Rental Data Event Study
Dataset
The data set contain information for Rental price base on additional number of room in MSA levels, observation start in 2001 to 2005 with annual frequency observation, its also contain information like Unemployee Rate,Personal Income and Resident Population.
We also create dummy date that indicate, an observation happens in a specifict year, for example A has observation in 2002, so d.2002 will assign to 1.
We log response variables, and regress with other variables but in event study we will focus on time effect in this case is dummy time, treatment is for every msa that in LA is equal to 1, and non-LA is 0.
-NOTE : In this analysis, we exclude New Orlean MSA.
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.1 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(ggplot2)
library(readr)
library(dplyr)
library(stringr)
library(lmtest)## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericlibrary(lfe)## Loading required package: Matrix
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
##
## Attaching package: 'lfe'
##
## The following object is masked from 'package:lmtest':
##
## waldtestRENT.merge <- read.csv("MSA-RENT merge All.csv")
RENT.merge$treat <- ifelse(RENT.merge$state == "LA", 1, 0)
colnames(RENT.merge)## [1] "FirstNAME" "AREANAME" "RENT_0"
## [4] "RENT_1" "RENT_2" "RENT_3"
## [7] "RENT_4" "YEAR" "NAME.x"
## [10] "state" "Unemployee.Rate" "Personal.Income"
## [13] "Resident.Population" "nyear" "MSA"
## [16] "MSA.Code" "Price" "Change"
## [19] "NAME.y" "treat"# Remove NA
RENT.merge <- RENT.merge %>%
group_by(MSA) %>%
filter(!any(is.na(Unemployee.Rate)))
dloop <- data.frame(YEAR = unique(RENT.merge$YEAR))
## YEAR DUMMY
for (i in 1:nrow(dloop)) {
RENT.merge[paste0("d.", dloop$YEAR[i])] <- as.numeric(RENT.merge$YEAR == unique(RENT.merge$YEAR)[i])
}
#REMOVE NEW ORLEAN
RENT.merge1 <- RENT.merge
RENT.merge1$NS <- paste0(RENT.merge1$FirstNAME, RENT.merge1$state)
RENT.merge1 <- RENT.merge1 %>%
filter(NS != "newLA")Rent 0
mpl.00 <- felm(log(RENT_0) ~ treat + Price + Unemployee.Rate +
Personal.Income + Resident.Population +
treat:(d.2001 + d.2002 + d.2003 +
d.2005 + d.2006 + d.2007 + d.2008 +
d.2009 + d.2010 + d.2011 + d.2012 +
d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA,
data = RENT.merge1)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinitesummary(mpl.00)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinite##
## Call:
## felm(formula = log(RENT_0) ~ treat + Price + Unemployee.Rate + Personal.Income + Resident.Population + treat:(d.2001 + d.2002 + d.2003 + d.2005 + d.2006 + d.2007 + d.2008 + d.2009 + d.2010 + d.2011 + d.2012 + d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA, data = RENT.merge1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.247660 -0.042112 0.000362 0.042852 0.306519
##
## Coefficients:
## Estimate Cluster s.e. t value Pr(>|t|)
## treat NaN 0.000e+00 NaN NaN
## Price 4.993e-04 1.328e-04 3.761 0.000218 ***
## Unemployee.Rate 1.625e-02 2.766e-03 5.875 1.58e-08 ***
## Personal.Income 4.765e-06 1.517e-06 3.142 0.001914 **
## Resident.Population -1.047e-04 3.350e-05 -3.125 0.002025 **
## treat:d.2001 -9.232e-03 1.264e-02 -0.731 0.465809
## treat:d.2002 1.282e-02 3.393e-03 3.778 0.000204 ***
## treat:d.2003 1.890e-03 2.566e-03 0.736 0.462282
## treat:d.2005 7.991e-02 3.121e-02 2.560 0.011150 *
## treat:d.2006 1.535e-01 5.307e-02 2.893 0.004205 **
## treat:d.2007 1.437e-01 5.407e-02 2.657 0.008474 **
## treat:d.2008 1.481e-01 4.693e-02 3.157 0.001822 **
## treat:d.2009 1.937e-01 4.550e-02 4.256 3.10e-05 ***
## treat:d.2010 2.147e-01 4.034e-02 5.322 2.57e-07 ***
## treat:d.2011 2.227e-01 3.728e-02 5.974 9.41e-09 ***
## treat:d.2012 1.501e-01 4.333e-02 3.464 0.000641 ***
## treat:d.2013 1.924e-01 2.212e-02 8.696 8.77e-16 ***
## treat:d.2014 1.539e-01 2.525e-02 6.095 4.97e-09 ***
## treat:d.2015 1.345e-01 2.664e-02 5.049 9.41e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.07021 on 2973 degrees of freedom
## Multiple R-squared(full model): 0.918 Adjusted R-squared: 0.9111
## Multiple R-squared(proj model): 0.09216 Adjusted R-squared: 0.01643
## F-statistic(full model, *iid*):134.2 on 248 and 2973 DF, p-value: < 2.2e-16
## F-statistic(proj model): 53.66 on 19 and 216 DF, p-value: < 2.2e-16coef_df <- coeftest(mpl.00)
coef_df <- coef_df[,] %>%
as_tibble() %>%
mutate(variables = rownames(coef_df))
coef_df <- coef_df[6:19,]
event_df <- data.frame(time = 1:nrow(coef_df),
coef = coef_df$Estimate,
se = coef_df$`Std. Error`)
event_df <- rbind(event_df, c("time" = 3.5, "coef" = 0, "se" = 0))
event_df <- arrange(event_df, time)
# Calculate confidence intervals
event_df$ci_upper <- event_df$coef + 1.96 * event_df$se
event_df$ci_lower <- event_df$coef - 1.96 * event_df$se
# Extract dates from row names of coef_df
##dates <- as.Date(paste0(row.names(coef_df),"0101"), format = "treat:YEAR%Y%m%d")
dates<-seq.Date(from = as.Date("2001-01-01"),as.Date("2015-01-01"),by="year")
# Define start and end dates for plot
start_date <- as.Date("2001-01-01")
end_date <- as.Date("2015-01-01")
# Create sequence of dates for x-axis
dates_seq <- seq(from = start_date, to = end_date, by = "year")
# Subset event_df to only include dates after or equal to start_date
event_df_sub <- event_df[dates >= start_date, ]
pl <- ggplot(event_df, aes(x = dates, y = coef)) +
geom_point() +geom_line()+
#geom_errorbar(aes(ymin = ci_lower, ymax = ci_upper), width = 0.2) +
geom_ribbon(aes(ymin = ci_lower, ymax = ci_upper), alpha = 0.2) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
geom_vline(xintercept = as.Date("2005-01-01"), linetype = "dashed", color = "blue") +
scale_x_date(date_labels = "%Y", limits = c(start_date, end_date), breaks = "1 year") +
labs(x = "Year", y = "Coefficient")+ #title = "Fixed effect of RENT_0") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+theme_bw()
pl
Rent 1
mpl.01 <- felm(log(RENT_1) ~ treat + Price + Unemployee.Rate +
Personal.Income + Resident.Population +
treat:(d.2001 + d.2002 + d.2003 +
d.2005 + d.2006 + d.2007 + d.2008 +
d.2009 + d.2010 + d.2011 + d.2012 +
d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA,
data = RENT.merge1)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinitesummary(mpl.01)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinite##
## Call:
## felm(formula = log(RENT_1) ~ treat + Price + Unemployee.Rate + Personal.Income + Resident.Population + treat:(d.2001 + d.2002 + d.2003 + d.2005 + d.2006 + d.2007 + d.2008 + d.2009 + d.2010 + d.2011 + d.2012 + d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA, data = RENT.merge1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.20465 -0.03133 -0.00177 0.03118 0.33066
##
## Coefficients:
## Estimate Cluster s.e. t value Pr(>|t|)
## treat NaN 0.000e+00 NaN NaN
## Price 6.290e-04 1.165e-04 5.400 1.75e-07 ***
## Unemployee.Rate 1.742e-02 2.248e-03 7.749 3.58e-13 ***
## Personal.Income 3.709e-06 1.514e-06 2.450 0.015088 *
## Resident.Population -4.208e-05 3.509e-05 -1.199 0.231788
## treat:d.2001 -2.243e-03 6.634e-03 -0.338 0.735589
## treat:d.2002 1.194e-02 3.747e-03 3.185 0.001661 **
## treat:d.2003 1.437e-03 2.919e-03 0.492 0.623054
## treat:d.2005 4.742e-02 2.210e-02 2.146 0.032998 *
## treat:d.2006 1.231e-01 4.631e-02 2.658 0.008453 **
## treat:d.2007 1.131e-01 4.725e-02 2.394 0.017543 *
## treat:d.2008 1.185e-01 4.024e-02 2.944 0.003592 **
## treat:d.2009 1.641e-01 3.825e-02 4.289 2.70e-05 ***
## treat:d.2010 1.814e-01 3.367e-02 5.389 1.85e-07 ***
## treat:d.2011 1.885e-01 3.149e-02 5.987 8.83e-09 ***
## treat:d.2012 1.501e-01 3.176e-02 4.726 4.12e-06 ***
## treat:d.2013 1.738e-01 3.409e-02 5.097 7.51e-07 ***
## treat:d.2014 1.341e-01 3.834e-02 3.498 0.000569 ***
## treat:d.2015 1.128e-01 3.368e-02 3.350 0.000952 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.0532 on 2973 degrees of freedom
## Multiple R-squared(full model): 0.9465 Adjusted R-squared: 0.9421
## Multiple R-squared(proj model): 0.1317 Adjusted R-squared: 0.05924
## F-statistic(full model, *iid*):212.3 on 248 and 2973 DF, p-value: < 2.2e-16
## F-statistic(proj model): 22.74 on 19 and 216 DF, p-value: < 2.2e-16coef_df1 <- coeftest(mpl.01)
coef_df1 <- coef_df1[,] %>%
as_tibble() %>%
mutate(variables = rownames(coef_df1))
coef_df1 <- coef_df1[6:19,]
event_df1 <- data.frame(time = 1:nrow(coef_df1),
coef = coef_df1$Estimate,
se = coef_df1$`Std. Error`)
event_df1 <- rbind(event_df1, c("time" = 3.5, "coef" = 0, "se" = 0))
event_df1 <- arrange(event_df1, time)
# Calculate confidence intervals
event_df1$ci_upper <- event_df1$coef + 1.96 * event_df1$se
event_df1$ci_lower <- event_df1$coef - 1.96 * event_df1$se
# Subset event_df to only include dates after or equal to start_date
event_df_sub1 <- event_df1[dates >= start_date, ]
pl1 <- ggplot(event_df1, aes(x = dates, y = coef)) +
geom_point() +geom_line()+
#geom_errorbar(aes(ymin = ci_lower, ymax = ci_upper), width = 0.2) +
geom_ribbon(aes(ymin = ci_lower, ymax = ci_upper), alpha = 0.2) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
geom_vline(xintercept = as.Date("2005-01-01"), linetype = "dashed", color = "blue") +
scale_x_date(date_labels = "%Y", limits = c(start_date, end_date), breaks = "1 year") +
labs(x = "Year", y = "Coefficient")+ #title = "Fixed effect of RENT_1") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+theme_bw()
pl1
Rent 2
mpl.02 <- felm(log(RENT_2) ~ treat + Price + Unemployee.Rate +
Personal.Income + Resident.Population +
treat:(d.2001 + d.2002 + d.2003 +
d.2005 + d.2006 + d.2007 + d.2008 +
d.2009 + d.2010 + d.2011 + d.2012 +
d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA,
data = RENT.merge1)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinitesummary(mpl.02)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinite##
## Call:
## felm(formula = log(RENT_2) ~ treat + Price + Unemployee.Rate + Personal.Income + Resident.Population + treat:(d.2001 + d.2002 + d.2003 + d.2005 + d.2006 + d.2007 + d.2008 + d.2009 + d.2010 + d.2011 + d.2012 + d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA, data = RENT.merge1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.167925 -0.030814 -0.001612 0.030462 0.293484
##
## Coefficients:
## Estimate Cluster s.e. t value Pr(>|t|)
## treat NaN 0.000e+00 NaN NaN
## Price 5.039e-04 1.117e-04 4.509 1.07e-05 ***
## Unemployee.Rate 1.502e-02 2.152e-03 6.981 3.56e-11 ***
## Personal.Income 2.482e-06 1.372e-06 1.809 0.071902 .
## Resident.Population -5.901e-05 3.618e-05 -1.631 0.104373
## treat:d.2001 7.816e-04 6.529e-03 0.120 0.904820
## treat:d.2002 1.278e-02 3.273e-03 3.906 0.000125 ***
## treat:d.2003 2.157e-03 2.336e-03 0.923 0.356856
## treat:d.2005 2.819e-02 1.977e-02 1.426 0.155367
## treat:d.2006 1.028e-01 4.394e-02 2.340 0.020171 *
## treat:d.2007 9.486e-02 4.503e-02 2.107 0.036284 *
## treat:d.2008 1.017e-01 3.815e-02 2.667 0.008236 **
## treat:d.2009 1.452e-01 3.655e-02 3.971 9.74e-05 ***
## treat:d.2010 1.649e-01 3.252e-02 5.071 8.50e-07 ***
## treat:d.2011 1.726e-01 3.076e-02 5.612 6.11e-08 ***
## treat:d.2012 1.250e-01 3.261e-02 3.832 0.000167 ***
## treat:d.2013 1.591e-01 3.712e-02 4.285 2.75e-05 ***
## treat:d.2014 1.218e-01 4.179e-02 2.914 0.003947 **
## treat:d.2015 1.005e-01 3.482e-02 2.886 0.004296 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.05202 on 2973 degrees of freedom
## Multiple R-squared(full model): 0.9442 Adjusted R-squared: 0.9395
## Multiple R-squared(proj model): 0.1046 Adjusted R-squared: 0.02987
## F-statistic(full model, *iid*):202.7 on 248 and 2973 DF, p-value: < 2.2e-16
## F-statistic(proj model): 23.73 on 19 and 216 DF, p-value: < 2.2e-16coef_df2 <- coeftest(mpl.02)
coef_df2 <- coef_df2[,] %>%
as_tibble() %>%
mutate(variables = rownames(coef_df2))
coef_df2 <- coef_df2[6:19,]
event_df2 <- data.frame(time = 1:nrow(coef_df2),
coef = coef_df2$Estimate,
se = coef_df2$`Std. Error`)
event_df2 <- rbind(event_df2, c("time" = 3.5, "coef" = 0, "se" = 0))
event_df2 <- arrange(event_df2, time)
# Calculate confidence intervals
event_df2$ci_upper <- event_df2$coef + 1.96 * event_df2$se
event_df2$ci_lower <- event_df2$coef - 1.96 * event_df2$se
# Subset event_df to only include dates after or equal to start_date
event_df_sub2 <- event_df2[dates >= start_date, ]
pl2 <- ggplot(event_df2, aes(x = dates, y = coef)) +
geom_point() +geom_line()+
#geom_errorbar(aes(ymin = ci_lower, ymax = ci_upper), width = 0.2) +
geom_ribbon(aes(ymin = ci_lower, ymax = ci_upper), alpha = 0.2) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
geom_vline(xintercept = as.Date("2005-01-01"), linetype = "dashed", color = "blue") +
scale_x_date(date_labels = "%Y", limits = c(start_date, end_date), breaks = "1 year") +
labs(x = "Year", y = "Coefficient")+ #title = "Fixed effect of RENT_2") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+theme_bw()
pl2
Rent 3
mpl.03 <- felm(log(RENT_3) ~ treat + Price + Unemployee.Rate +
Personal.Income + Resident.Population +
treat:(d.2001 + d.2002 + d.2003 +
d.2005 + d.2006 + d.2007 + d.2008 +
d.2009 + d.2010 + d.2011 + d.2012 +
d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA,
data = RENT.merge1)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinitesummary(mpl.03)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinite##
## Call:
## felm(formula = log(RENT_3) ~ treat + Price + Unemployee.Rate + Personal.Income + Resident.Population + treat:(d.2001 + d.2002 + d.2003 + d.2005 + d.2006 + d.2007 + d.2008 + d.2009 + d.2010 + d.2011 + d.2012 + d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA, data = RENT.merge1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.183806 -0.033039 -0.001461 0.032035 0.238102
##
## Coefficients:
## Estimate Cluster s.e. t value Pr(>|t|)
## treat NaN 0.000e+00 NaN NaN
## Price 4.841e-04 1.093e-04 4.430 1.50e-05 ***
## Unemployee.Rate 1.362e-02 2.391e-03 5.697 3.96e-08 ***
## Personal.Income 1.751e-06 1.544e-06 1.134 0.258010
## Resident.Population -7.541e-05 4.154e-05 -1.815 0.070888 .
## treat:d.2001 1.750e-03 7.046e-03 0.248 0.804044
## treat:d.2002 1.409e-02 3.229e-03 4.364 1.98e-05 ***
## treat:d.2003 3.143e-03 2.439e-03 1.289 0.198925
## treat:d.2005 -3.690e-02 1.302e-02 -2.833 0.005042 **
## treat:d.2006 4.484e-02 4.387e-02 1.022 0.307849
## treat:d.2007 3.779e-02 4.476e-02 0.844 0.399429
## treat:d.2008 4.466e-02 3.886e-02 1.149 0.251729
## treat:d.2009 8.632e-02 3.733e-02 2.312 0.021712 *
## treat:d.2010 1.074e-01 3.469e-02 3.094 0.002234 **
## treat:d.2011 1.152e-01 3.373e-02 3.417 0.000757 ***
## treat:d.2012 7.001e-02 3.058e-02 2.290 0.023007 *
## treat:d.2013 8.632e-02 3.665e-02 2.355 0.019405 *
## treat:d.2014 4.999e-02 4.027e-02 1.241 0.215863
## treat:d.2015 2.868e-02 3.135e-02 0.915 0.361222
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.05444 on 2973 degrees of freedom
## Multiple R-squared(full model): 0.9449 Adjusted R-squared: 0.9403
## Multiple R-squared(proj model): 0.07094 Adjusted R-squared: -0.006557
## F-statistic(full model, *iid*):205.6 on 248 and 2973 DF, p-value: < 2.2e-16
## F-statistic(proj model): 15.24 on 19 and 216 DF, p-value: < 2.2e-16coef_df3 <- coeftest(mpl.03)
coef_df3 <- coef_df3[,] %>%
as_tibble() %>%
mutate(variables = rownames(coef_df3))
coef_df3 <- coef_df3[6:19,]
event_df3 <- data.frame(time = 1:nrow(coef_df3),
coef = coef_df3$Estimate,
se = coef_df3$`Std. Error`)
event_df3 <- rbind(event_df3, c("time" = 3.5, "coef" = 0, "se" = 0))
event_df3 <- arrange(event_df3, time)
# Calculate confidence intervals
event_df3$ci_upper <- event_df3$coef + 1.96 * event_df3$se
event_df3$ci_lower <- event_df3$coef - 1.96 * event_df3$se
# Subset event_df to only include dates after or equal to start_date
event_df_sub3 <- event_df3[dates >= start_date, ]
pl3 <- ggplot(event_df3, aes(x = dates, y = coef)) +
geom_point() +geom_line()+
#geom_errorbar(aes(ymin = ci_lower, ymax = ci_upper), width = 0.2) +
geom_ribbon(aes(ymin = ci_lower, ymax = ci_upper), alpha = 0.2) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
geom_vline(xintercept = as.Date("2005-01-01"), linetype = "dashed", color = "blue") +
scale_x_date(date_labels = "%Y", limits = c(start_date, end_date), breaks = "1 year") +
labs(x = "Year", y = "Coefficient")+ #title = "Fixed effect of RENT_3") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+theme_bw()
pl3
Rent 4
mpl.04 <- felm(log(RENT_4) ~ treat + Price + Unemployee.Rate +
Personal.Income + Resident.Population +
treat:(d.2001 + d.2002 + d.2003 +
d.2005 + d.2006 + d.2007 + d.2008 +
d.2009 + d.2010 + d.2011 + d.2012 +
d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA,
data = RENT.merge1)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinitesummary(mpl.04)## Warning in chol.default(mat, pivot = TRUE, tol = tol): the matrix is either
## rank-deficient or indefinite##
## Call:
## felm(formula = log(RENT_4) ~ treat + Price + Unemployee.Rate + Personal.Income + Resident.Population + treat:(d.2001 + d.2002 + d.2003 + d.2005 + d.2006 + d.2007 + d.2008 + d.2009 + d.2010 + d.2011 + d.2012 + d.2013 + d.2014 + d.2015) | MSA + YEAR | 0 | MSA, data = RENT.merge1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.22538 -0.03951 -0.00011 0.03889 0.24607
##
## Coefficients:
## Estimate Cluster s.e. t value Pr(>|t|)
## treat NaN 0.000e+00 NaN NaN
## Price 5.579e-04 1.261e-04 4.424 1.54e-05 ***
## Unemployee.Rate 1.422e-02 2.826e-03 5.030 1.03e-06 ***
## Personal.Income 2.197e-06 1.553e-06 1.415 0.158456
## Resident.Population -5.515e-05 4.626e-05 -1.192 0.234562
## treat:d.2001 -2.059e-02 2.459e-02 -0.837 0.403383
## treat:d.2002 1.271e-02 3.339e-03 3.806 0.000184 ***
## treat:d.2003 2.591e-03 2.416e-03 1.073 0.284584
## treat:d.2005 -1.406e-02 3.417e-02 -0.412 0.681027
## treat:d.2006 4.776e-02 5.507e-02 0.867 0.386760
## treat:d.2007 4.026e-02 5.581e-02 0.721 0.471503
## treat:d.2008 4.613e-02 5.121e-02 0.901 0.368680
## treat:d.2009 8.798e-02 4.986e-02 1.764 0.079062 .
## treat:d.2010 1.076e-01 4.644e-02 2.316 0.021497 *
## treat:d.2011 1.155e-01 4.545e-02 2.541 0.011750 *
## treat:d.2012 7.992e-02 4.705e-02 1.699 0.090849 .
## treat:d.2013 1.041e-01 5.176e-02 2.012 0.045472 *
## treat:d.2014 6.753e-02 5.714e-02 1.182 0.238535
## treat:d.2015 4.680e-02 4.305e-02 1.087 0.278189
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.06609 on 2973 degrees of freedom
## Multiple R-squared(full model): 0.9314 Adjusted R-squared: 0.9256
## Multiple R-squared(proj model): 0.0544 Adjusted R-squared: -0.02448
## F-statistic(full model, *iid*):162.7 on 248 and 2973 DF, p-value: < 2.2e-16
## F-statistic(proj model): 19.86 on 19 and 216 DF, p-value: < 2.2e-16coef_df4 <- coeftest(mpl.04)
coef_df4 <- coef_df4[,] %>%
as_tibble() %>%
mutate(variables = rownames(coef_df4))
coef_df4 <- coef_df4[6:19,]
event_df4 <- data.frame(time = 1:nrow(coef_df4),
coef = coef_df4$Estimate,
se = coef_df4$`Std. Error`)
event_df4 <- rbind(event_df4, c("time" = 3.5, "coef" = 0, "se" = 0))
event_df4 <- arrange(event_df4, time)
# Calculate confidence intervals
event_df4$ci_upper <- event_df4$coef + 1.96 * event_df4$se
event_df4$ci_lower <- event_df4$coef - 1.96 * event_df4$se
# Subset event_df to only include dates after or equal to start_date
event_df_sub4 <- event_df4[dates >= start_date, ]
pl4 <- ggplot(event_df4, aes(x = dates, y = coef)) +
geom_point() +geom_line()+
#geom_errorbar(aes(ymin = ci_lower, ymax = ci_upper), width = 0.2) +
geom_ribbon(aes(ymin = ci_lower, ymax = ci_upper), alpha = 0.2) +
geom_hline(yintercept = 0, linetype = "dashed", color = "red") +
geom_vline(xintercept = as.Date("2005-01-01"), linetype = "dashed", color = "blue") +
scale_x_date(date_labels = "%Y", limits = c(start_date, end_date), breaks = "1 year") +
labs(x = "Year", y = "Coefficient")+ #title = "Fixed effect of RENT_4") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+theme_bw()
pl4