diff --git a/DataWork/descriptive-statistics.R b/DataWork/descriptive-statistics.R
new file mode 100644
index 0000000..eb80402
--- /dev/null
+++ b/DataWork/descriptive-statistics.R
@@ -0,0 +1,101 @@
+# Load packages ################################################################
+
+library(here)
+library(tidyverse)
+library(skimr)
+library(lfe)
+library(huxtable)
+library(openxlsx)
+
+# Load data
+census <-
+ read_rds(here("DataWork",
+ "DataSets",
+ "Final",
+ "census.RDS"))
+
+# Exploring the data ###########################################################
+
+# See summary statistics for the whole data set:
+summary(census)
+summary(census, 0)
+
+# See summary statistics for a single variable:
+summary(census$region)
+summary(census$death)
+
+# Frequency table using table()
+table(census$region)
+table(census$state, census$region)
+
+# Now with skimr
+skim(census)
+
+# Creating custom summary statistics tables ####################################
+
+summary_stats <-
+ skim_with(numeric = sfl(Mean = mean, # Variable name = statistic
+ Median = median,
+ SD = sd,
+ Min = min,
+ Max = max),
+ append = FALSE) # Remove all default statistics
+
+summary_stats_table <-
+ census %>%
+ summary_stats() %>%
+ yank("numeric") %>%
+ select(- complete_rate) %>%
+ rename(`Missings` = n_missing)
+
+# Exporting tables #############################################################
+
+quick_xlsx(table,
+ file = here("DataWork",
+ "Output",
+ "Raw",
+ "summary-statistics.xlsx"))
+
+## Add variable names --------------------------------------------
+# Extract variable labels from data frame
+# Extract variable labels from data frame
+census_dictionary <-
+ data.frame("Variable" = attributes(census)$var.labels,
+ "name" = names(census))
+
+summary_stats_table <-
+ summary_stats_table %>%
+ rename(name = skim_variable) %>% # Rename var with var names so we can merge the datasets
+ left_join(census_dictionary) %>% # Merge to variable labels
+ select(-name) %>% # Keep only variable labels instead of names
+ as_hux # Convert it into a huxtable object
+
+summary_stats_table <-
+ summary_stats_table %>%
+ relocate(Variable) %>% # Make variable labels the first column
+ set_header_rows(1, TRUE) %>% # Use stats name as table header
+ set_header_cols("Variable", TRUE) %>% # Use variable name as row header
+ set_number_format(everywhere, 2:ncol(.), "%9.0f") %>% # Don't round large numbers
+ theme_basic() # Set a theme for quick formatting
+
+quick_xlsx(summary_stats_table,
+ file = here("DataWork",
+ "Output",
+ "Raw",
+ "summary-statistics-formatted.xlsx"))
+
+# Aggregate tables ###########################################################
+
+census_region <-
+ census %>%
+ group_by(region) %>%
+ summarise(`Number of States` = n_distinct(state),
+ `Total Population` = sum(pop))
+
+
+# Run regression ######################################################
+
+reg1 <-
+ lm(divorce ~ pop + popurban + marriage,
+ census)
+
diff --git a/Presentations/05-descriptive-analysis.Rmd b/Presentations/05-descriptive-analysis.Rmd
index 07e44e3..9043abf 100644
--- a/Presentations/05-descriptive-analysis.Rmd
+++ b/Presentations/05-descriptive-analysis.Rmd
@@ -129,6 +129,30 @@ But that's enough of me talking. Let's get you all to run some code
# Setting the stage
+
+Load the packages that we will use today
+```{r, eval = F}
+ # Install new packages
+ install.packages("skimr")
+ install.packages("lfe")
+ install.packages("huxtable")
+ install.packages("openxlsx")
+```
+
+```{r, warning = FALSE}
+ # Load packages
+ library(here)
+ library(tidyverse)
+ library(skimr)
+ library(lfe)
+ library(huxtable)
+ library(openxlsx)
+```
+
+---
+
+# Setting the stage
+
Load the data that we will use today: Stata's `census` dataset
```{r}
# Load data
@@ -161,27 +185,6 @@ glimpse(census)
---
-# Setting the stage
-
-
-Load the packages that we will use today
-```{r, eval = F}
- # Install new packages
- install.packages("skimr")
- install.packages("lfe")
- install.packages("huxtable")
-```
-
-```{r, warning = FALSE}
- # Load packages
- library(tidyverse)
- library(skimr)
- library(lfe)
- library(huxtable)
-```
-
----
-
class: inverse, center, middle
name: exploring
@@ -214,8 +217,8 @@ Use the `summary()` function to describe the `census` data frame.
# Exploring a dataset
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
+```{r}
+summary(census)
```
---
@@ -238,11 +241,6 @@ include_app("https://luizaandrade.shinyapps.io/learnr/")
Use the `summary()` function to display summary statistics for a continuous variable in the `census` data frame.
]
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
-```
-
-
---
# Summarizing categorical variables
@@ -268,8 +266,10 @@ Use the `table()` function to display frequency tables for:
## One way tabulation
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
+--
+
+```{r}
+table(census$region)
```
@@ -279,8 +279,10 @@ include_app("https://luizaandrade.shinyapps.io/learnr/")
## Two way tabulation
+--
+
```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
+table(census$state, census$region)
```
@@ -402,12 +404,10 @@ census %>%
```
Here are a few functions that can be used within `sfl()`:
-- Center: `mean()`, `median()`
-- Spread: `sd()`, `IQR()`, `mad()`
-- Range: `min()`, `max()`, `quantile()`
-- Position: `first()`, `last()`, `nth()`,
-- Count: `n()`, `n_distinct()`
-- Logical: `any()`, `all()`
+- Center: `mean`, `median`
+- Spread: `sd`, `IQR`, `variance`
+- Range: `min`, `max`, `quantile`
+- Count: `n_complete`, `n_missing`, `length`
---
@@ -574,7 +574,7 @@ summary_stats_table <- #<<
relocate(Variable) %>% # Make variable labels the first column #<<
set_header_rows(1, TRUE) %>% # Use stats name as table header #<<
set_header_cols("Variable", TRUE) %>% # Use variable name as row header #<<
- set_number_format("\"%9.0f\"" ) %>% # Don't round large numbers #<<
+ set_number_format(everywhere, 2:ncol(.), "%9.0f") %>% # Don't round large numbers
theme_basic() # Set a theme for quick formatting #<<
```
@@ -591,7 +591,7 @@ summary_stats_table <- #<<
# Beautifying tables
.small[
-```{r, message = FALSE, eval = F}
+```{r, message = FALSE}
# Extract variable labels from data frame
census_dictionary <-
@@ -611,12 +611,15 @@ summary_stats_table <-
relocate(Variable) %>% # Make variable labels the first column
set_header_rows(1, TRUE) %>% # Use stats name as table header
set_header_cols("Variable", TRUE) %>% # Use variable name as row header
- set_number_format("\"%9.0f\"" ) %>% # Don't round large numbers
+ set_number_format(everywhere, 2:ncol(.), "%9.0f") %>% # Don't round large numbers
theme_basic() # Set a theme for quick formatting
# Now export it #<<
quick_xlsx(summary_stats_table, #<<
- file = file.path(rawOutput, "summary-stats-basic.xlsx")) #<<
+ file = here("DataWork", #<<
+ "Output", #<<
+ "Raw", #<<
+ "summary-stats-basic.xlsx")) #<<
quick_latex(summary_stats_table, #<<
file = here("DataWork", #<<
@@ -706,11 +709,6 @@ The "name-value" pairs mentioned under `...` look like this: `new_variable = sta
Recreate the `region_stats` data set, now including the average and the standard deviation of the population.
]
-
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
-```
-
---
# Aggregating observations
@@ -820,8 +818,10 @@ Using the `census` data, run a regression of the number of divorces on populatio
]
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
+```{r}
+reg1 <-
+ lm(divorce ~ pop + popurban + marriage,
+ census)
```
@@ -897,8 +897,12 @@ Using the `census` data, run a regression of the number of divorces on populatio
Using the `census` data, run a regression of divorce on population, urban population and number of marriages controlling for region fixed effects.
]
-```{r, echo = FALSE}
-include_app("https://luizaandrade.shinyapps.io/learnr/")
+```{r, evalt = FALSE}
+reg2 <-
+ felm(divorce ~ pop + popurban + marriage | region | 0 | 0,
+ census)
+
+summary(reg2)
```
---
diff --git a/Presentations/05-descriptive-analysis.html b/Presentations/05-descriptive-analysis.html
index 46ae738..5a30d5c 100644
--- a/Presentations/05-descriptive-analysis.html
+++ b/Presentations/05-descriptive-analysis.html
@@ -20,6 +20,7 @@
+