-
Notifications
You must be signed in to change notification settings - Fork 10
/
Copy path03b_stocks_select_sumstats.Rmd
153 lines (118 loc) · 4.87 KB
/
03b_stocks_select_sumstats.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
---
title: "Identifying Price Informativeness"
author: "Eduardo Davila^[Yale] & Cecilia Parlatore^[NYU Stern]"
date: "`r Sys.Date()`"
output:
html_document: default
pdf_document: default
---
```{r echo=FALSE, include=FALSE}
library(here); library(tidyverse); library(kableExtra);
path <- here::here(); print(path); setwd(path); rm(path)
load("intermediate/data_selected.RData")
options(scipen = 999) # no scientific notation
```
# Summary Statistics: Data
First define function sum_stat().
```{r}
# input_df <- df_q
sum_stats <- function(input_df, namefile){
results <- input_df %>%
select(delta_log_price,ebit) %>%
summarize(across(everything(),
list(mean = ~ mean(., na.rm = T),
sd = ~ sd(., na.rm = T),
p10 = ~ quantile(., 0.1, na.rm = T, names = F),
median = ~ median(., na.rm = T),
p90 = ~ quantile(., 0.9, na.rm = T, names = F)),
.names = "{fn}.{col}")) %>%
pivot_longer(everything()) %>%
separate(name, c("stat", "var"), sep = "(\\.)") %>%
pivot_wider(names_from = stat, values_from = value) %>%
mutate(across(where(is.numeric), format, digits = 4, nsmall = 2)) %>%
rename("Mean" = mean,
"St. Dev" = sd,
"P10" = p10,
"Median" = median,
"P90" = p90) %>%
data.frame() %>%
select(-var)
rownames(results) <- c("Change in log price", "Earnings")
directory <- "output/output_tables/"
kab <- kable(results, "latex", booktabs = T)
path <- paste(directory, namefile, ".tex", sep = "")
fileConn <- file(path); writeLines(kab, fileConn); close(fileConn)
results2 <- input_df %>% group_by(permno) %>%
summarize(count = n(),
mean_payoff = mean(ebit, na.rm = T),
std_payoff = sd(ebit, na.rm = T)) %>%
select(mean_payoff,std_payoff) %>%
summarize(across(everything(),
list(mean = ~ mean(., na.rm = T),
sd = ~ sd(., na.rm = T),
p10 = ~ quantile(., 0.1, na.rm = T, names = F),
median = ~ median(., na.rm = T),
p90 = ~ quantile(., 0.9, na.rm = T, names = F)),
.names = "{fn}.{col}")) %>%
pivot_longer(everything()) %>%
separate(name, c("stat", "var"), sep = "(\\.)") %>%
pivot_wider(names_from = stat, values_from = value) %>%
mutate(across(where(is.numeric), format, digits = 4, nsmall = 2)) %>%
rename("Mean" = mean,
"St. Dev" = sd,
"P10" = p10,
"Median" = median,
"P90" = p90) %>%
data.frame() %>%
select(-var)
rownames(results2) <- c("Mean Earnings","St. Dev Earnings")
directory <- "output/output_tables/"
kab <- kable(results, "latex", booktabs = T)
path <- paste(directory, namefile,"_permno", ".tex", sep = "")
fileConn <- file(path); writeLines(kab, fileConn); close(fileConn)
p <- input_df %>% group_by(permno) %>%
summarize(count = n(),
std_payoff = sd(ebit, na.rm = T)) %>%
ggplot() +
aes(std_payoff) +
geom_density() +
scale_x_log10() +
labs(x = "St. Dev. Earnings", y = "Density (# of securities)")
name <- paste("output/output_figures/", namefile, ".pdf", sep = "")
ggsave(name, plot = p, width = 12, height = 5, units = "in", dpi = 300)
return()
}
summ_q <- sum_stats(df_q, "summary_stats_q")
summ_a <- sum_stats(df_a, "summary_stats_a")
```
```{r}
## Average growth rate dispersion
df_earnings <- df_q %>% group_by(permno) %>%
summarize(count = n(),
mean_payoff = mean(delta_log_payoff_growth, na.rm = T),
std_payoff = sd(delta_log_payoff_growth, na.rm = T)) %>%
mutate(log_std_payoff = log(std_payoff))
mean(df_earnings$mean_payoff)
median(df_earnings$mean_payoff)
x_start <- -3
x_end <- 7.5
x_step <- 1
x_axis <- seq(x_start, x_end, x_step)
x_labels <- exp(x_axis) %>% format(digits = 1)
y_start <- 0
y_end <- 0.05
y_step <- 0.01
y_axis <- seq(y_start, y_end, y_step)
p <- df_earnings %>%
ggplot(aes(x = log_std_payoff)) +
geom_histogram(aes(y = stat(count) / sum(count)), bins = 81, colour = "black", fill = "steelblue", alpha = 0.2) +
labs(x = "Standard Deviation of Earnings' Growth Rates (log-scale)",
y = "Frequency") +
theme_classic() +
theme(text = element_text(size = 16)) +
scale_x_continuous(breaks = x_axis, labels = x_labels, expand = c(0.003, 0.009)) +
scale_y_continuous(breaks = y_axis, expand = c(0.0, 0.0)) +
coord_cartesian(xlim = c(x_start, x_end), ylim = c(y_start, y_end))
p
ggsave("output/output_figures/earnings_sd_histogram_quarterly.pdf", plot = p, width = 12, height = 5, units = "in", dpi = 300)
```