我有两个变量矩阵：lagcolmean（独立）和Dropcolmax（依赖）。
head(lagcolmean)
MSFT AAPL GOOGL
2 -0.2130120 0.8115149 -0.2093960
3 -0.1824693 -0.3352958 -0.1845572
4 0.2175819 -0.6885582 0.9421018
head(Dropcolmax)
MSFT AAPL GOOGL
1 0.3837303 3.871109 6.618858
2 0.6723379 4.369627 7.070757
3 1.1848480 2.565165 2.079593
我使用这个公式来回归这两个变量：
fit <- lapply(names(Dropcolmax), function(x){
lm(lagcolmean[[x]] ~ Dropcolmax[[x]])
})
因此我得到三个截距和三个没有任何t值的系数。现在我想用相应的平均值来报告这三个截距和系数的平均值。
答案 0 :(得分：0)
我正在逐步修改您的功能，以显示您可以获得的不同输出。在我看来，broom包使您的生活更轻松，因为它为您在大数据框中组合的每个模型提供了有用的信息。然后，您可以使用适当的列和过滤器计算所需的所有内容。
library(broom)
lagcolmean = read.table(text="
MSFT AAPL GOOGL
-0.2130120 0.8115149 -0.2093960
-0.1824693 -0.3352958 -0.1845572
0.2175819 -0.6885582 0.9421018", sep="", header=T)
Dropcolmax = read.table(text="
MSFT AAPL GOOGL
0.3837303 3.871109 6.618858
0.6723379 4.369627 7.070757
1.1848480 2.565165 2.079593", sep="", header=T)
# returns list of models with minimal info
fit1 <- lapply(names(Dropcolmax), function(x){
lm(lagcolmean[[x]] ~ Dropcolmax[[x]]) })
fit1
# [[1]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Coefficients:
# (Intercept) Dropcolmax[[x]]
# -0.4819 0.5657
#
#
# [[2]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Coefficients:
# (Intercept) Dropcolmax[[x]]
# -1.4706 0.3886
#
#
# [[3]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Coefficients:
# (Intercept) Dropcolmax[[x]]
# 1.4289 -0.2371
# returns a list of models with useful info
fit2 <- lapply(names(Dropcolmax), function(x){
summary(lm(lagcolmean[[x]] ~ Dropcolmax[[x]])) })
fit2
# [[1]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Residuals:
# 1 2 3
# 0.05179 -0.08095 0.02916
#
# Coefficients:
# Estimate Std. Error t value Pr(>|t|)
# (Intercept) -0.4819 0.1430 -3.370 0.184
# Dropcolmax[[x]] 0.5657 0.1750 3.233 0.191
#
# Residual standard error: 0.1004 on 1 degrees of freedom
# Multiple R-squared: 0.9127, Adjusted R-squared: 0.8253
# F-statistic: 10.45 on 1 and 1 DF, p-value: 0.191
#
#
# [[2]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Residuals:
# 1 2 3
# 0.7777 -0.5628 -0.2149
#
# Coefficients:
# Estimate Std. Error t value Pr(>|t|)
# (Intercept) -1.4706 2.7482 -0.535 0.687
# Dropcolmax[[x]] 0.3886 0.7465 0.521 0.694
#
# Residual standard error: 0.9838 on 1 degrees of freedom
# Multiple R-squared: 0.2132, Adjusted R-squared: -0.5735
# F-statistic: 0.271 on 1 and 1 DF, p-value: 0.6944
#
#
# [[3]]
#
# Call:
# lm(formula = lagcolmean[[x]] ~ Dropcolmax[[x]])
#
# Residuals:
# 1 2 3
# -0.069114 0.062857 0.006258
#
# Coefficients:
# Estimate Std. Error t value Pr(>|t|)
# (Intercept) 1.42885 0.13717 10.417 0.0609 .
# Dropcolmax[[x]] -0.23707 0.02398 -9.884 0.0642 .
# ---
# Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#
# Residual standard error: 0.09363 on 1 degrees of freedom
# Multiple R-squared: 0.9899, Adjusted R-squared: 0.9797
# F-statistic: 97.7 on 1 and 1 DF, p-value: 0.06419
# returns list of dataframes with useful info
fit3 <- lapply(names(Dropcolmax), function(x){
tidy(lm(lagcolmean[[x]] ~ Dropcolmax[[x]])) })
fit3
# [[1]]
# term estimate std.error statistic p.value
# 1 (Intercept) -0.4818854 0.1430076 -3.369648 0.1836572
# 2 Dropcolmax[[x]] 0.5657314 0.1750100 3.232566 0.1909950
#
# [[2]]
# term estimate std.error statistic p.value
# 1 (Intercept) -1.4705816 2.7481718 -0.5351127 0.6872022
# 2 Dropcolmax[[x]] 0.3886215 0.7464919 0.5205971 0.6944294
#
# [[3]]
# term estimate std.error statistic p.value
# 1 (Intercept) 1.4288545 0.13717192 10.416523 0.06092962
# 2 Dropcolmax[[x]] -0.2370706 0.02398423 -9.884433 0.06418790
# collapse the list to a big dataframe
dt = do.call(rbind, fit3)
dt
# term estimate std.error statistic p.value
# 1 (Intercept) -0.4818854 0.14300765 -3.3696477 0.18365719
# 2 Dropcolmax[[x]] 0.5657314 0.17501003 3.2325659 0.19099495
# 3 (Intercept) -1.4705816 2.74817181 -0.5351127 0.68720222
# 4 Dropcolmax[[x]] 0.3886215 0.74649192 0.5205971 0.69442940
# 5 (Intercept) 1.4288545 0.13717192 10.4165232 0.06092962
# 6 Dropcolmax[[x]] -0.2370706 0.02398423 -9.8844330 0.06418790
# returns list of dataframes with useful info and the name of the variable
fit4 <- lapply(names(Dropcolmax), function(x){
dd = tidy(lm(lagcolmean[[x]] ~ Dropcolmax[[x]]))
data.frame(name = x, dd)})
fit4
# [[1]]
# name term estimate std.error statistic p.value
# 1 MSFT (Intercept) -0.4818854 0.1430076 -3.369648 0.1836572
# 2 MSFT Dropcolmax[[x]] 0.5657314 0.1750100 3.232566 0.1909950
#
# [[2]]
# name term estimate std.error statistic p.value
# 1 AAPL (Intercept) -1.4705816 2.7481718 -0.5351127 0.6872022
# 2 AAPL Dropcolmax[[x]] 0.3886215 0.7464919 0.5205971 0.6944294
#
# [[3]]
# name term estimate std.error statistic p.value
# 1 GOOGL (Intercept) 1.4288545 0.13717192 10.416523 0.06092962
# 2 GOOGL Dropcolmax[[x]] -0.2370706 0.02398423 -9.884433 0.06418790
# collapse the list to a big dataframe
dt = do.call(rbind, fit4)
dt
# name term estimate std.error statistic p.value
# 1 MSFT (Intercept) -0.4818854 0.14300765 -3.3696477 0.18365719
# 2 MSFT Dropcolmax[[x]] 0.5657314 0.17501003 3.2325659 0.19099495
# 3 AAPL (Intercept) -1.4705816 2.74817181 -0.5351127 0.68720222
# 4 AAPL Dropcolmax[[x]] 0.3886215 0.74649192 0.5205971 0.69442940
# 5 GOOGL (Intercept) 1.4288545 0.13717192 10.4165232 0.06092962
# 6 GOOGL Dropcolmax[[x]] -0.2370706 0.02398423 -9.8844330 0.06418790
# get average of intercepts
mean(dt$estimate[dt$term == "(Intercept)"])
[1] -0.1745375