| Title: | Seek the Significant Cutoff Value |
| Version: | 1.3 |
| Description: | Seek the significant cutoff value for a continuous variable, which will be transformed into a classification, for linear regression, logistic regression, logrank analysis and cox regression. First of all, all combinations will be gotten by combn() function. Then n.per argument, abbreviated of total number percentage, will be used to remove the combination of smaller data group. In logistic, Cox regression and logrank analysis, we will also use p.per argument, patient percentage, to filter the lower proportion of patients in each group. Finally, p value in regression results will be used to get the significant combinations and output relevant parameters. In this package, there is no limit to the number of cutoff points, which can be 1, 2, 3 or more. Still, we provide 2 methods, typical Bonferroni and Duglas G (1994) <doi:10.1093/jnci/86.11.829>, to adjust the p value, Missing values will be deleted by na.omit() function before analysis. |
| License: | GPL-3 |
| Encoding: | UTF-8 |
| LazyData: | true |
| RoxygenNote: | 6.1.1 |
| Imports: | survival, set, do, ROCit |
| URL: | https://github.com/yikeshu0611/cutoff |
| BugReports: | https://github.com/yikeshu0611/cutoff/issues |
| NeedsCompilation: | no |
| Packaged: | 2019-12-15 12:00:44 UTC; asus |
| Author: | Jing Zhang [aut, cre], Zhi Jin [aut] |
| Maintainer: | Jing Zhang <zj391120@163.com> |
| Repository: | CRAN |
| Date/Publication: | 2019-12-20 10:10:05 UTC |
Significant Cutoff Value for Cox Regression
Description
Significant Cutoff Value for Cox Regression
Usage
cox(data, time, y, x, cut.numb, n.per, y.per, p.cut = 0.05,
strict = TRUE, include = "low", round = 2, adjust = 1)
Arguments
data |
data |
time |
name for time variable |
y |
name for y, must be coded as 1 and 0. The outcome must be 1 |
x |
name for x |
cut.numb |
number of cutoff points |
n.per |
the least percentage of the smaller group comprised in all patients |
y.per |
the least percentage of the smaller outcome patients comprised in each group |
p.cut |
cutoff of p value, default is 0.05 |
strict |
logical. TRUE means significant differences for each group combination were considered. FALSE means considering for any combination |
include |
direction of cutoff point. Any left letter of lower or upper |
round |
digital. Default is 2 |
adjust |
numeric value, adjust methord for p value. 1, defaulted, represents Bonferroni. 2 represent formula given by Douglas G in 1994 |
Value
a dataframe contains cutoff points value, subject numbers in each group, dumb variable, beta of regression and p value.
Examples
cox(data=mtcars,
time = 'disp', y='am', x='wt',
cut.numb=2,
n.per=0.25,
y.per=0.10)
cox(data=mtcars,
time = 'disp', y='am', x='wt',
cut.numb=2,
n.per=0.25,
y.per=0.10,
p.cut=0.05,
strict=TRUE,
include='low',
round=2)
Cut Continuous Vector to Classification
Description
Cut Continuous Vector to Classification
Usage
cutit(x, cut_points, include = "low", labels = FALSE)
Arguments
x |
numeric vector |
cut_points |
cuting points value |
include |
The direction of cutoff point. Any left letter of lower or upper |
labels |
logical. False is defaulted. TRUE means set range as factor. |
Value
numeric vector or factor
Examples
cutit(mtcars$disp,c(150,190))
cutit(mtcars$disp,c(150,190),labels = TRUE)
Whether the Data Is Arranged from Small to Large
Description
Whether the Data Is Arranged from Small to Large
Usage
judge_123(x)
Arguments
x |
numeric vector |
Value
logical
Examples
judge_123(c(1,2,3,4,5))
judge_123(c(1,3,2))
Whether the Data Is Arranged from Large to Small
Description
Whether the Data Is Arranged from Large to Small
Usage
judge_321(x)
Arguments
x |
numeric vector |
Value
logical
Examples
judge_321(c(5,4,3,2,1))
judge_321(c(3,1,2))
Significant Cutoff Value for Linear Regression
Description
Significant Cutoff Value for Linear Regression
Usage
linear(data, y, x, cut.numb, n.per, p.cut = 0.05, strict = TRUE,
include = "low", round = 2, adjust = 1)
Arguments
data |
data |
y |
name for y |
x |
name for x |
cut.numb |
number of cutoff points |
n.per |
the least percentage of the smaller group comprised in all patients |
p.cut |
cutoff of p value, default is 0.05 |
strict |
logical. TRUE means significant differences for each group combination were considered. FALSE means considering for any combination |
include |
direction of cutoff point. Any left letter of lower or upper |
round |
digital. Default is 2 |
adjust |
numeric value, adjust methord for p value. 1, defaulted, represents Bonferroni. 2 represent formula given by Douglas G in 1994 |
Value
a dataframe contains cutoff points value, subject numbers in each group, dumb variable, beta of regression and p value.
Examples
linear(data=mtcars,y='qsec',x='disp',
cut.numb=2,
n.per=0.25)
linear(data=mtcars,y='qsec',x='disp',
cut.numb=2,
n.per=0.25,
p.cut=0.05,
strict=TRUE,
include='low',
round=2)
linear(data=mtcars,y='qsec',x='disp',
cut.numb=2,
n.per=0.25,
p.cut=0.05,
strict=FALSE,
include='low',
round=2)
Significant Cutoff Value for Logistic Regression
Description
Significant Cutoff Value for Logistic Regression
Usage
logit(data, y, x, cut.numb, n.per, y.per, p.cut = 0.05, strict = TRUE,
include = "low", round = 2, adjust = 1)
Arguments
data |
data |
y |
name for y, must be coded as 1 and 0. The outcome must be 1 |
x |
name for x |
cut.numb |
number of cutoff points |
n.per |
the least percentage of the smaller group comprised in all patients |
y.per |
the least percentage of the smaller outcome patients comprised in each group |
p.cut |
cutoff of p value, default is 0.05 |
strict |
logical. TRUE means significant differences for each group combination were considered. FALSE means considering for any combination |
include |
direction of cutoff point. Any left letter of lower or upper |
round |
digital. Default is 2 |
adjust |
numeric value, adjust methord for p value. 1, defaulted, represents Bonferroni. 2 represent formula given by Douglas G in 1994 |
Value
a dataframe contains cutoff points value, subject numbers in each group, dumb variable, or of regression and p value.
Examples
logit(data=mtcars,
y='am',
x='disp',
cut.numb=1,
n.per=0.25,
y.per=0.25)
logit(data=mtcars,
y='am',
x='disp',
cut.numb=1,
n.per=0.25,
y.per=0.20,
p.cut=0.05,
strict=TRUE,
include='low',
round=2)
Significant Cutoff Value for Logrank Analysis
Description
Significant Cutoff Value for Logrank Analysis
Usage
logrank(data, time, y, x, cut.numb, n.per, y.per, p.cut = 0.05,
strict = TRUE, include = "low", round = 2, adjust = 1)
Arguments
data |
data |
time |
name for time variable |
y |
name for y, must be coded as 1 and 0. The outcome must be 1 |
x |
name for x |
cut.numb |
number of cutoff points |
n.per |
the least percentage of the smaller group comprised in all patients |
y.per |
the least percentage of the smaller outcome patients comprised in each group |
p.cut |
cutoff of p value, default is 0.05 |
strict |
logical. TRUE means significant differences for each group combination were considered. FALSE means considering for any combination |
include |
direction of cutoff point. Any left letter of lower or upper |
round |
digital. Default is 2 |
adjust |
numeric value, adjust methord for p value. 1, defaulted, represents Bonferroni. 2 represent formula given by Douglas G in 1994 |
Value
a dataframe contains cutoff points value, subject numbers in each group, dumb variable, beta of regression and p value.
Examples
logrank(data=mtcars,
time = 'disp',y='am', x='wt',
cut.numb=2,
n.per=0.25,
y.per=0.10)
logrank(data=mtcars,
time = 'disp',y='am', x='wt',
cut.numb=2,
n.per=0.25,
y.per=0.10,
p.cut=0.05,
strict=TRUE,
include='low',
round=2)
To Get the Best Cutoff Value for ROC Curve
Description
Youden index is used for seeking the best cutoff value for ROC Curve.
Usage
roc(score, class)
Arguments
score |
continuous value |
class |
bianary value, 0 and 1 |
Value
If the auc of a variate is lower than 0.5, we treat it as negative classification and return information about the negative prediction. Otherwise, The variate will be treated as positive one.
Examples
roc(score = mtcars$qsec,class = mtcars$am)
roc(score = mtcars$drat,class = mtcars$am)
Return x Between a and b
Description
Return x Between a and b
Usage
x_ab(x, a, b, include = "l")
Arguments
x |
numeric vector |
a |
one number |
b |
one number |
include |
The direction of a and b. Any left letter of lower or upper |
Value
values of x between a and b
Examples
x_ab(mtcars$disp,150,190)