Stargazer 中的 Betareg（分配大小为 __ 的向量时出错）
Betareg in Stargazer (Error to allocate vector of size __)
betareg默认残差很重，由于其尺寸较大，可能会导致分配向量时出错。这可以通过更改 summary 调用中残差的 type 来解决，如 here.
所述
但是，当使用 stargazer 呈现回归表时，无法明确设置残差类型。
有没有办法让（大）betareg 对象在 stargazer 中工作？
我能想到但不知道如何实施的潜在解决方案是：
- 指示原始
betareg 调用中的剩余 type（type = "pearson"（或任何其他类型）不起作用）。
- 明确指出在
betareg 对象上调用 summary 时 stargazer 应该包含的参数。
- 还有其他吗？
示例：
set.seed(1)
df <- data.frame(y=runif(100000), x=runif(100000))
library(betareg)
beta <- betareg(y ~ x, data=df)
library(stargazer)
stargazer(beta)
# Error: cannot allocate vector of size 74.5 Gb
您可以 stargazer::.stargazer.wrap 完成任务并更改模型摘要的计算方式，但它大约有 8000 行长。
作为一种解决方法，首先计算一个可以被 table 生成函数消化的更小的回归，然后在编译之前替换系数和统计数据可能会容易得多。
我给你展示了使用 texreg 包的方法，用 stargazer 也可能。
foo <- y ~ x
beta0 <- betareg::betareg(foo, data=df[sample(nrow(df), 1e3), ]) ## small version
beta <- betareg::betareg(foo, data=df) ## actual version
(beta.sum <- betareg:::summary.betareg(beta, type='pearson')$coe) ## actual summary
# $mean
# Estimate Std. Error z value Pr(>|z|)
# (Intercept) 0.007933124 0.006967576 1.1385773 0.2548795
# x -0.010845820 0.012080681 -0.8977822 0.3693017
#
# $precision
# Estimate Std. Error z value Pr(>|z|)
# (phi) 1.999218 0.007501926 266.494 0
Table
屏幕：
texreg::screenreg(beta0,
digits=3,
override.coef=unlist(lapply(beta.sum, \(x) x[, 1])),
override.se=unlist(lapply(beta.sum, \(x) x[, 2])),
override.pvalues=unlist(lapply(beta.sum, \(x) x[, 4]))
)
# ==============================
# Model 1
# ------------------------------
# (Intercept) 0.008
# (0.007)
# x -0.011
# (0.012)
# Precision: (phi) 1.999 ***
# (0.008)
# ------------------------------
# Pseudo R^2 0.000
# Log Likelihood 2.137
# Num. obs. 1000
# ==============================
# *** p < 0.001; ** p < 0.01; * p < 0.05
LaTeX:
texreg::texreg(beta0,
digits=3,
override.coef=unlist(lapply(beta.sum, \(x) x[, 1])),
override.se=unlist(lapply(beta.sum, \(x) x[, 2])),
override.pvalues=unlist(lapply(beta.sum, \(x) x[, 4]))
)
# \begin{table}
# \begin{center}
# \begin{tabular}{l c}
# \hline
# & Model 1 \
# \hline
# (Intercept) & [=12=].008$ \
# & $(0.007)$ \
# x & $-0.011$ \
# & $(0.012)$ \
# Precision: (phi) & .999^{***}$ \
# & $(0.008)$ \
# \hline
# Pseudo R$^2$ & [=12=].000$ \
# Log Likelihood & .137$ \
# Num. obs. & 00$ \
# \hline
# \multicolumn{2}{l}{\scriptsize{$^{***}p<0.001$; $^{**}p<0.01$; $^{*}p<0.05$}}
# \end{tabular}
# \caption{Statistical models}
# \label{table:coefficients}
# \end{center}
# \end{table}
要获取 HTML 代码，请使用：
texreg::htmlreg
数据：
set.seed(1)
n <- 1e5
df <- data.frame(y=runif(n), x=runif(n))
我最终解决这个问题的方法是修改stargazer函数。特别是，在 .stargazer.wrap 中，您可以找到 here 的代码，我添加了以下代码：
else if (class(object.name)[1] == "betareg") { #betareg
.summary.object <<- summary(object.name, type = "person")
在 .add.model 内，即在这些代码行之后：
.add.model <-
function(object.name, user.coef=NULL, user.se=NULL, user.t=NULL, user.p=NULL, auto.t=TRUE, auto.p=TRUE, user.ci.lb=NULL, user.ci.rb=NULL) {
if (class(object.name)[1] == "Glm") {
.summary.object <<- summary.glm(object.name)
}
请注意，您需要使用新的 .stargazer.wrap 创建一个新的 stargazer 函数。我只是称它为 stargazer2:
stargazer2 <-
function(..., type = "latex", title="", style="default", summary=NULL, out=NULL, out.header=FALSE,
column.labels=NULL, column.separate = NULL, covariate.labels=NULL, dep.var.caption=NULL,
dep.var.labels=NULL, dep.var.labels.include=TRUE, align=FALSE, coef=NULL, se=NULL, t=NULL,
p=NULL, t.auto=TRUE, p.auto=TRUE, ci=FALSE, ci.custom=NULL, ci.level=0.95, ci.separator=NULL,
add.lines=NULL, apply.coef=NULL, apply.se=NULL, apply.t=NULL, apply.p=NULL, apply.ci=NULL,
colnames = NULL, column.sep.width = "5pt",
decimal.mark=NULL, df=TRUE, digit.separate=NULL, digit.separator=NULL, digits=NULL, digits.extra=NULL,
flip=FALSE,
float=TRUE, float.env="table", font.size=NULL, header=TRUE, initial.zero=NULL, intercept.bottom=TRUE,
intercept.top=FALSE, keep=NULL, keep.stat=NULL, label="", model.names=NULL, model.numbers=NULL,
multicolumn=TRUE, no.space=NULL, notes=NULL, notes.align=NULL, notes.append=TRUE, notes.label=NULL,
object.names=FALSE,
omit=NULL, omit.labels=NULL, omit.stat=NULL, omit.summary.stat=NULL, omit.table.layout=NULL,
omit.yes.no=c("Yes","No"), order=NULL, ord.intercepts=FALSE,
perl=FALSE, report=NULL, rownames = NULL,
rq.se = "nid", selection.equation=FALSE, single.row=FALSE, star.char=NULL,
star.cutoffs=NULL, suppress.errors=FALSE, table.layout=NULL, table.placement = "!htbp", zero.component=FALSE,
summary.logical=TRUE, summary.stat=NULL, nobs=TRUE, mean.sd=TRUE, min.max=TRUE, median=FALSE,
iqr=FALSE) {
save.warn.option <- getOption("warn")
options(warn=-1)
return(.stargazer.wrap(..., type=type, title=title, style=style, summary=summary, out=out, out.header=out.header,
column.labels=column.labels, column.separate = column.separate,
covariate.labels=covariate.labels, dep.var.caption = dep.var.caption,
dep.var.labels=dep.var.labels, dep.var.labels.include=dep.var.labels.include,
align=align, coef=coef, se=se, t=t, p=p, t.auto=t.auto, p.auto=p.auto,
ci=ci, ci.custom=ci.custom, ci.level=ci.level, ci.separator = ci.separator,
add.lines=add.lines, apply.coef=apply.coef, apply.se=apply.se, apply.t=apply.t,
apply.p=apply.p, apply.ci=apply.ci, colnames=colnames,
column.sep.width=column.sep.width, decimal.mark=decimal.mark, df=df,
digit.separate=digit.separate, digit.separator=digit.separator,
digits=digits, digits.extra=digits.extra,
flip=flip,
float=float, float.env=float.env,
font.size=font.size, header=header,
initial.zero=initial.zero,
intercept.bottom=intercept.bottom, intercept.top=intercept.top,
keep = keep, keep.stat = keep.stat,
label = label,
model.names=model.names, model.numbers=model.numbers,
multicolumn = multicolumn,
no.space=no.space, notes=notes, notes.align=notes.align,
notes.append=notes.append, notes.label=notes.label, object.names=object.names,
omit=omit, omit.labels=omit.labels, omit.stat=omit.stat, omit.summary.stat=omit.summary.stat,
omit.table.layout=omit.table.layout,omit.yes.no=omit.yes.no,
order=order, ord.intercepts=ord.intercepts, perl=perl,
report=report, rownames=rownames, rq.se=rq.se, selection.equation=selection.equation,
single.row=single.row, star.char=star.char,
star.cutoffs=star.cutoffs, suppress.errors=suppress.errors,
table.layout=table.layout,
table.placement = table.placement, zero.component=zero.component,
summary.logical = summary.logical,
summary.stat = summary.stat,
nobs=nobs, mean.sd=mean.sd,
min.max=min.max, median=median, iqr=iqr, warn=save.warn.option))
}
betareg默认残差很重，由于其尺寸较大，可能会导致分配向量时出错。这可以通过更改 summary 调用中残差的 type 来解决，如 here.
但是，当使用 stargazer 呈现回归表时，无法明确设置残差类型。
有没有办法让（大）betareg 对象在 stargazer 中工作？
我能想到但不知道如何实施的潜在解决方案是：
- 指示原始
betareg调用中的剩余type（type = "pearson"（或任何其他类型）不起作用）。 - 明确指出在
betareg对象上调用summary时stargazer应该包含的参数。 - 还有其他吗？
示例：
set.seed(1)
df <- data.frame(y=runif(100000), x=runif(100000))
library(betareg)
beta <- betareg(y ~ x, data=df)
library(stargazer)
stargazer(beta)
# Error: cannot allocate vector of size 74.5 Gb
您可以 stargazer::.stargazer.wrap 完成任务并更改模型摘要的计算方式，但它大约有 8000 行长。
作为一种解决方法，首先计算一个可以被 table 生成函数消化的更小的回归，然后在编译之前替换系数和统计数据可能会容易得多。
我给你展示了使用 texreg 包的方法，用 stargazer 也可能。
foo <- y ~ x
beta0 <- betareg::betareg(foo, data=df[sample(nrow(df), 1e3), ]) ## small version
beta <- betareg::betareg(foo, data=df) ## actual version
(beta.sum <- betareg:::summary.betareg(beta, type='pearson')$coe) ## actual summary
# $mean
# Estimate Std. Error z value Pr(>|z|)
# (Intercept) 0.007933124 0.006967576 1.1385773 0.2548795
# x -0.010845820 0.012080681 -0.8977822 0.3693017
#
# $precision
# Estimate Std. Error z value Pr(>|z|)
# (phi) 1.999218 0.007501926 266.494 0
Table
屏幕：
texreg::screenreg(beta0,
digits=3,
override.coef=unlist(lapply(beta.sum, \(x) x[, 1])),
override.se=unlist(lapply(beta.sum, \(x) x[, 2])),
override.pvalues=unlist(lapply(beta.sum, \(x) x[, 4]))
)
# ==============================
# Model 1
# ------------------------------
# (Intercept) 0.008
# (0.007)
# x -0.011
# (0.012)
# Precision: (phi) 1.999 ***
# (0.008)
# ------------------------------
# Pseudo R^2 0.000
# Log Likelihood 2.137
# Num. obs. 1000
# ==============================
# *** p < 0.001; ** p < 0.01; * p < 0.05
LaTeX:
texreg::texreg(beta0,
digits=3,
override.coef=unlist(lapply(beta.sum, \(x) x[, 1])),
override.se=unlist(lapply(beta.sum, \(x) x[, 2])),
override.pvalues=unlist(lapply(beta.sum, \(x) x[, 4]))
)
# \begin{table}
# \begin{center}
# \begin{tabular}{l c}
# \hline
# & Model 1 \
# \hline
# (Intercept) & [=12=].008$ \
# & $(0.007)$ \
# x & $-0.011$ \
# & $(0.012)$ \
# Precision: (phi) & .999^{***}$ \
# & $(0.008)$ \
# \hline
# Pseudo R$^2$ & [=12=].000$ \
# Log Likelihood & .137$ \
# Num. obs. & 00$ \
# \hline
# \multicolumn{2}{l}{\scriptsize{$^{***}p<0.001$; $^{**}p<0.01$; $^{*}p<0.05$}}
# \end{tabular}
# \caption{Statistical models}
# \label{table:coefficients}
# \end{center}
# \end{table}
要获取 HTML 代码，请使用：
texreg::htmlreg
数据：
set.seed(1)
n <- 1e5
df <- data.frame(y=runif(n), x=runif(n))
我最终解决这个问题的方法是修改stargazer函数。特别是，在 .stargazer.wrap 中，您可以找到 here 的代码，我添加了以下代码：
else if (class(object.name)[1] == "betareg") { #betareg
.summary.object <<- summary(object.name, type = "person")
在 .add.model 内，即在这些代码行之后：
.add.model <-
function(object.name, user.coef=NULL, user.se=NULL, user.t=NULL, user.p=NULL, auto.t=TRUE, auto.p=TRUE, user.ci.lb=NULL, user.ci.rb=NULL) {
if (class(object.name)[1] == "Glm") {
.summary.object <<- summary.glm(object.name)
}
请注意，您需要使用新的 .stargazer.wrap 创建一个新的 stargazer 函数。我只是称它为 stargazer2:
stargazer2 <-
function(..., type = "latex", title="", style="default", summary=NULL, out=NULL, out.header=FALSE,
column.labels=NULL, column.separate = NULL, covariate.labels=NULL, dep.var.caption=NULL,
dep.var.labels=NULL, dep.var.labels.include=TRUE, align=FALSE, coef=NULL, se=NULL, t=NULL,
p=NULL, t.auto=TRUE, p.auto=TRUE, ci=FALSE, ci.custom=NULL, ci.level=0.95, ci.separator=NULL,
add.lines=NULL, apply.coef=NULL, apply.se=NULL, apply.t=NULL, apply.p=NULL, apply.ci=NULL,
colnames = NULL, column.sep.width = "5pt",
decimal.mark=NULL, df=TRUE, digit.separate=NULL, digit.separator=NULL, digits=NULL, digits.extra=NULL,
flip=FALSE,
float=TRUE, float.env="table", font.size=NULL, header=TRUE, initial.zero=NULL, intercept.bottom=TRUE,
intercept.top=FALSE, keep=NULL, keep.stat=NULL, label="", model.names=NULL, model.numbers=NULL,
multicolumn=TRUE, no.space=NULL, notes=NULL, notes.align=NULL, notes.append=TRUE, notes.label=NULL,
object.names=FALSE,
omit=NULL, omit.labels=NULL, omit.stat=NULL, omit.summary.stat=NULL, omit.table.layout=NULL,
omit.yes.no=c("Yes","No"), order=NULL, ord.intercepts=FALSE,
perl=FALSE, report=NULL, rownames = NULL,
rq.se = "nid", selection.equation=FALSE, single.row=FALSE, star.char=NULL,
star.cutoffs=NULL, suppress.errors=FALSE, table.layout=NULL, table.placement = "!htbp", zero.component=FALSE,
summary.logical=TRUE, summary.stat=NULL, nobs=TRUE, mean.sd=TRUE, min.max=TRUE, median=FALSE,
iqr=FALSE) {
save.warn.option <- getOption("warn")
options(warn=-1)
return(.stargazer.wrap(..., type=type, title=title, style=style, summary=summary, out=out, out.header=out.header,
column.labels=column.labels, column.separate = column.separate,
covariate.labels=covariate.labels, dep.var.caption = dep.var.caption,
dep.var.labels=dep.var.labels, dep.var.labels.include=dep.var.labels.include,
align=align, coef=coef, se=se, t=t, p=p, t.auto=t.auto, p.auto=p.auto,
ci=ci, ci.custom=ci.custom, ci.level=ci.level, ci.separator = ci.separator,
add.lines=add.lines, apply.coef=apply.coef, apply.se=apply.se, apply.t=apply.t,
apply.p=apply.p, apply.ci=apply.ci, colnames=colnames,
column.sep.width=column.sep.width, decimal.mark=decimal.mark, df=df,
digit.separate=digit.separate, digit.separator=digit.separator,
digits=digits, digits.extra=digits.extra,
flip=flip,
float=float, float.env=float.env,
font.size=font.size, header=header,
initial.zero=initial.zero,
intercept.bottom=intercept.bottom, intercept.top=intercept.top,
keep = keep, keep.stat = keep.stat,
label = label,
model.names=model.names, model.numbers=model.numbers,
multicolumn = multicolumn,
no.space=no.space, notes=notes, notes.align=notes.align,
notes.append=notes.append, notes.label=notes.label, object.names=object.names,
omit=omit, omit.labels=omit.labels, omit.stat=omit.stat, omit.summary.stat=omit.summary.stat,
omit.table.layout=omit.table.layout,omit.yes.no=omit.yes.no,
order=order, ord.intercepts=ord.intercepts, perl=perl,
report=report, rownames=rownames, rq.se=rq.se, selection.equation=selection.equation,
single.row=single.row, star.char=star.char,
star.cutoffs=star.cutoffs, suppress.errors=suppress.errors,
table.layout=table.layout,
table.placement = table.placement, zero.component=zero.component,
summary.logical = summary.logical,
summary.stat = summary.stat,
nobs=nobs, mean.sd=mean.sd,
min.max=min.max, median=median, iqr=iqr, warn=save.warn.option))
}