1
R线性回归分类变量“隐藏”值
这只是我多次遇到的示例,因此我没有任何示例数据。在R中运行线性回归模型: a.lm = lm(Y ~ x1 + x2) x1是一个连续变量。x2是分类的,具有三个值,例如“低”,“中”和“高”。但是,R给出的输出将类似于: summary(a.lm) Estimate Std. Error t value Pr(>|t|) (Intercept) 0.521 0.20 1.446 0.19 x1 -0.61 0.11 1.451 0.17 x2Low -0.78 0.22 -2.34 0.005 x2Medium -0.56 0.45 -2.34 0.005 我知道R在这种因素(x2是一个因素)上引入了某种虚拟编码。我只是想知道,如何解释x2“高”值?例如,x2在此处给出的示例中,“ High” 对响应变量有什么影响? 我在其他地方(例如这里)已经看到了这样的示例,但是还没有找到我能理解的解释。
10
r
regression
categorical-data
regression-coefficients
categorical-encoding
machine-learning
random-forest
anova
spss
r
self-study
bootstrap
monte-carlo
r
multiple-regression
partitioning
neural-networks
normalization
machine-learning
svm
kernel-trick
self-study
survival
cox-model
repeated-measures
survey
likert
correlation
variance
sampling
meta-analysis
anova
independence
sample
assumptions
bayesian
covariance
r
regression
time-series
mathematical-statistics
graphical-model
machine-learning
linear-model
kernel-trick
linear-algebra
self-study
moments
function
correlation
spss
probability
confidence-interval
sampling
mean
population
r
generalized-linear-model
prediction
offset
data-visualization
clustering
sas
cart
binning
sas
logistic
causality
regression
self-study
standard-error
r
distributions
r
regression
time-series
multiple-regression
python
chi-squared
independence
sample
clustering
data-mining
rapidminer
probability
stochastic-processes
clustering
binary-data
dimensionality-reduction
svd
correspondence-analysis
data-visualization
excel
c#
hypothesis-testing
econometrics
survey
rating
composite
regression
least-squares
mcmc
markov-process
kullback-leibler
convergence
predictive-models
r
regression
anova
confidence-interval
survival
cox-model
hazard
normal-distribution
autoregressive
mixed-model
r
mixed-model
sas
hypothesis-testing
mediation
interaction