Getting started
The example data is a hypothetical dataset extracting a subset from package PredictABEL. It has no practical implications and only be used to demostrate the main idea of the package.
# If you haven't install the package, you can download it from cran
# install.packages("quickReg")
library(quickReg)
library(ggplot2)
library(rlang)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
# Load the dataset
data(diabetes)
# Show the first 6 rows of the data
head(diabetes)
## sex age smoking education diabetes BMI systolic diastolic CFHrs1061170 LOCrs10490924 CFHrs1410996 C2rs9332739 CFBrs641153 CFHrs2230199
## 1 1 44 1 0 1 40 129 91 1 2 2 1 1 0
## 2 0 53 0 0 0 29 137 98 2 1 1 1 0 0
## 3 1 46 1 0 0 29 136 93 1 1 2 1 1 1
## 4 1 63 0 0 0 29 176 119 1 0 1 1 0 0
## 5 0 60 NA 0 1 30 148 107 1 2 1 1 0 2
## 6 0 52 0 1 1 29 133 91 1 1 1 1 1 0
We can use the function display_table or display_table_group to show statistical descriptions of the data.
display_1<-display_table(data=diabetes,variables=c("age","smoking","education"),group="CFHrs2230199")
display_1
## variable level All sample CFHrs2230199 = 0 CFHrs2230199 = 1 CFHrs2230199 = 2 P.value1 P.value2 normality
## 1 age mean +- sd 58.98 +- 13.27 59.23 +- 13.36 58.34 +- 13.14 60.59 +- 13.16 0.36 0.47 6.45E-08; 3.01E-05; 0.24
## 2 NA 0 0 0 0
## 3 smoking 0 455 (49.14%) 259 (49.81%) 166 (48.4%) 30 (47.62%) 0.89 <NA>
## 4 1 471 (50.86%) 261 (50.19%) 177 (51.6%) 33 (52.38%)
## 5 NA 74 38 33 3
## 6 education 0 661 (66.1%) 370 (66.31%) 248 (65.96%) 43 (65.15%) 0.98 <NA>
## 7 1 339 (33.9%) 188 (33.69%) 128 (34.04%) 23 (34.85%)
## 8 NA 0 0 0 0
# You could do a sub-group analysis by sex
display_2<-display_table_group(data=diabetes,variables=c("age","smoking"),group="CFHrs2230199",super_group = "sex")
display_2
## # A tibble: 10 x 10
## sex variable level `All sample` `CFHrs2230199 = 0` `CFHrs2230199 = 1` `CFHrs2230199 = 2` P.value1 P.value2 normality
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 0 age mean +- sd 59.22 +- 13.72 59.94 +- 14.09 58.52 +- 13.38 57.54 +- 12.53 0.36 0.40 2.71E-05; 1.59E-03; 0.08
## 2 0 NA 0 0 0 0
## 3 0 smoking 0 259 (49.05%) 142 (48.63%) 100 (50.51%) 17 (44.74%) 0.79 <NA>
## 4 0 1 269 (50.95%) 150 (51.37%) 98 (49.49%) 21 (55.26%)
## 5 0 NA 44 20 21 3
## 6 1 age mean +- sd 58.66 +- 12.65 58.33 +- 12.34 58.08 +- 12.84 65.60 +- 12.86 0.02 0.02 3.56E-04; 0.01; 0.95
## 7 1 NA 0 0 0 0
## 8 1 smoking 0 196 (49.25%) 117 (51.32%) 66 (45.52%) 13 (52%) 0.53 <NA>
## 9 1 1 202 (50.75%) 111 (48.68%) 79 (54.48%) 12 (48%)
## 10 1 NA 30 18 12 0
# You could do a sub-group analysis by two variables
display_3<-display_table_group(data=diabetes,variables=c("age","smoking"),group="CFHrs2230199",super_group = c("sex","education"))
display_3
## super_group super_group_level variable level All sample CFHrs2230199 = 0 CFHrs2230199 = 1 CFHrs2230199 = 2 P.value1 P.value2
## 1 sex 0 age mean +- sd 59.22 +- 13.72 59.94 +- 14.09 58.52 +- 13.38 57.54 +- 12.53 0.36 0.40
## 2 sex 0 NA 0 0 0 0
## 3 sex 0 smoking 0 259 (49.05%) 142 (48.63%) 100 (50.51%) 17 (44.74%) 0.79 <NA>
## 4 sex 0 1 269 (50.95%) 150 (51.37%) 98 (49.49%) 21 (55.26%)
## 5 sex 0 NA 44 20 21 3
## 6 sex 1 age mean +- sd 58.66 +- 12.65 58.33 +- 12.34 58.08 +- 12.84 65.60 +- 12.86 0.02 0.02
## 7 sex 1 NA 0 0 0 0
## 8 sex 1 smoking 0 196 (49.25%) 117 (51.32%) 66 (45.52%) 13 (52%) 0.53 <NA>
## 9 sex 1 1 202 (50.75%) 111 (48.68%) 79 (54.48%) 12 (48%)
## 10 sex 1 NA 30 18 12 0
## 11 education 0 age mean +- sd 58.68 +- 12.98 59.15 +- 12.95 57.73 +- 12.95 60.09 +- 13.36 0.31 0.49
## 12 education 0 NA 0 0 0 0
## 13 education 0 smoking 0 307 (49.68%) 166 (47.56%) 126 (55.26%) 15 (36.59%) 0.04 <NA>
## 14 education 0 1 311 (50.32%) 183 (52.44%) 102 (44.74%) 26 (63.41%)
## 15 education 0 NA 43 21 20 2
## 16 education 1 age mean +- sd 59.57 +- 13.81 59.37 +- 14.17 59.52 +- 13.48 61.52 +- 13.02 0.78 0.72
## 17 education 1 NA 0 0 0 0
## 18 education 1 smoking 0 148 (48.05%) 93 (54.39%) 40 (34.78%) 15 (68.18%) 7.35E-04 <NA>
## 19 education 1 1 160 (51.95%) 78 (45.61%) 75 (65.22%) 7 (31.82%)
## 20 education 1 NA 31 17 13 1
## normality
## 1 2.71E-05; 1.59E-03; 0.08
## 2
## 3
## 4
## 5
## 6 3.56E-04; 0.01; 0.95
## 7
## 8
## 9
## 10
## 11 1.18E-05; 7.28E-04; 0.39
## 12
## 13
## 14
## 15
## 16 5.73E-04; 4.11E-03; 0.84
## 17
## 18
## 19
## 20
# Sub-group analysis can be a combination
display_4<-display_table_group(data=diabetes,variables=c("age","smoking"),group="CFHrs2230199",super_group = c("sex","education"),group_combine = TRUE)
display_4
## # A tibble: 20 x 11
## sex education variable level `All sample` `CFHrs2230199 = 0` `CFHrs2230199 = 1` `CFHrs2230199 = 2` P.value1 P.value2 normality
## <dbl> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 0 0 age mean +- sd 59.15 +- 13.47 60.08 +- 13.66 58.03 +- 13.20 58.52 +- 13.54 0.35 0.40 8.20E-04; 0.01; 0.13
## 2 0 0 NA 0 0 0 0
## 3 0 0 smoking 0 181 (49.86%) 91 (46.91%) 81 (57.04%) 9 (33.33%) 0.04 <NA>
## 4 0 0 1 182 (50.14%) 103 (53.09%) 61 (42.96%) 18 (66.67%)
## 5 0 0 NA 28 13 13 2
## 6 0 1 age mean +- sd 59.38 +- 14.28 59.66 +- 14.99 59.72 +- 13.84 55.17 +- 9.77 0.57 0.63 0.01; 0.07; 0.89
## 7 0 1 NA 0 0 0 0
## 8 0 1 smoking 0 78 (47.27%) 51 (52.04%) 19 (33.93%) 8 (72.73%) 0.02 <NA>
## 9 0 1 1 87 (52.73%) 47 (47.96%) 37 (66.07%) 3 (27.27%)
## 10 0 1 NA 16 7 8 1
## 11 1 0 age mean +- sd 58.00 +- 12.23 57.98 +- 11.94 57.24 +- 12.58 63.36 +- 12.83 0.22 0.25 0.01; 0.01; 0.94
## 12 1 0 NA 0 0 0 0
## 13 1 0 smoking 0 126 (49.41%) 75 (48.39%) 45 (52.33%) 6 (42.86%) 0.74 <NA>
## 14 1 0 1 129 (50.59%) 80 (51.61%) 41 (47.67%) 8 (57.14%)
## 15 1 0 NA 15 8 7 0
## 16 1 1 age mean +- sd 59.79 +- 13.29 59.01 +- 13.15 59.31 +- 13.22 68.45 +- 12.92 0.08 0.08 0.04; 0.04; 0.92
## 17 1 1 NA 0 0 0 0
## 18 1 1 smoking 0 70 (48.95%) 42 (57.53%) 21 (35.59%) 7 (63.64%) 0.03 <NA>
## 19 1 1 1 73 (51.05%) 31 (42.47%) 38 (64.41%) 4 (36.36%)
## 20 1 1 NA 15 10 5 0
Build regression models
# Apply univariate regression models
reg_1<-reg_x(data = diabetes, y = 5, factors = c(1, 3, 4), model = 'glm')
reg_1
## x term estimate std.error statistic p.value OR OR.low OR.high N
## 1 sex sex_1 -0.0995619364 0.163419266 -0.60924234 5.423638e-01 0.9052339 0.6571403 1.246992 1000
## 2 age age -0.0016515166 0.006083056 -0.27149453 7.860107e-01 0.9983498 0.9865176 1.010324 1000
## 3 smoking smoking_1 0.2203884367 0.171356638 1.28613889 1.983946e-01 1.2465608 0.8909523 1.744105 926
## 4 education education_1 0.0072440035 0.169823173 0.04265615 9.659756e-01 1.0072703 0.7220916 1.405076 1000
## 5 BMI BMI -0.0205541093 0.021530295 -0.95465990 3.397497e-01 0.9796557 0.9391757 1.021880 994
## 6 systolic systolic -0.0001758354 0.004399858 -0.03996388 9.681219e-01 0.9998242 0.9912392 1.008484 995
## 7 diastolic diastolic -0.0010196342 0.007323325 -0.13923104 8.892676e-01 0.9989809 0.9847445 1.013423 995
## 8 CFHrs1061170 CFHrs1061170 0.1648181445 0.108731134 1.51583211 1.295618e-01 1.1791787 0.9528565 1.459257 1000
## 9 LOCrs10490924 LOCrs10490924 0.6243454613 0.112922906 5.52895320 3.221473e-08 1.8670235 1.4963378 2.329539 1000
## 10 CFHrs1410996 CFHrs1410996 0.3154310240 0.128347280 2.45763699 1.398545e-02 1.3708501 1.0659591 1.762947 1000
## 11 C2rs9332739 C2rs9332739 1.0717936770 0.433256076 2.47381107 1.336804e-02 2.9206134 1.2493549 6.827510 1000
## 12 CFBrs641153 CFBrs641153 0.1993582016 0.253688461 0.78583866 4.319620e-01 1.2206191 0.7424038 2.006874 1000
## 13 CFHrs2230199 CFHrs2230199 0.3402726917 0.125293121 2.71581303 6.611324e-03 1.4053308 1.0993320 1.796504 1000
# Or a survial analysis
reg_2<-reg_x(data = diabetes, x = c(3:4, 6), y ="diabetes",time=2,factors = c(1, 3, 4), model = 'coxph')
reg_2
## x term estimate std.error statistic p.value HR HR.low HR.high N
## 1 smoking smoking_1 0.17247504 0.15526447 1.1108468 0.266634305 1.1882422 0.8764832 1.6108916 926
## 2 education education_1 -0.06871785 0.15313905 -0.4487285 0.653627559 0.9335901 0.6915188 1.2604001 1000
## 3 BMI BMI -0.05564539 0.02111973 -2.6347584 0.008419718 0.9458745 0.9075203 0.9858496 994
# adjust some covariates
reg_3<-reg_x(data = diabetes, x = c("sex","age"), y ="diabetes" ,cov=c("CFBrs641153","CFHrs2230199"), factors ="sex", model = 'glm',cov_show = TRUE)
reg_3
## x term estimate std.error statistic p.value OR OR.low OR.high N
## 2 sex sex_1 -0.095195435 0.164518306 -0.5786313 0.562838007 0.9091952 0.6585957 1.255149 1000
## 3 sex CFBrs641153 0.230790886 0.255559041 0.9030825 0.366482136 1.2595958 0.7633065 2.078564 1000
## 4 sex CFHrs2230199 0.342102415 0.125633639 2.7230160 0.006468892 1.4079045 1.1006105 1.800996 1000
## 6 age age -0.001887778 0.006114376 -0.3087442 0.757516121 0.9981140 0.9862240 1.010147 1000
## 7 age CFBrs641153 0.224355970 0.255129981 0.8793791 0.379195768 1.2515164 0.7590485 2.063496 1000
## 8 age CFHrs2230199 0.344428164 0.125604894 2.7421556 0.006103742 1.4111827 1.1032354 1.805088 1000
# How about regression on several dependent variables
reg_4<-reg_y(data = diabetes, x = c("sex","age","CFHrs1061170"), y =c("systolic","diastolic","BMI") ,cov=c("CFBrs641153","CFHrs2230199"), factors ="sex", model = 'lm')
reg_4
## y x term estimate std.error statistic p.value coef coef.low coef.high N
## 1 systolic sex sex_1 -2.69428330 1.177660308 -2.2878272 2.235750e-02 -2.69428330 -5.00527758 -0.38328902 995
## 2 systolic age age 0.62409179 0.039210814 15.9163181 5.778111e-51 0.62409179 0.54714603 0.70103755 995
## 3 systolic CFHrs1061170 CFHrs1061170 0.49087994 0.783066116 0.6268691 5.308894e-01 0.49087994 -1.04577821 2.02753809 995
## 4 diastolic sex sex_1 -1.73296131 0.708148117 -2.4471735 1.457089e-02 -1.73296131 -3.12260333 -0.34331929 995
## 5 diastolic age age 0.15343916 0.025977166 5.9066936 4.793066e-09 0.15343916 0.10246259 0.20441573 995
## 6 diastolic CFHrs1061170 CFHrs1061170 -0.30611928 0.471042899 -0.6498756 5.159232e-01 -0.30611928 -1.23047534 0.61823679 995
## 7 BMI sex sex_1 -0.39143773 0.243573523 -1.6070619 1.083597e-01 -0.39143773 -0.86941742 0.08654197 994
## 8 BMI age age 0.05159255 0.008939646 5.7712071 1.052213e-08 0.05159255 0.03404972 0.06913538 994
## 9 BMI CFHrs1061170 CFHrs1061170 -0.10033051 0.161718714 -0.6204013 5.351364e-01 -0.10033051 -0.41768134 0.21702033 994
# Cool, but I want to do a subgroup analysis
reg_5<-reg(data = diabetes, x = c("age","CFHrs1061170"), y =c("systolic","diastolic") ,cov=c("CFBrs641153","CFHrs2230199"), model = 'lm',group="sex")
reg_5
## # A tibble: 8 x 12
## sex y x term estimate std.error statistic p.value coef coef.low coef.high N
## <dbl> <fctr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0 systolic age age 0.6477326 0.05076473 12.7594992 6.063847e-33 0.6477326 0.54802193 0.7474432 569
## 2 0 systolic CFHrs1061170 CFHrs1061170 1.1440952 1.05733099 1.0820597 2.796876e-01 1.1440952 -0.93268422 3.2208747 569
## 3 0 diastolic age age 0.1303477 0.03356128 3.8838704 1.149692e-04 0.1303477 0.06442756 0.1962678 569
## 4 0 diastolic CFHrs1061170 CFHrs1061170 0.2286169 0.62463113 0.3660031 7.144998e-01 0.2286169 -0.99826579 1.4554996 569
## 5 1 systolic age age 0.5930679 0.06179047 9.5980472 7.305923e-20 0.5930679 0.47161244 0.7145233 426
## 6 1 systolic CFHrs1061170 CFHrs1061170 -0.4651260 1.15629722 -0.4022547 6.877002e-01 -0.4651260 -2.73794544 1.8076933 426
## 7 1 diastolic age age 0.1937122 0.04099307 4.7254861 3.132224e-06 0.1937122 0.11313616 0.2742882 426
## 8 1 diastolic CFHrs1061170 CFHrs1061170 -1.0898894 0.71130615 -1.5322366 1.262133e-01 -1.0898894 -2.48803370 0.3082550 426
# or two subgroup analysis
reg_6<-reg(data = diabetes, x = c("age","CFHrs1061170"), y =c("systolic","diastolic") ,cov=c("CFBrs641153","CFHrs2230199"), model = 'lm',group=c("sex","smoking"))
reg_6
## group level y x term estimate std.error statistic p.value coef coef.low coef.high N
## 1 sex 0 systolic age age 0.64773257 0.05076473 12.75949920 6.063847e-33 0.64773257 0.54802193 0.7474432 569
## 2 sex 0 systolic CFHrs1061170 CFHrs1061170 1.14409524 1.05733099 1.08205968 2.796876e-01 1.14409524 -0.93268422 3.2208747 569
## 3 sex 0 diastolic age age 0.13034768 0.03356128 3.88387043 1.149692e-04 0.13034768 0.06442756 0.1962678 569
## 4 sex 0 diastolic CFHrs1061170 CFHrs1061170 0.22861690 0.62463113 0.36600306 7.144998e-01 0.22861690 -0.99826579 1.4554996 569
## 5 sex 1 systolic age age 0.59306788 0.06179047 9.59804724 7.305923e-20 0.59306788 0.47161244 0.7145233 426
## 6 sex 1 systolic CFHrs1061170 CFHrs1061170 -0.46512605 1.15629722 -0.40225475 6.877002e-01 -0.46512605 -2.73794544 1.8076933 426
## 7 sex 1 diastolic age age 0.19371219 0.04099307 4.72548612 3.132224e-06 0.19371219 0.11313616 0.2742882 426
## 8 sex 1 diastolic CFHrs1061170 CFHrs1061170 -1.08988936 0.71130615 -1.53223665 1.262133e-01 -1.08988936 -2.48803370 0.3082550 426
## 9 smoking 0 systolic age age 0.56709310 0.05775625 9.81873047 9.527853e-21 0.56709310 0.45358764 0.6805986 454
## 10 smoking 0 systolic CFHrs1061170 CFHrs1061170 0.09315881 1.09475817 0.08509533 9.322234e-01 0.09315881 -2.05831432 2.2446319 454
## 11 smoking 0 diastolic age age 0.12266643 0.03938756 3.11434456 1.961246e-03 0.12266643 0.04526004 0.2000728 454
## 12 smoking 0 diastolic CFHrs1061170 CFHrs1061170 0.34433728 0.68460209 0.50297434 6.152284e-01 0.34433728 -1.00107674 1.6897513 454
## 13 smoking 1 systolic age age 0.70147846 0.05756805 12.18520429 8.091810e-30 0.70147846 0.58835143 0.8146055 467
## 14 smoking 1 systolic CFHrs1061170 CFHrs1061170 0.48555084 1.21375126 0.40004147 6.893105e-01 0.48555084 -1.89959281 2.8706945 467
## 15 smoking 1 diastolic age age 0.19687617 0.03742561 5.26046659 2.200772e-07 0.19687617 0.12333107 0.2704213 467
## 16 smoking 1 diastolic CFHrs1061170 CFHrs1061170 -0.97263707 0.70551713 -1.37861582 1.686790e-01 -0.97263707 -2.35904940 0.4137752 467
## 17 smoking NA systolic age age 0.53068925 0.14994046 3.53933329 7.175890e-04 0.53068925 0.23164244 0.8297361 74
## 18 smoking NA systolic CFHrs1061170 CFHrs1061170 2.87081804 2.97945574 0.96353774 3.385946e-01 2.87081804 -3.07151907 8.8131551 74
## 19 smoking NA diastolic age age 0.10466712 0.09433926 1.10947570 2.710221e-01 0.10466712 -0.08348661 0.2928208 74
## 20 smoking NA diastolic CFHrs1061170 CFHrs1061170 -0.23489246 1.75288157 -0.13400361 8.937842e-01 -0.23489246 -3.73090451 3.2611196 74
# or subgroup combination analysis
reg_7<-reg(data = diabetes, x = c("age","CFHrs1061170"), y =c("systolic","diastolic") ,cov=c("CFBrs641153","CFHrs2230199"), model = 'lm',group=c("sex","smoking"),group_combine = TRUE)
reg_7
## # A tibble: 24 x 13
## sex smoking y x term estimate std.error statistic p.value coef coef.low coef.high N
## <dbl> <dbl> <fctr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0 0 systolic age age 0.56566186 0.07304951 7.74354045 2.301974e-13 0.56566186 0.42180198 0.7095217 258
## 2 0 0 systolic CFHrs1061170 CFHrs1061170 0.03696846 1.39565115 0.02648833 9.788886e-01 0.03696846 -2.71155369 2.7854906 258
## 3 0 0 diastolic age age 0.05249817 0.05145244 1.02032422 3.085456e-01 0.05249817 -0.04882956 0.1538259 258
## 4 0 0 diastolic CFHrs1061170 CFHrs1061170 0.01277514 0.88599675 0.01441894 9.885071e-01 0.01277514 -1.73206039 1.7576107 258
## 5 0 1 systolic age age 0.70618780 0.07593126 9.30035608 5.640935e-18 0.70618780 0.55667724 0.8556984 267
## 6 0 1 systolic CFHrs1061170 CFHrs1061170 2.02610247 1.69213826 1.19736225 2.322435e-01 2.02610247 -1.30576002 5.3579650 267
## 7 0 1 diastolic age age 0.20585792 0.04809969 4.27981799 2.622268e-05 0.20585792 0.11114843 0.3005674 267
## 8 0 1 diastolic CFHrs1061170 CFHrs1061170 0.42781849 0.96394397 0.44382091 6.575370e-01 0.42781849 -1.47021125 2.3258482 267
## 9 0 NA systolic age age 0.81921451 0.20115008 4.07265312 2.135090e-04 0.81921451 0.41267503 1.2257540 44
## 10 0 NA systolic CFHrs1061170 CFHrs1061170 2.31536173 4.56061889 0.50768586 6.144618e-01 2.31536173 -6.90199287 11.5327163 44
## 11 0 NA diastolic age age 0.12892734 0.12646759 1.01944967 3.141161e-01 0.12892734 -0.12667319 0.3845279 44
## 12 0 NA diastolic CFHrs1061170 CFHrs1061170 -0.17778391 2.44958412 -0.07257718 9.425043e-01 -0.17778391 -5.12857809 4.7730103 44
## 13 1 0 systolic age age 0.57996701 0.09378644 6.18391135 3.684510e-09 0.57996701 0.39498297 0.7649511 196
## 14 1 0 systolic CFHrs1061170 CFHrs1061170 -0.11335576 1.77338944 -0.06392040 9.491001e-01 -0.11335576 -3.61118286 3.3844713 196
## 15 1 0 diastolic age age 0.22779350 0.06043316 3.76934634 2.177436e-04 0.22779350 0.10859535 0.3469917 196
## 16 1 0 diastolic CFHrs1061170 CFHrs1061170 0.57770379 1.08064396 0.53459216 5.935504e-01 0.57770379 -1.55375456 2.7091621 196
## 17 1 1 systolic age age 0.69287978 0.08951395 7.74046694 5.144888e-13 0.69287978 0.51634563 0.8694139 200
## 18 1 1 systolic CFHrs1061170 CFHrs1061170 -1.14297702 1.72236416 -0.66360938 5.077201e-01 -1.14297702 -4.53972238 2.2537684 200
## 19 1 1 diastolic age age 0.18182606 0.06063870 2.99851533 3.064515e-03 0.18182606 0.06223799 0.3014141 200
## 20 1 1 diastolic CFHrs1061170 CFHrs1061170 -2.58830102 1.02894363 -2.51549350 1.268953e-02 -2.58830102 -4.61752317 -0.5590789 200
## 21 1 NA systolic age age 0.13268222 0.18812265 0.70529638 4.868970e-01 0.13268222 -0.25400942 0.5193739 30
## 22 1 NA systolic CFHrs1061170 CFHrs1061170 2.91196013 3.01091415 0.96713489 3.423874e-01 2.91196013 -3.27706254 9.1009828 30
## 23 1 NA diastolic age age 0.05955039 0.13652874 0.43617474 6.663104e-01 0.05955039 -0.22108846 0.3401892 30
## 24 1 NA diastolic CFHrs1061170 CFHrs1061170 -0.73920266 2.20642133 -0.33502335 7.402955e-01 -0.73920266 -5.27456666 3.7961613 30
How about plot these regression models
# One OR value is larger than others, we can set the limits
plot(reg_1,limits=c(NA,3))
# Sort the variables according to alphabetical
plot(reg_1,limits=c(NA,3), sort ="alphabetical")
# Similarly, we can plot for several dependent variables result
plot(reg_4)
## Some variables are duplicated in your regression result.
## Using cov_show = FALSE for covariate variables or facet for subgroup result.
# Subgroup and several dependent variables result
plot(reg_5)+facet_grid(sex~y)
## Some variables are duplicated in your regression result.
## Using cov_show = FALSE for covariate variables or facet for subgroup result.
# Actually, you can modify the plot like ggplot2
library(ggplot2);library(ggthemes)
plot(reg_1,limits=c(0.5,2))+
labs(list(title = "Regression Model", x = "variables"))+
theme_classic() %+replace%
theme(legend.position ="none",axis.text.x=element_text(angle=45,size=rel(1.5)))
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.