0.296831637372803, -0.296831637372803, -0.290525114155251, -0.296831637372803, 
-0.290525114155251, -0.413776015857284, -0.290525114155251, -0.413776015857284, 
-0.290525114155251, -0.413776015857284, -0.090092058149894, -0.090092058149894, 
-0.090092058149894, -0.090092058149894, -0.090092058149894, 0.050859589858221, 
0.050859589858221, 0.0598615416000369, 0.050859589858221, 0.0598615416000369, 
0.0726681591500077, 0.0726681591500077, 0.0598615416000369, 0.0598615416000369, 
0.0726681591500077), cent.EXP_STUDENT = c(-3.72218548942621, 
-3.61253434267435, -3.10258387148105, -3.10258387148105, -2.71672989904546, 
-1.95372393257489, -2.38179573785168, -2.60879758180183, -2.61038776322911, 
-2.94918847170011, -3.02051953530701, -1.60159177350076, -2.25862449542457, 
-1.41205957625478, -2.08288753126124, -2.04496513598071, -4.20818255617728, 
-4.59560747955197, -3.31451165384809, -3.31451165384809, -2.56338597163748, 
-1.91229080034399, -1.45479887715798, -1.99471957909402, -1.65476571654116, 
-1.85571901038984, -1.41938647059928, -1.26467501039382, -1.72290900716553, 
-1.73386058235755, -1.73110488732483), cent.log.pop.dens = c(-2.17092393187846, 
-2.14917631925116, -2.17554451944874, -2.17554451944874, -2.18377207435631, 
-2.19897323568836, -2.20923725541581, -2.21757722035684, -2.24625843160356, 
-2.22167787847953, -2.23977109727, -2.2640263768243, -2.25278812639989, 
-2.26519619563581, -2.25548926637909, -2.26130210971813, -1.8854946581827, 
-1.86187562732894, -1.89420421934593, -1.89420421934593, -1.90579233185198, 
-1.922113007463, -2.17806527577796, -2.1887367865658, -2.18383153704235, 
-2.19344162329418, -2.21868457817764, -2.2226075092499, -2.19816870018876, 
-2.20405240125359, -2.21157037720296), cent.log.pop = c(-1.514194735195, 
-1.49244712256769, -1.51881532276528, -1.51881532276528, -1.52704287767285, 
-1.5422440390049, -1.55250805873235, -1.56213419748412, -1.59081540873084, 
-1.56623485560681, -1.58432807439728, -1.60858335395158, -1.59734510352717, 
-1.60975317276309, -1.60004624350637, -1.60585908684542, -0.997429340041226, 
-0.973810309187465, -1.00613890120446, -1.00613890120446, -1.01772701371051, 
-1.03404768932153, -1.04197724628925, -1.05264875707709, -1.04774350755363, 
-1.05735359380546, -1.08259654868892, -1.08651947976118, -1.06208067070004, 
-1.06796437176487, -1.07548234771424), per_capita_income = c(9.75353637577262, 
9.75353637577262, 9.75353637577262, 9.71256914851666, 9.71256914851666, 
9.71256914851666, 9.71256914851666, 9.78447876595393, 9.76370811000784, 
9.65931186839349, 9.75903964817025, 10.0614737245929, 9.81988852865982, 
10.118477957094, 9.86588952212081, 9.94059064048763, 9.8253097714721, 
9.8253097714721, 9.8253097714721, 9.94179438669071, 9.94179438669071, 
9.94179438669071, 10.063094747045, 9.96161494121274, 9.97961491292368, 
10.0361810942616, 10.0623698775963, 9.92842403782616, 10.0601921112938, 
10.0002512209684, 10.0745796273785), prop5.17.pov = c(0.233124308373294, 
0.248632883703974, 0.243491015768244, 0.243491015768244, 0.271125494426465, 
0.237591240875912, 0.260570642832589, 0.255970400269088, 0.268531976744186, 
0.261209239130435, 0.274591588460202, 0.254606995110944, 0.258588843738456, 
NA, 0.270440251572327, 0.256751757306696, 0.160237230177388, 
0.0915986581885545, 0.139011297171701, 0.139011297171701, 0.147240594166757, 
0.165122526177293, 0.196366212865024, 0.189709378115175, 0.193337389717067, 
0.181609254104849, 0.165587347454785, NA, 0.219598733918726, 
0.195454545454545, 0.168561580409507), unemployment_rate = c(1.1314021114911, 
1.1314021114911, 1.1314021114911, 2.21920348405499, 2.21920348405499, 
2.21920348405499, 2.21920348405499, 2.56494935746154, 2.80336038090653, 
2.95491027903374, 2.91777073208428, 1.88706964903238, 2.8094026953625, 
1.84054963339749, 2.3887627892351, 2.12823170584927, 0.470003629245736, 
0.470003629245736, 0.470003629245736, 1.25276296849537, 1.25276296849537, 
1.25276296849537, 1.64865862558738, 2.41591377830105, 2.35137525716348, 
2.57261223020711, 2.34180580614733, 2.45100509811232, 2.62466859216316, 
2.51769647261099, 1.97408102602201), log.officers = c(NA, 2.30258509299405, 
1.94591014905531, 1.94591014905531, 2.30258509299405, 2.30258509299405, 
2.07944154167984, 1.94591014905531, 2.484906649788, 2.39789527279837, 
2.19722457733622, NA, NA, 1.94591014905531, 2.07944154167984, 
2.19722457733622, 2.89037175789616, 2.89037175789616, 2.89037175789616, 
2.89037175789616, 3.04452243772342, 3.04452243772342, 2.83321334405622, 
2.89037175789616, 2.94443897916644, 2.94443897916644, 2.99573227355399, 
2.83321334405622, NA, 2.63905732961526, NA), median.inc = c(9.80394342219974, 
9.80394342219974, 9.80394342219974, 9.86011021256656, 9.86011021256656, 
9.86011021256656, 9.86011021256656, 9.86011021256656, 9.78824503702385, 
9.7326399178158, 9.78543573075999, 9.92034466960255, 9.73453621468034, 
9.96847909604357, 9.69467827290507, 9.77866101958928, 10.1412832351827, 
10.1412832351827, 10.1412832351827, 10.1769439177239, 10.1769439177239, 
10.1769439177239, 10.1769439177239, 10.1393103810074, 10.1791856025852, 
10.1567334476668, 10.2379219999889, 10.1727510394639, 10.1759163835251, 
10.1066732645094, 10.1811950438407), per.asian = structure(c(-0.0233754685357543, 
-0.0233754685357543, -0.0233754685357543, -0.0233754685357543, 
-0.0233754685357543, -0.0240450366643114, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114, 
-0.0226351675807263, -0.0226351675807263, -0.0226351675807263, 
-0.0226351675807263, -0.0226351675807263, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114, 
-0.0240450366643114, -0.0240450366643114, -0.0240450366643114
), .Dim = c(31L, 1L), "`scaled:center`" = 0.0240450366643114), 
    per.black = structure(c(0.307416329153922, 0.307416329153922, 
    0.307416329153922, 0.307416329153922, 0.307416329153922, 
    0.296828599845166, 0.296828599845166, 0.296828599845166, 
    0.296828599845166, 0.296828599845166, 0.296828599845166, 
    0.37441603384553, 0.37441603384553, 0.37441603384553, 0.37441603384553, 
    0.37441603384553, 0.138290365048303, 0.138290365048303, 0.138290365048303, 
    0.138290365048303, 0.138290365048303, 0.262295386499834, 
    0.262295386499834, 0.262295386499834, 0.262295386499834, 
    0.262295386499834, 0.343342026634503, 0.343342026634503, 
    0.343342026634503, 0.343342026634503, 0.343342026634503), .Dim = c(31L, 
    1L), "`scaled:center`" = 0.0893027870161479), per.white = structure(c(-0.209563911114078, 
    -0.209563911114078, -0.209563911114078, -0.209563911114078, 
    -0.209563911114078, -0.279665372678668, -0.279665372678668, 
    -0.279665372678668, -0.279665372678668, -0.279665372678668, 
    -0.279665372678668, -0.244412325798927, -0.244412325798927, 
    -0.244412325798927, -0.244412325798927, -0.244412325798927, 
    -0.0169155399076651, -0.0169155399076651, -0.0169155399076651, 
    -0.0169155399076651, -0.0169155399076651, -0.163825448734554, 
    -0.163825448734554, -0.163825448734554, -0.163825448734554, 
    -0.163825448734554, -0.295799971612129, -0.295799971612129, 
    -0.295799971612129, -0.295799971612129, -0.295799971612129
    ), .Dim = c(31L, 1L), "`scaled:center`" = 0.772001139102026), 
    no.grad.hs = structure(c(-0.12880860596148, -0.12880860596148, 
    0.186134224520635, 0.186134224520635, 0.186134224520635, 
    0.186134224520635, 0.186134224520635, 0.186134224520635, 
    0.206056267988099, 0.228723870329352, 0.208767767095514, 
    0.0776980894098866, 0.200663895322546, 0.0737416957854756, 
    0.177777246455822, 0.0935963809426578, -0.12949860596148, 
    -0.12949860596148, 0.00680242852127813, 0.00680242852127813, 
    0.00680242852127813, 0.00680242852127813, 0.00680242852127813, 
    0.0452070217015808, 0.0380146125020036, 0.0619327496440447, 
    0.0340514402889324, 0.0590924255187606, 0.0560437652996974, 
    0.0793806382811403, 0.0347745353997761), .Dim = c(31L, 1L
    ), "`scaled:center`" = 0.13112860596148), hs = structure(c(-0.266038436726551, 
    -0.266038436726551, 0.00849893496862753, 0.00849893496862753, 
    0.00849893496862753, 0.00849893496862753, 0.00849893496862753, 
    0.00849893496862753, 0.0231631599121042, -0.000678278665434351, 
    -0.0222144470892456, 0.0772043942745251, 0.0223752099092987, 
    0.0990617167938299, 0.0609336497874436, 0.0758308089518143, 
    -0.264318436726551, -0.264318436726551, 0.172558262780838, 
    0.172558262780838, 0.172558262780838, 0.172558262780838, 
    0.172558262780838, 0.148911812372105, 0.148680731784356, 
    0.113297004969562, 0.0712817383642977, 0.0504927287121626, 
    0.12513440632001, 0.0845745798157776, 0.0693678983519827), .Dim = c(31L, 
    1L), "`scaled:center`" = 0.268328436726551), some.college = structure(c(-0.250887288160476, 
    -0.250887288160476, -0.0525036074969198, -0.0525036074969198, 
    -0.0525036074969198, -0.0525036074969198, -0.0525036074969198, 
    -0.0525036074969198, -0.0110106495050139, -0.0518696696146383, 
    -0.00752956795322218, 0.0590181154993732, -0.0225097021306866, 
    0.0263763010401592, -0.0235996545726898, 0.0433591864335522, 
    -0.250697288160476, -0.250697288160476, 0.0531193128247456, 
    0.0531193128247456, 0.0531193128247456, 0.0531193128247456, 
    0.0531193128247456, 0.0312340753269051, 0.036991194292891, 
    0.0345754937219525, 0.0962529695203961, 0.0712373200109908, 
    0.0128876239579328, 0.0347751315605749, 0.0844345966562778
    ), .Dim = c(31L, 1L), "`scaled:center`" = 0.252607288160476), 
    ba = structure(c(-0.13703822478782, -0.13703822478782, 0.0109535274153938, 
    0.0109535274153938, 0.0109535274153938, 0.0109535274153938, 
    0.0109535274153938, 0.0109535274153938, -0.0616727626029464, 
    -0.0134868127751755, -0.022802318052069, -0.0775483539589721, 
    -0.0546232941252626, -0.0870076848195832, -0.0701437464163191, 
    -0.0770634264640906, -0.13677822478782, -0.13677822478782, 
    -0.0633208356252588, -0.0633208356252588, -0.0633208356252588, 
    -0.0633208356252588, -0.0633208356252588, -0.0549045931916224, 
    -0.0568924043641719, -0.0427430979005733, -0.0443363186100866, 
    -0.010232779375898, -0.0342204542050266, -0.0460345173599903, 
    -0.0393334603899146), .Dim = c(31L, 1L), "`scaled:center`" = 0.13782822478782), 
    ma.plus = structure(c(-0.0789157233500541, -0.0789157233500541, 
    -0.0224813583941184, -0.0224813583941184, -0.0224813583941184, 
    -0.0224813583941184, -0.0224813583941184, -0.0224813583941184, 
    -0.0259342947786255, -0.0320873882604861, -0.0256197129873598, 
    -0.00577052421119512, -0.0153043879622781, 0.0184296922137362, 
    -0.0143657742406394, -0.00512122885031603, -0.0792357233500541, 
    -0.0792357233500541, -0.0385574474879851, -0.0385574474879851, 
    -0.0385574474879851, -0.0385574474879851, -0.0385574474879851, 
    -0.0398465951953507, -0.036192413201461, -0.036460429421368, 
    -0.026648108549922, -0.0399879738523984, -0.0292436203589964, 
    -0.0220941112838848, -0.0186418490045044), .Dim = c(31L, 
    1L), "`scaled:center`" = 0.0795057233500541)), row.names = c(NA, 
-31L), class = c("tbl_df", "tbl", "data.frame"))

stefvanbuuren · 2020-06-02T21:17:20Z

stefvanbuuren
Jun 2, 2020
Maintainer

mice cannot handle nested matrices or nested data.frames. The solution is to transform your input data to a conventional data frame. Hope this helps.

0 replies

Jades1 · 2020-06-02T22:57:07Z

Jades1
Jun 2, 2020
Author

Thanks. I fixed the final few columns that were causing that. I now have this error:

Error in isclassvar[j] && lapply(data, is.factor)[[j]] : 
  invalid 'y' type in 'x && y'

I did some googling but couldn't find the same issue. It seems that it wants me to use lapply and that it thinks this is a list, but there should only be a matrix, correct? It's odd because when I don't add the final 8 variables (which have collinearity), I don't receive this warning.

0 replies

stefvanbuuren · 2020-06-03T07:42:59Z

stefvanbuuren
Jun 3, 2020
Maintainer

I have no idea where this comes from. I'd be happy to take a look at a reproducible example.

For now, I would suggest deleting remove.collinear = FALSE, and calculate any variables you need afterwards.

0 replies

Jades1 · 2020-06-03T18:24:21Z

Jades1
Jun 3, 2020
Author

Okay, thanks. I've included the dput and the matrix above. I thought that would be enough for a reproducible example. Is there more you need?

0 replies

stefvanbuuren · 2020-06-03T19:02:03Z

stefvanbuuren
Jun 3, 2020
Maintainer

Yes, a smaller example. There's a lot going on in your data. There are matrices, text variables, and so on, that all could cause a problems. There is a row in pm with all -2. Please make it a little easier for me, and tidy up things a little.

0 replies

Jades1 · 2020-06-04T17:34:42Z

Jades1
Jun 4, 2020
Author

Sorry--I'd classify myself as "intermediate," so while I read through posts like Stack Overflows "minimum reproducible code," it isn't always imminently clear to me how my own example deviates from that. Oddly, I was able to get it to run (perhaps it was the row with "-2s." It does take a very long time (I ran two iterations). I received 5 logged issues.

and when I look at the trace plots of two of the variables, their awful:

Is this because of using 2l.norm, or because of the collinearity. Would more iterations solve the issue, or is this something I just won't get around because of the collinearity? Should I look at something like 2l.pan or another function?

0 replies

stefvanbuuren · 2020-06-04T19:43:19Z

stefvanbuuren
Jun 4, 2020
Maintainer

Great that you managed to get by. Simplying often solves the problem. You might find https://reprex.tidyverse.org/articles/reprex-dos-and-donts.html helpful.

For your problem, I would do some more iterations (10-20) to see chain covergence Two won't work. You could perhaps also consider a simpler model with fixed effects if you have a reasonable number of observations per class.

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Error in check.dataform(data) : Cannot handle columns with class matrix: #363

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Replies: 7 comments

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

Select a reply

Error in check.dataform(data) : Cannot handle columns with class matrix: #363

Jades1 Jun 2, 2020

Replies: 7 comments

stefvanbuuren Jun 2, 2020 Maintainer

Jades1 Jun 2, 2020 Author

stefvanbuuren Jun 3, 2020 Maintainer

Jades1 Jun 3, 2020 Author

stefvanbuuren Jun 3, 2020 Maintainer

Jades1 Jun 4, 2020 Author

stefvanbuuren Jun 4, 2020 Maintainer

Jades1
Jun 2, 2020

stefvanbuuren
Jun 2, 2020
Maintainer

Jades1
Jun 2, 2020
Author

stefvanbuuren
Jun 3, 2020
Maintainer

Jades1
Jun 3, 2020
Author

stefvanbuuren
Jun 3, 2020
Maintainer

Jades1
Jun 4, 2020
Author

stefvanbuuren
Jun 4, 2020
Maintainer