急求解决 "duplicate 'row.names' are not allowed" in R plm package: There are no duplicates
Desperate to solve "duplicate 'row.names' are not allowed" in R plm package: There are no duplicates
我需要帮助解决以下代码末尾的错误。我不明白发生了什么。
library(plm)
sessionInfo()
# R version 4.0.3 (2020-10-10)
# Platform: x86_64-w64-mingw32/x64 (64-bit)
# Running under: Windows 10 x64 (build 19042)
#
# Matrix products: default
#
# locale:
# [1] LC_COLLATE=Spanish_Spain.1252 LC_CTYPE=Spanish_Spain.1252
# [3] LC_MONETARY=Spanish_Spain.1252 LC_NUMERIC=C
# [5] LC_TIME=Spanish_Spain.1252
#
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
#
# other attached packages:
# [1] plm_2.2-5
#
# loaded via a namespace (and not attached):
# [1] bdsmatrix_1.3-4 lattice_0.20-41 zoo_1.8-8 digest_0.6.27
# [5] lmtest_0.9-38 rbibutils_2.0 MASS_7.3-53 grid_4.0.3
# [9] nlme_3.1-149 Rdpack_2.1 miscTools_0.6-26 sandwich_3.0-0
# [13] Formula_1.2-4 tools_4.0.3 tinytex_0.28 xfun_0.20
# [17] compiler_4.0.3 gbRd_0.4-11 maxLik_1.4-6
load("Errordug.RData")
class(gust)
# [1] "data.frame"
summary(gust)
# ETreg year Country ETregName
# Length:33 Min. :2007 Length:33 Length:33
# Class :character 1st Qu.:2009 Class :character Class :character
# Mode :character Median :2012 Mode :character Mode :character
# Mean :2012
# 3rd Qu.:2015
# Max. :2017
# du g
# Min. :-4.4000 Min. :-15.000
# 1st Qu.:-1.2000 1st Qu.: -0.800
# Median : 0.0000 Median : 2.600
# Mean : 0.2212 Mean : 1.724
# 3rd Qu.: 0.9000 3rd Qu.: 4.600
# Max. : 8.0000 Max. : 8.500
dput(gust)
structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
"CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
"EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
"EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
"LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017), Country = c("CY",
"CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
"EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
"LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU"),
ETregName = c("Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
"Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
"Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
"Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
"Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
"Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"),
du = c(`CY00-2007` = -0.6, `CY00-2008` = -0.2, `CY00-2009` = 1.7,
`CY00-2010` = 0.899999999999999, `CY00-2011` = 1.6, `CY00-2012` = 3.9,
`CY00-2013` = 4.1, `CY00-2014` = 0.200000000000001, `CY00-2015` = -1.2,
`CY00-2016` = -2, `CY00-2017` = -1.8, `EE00-2007` = -1.3,
`EE00-2008` = 0.9, `EE00-2009` = 8, `EE00-2010` = 3.2, `EE00-2011` = -4.4,
`EE00-2012` = -2.3, `EE00-2013` = -1.4, `EE00-2014` = -1.2,
`EE00-2015` = -1.2, `EE00-2016` = 0.6, `EE00-2017` = -1,
`LU00-2007` = -0.600000000000001, `LU00-2008` = 1, `LU00-2009` = 0,
`LU00-2010` = -0.699999999999999, `LU00-2011` = 0.5, `LU00-2012` = 0.199999999999999,
`LU00-2013` = 0.7, `LU00-2014` = 0.100000000000001, `LU00-2015` = 0.8,
`LU00-2016` = -0.4, `LU00-2017` = -0.8), g = c(5.1, 3.6,
-2, 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15,
4.1, 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6,
5, 2, -0.8, 3.6, 3.9, 4.6, 4.9, 1.7)), row.names = c(NA,
-33L), class = "data.frame")
pdim(gust)
# Balanced Panel: n = 3, T = 11, N = 33
sum(is.na(gust))
# [1] 0
any(duplicated(rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))))
# [1] FALSE
rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))
# [1] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" "CY00-2011"
# [6] "CY00-2012" "CY00-2013" "CY00-2014" "CY00-2015" "CY00-2016"
# [11] "CY00-2017" "EE00-2007" "EE00-2008" "EE00-2009" "EE00-2010"
# [16] "EE00-2011" "EE00-2012" "EE00-2013" "EE00-2014" "EE00-2015"
# [21] "EE00-2016" "EE00-2017" "LU00-2007" "LU00-2008" "LU00-2009"
# [26] "LU00-2010" "LU00-2011" "LU00-2012" "LU00-2013" "LU00-2014"
# [31] "LU00-2015" "LU00-2016" "LU00-2017"
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Error in `.rowNamesDF<-`(x, value = value) :
# duplicate 'row.names' are not allowed
# Además: Warning messages:
# 1: In `[.data.frame`(index, as.numeric(rownames(mf)), ) :
# NAs introducidos por coerción
# 2: In plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling") :
# NAs introducidos por coerción
# 3: non-unique values when setting 'row.names':
这看起来像是 plm 函数中的错误。 gust 中的 du 列已命名值；这导致 plm 崩溃。
您可以通过删除这些名称来解决此错误：
gust$du <- unname(gust$du)
在我这样做之后，我得到了成功的结果：
> summary(plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling"))
Pooling Model
Call:
plm(formula = du ~ g, data = gust, model = "pooling", index = c("ETreg",
"year"))
Balanced Panel: n = 3, T = 11, N = 33
Residuals:
Min. 1st Qu. Median 3rd Qu. Max.
-2.53175 -1.02819 0.27557 0.77953 3.84676
Coefficients:
Estimate Std. Error t-value Pr(>|t|)
(Intercept) 0.851158 0.263640 3.2285 0.002939 **
g -0.365347 0.053228 -6.8639 1.079e-07 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Total Sum of Squares: 157.46
Residual Sum of Squares: 62.488
R-Squared: 0.60314
Adj. R-Squared: 0.59034
F-statistic: 47.1127 on 1 and 31 DF, p-value: 1.0794e-07
关于我如何到达检测到的问题的可重现的详细信息。
library(plm)
# I have needed eurostat package to create the dataframes g and u
library(eurostat)
sessionInfo()
# R version 4.0.3 (2020-10-10)
# Platform: x86_64-w64-mingw32/x64 (64-bit)
# Running under: Windows 10 x64 (build 19042)
# Matrix products: default
# locale:
# [1] LC_COLLATE=Spanish_Spain.1252 LC_CTYPE=Spanish_Spain.1252
# [3] LC_MONETARY=Spanish_Spain.1252 LC_NUMERIC=C
# [5] LC_TIME=Spanish_Spain.1252
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
# other attached packages:
# [1] plm_2.2-5 eurostat_3.6.84
# loaded via a namespace (and not attached):
# [1] tinytex_0.28 zoo_1.8-8 tidyselect_1.1.0
# [4] xfun_0.20 purrr_0.3.4 sf_0.9-7
# [7] lattice_0.20-41 vctrs_0.3.6 generics_0.1.0
# [10] utf8_1.1.4 rlang_0.4.10 e1071_1.7-4
# [13] pillar_1.4.7 glue_1.4.2 DBI_1.1.0
# [16] sp_1.4-4 RColorBrewer_1.1-2 lifecycle_0.2.0
# [19] plyr_1.8.6 stringr_1.4.0 bdsmatrix_1.3-4
# [22] miscTools_0.6-26 gbRd_0.4-11 lmtest_0.9-38
# [25] curl_4.3 class_7.3-17 fansi_0.4.1
# [28] broom_0.7.3 Rcpp_1.0.5 KernSmooth_2.23-17
# [31] readr_1.4.0 backports_1.2.1 classInt_0.4-3
# [34] jsonlite_1.7.2 countrycode_1.2.0 maxLik_1.4-6
# [37] digest_0.6.27 hms_0.5.3 stringi_1.5.3
# [40] dplyr_1.0.2 rbibutils_2.0 grid_4.0.3
# [43] Rdpack_2.1 cli_2.2.0 tools_4.0.3
# [46] sandwich_3.0-0 magrittr_2.0.1 tibble_3.0.4
# [49] Formula_1.2-4 RefManageR_1.3.0 crayon_1.3.4
# [52] tidyr_1.1.2 pkgconfig_2.0.3 ellipsis_0.3.1
# [55] MASS_7.3-53 xml2_1.3.2 lubridate_1.7.9.2
# [58] assertthat_0.2.1 httr_1.4.2 R6_2.5.0
# [61] nlme_3.1-149 units_0.6-7 compiler_4.0.3
ls()
# [1] "g" "u"
dput(g)
# structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017), g = c(5.1, 3.6, -2,
# 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15, 4.1,
# 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6, 5, 2, -0.8,
# 3.6, 3.9, 4.6, 4.9, 1.7), ETregName = c("Kypros", "Kypros", "Kypros",
# "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Kypros", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
# "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"), Country = c("CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
# "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU")), row.names = c(NA,
# -33L), class = c("tbl_df", "tbl", "data.frame"))
dput(u)
# structure(list(ETreg = c("CY", "CY", "CY", "CY", "CY", "CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY0", "CY0", "CY0", "CY0",
# "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "EE", "EE", "EE", "EE", "EE", "EE", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE0", "EE0", "EE0", "EE0", "EE0",
# "EE0", "EE0", "EE0", "EE0", "EE0", "EE0", "EE0", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "EE00", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU",
# "LU", "LU", "LU", "LU", "LU0", "LU0", "LU0", "LU0", "LU0", "LU0",
# "LU0", "LU0", "LU0", "LU0", "LU0", "LU0", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00"), year = c(2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013,
# 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010, 2011, 2012,
# 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010, 2011,
# 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009,
# 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008,
# 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007,
# 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006,
# 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017,
# 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016,
# 2017), u = c(4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7,
# 6.3, 5.5, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3,
# 5.5, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3, 5.5
# )), row.names = c(NA, -108L), class = c("tbl_df", "tbl", "data.frame"
# ))
u.pd <- pdata.frame(u,index = c("ETreg", "year"))
u.pd$du <- diff(u.pd$u)
class(u.pd$du)
# [1] "pseries" "numeric"
u$du <- u.pd$du
head(u)
# A tibble: 6 x 4
# ETreg year u du
# <chr<dbl<dbl<pseries>
# 1 CY 2006 4.5 NA
# 2 CY 2007 3.9 -0.6
# 3 CY 2008 3.7 -0.2
# 4 CY 2009 5.4 1.7
# 5 CY 2010 6.3 0.9
# 6 CY 2011 7.9 1.6
class(u$du)
# [1] "pseries" "numeric"
gust <- merge(g, u, by=c("ETreg", "year"))
gust <- gust[ c("ETreg","year", "Country", "ETregName", "u", "du", "g" )]
class(gust$du)
# [1] "numeric"
dput(gust)
# structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017), Country = c("CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
# "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU"),
# ETregName = c("Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
# "Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"),
# u = c(3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1, 14.9, 12.9,
# 11.1, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4, 6.2, 6.8,
# 5.8, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3, 5.5
# ), du = c(`CY00-2007` = -0.6, `CY00-2008` = -0.2, `CY00-2009` = 1.7,
# `CY00-2010` = 0.899999999999999, `CY00-2011` = 1.6, `CY00-2012` = 3.9,
# `CY00-2013` = 4.1, `CY00-2014` = 0.200000000000001, `CY00-2015` = -1.2,
# `CY00-2016` = -2, `CY00-2017` = -1.8, `EE00-2007` = -1.3,
# `EE00-2008` = 0.9, `EE00-2009` = 8, `EE00-2010` = 3.2, `EE00-2011` = -4.4,
# `EE00-2012` = -2.3, `EE00-2013` = -1.4, `EE00-2014` = -1.2,
# `EE00-2015` = -1.2, `EE00-2016` = 0.6, `EE00-2017` = -1,
# `LU00-2007` = -0.600000000000001, `LU00-2008` = 1, `LU00-2009` = 0,
# `LU00-2010` = -0.699999999999999, `LU00-2011` = 0.5, `LU00-2012` = 0.199999999999999,
# `LU00-2013` = 0.7, `LU00-2014` = 0.100000000000001, `LU00-2015` = 0.8,
# `LU00-2016` = -0.4, `LU00-2017` = -0.8), g = c(5.1, 3.6,
# -2, 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15,
# 4.1, 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6,
# 5, 2, -0.8, 3.6, 3.9, 4.6, 4.9, 1.7)), row.names = c(NA,
# -33L), class = "data.frame")
pdim(gust)
# Balanced Panel: n = 3, T = 11, N = 33
sum(is.na(gust))
# [1] 0
any(duplicated(rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))))
# [1] FALSE
rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))
# [1] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" "CY00-2011"
# [6] "CY00-2012" "CY00-2013" "CY00-2014" "CY00-2015" "CY00-2016"
# [11] "CY00-2017" "EE00-2007" "EE00-2008" "EE00-2009" "EE00-2010"
# [16] "EE00-2011" "EE00-2012" "EE00-2013" "EE00-2014" "EE00-2015"
# [21] "EE00-2016" "EE00-2017" "LU00-2007" "LU00-2008" "LU00-2009"
# [26] "LU00-2010" "LU00-2011" "LU00-2012" "LU00-2013" "LU00-2014"
# [31] "LU00-2015" "LU00-2016" "LU00-2017"
str(gust$g)
# num [1:33] 5.1 3.6 -2 2 0.4 -3.4 -6.6 -1.9 3.4 6.7 ...
str(gust$du)
# Named num [1:33] -0.6 -0.2 1.7 0.9 1.6 ...
# - attr(*, "names")= chr [1:33] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" ...
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Error in `.rowNamesDF<-`(x, value = value) :
# duplicate 'row.names' are not allowed
# Además: Warning messages:
# 1: In `[.data.frame`(index, as.numeric(rownames(mf)), ) :
# NAs introducidos por coerción
# 2: In plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling") :
# NAs introducidos por coerción
# 3: non-unique values when setting 'row.names':
# Timing stopped at: 0.71 0.14 7.11
gust$du <- unname(gust$du)
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Pooling Model
# Call:
# plm(formula = du ~ g, data = gust, model = "pooling", index = c("ETreg",
# "year"))
# Balanced Panel: n = 3, T = 11, N = 33
# Residuals:
# Min. 1st Qu. Median 3rd Qu. Max.
# -2.53175 -1.02819 0.27557 0.77953 3.84676
# Coefficients:
# Estimate Std. Error t-value Pr(>|t|)
# (Intercept) 0.851158 0.263640 3.2285 0.002939 **
# g -0.365347 0.053228 -6.8639 1.079e-07 ***
# ---
# Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
# Total Sum of Squares: 157.46
# Residual Sum of Squares: 62.488
# R-Squared: 0.60314
# Adj. R-Squared: 0.59034
# F-statistic: 47.1127 on 1 and 31 DF, p-value: 1.0794e-07
这是一个简短的例子，说明了数据框和 tibble（tibble 3.0.4）在添加具有 names 属性的向量的行为方面的区别：
library(tibble)
a <- 1:5
df <- data.frame(a, a * 2)
tb <- tibble(df)
b <- 6:10
names(b) <- letters[1:5]
df$b <- b
tb$b <- b
lapply(df, names) # data frame's columns do not have names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> NULL
lapply(tb, names) # tibble's column b preserved names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> [1] "a" "b" "c" "d" "e"
df_tb <- as.data.frame(tb)
lapply(df_tb, names) # data frame's column b has names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> [1] "a" "b" "c" "d" "e"
我需要帮助解决以下代码末尾的错误。我不明白发生了什么。
library(plm)
sessionInfo()
# R version 4.0.3 (2020-10-10)
# Platform: x86_64-w64-mingw32/x64 (64-bit)
# Running under: Windows 10 x64 (build 19042)
#
# Matrix products: default
#
# locale:
# [1] LC_COLLATE=Spanish_Spain.1252 LC_CTYPE=Spanish_Spain.1252
# [3] LC_MONETARY=Spanish_Spain.1252 LC_NUMERIC=C
# [5] LC_TIME=Spanish_Spain.1252
#
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
#
# other attached packages:
# [1] plm_2.2-5
#
# loaded via a namespace (and not attached):
# [1] bdsmatrix_1.3-4 lattice_0.20-41 zoo_1.8-8 digest_0.6.27
# [5] lmtest_0.9-38 rbibutils_2.0 MASS_7.3-53 grid_4.0.3
# [9] nlme_3.1-149 Rdpack_2.1 miscTools_0.6-26 sandwich_3.0-0
# [13] Formula_1.2-4 tools_4.0.3 tinytex_0.28 xfun_0.20
# [17] compiler_4.0.3 gbRd_0.4-11 maxLik_1.4-6
load("Errordug.RData")
class(gust)
# [1] "data.frame"
summary(gust)
# ETreg year Country ETregName
# Length:33 Min. :2007 Length:33 Length:33
# Class :character 1st Qu.:2009 Class :character Class :character
# Mode :character Median :2012 Mode :character Mode :character
# Mean :2012
# 3rd Qu.:2015
# Max. :2017
# du g
# Min. :-4.4000 Min. :-15.000
# 1st Qu.:-1.2000 1st Qu.: -0.800
# Median : 0.0000 Median : 2.600
# Mean : 0.2212 Mean : 1.724
# 3rd Qu.: 0.9000 3rd Qu.: 4.600
# Max. : 8.0000 Max. : 8.500
dput(gust)
structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
"CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
"EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
"EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
"LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017), Country = c("CY",
"CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
"EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
"LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU"),
ETregName = c("Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
"Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
"Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
"Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
"Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
"Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"),
du = c(`CY00-2007` = -0.6, `CY00-2008` = -0.2, `CY00-2009` = 1.7,
`CY00-2010` = 0.899999999999999, `CY00-2011` = 1.6, `CY00-2012` = 3.9,
`CY00-2013` = 4.1, `CY00-2014` = 0.200000000000001, `CY00-2015` = -1.2,
`CY00-2016` = -2, `CY00-2017` = -1.8, `EE00-2007` = -1.3,
`EE00-2008` = 0.9, `EE00-2009` = 8, `EE00-2010` = 3.2, `EE00-2011` = -4.4,
`EE00-2012` = -2.3, `EE00-2013` = -1.4, `EE00-2014` = -1.2,
`EE00-2015` = -1.2, `EE00-2016` = 0.6, `EE00-2017` = -1,
`LU00-2007` = -0.600000000000001, `LU00-2008` = 1, `LU00-2009` = 0,
`LU00-2010` = -0.699999999999999, `LU00-2011` = 0.5, `LU00-2012` = 0.199999999999999,
`LU00-2013` = 0.7, `LU00-2014` = 0.100000000000001, `LU00-2015` = 0.8,
`LU00-2016` = -0.4, `LU00-2017` = -0.8), g = c(5.1, 3.6,
-2, 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15,
4.1, 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6,
5, 2, -0.8, 3.6, 3.9, 4.6, 4.9, 1.7)), row.names = c(NA,
-33L), class = "data.frame")
pdim(gust)
# Balanced Panel: n = 3, T = 11, N = 33
sum(is.na(gust))
# [1] 0
any(duplicated(rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))))
# [1] FALSE
rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))
# [1] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" "CY00-2011"
# [6] "CY00-2012" "CY00-2013" "CY00-2014" "CY00-2015" "CY00-2016"
# [11] "CY00-2017" "EE00-2007" "EE00-2008" "EE00-2009" "EE00-2010"
# [16] "EE00-2011" "EE00-2012" "EE00-2013" "EE00-2014" "EE00-2015"
# [21] "EE00-2016" "EE00-2017" "LU00-2007" "LU00-2008" "LU00-2009"
# [26] "LU00-2010" "LU00-2011" "LU00-2012" "LU00-2013" "LU00-2014"
# [31] "LU00-2015" "LU00-2016" "LU00-2017"
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Error in `.rowNamesDF<-`(x, value = value) :
# duplicate 'row.names' are not allowed
# Además: Warning messages:
# 1: In `[.data.frame`(index, as.numeric(rownames(mf)), ) :
# NAs introducidos por coerción
# 2: In plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling") :
# NAs introducidos por coerción
# 3: non-unique values when setting 'row.names':
这看起来像是 plm 函数中的错误。 gust 中的 du 列已命名值；这导致 plm 崩溃。
您可以通过删除这些名称来解决此错误：
gust$du <- unname(gust$du)
在我这样做之后，我得到了成功的结果：
> summary(plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling"))
Pooling Model
Call:
plm(formula = du ~ g, data = gust, model = "pooling", index = c("ETreg",
"year"))
Balanced Panel: n = 3, T = 11, N = 33
Residuals:
Min. 1st Qu. Median 3rd Qu. Max.
-2.53175 -1.02819 0.27557 0.77953 3.84676
Coefficients:
Estimate Std. Error t-value Pr(>|t|)
(Intercept) 0.851158 0.263640 3.2285 0.002939 **
g -0.365347 0.053228 -6.8639 1.079e-07 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Total Sum of Squares: 157.46
Residual Sum of Squares: 62.488
R-Squared: 0.60314
Adj. R-Squared: 0.59034
F-statistic: 47.1127 on 1 and 31 DF, p-value: 1.0794e-07
关于我如何到达检测到的问题的可重现的详细信息。
library(plm)
# I have needed eurostat package to create the dataframes g and u
library(eurostat)
sessionInfo()
# R version 4.0.3 (2020-10-10)
# Platform: x86_64-w64-mingw32/x64 (64-bit)
# Running under: Windows 10 x64 (build 19042)
# Matrix products: default
# locale:
# [1] LC_COLLATE=Spanish_Spain.1252 LC_CTYPE=Spanish_Spain.1252
# [3] LC_MONETARY=Spanish_Spain.1252 LC_NUMERIC=C
# [5] LC_TIME=Spanish_Spain.1252
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
# other attached packages:
# [1] plm_2.2-5 eurostat_3.6.84
# loaded via a namespace (and not attached):
# [1] tinytex_0.28 zoo_1.8-8 tidyselect_1.1.0
# [4] xfun_0.20 purrr_0.3.4 sf_0.9-7
# [7] lattice_0.20-41 vctrs_0.3.6 generics_0.1.0
# [10] utf8_1.1.4 rlang_0.4.10 e1071_1.7-4
# [13] pillar_1.4.7 glue_1.4.2 DBI_1.1.0
# [16] sp_1.4-4 RColorBrewer_1.1-2 lifecycle_0.2.0
# [19] plyr_1.8.6 stringr_1.4.0 bdsmatrix_1.3-4
# [22] miscTools_0.6-26 gbRd_0.4-11 lmtest_0.9-38
# [25] curl_4.3 class_7.3-17 fansi_0.4.1
# [28] broom_0.7.3 Rcpp_1.0.5 KernSmooth_2.23-17
# [31] readr_1.4.0 backports_1.2.1 classInt_0.4-3
# [34] jsonlite_1.7.2 countrycode_1.2.0 maxLik_1.4-6
# [37] digest_0.6.27 hms_0.5.3 stringi_1.5.3
# [40] dplyr_1.0.2 rbibutils_2.0 grid_4.0.3
# [43] Rdpack_2.1 cli_2.2.0 tools_4.0.3
# [46] sandwich_3.0-0 magrittr_2.0.1 tibble_3.0.4
# [49] Formula_1.2-4 RefManageR_1.3.0 crayon_1.3.4
# [52] tidyr_1.1.2 pkgconfig_2.0.3 ellipsis_0.3.1
# [55] MASS_7.3-53 xml2_1.3.2 lubridate_1.7.9.2
# [58] assertthat_0.2.1 httr_1.4.2 R6_2.5.0
# [61] nlme_3.1-149 units_0.6-7 compiler_4.0.3
ls()
# [1] "g" "u"
dput(g)
# structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017), g = c(5.1, 3.6, -2,
# 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15, 4.1,
# 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6, 5, 2, -0.8,
# 3.6, 3.9, 4.6, 4.9, 1.7), ETregName = c("Kypros", "Kypros", "Kypros",
# "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Kypros", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
# "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"), Country = c("CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
# "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU")), row.names = c(NA,
# -33L), class = c("tbl_df", "tbl", "data.frame"))
dput(u)
# structure(list(ETreg = c("CY", "CY", "CY", "CY", "CY", "CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY0", "CY0", "CY0", "CY0",
# "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY0", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "EE", "EE", "EE", "EE", "EE", "EE", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE0", "EE0", "EE0", "EE0", "EE0",
# "EE0", "EE0", "EE0", "EE0", "EE0", "EE0", "EE0", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "EE00", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU",
# "LU", "LU", "LU", "LU", "LU0", "LU0", "LU0", "LU0", "LU0", "LU0",
# "LU0", "LU0", "LU0", "LU0", "LU0", "LU0", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00"), year = c(2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013,
# 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010, 2011, 2012,
# 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010, 2011,
# 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008, 2009,
# 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007, 2008,
# 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006, 2007,
# 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2006,
# 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017,
# 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016,
# 2017), u = c(4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 4.5, 3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1,
# 14.9, 12.9, 11.1, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 5.9, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4,
# 6.2, 6.8, 5.8, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7,
# 6.3, 5.5, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3,
# 5.5, 4.7, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3, 5.5
# )), row.names = c(NA, -108L), class = c("tbl_df", "tbl", "data.frame"
# ))
u.pd <- pdata.frame(u,index = c("ETreg", "year"))
u.pd$du <- diff(u.pd$u)
class(u.pd$du)
# [1] "pseries" "numeric"
u$du <- u.pd$du
head(u)
# A tibble: 6 x 4
# ETreg year u du
# <chr<dbl<dbl<pseries>
# 1 CY 2006 4.5 NA
# 2 CY 2007 3.9 -0.6
# 3 CY 2008 3.7 -0.2
# 4 CY 2009 5.4 1.7
# 5 CY 2010 6.3 0.9
# 6 CY 2011 7.9 1.6
class(u$du)
# [1] "pseries" "numeric"
gust <- merge(g, u, by=c("ETreg", "year"))
gust <- gust[ c("ETreg","year", "Country", "ETregName", "u", "du", "g" )]
class(gust$du)
# [1] "numeric"
dput(gust)
# structure(list(ETreg = c("CY00", "CY00", "CY00", "CY00", "CY00",
# "CY00", "CY00", "CY00", "CY00", "CY00", "CY00", "EE00", "EE00",
# "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00", "EE00",
# "EE00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00", "LU00",
# "LU00", "LU00", "LU00", "LU00"), year = c(2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2007, 2008, 2009, 2010,
# 2011, 2012, 2013, 2014, 2015, 2016, 2017), Country = c("CY",
# "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "CY", "EE",
# "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "EE", "LU",
# "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU", "LU"),
# ETregName = c("Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Kypros", "Kypros", "Kypros", "Kypros", "Kypros", "Kypros",
# "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti", "Eesti",
# "Eesti", "Eesti", "Eesti", "Eesti", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg",
# "Luxembourg", "Luxembourg", "Luxembourg", "Luxembourg"),
# u = c(3.9, 3.7, 5.4, 6.3, 7.9, 11.8, 15.9, 16.1, 14.9, 12.9,
# 11.1, 4.6, 5.5, 13.5, 16.7, 12.3, 10, 8.6, 7.4, 6.2, 6.8,
# 5.8, 4.1, 5.1, 5.1, 4.4, 4.9, 5.1, 5.8, 5.9, 6.7, 6.3, 5.5
# ), du = c(`CY00-2007` = -0.6, `CY00-2008` = -0.2, `CY00-2009` = 1.7,
# `CY00-2010` = 0.899999999999999, `CY00-2011` = 1.6, `CY00-2012` = 3.9,
# `CY00-2013` = 4.1, `CY00-2014` = 0.200000000000001, `CY00-2015` = -1.2,
# `CY00-2016` = -2, `CY00-2017` = -1.8, `EE00-2007` = -1.3,
# `EE00-2008` = 0.9, `EE00-2009` = 8, `EE00-2010` = 3.2, `EE00-2011` = -4.4,
# `EE00-2012` = -2.3, `EE00-2013` = -1.4, `EE00-2014` = -1.2,
# `EE00-2015` = -1.2, `EE00-2016` = 0.6, `EE00-2017` = -1,
# `LU00-2007` = -0.600000000000001, `LU00-2008` = 1, `LU00-2009` = 0,
# `LU00-2010` = -0.699999999999999, `LU00-2011` = 0.5, `LU00-2012` = 0.199999999999999,
# `LU00-2013` = 0.7, `LU00-2014` = 0.100000000000001, `LU00-2015` = 0.8,
# `LU00-2016` = -0.4, `LU00-2017` = -0.8), g = c(5.1, 3.6,
# -2, 2, 0.4, -3.4, -6.6, -1.9, 3.4, 6.7, 4.4, 7.1, -2.9, -15,
# 4.1, 7.6, 2.6, 1.1, 2.8, 1.7, 2.1, 6.7, 8.5, -1.5, -4.6,
# 5, 2, -0.8, 3.6, 3.9, 4.6, 4.9, 1.7)), row.names = c(NA,
# -33L), class = "data.frame")
pdim(gust)
# Balanced Panel: n = 3, T = 11, N = 33
sum(is.na(gust))
# [1] 0
any(duplicated(rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))))
# [1] FALSE
rownames(pdata.frame(gust, , index = c("ETreg", "year"), row.names = TRUE))
# [1] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" "CY00-2011"
# [6] "CY00-2012" "CY00-2013" "CY00-2014" "CY00-2015" "CY00-2016"
# [11] "CY00-2017" "EE00-2007" "EE00-2008" "EE00-2009" "EE00-2010"
# [16] "EE00-2011" "EE00-2012" "EE00-2013" "EE00-2014" "EE00-2015"
# [21] "EE00-2016" "EE00-2017" "LU00-2007" "LU00-2008" "LU00-2009"
# [26] "LU00-2010" "LU00-2011" "LU00-2012" "LU00-2013" "LU00-2014"
# [31] "LU00-2015" "LU00-2016" "LU00-2017"
str(gust$g)
# num [1:33] 5.1 3.6 -2 2 0.4 -3.4 -6.6 -1.9 3.4 6.7 ...
str(gust$du)
# Named num [1:33] -0.6 -0.2 1.7 0.9 1.6 ...
# - attr(*, "names")= chr [1:33] "CY00-2007" "CY00-2008" "CY00-2009" "CY00-2010" ...
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Error in `.rowNamesDF<-`(x, value = value) :
# duplicate 'row.names' are not allowed
# Además: Warning messages:
# 1: In `[.data.frame`(index, as.numeric(rownames(mf)), ) :
# NAs introducidos por coerción
# 2: In plm(du ~ g, data = gust, index = c("ETreg", "year"), model = "pooling") :
# NAs introducidos por coerción
# 3: non-unique values when setting 'row.names':
# Timing stopped at: 0.71 0.14 7.11
gust$du <- unname(gust$du)
summary( plm(du ~ g, data = gust, index = c("ETreg", "year"), model="pooling") )
# Pooling Model
# Call:
# plm(formula = du ~ g, data = gust, model = "pooling", index = c("ETreg",
# "year"))
# Balanced Panel: n = 3, T = 11, N = 33
# Residuals:
# Min. 1st Qu. Median 3rd Qu. Max.
# -2.53175 -1.02819 0.27557 0.77953 3.84676
# Coefficients:
# Estimate Std. Error t-value Pr(>|t|)
# (Intercept) 0.851158 0.263640 3.2285 0.002939 **
# g -0.365347 0.053228 -6.8639 1.079e-07 ***
# ---
# Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
# Total Sum of Squares: 157.46
# Residual Sum of Squares: 62.488
# R-Squared: 0.60314
# Adj. R-Squared: 0.59034
# F-statistic: 47.1127 on 1 and 31 DF, p-value: 1.0794e-07
这是一个简短的例子，说明了数据框和 tibble（tibble 3.0.4）在添加具有 names 属性的向量的行为方面的区别：
library(tibble)
a <- 1:5
df <- data.frame(a, a * 2)
tb <- tibble(df)
b <- 6:10
names(b) <- letters[1:5]
df$b <- b
tb$b <- b
lapply(df, names) # data frame's columns do not have names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> NULL
lapply(tb, names) # tibble's column b preserved names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> [1] "a" "b" "c" "d" "e"
df_tb <- as.data.frame(tb)
lapply(df_tb, names) # data frame's column b has names
#> $a
#> NULL
#>
#> $a...2
#> NULL
#>
#> $b
#> [1] "a" "b" "c" "d" "e"