Blog roll
R-bloggers, Debian Weekly![[Valid RSS]](valid-rss-rogers.png "Validate my RSS feed")
Last modified:
oktober 17, 2019
This is a short introdution on how to use the mi package to impute data where it is missing.
mp.plot(my.df, y.order = TRUE, x.order = TRUE, clustered = TRUE)
mi.info(my.df)
names include order number.mis all.mis type collinear
1 CIRI_WEC Yes 1 1 No ordered-categorical No
2 CIRI_WOS Yes 2 1 No ordered-categorical No
3 CIRI_WOP Yes 3 1 No ordered-categorical No
4 CIRI_POL Yes 4 1 No ordered-categorical No
5 CIRI_ASS Yes 5 1 No ordered-categorical No
6 CIRI_REL Yes 6 1 No binary No
7 CIRI_SPE Yes 7 1 No ordered-categorical No
8 CIRI_PHY Yes 8 1 No nonnegative No
9 BDLLS_OA Yes 9 109 No nonnegative No
10 BDLLS_SH Yes 10 109 No nonnegative No
11 BDLLS_UB Yes 11 109 No nonnegative No
12 CIRI_WOR Yes 12 1 No ordered-categorical No
13 FH_IPOLI Yes NA 0 No nonnegative No
14 DPI_LIPC Yes 13 20 No positive-continuous No
15 DPI_FINT Yes 14 19 No binary No
16 DPI_CEMO Yes 15 19 No binary No
17 DPI_VSLO Yes 16 27 No nonnegative No
18 DPI_FRAU Yes 17 31 No binary No
19 DPI_MUNI Yes 18 71 No ordered-categorical No
20 WBGI_RLE Yes NA 0 No continuous No
21 FI_LEGPR Yes 19 71 No positive-continuous No
22 CIRI_INJ Yes 20 2 No ordered-categorical No
23 ICRG_QOG Yes 21 54 No positive-continuous No
24 WBGI_GEE Yes NA 0 No continuous No
25 WBGI_CCE Yes 22 2 No continuous No
26 QS_IMPAR Yes 23 140 No continuous No
27 EIU_FOG Yes 24 30 No nonnegative No
28 FH_ECON Yes NA 0 No nonnegative No
29 FH_POL Yes NA 0 No nonnegative No
30 FH_LAW Yes NA 0 No nonnegative No
31 FH_REPRE Yes 25 8 No nonnegative No
32 HR Yes NA 0 No continuous No
33 DEMOC Yes NA 0 No continuous No
34 ROL Yes NA 0 No continuous No
35 PM Yes NA 0 No continuous No
36 TRANSPAR Yes NA 0 No continuous No
37 QOG Yes NA 0 No continuous No
38 <NA> Yes NA 0 No continuous No
39 <NA> Yes NA 0 No continuous No
IMP <- mi(my.df, preprocess = TRUE)Multiple Imputation with Diagnostics (mi) in R: Opening Windows into the Black Box