+ - 0:00:00
Notes for current slide
Notes for next slide

1.3: Meet R

ECON 480 · Econometrics · Fall 2019

Ryan Safner
Assistant Professor of Economics
safner@hood.edu
ryansafner/metricsf19
metricsF19.classes.ryansafner.com

Data Science

  • You go into data analysis with the tools you know, not the tools you need

  • The next 2-3 weeks are all about giving you the tools you need

    • Admittedly, a bit before you know what you need them for

  • We will extend them as we learn specific models

Why Not Excel? I

Why Not Excel? II

Why Use R?

  • Free and open source

  • A very large community

    • Written by statisticians for statistics
    • Most packages are written for R first

  • Can handle virtually any data format

  • Makes replication easy

  • Can integrate into documents (with R markdown)

  • R is a language so it can do everything

    • A good stepping stone to learning other languages like Python

Excel and Stata Can't Do This (Execute Inside the Slides)

library("gapminder")
ggplot(data = gapminder, 
       aes(x = gdpPercap,
           y = lifeExp,
           color = continent))+
  geom_point(alpha=0.3)+
  geom_smooth(method = "lm")+
    scale_x_log10(breaks=c(1000,10000, 100000),
                  label=scales::dollar)+
    labs(x = "GDP/Capita",
         y = "Life Expectancy (Years)")+
  facet_wrap(~continent)+
  guides(color = F)+
  theme_light()

Or This: Execute R Code Inside Your Documents

Code

  library(gapminder)

The average GDP per capita is $`r round(mean(gapminder$gdpPercap),2)` with a standard deviation of $`r round(sd(gapminder$gdpPercap),2)` .

Output

The average GDP per capita is $7215.33 with a standard deviation of $9857.45.

Meet R and R Studio

R and R Studio I

  • R is the programming language that executes commands

  • R Studio is an integrated development environment (IDE) that makes your coding life a lot easier

    • Write code in scripts
    • Execture individual commands or entire scripts
    • Auto-complete, highlight syntax
    • View data, objects, and plots
    • Get help and documentation on commands and functions
    • Integration code into documents with R Markdown

R Studio

R Studio

R and R Studio II

  • Download and install R & R Studio1 (in that order)

  • R is like your car's engine, R Studio is the dashboard

  • You will do everything in R Studio and never open the R program itself

  • R itself is just a command language

  • The R app is basically just a command line, you can even just use your computer's command line!2

R Studio

R Studio

1The (free) Desktop version.

2 "Command Prompt" on Windows, "Terminal" on Unix (Mac and Linux). Type r and hit enter, and you can now execute R commands.

R and R Studio III

R Studio has 4 window panes:

  1. Source1: a text editor for documents, R scripts, etc.
  2. Console: type in commands to run
  3. Browser: view files, plots, help, etc
  4. Environment: view created objects, command history, version control
  • Customize the sizes of these panes (I often hide the console and use the text editor)
    • CTRL+SHIFT+[number] will maximize a pane. Type again to see all four.

R Studio

R Studio

1May not be immediately visible until you create new files.

Learning...

  • You don't "learn R", you learn how to do things in R

  • In order to do learn this, you need to learn how to search for what you want to do

Learning...

  • You don't "learn R", you learn how to do things in R

  • In order to do learn this, you need to learn how to search for what you want to do

...and Sucking

Ways to Use R

1. Using the Console

  • Type individual commands into the console window

  • Great for testing individual commands to see what happens

  • Not saved! Not reproducible! Not recommended! 

2+2
## [1] 4
summary(mpg$hwy)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   12.00   18.00   24.00   23.44   27.00   44.00

1. Using the Console

  • Type individual commands into the console window

  • Great for testing individual commands to see what happens

  • Not saved! Not reproducible! Not recommended! 

ggplot(mpg, aes(x=displ, y=hwy))+
geom_point(aes(color=class))+
geom_smooth()

2. Writing an R Script

  • Source pane is a text-editor

  • Make .R files: all input commands in a single script

  • Comment with #

  • Can run any or all of script at once

  • Can save, reproduce, and send to others!

2+2 # just testing!
head(mpg) # look at mpg data 
# create a plot 
ggplot(mpg, aes(x=displ, y=hwy))+
geom_point(aes(color=class))+
geom_smooth()

3. Using Markdown

  • For a later lecture: R Markdown, a simple markup language to write documents in

    • Optional, but many students have enjoyed it and use it well beyond this class!

  • Can integrate text, R code, figures, citations and bibliographies into a single plain-text file1 and then output into a variety of formats: PDF, webpage, slides, Word doc, etc.

1OK, to be fair, citations require one additional file!

For Today

  • Practicing typing at the Command line/Console

  • Learning different commands and objects relevant for analysis

  • Saving and running .R scripts

  • Later: R markdown, literate programming, workflow management

  • Today may seem a bit overwhelming

    • You don't need to know or internalize all of this today
    • Use this as a reference to come back to over the semester
    • Last year I started making a partial book, I may revive it

Coding Basics

Getting to Know Your Computer

  • R assumes a default (often inconvenient) "working directory" on your computer

    • The first place it looks to open or save files

  • Find out where R this is with getwd()

  • Change it with setwd(path/to/folder)1

  • Soon I'll show you better ways where you won't ever have to worry about this

1 Note the path will be OS-specific. For Windows it might be C:/Documents/. For Mac it is often your username folder.

Coding

Hadley Wickham

Chief Scientist, R Studio

"There’s an implied contract between you and R: it will do the tedious computation for you, but in return, you must be completely precise in your instructions. Typos matter. Case matters." - R for Data Science, Ch. 4

Say Hello to My Little Friend

Say Hello to My Better Friend

R Is Helpful Too!

  • type help(function_name) or ?(function_name) to get documentation on a function

    From Kieran Healy's excellent (free online!) book on Data Visualization.

]

Tips for Writing Code

  • Comment, comment, comment!
  • The hashtag # starts a comment, R will ignore everything on the rest of that line
# Run regression of y on x, save as reg1 
reg1<-lm(y~x, data=data) #runs regression 
summary(reg1$coefficients) #prints coefficients
  • Save often!
    • Write scripts that save the commands that did what you wanted (and comment them!)
    • Better yet, use a version control system like Git (I hope to cover this later)

Style and Naming

  • Once we start writing longer blocks of code, it helps to have a consistent (and human-readable!) style

  • I follow this style guide (you are not required to)1

  • Naming objects and files will become important2

    • DO NOT USE SPACES! You've seen seen webpages intended to be called my webpage in html turned into http://my%20webpage%20in%20html.html
i_use_underscores
some.people.use.snake.case
othersUseCamelCase

1 Also described in today's course notes page and the course reference page.

2 Consider your folders on your computer as well...

Coding Basics

  • You'll have to get used to the fact that you are coding in commands to execute

  • Start with the easiest: simple math operators and calculations:

Coding Basics

  • You'll have to get used to the fact that you are coding in commands to execute

  • Start with the easiest: simple math operators and calculations:

> 2+2
## [1] 4

Coding Basics

  • You'll have to get used to the fact that you are coding in commands to execute

  • Start with the easiest: simple math operators and calculations:

> 2+2
## [1] 4
  • Note that R will ask for input with > and give you output starting with ## [1]

Coding Basics II

  • We can start using more fancy commands
2^3
## [1] 8

Coding Basics II

  • We can start using more fancy commands
2^3
## [1] 8
sqrt(25)
## [1] 5

Coding Basics II

  • We can start using more fancy commands
2^3
## [1] 8
sqrt(25)
## [1] 5
log(6)
## [1] 1.791759

Coding Basics II

  • We can start using more fancy commands
2^3
## [1] 8
sqrt(25)
## [1] 5
log(6)
## [1] 1.791759
pi/2
## [1] 1.570796

Packages

  • Since R is open source, users contribute packages
    • Really it's just users writing custom functions and saving them for others to use
  • Load packages with library()
    • e.g. library("package_name")
  • If you don't have a package, you must first install.packages()1
    • e.g. install.packages("package_name")

1 Yes, note the plural, even if it's just for one package!

Common Packages

  • In this class, we will make extensive use of the following packages:
    • tidyverse: really a meta-package combining the following packages (among others)
      • dplyr: used for better data-wrangling
      • ggplot2: used for fancy plotting
    • huxtable: used for automatically producing regression tables

R: Objects and Functions

  • R is an object-oriented programming language
  • 99% of the time, you will be:

  1. creating objects

    • assign values to an object with <-

  2. running functions on objects

    • syntax: function_name(object_name)
# make an object
my_object<-c(1,2,3,4,5)
# look at it 
my_object
## [1] 1 2 3 4 5
# find the sum
sum(my_object)
## [1] 15
# find the mean 
mean(my_object)
## [1] 3

R: Objects and Functions II

  • Functions have "arguments," the input(s)

  • Some functions may have multiple inputs

  • The argument of a function can be another function!

# find the sd
sd(my_object)
## [1] 1.581139
# round everything in my object to two decimals
round(my_object,2)
## [1] 1 2 3 4 5
# round the sd to two decimals
round(sd(my_object),2)
## [1] 1.58

Types of R Objects

Numeric

  • Numeric objects are just numbers1

  • Can be mathematically manipulated

x <- 2 
y <- 3
x+y
## [1] 5
x*y
## [1] 6
1 If you want to get technical, R may call these integer or double if there are decimal values.

Character

  • Character objects are "strings" of text held inside quote marks

  • Can contain spaces, so long as contained within quote marks

name <- "Ryan Safner"
address <- "401 Rosemont Ave."
name
## [1] "Ryan Safner"
address
## [1] "401 Rosemont Ave."

Logical

  • Logical objects are binary TRUE or FALSE indicators
  • Used a lot to evaluate conditionals:
    • >, <: greater than, less than
    • >=, <=: greater than or equal to, less than or equal to
    • ==, !=: is equal to, is not equal to1
    • &in& : Is a member of the set of ($\in$)
    • &: "AND"
    • |: "OR" 
z <- 10 # set z equal to 10
z==10 # is z equal to 10?
## [1] TRUE
"red"=="blue" # is red equal to blue?
## [1] FALSE
z > 1 & z < 12 # is z > 1 AND < 12?
## [1] TRUE
z <= 1 | z==10 # is z >= 1 OR equal to 10?
## [1] TRUE

1 One = assigns a value (like <-). Two == evaluate a conditional statement.

Factor

  • Factor objects contain categorical data - membership in mutually exclusive groups

  • Look like strings, behave more like logicals, but with more than two options

##  [1] junior    sophomore sophomore senior    sophomore sophomore junior   
##  [8] junior    freshman  junior   
## Levels: freshman sophomore junior senior
  • We'll make much more extensive use of them later
##  [1] junior    sophomore sophomore senior    sophomore sophomore junior   
##  [8] junior    freshman  junior   
## Levels: freshman < sophomore < junior < senior

Data Structures

Vectors

  • Vector: the simplest type of object, just a collection of objects

  • Make a vector using the combine c() function

# create a vector called vec
vec<-c(1,"orange", 83.5, pi)
# look at vec
vec
## [1] "1"                "orange"           "83.5"            
## [4] "3.14159265358979"

Data Frames I

  • Data frame: what we'll be using almost always

  • Think like a "spreadsheet"

  • Each column is a vector (variable)

  • Each row is an observation (pair of values for all variables)

library("ggplot2")
diamonds
## # A tibble: 53,940 x 10
##    carat cut       color clarity depth table price     x     y     z
##    <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
##  1 0.23  Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
##  2 0.21  Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
##  3 0.23  Good      E     VS1      56.9    65   327  4.05  4.07  2.31
##  4 0.290 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
##  5 0.31  Good      J     SI2      63.3    58   335  4.34  4.35  2.75
##  6 0.24  Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48
##  7 0.24  Very Good I     VVS1     62.3    57   336  3.95  3.98  2.47
##  8 0.26  Very Good H     SI1      61.9    55   337  4.07  4.11  2.53
##  9 0.22  Fair      E     VS2      65.1    61   337  3.87  3.78  2.49
## 10 0.23  Very Good H     VS1      59.4    61   338  4     4.05  2.39
## # … with 53,930 more rows

Data Frames II

  • Dataframes are really just combinations of (column) vectors

  • You can make data frames by combinining named vectors with data.frame() or creating each column/vector in each argument 

# make two vectors
fruits<-c("apple","orange","pear","kiwi","pineapple")
numbers<-c(3.3,2.0,6.1,7.5,4.2)
# combine into dataframe
df<-data.frame(fruits,numbers)
# do it all in one step (note the = instead of <-)
df<-data.frame(fruits=c("apple","orange","pear","kiwi","pineapple"),
               numbers=c(3.3,2.0,6.1,7.5,4.2))
# look at it
df
##      fruits numbers
## 1     apple     3.3
## 2    orange     2.0
## 3      pear     6.1
## 4      kiwi     7.5
## 5 pineapple     4.2

Working with Objects

Objects: Storing, Viewing, and Overwriting

  • We want to store things in objects to run functions on them later
  • Recall, any object is created with the assignment operator <- 
my_vector <- c(1,2,3,4,5)
  • R will not give any output after an assignment

Objects: Storing, Viewing, and Overwriting

  • We want to store things in objects to run functions on them later
  • Recall, any object is created with the assignment operator <- 
my_vector <- c(1,2,3,4,5)

  • R will not give any output after an assignment

  • View an object (and list its contents) by typing its name

my_vector
## [1] 1 2 3 4 5

Objects: Storing, Viewing, and Overwriting

  • We want to store things in objects to run functions on them later
  • Recall, any object is created with the assignment operator <- 
my_vector <- c(1,2,3,4,5)

  • R will not give any output after an assignment

  • View an object (and list its contents) by typing its name

my_vector
## [1] 1 2 3 4 5
  • objects maintain their values until they are assigned different values that will overwrite the object
my_vector <- c(2,7,9,1,5)
my_vector
## [1] 2 7 9 1 5

Objects: Checking and Changing Classes

  • Check what type of object something is with class()
class("six")
## [1] "character"
class(6)
## [1] "numeric"

Objects: Checking and Changing Classes

  • Check what type of object something is with class()
class("six")
## [1] "character"
class(6)
## [1] "numeric"
  • Can also use logical tests of is.() 
is.numeric("six")
## [1] FALSE
is.character("six")
## [1] TRUE
  • You can convert objects from one class to another with as.object_class()
    • Pay attention: you can't convert non-numbers to numeric, etc! 
as.character(6)
## [1] "6"
as.numeric("six")
## [1] NA

Objects: Different Classes and Coercion I

  • Different types of objects have different rules about mixing classes
  • Vectors can not contain different types of data
    • Different types of data will be "coerced" into the lowest-common denominator type of object
mixed_vector <- c(pi, 12, "apple", 6.32)
class(mixed_vector)
## [1] "character"
mixed_vector
## [1] "3.14159265358979" "12"               "apple"           
## [4] "6.32"

Objects: Different Classes and Coercion II

  • Data frames can have columns with different types of data, so long as all the elements in each column are the same class1
df
##      fruits numbers
## 1     apple     3.3
## 2    orange     2.0
## 3      pear     6.1
## 4      kiwi     7.5
## 5 pineapple     4.2
class(df$fruits)
## [1] "factor"
class(df$numbers)
## [1] "numeric"

1remember each column in a data frame is a vector!

More on Data Frames I

  • Learn more about a data frame with the str() command to view its structure
class(df)
## [1] "data.frame"
str(df)
## 'data.frame':    5 obs. of  2 variables:
##  $ fruits : Factor w/ 5 levels "apple","kiwi",..: 1 3 4 2 5
##  $ numbers: num  3.3 2 6.1 7.5 4.2

More on Data Frames II

  • Take a look at the first 5 (or n) rows with head()
head(df)
##      fruits numbers
## 1     apple     3.3
## 2    orange     2.0
## 3      pear     6.1
## 4      kiwi     7.5
## 5 pineapple     4.2
head(df, n=2)
##   fruits numbers
## 1  apple     3.3
## 2 orange     2.0

More on Data Frames III

  • Get summary statistics1 by column (variable) with summary()
summary(df)
##        fruits     numbers    
##  apple    :1   Min.   :2.00  
##  kiwi     :1   1st Qu.:3.30  
##  orange   :1   Median :4.20  
##  pear     :1   Mean   :4.62  
##  pineapple:1   3rd Qu.:6.10  
##                Max.   :7.50

1 for numeric data only; a frequency table is displayed for character or factor data

More on Data Frames IV

  • Note, once you save an object, it shows up in the Environment Pane in the upper right window
  • Click the blue arrow button in front of the object for some more information

More on Data Frames V

  • data.frame objects can be viewed in their own panel by clicking on the name of the object
  • Note you cannot edit anything in this pane, it is for viewing only

Functions Again I

  • Functions in R are vectorized, meaning running a function on a vector applies it to each element
my_vector<-c(2,4,5,10)
my_vector+4 # add 4 to all elements
## [1]  6  8  9 14
my_vector^2 # square all elements
## [1]   4  16  25 100

Functions Again II

  • But often we want to run functions on vectors that aggregate to a result (e.g. a statistic):
length(my_vector) # how many elements
## [1] 4
sum(my_vector) # add all elements
## [1] 21
max(my_vector) # find largest element
## [1] 10
min(my_vector) # find smallest element
## [1] 2
mean(my_vector) # mean of all elements
## [1] 5.25
median(my_vector) # median of all elements
## [1] 4.5
sd(my_vector) # standard deviation
## [1] 3.40343

Common Errors

  • If you make a coding error (e.g. forget to close a parenthesis), R might show a + sign waiting for you to finish the command
> 2+(2*3
+
  • Either finish the command-- e.g. add )--or hit Esc to cancel

Working with Data

Indexing and Subsetting I

mtcars
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
## 12 16.4   8 275.8 180 3.07 4.070 17.40
  • Each element in a data frame is indexed by referring to its row and column: df[r,c]
  • To select elements by row and column ("subset"), type in the row(s) and/or column(s) to select
    • Leaving r or c blank selects all rows or columns
    • Select multiple values with c()1
    • Select a range of values with :
    • Don't forget the comma between r and c!

1 You can also "negate" values, selecting everything except for values with a - in front of them.

Indexing and Subsetting II

mtcars
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
## 12 16.4   8 275.8 180 3.07 4.070 17.40

Subset by Row (Observations)

mtcars[1,] # first row
##   mpg cyl disp  hp drat   wt  qsec
## 1  21   6  160 110  3.9 2.62 16.46
mtcars[c(1,3,4),] # first, third, and fourth rows
##    mpg cyl disp  hp drat    wt  qsec
## 1 21.0   6  160 110 3.90 2.620 16.46
## 3 22.8   4  108  93 3.85 2.320 18.61
## 4 21.4   6  258 110 3.08 3.215 19.44
mtcars[1:3,] # first three rows
##    mpg cyl disp  hp drat    wt  qsec
## 1 21.0   6  160 110 3.90 2.620 16.46
## 2 21.0   6  160 110 3.90 2.875 17.02
## 3 22.8   4  108  93 3.85 2.320 18.61

Indexing and Subsetting III

mtcars
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
## 12 16.4   8 275.8 180 3.07 4.070 17.40

Subset by Column (Variable)

mtcars[,6] # select column 6
##  [1] 2.620 2.875 2.320 3.215 3.440 3.460 3.570 3.190 3.150 3.440 3.440
## [12] 4.070
mtcars[,2:4] # select columns 2 through 4
##    cyl  disp  hp
## 1    6 160.0 110
## 2    6 160.0 110
## 3    4 108.0  93
## 4    6 258.0 110
## 5    8 360.0 175
## 6    6 225.0 105
## 7    8 360.0 245
## 8    4 146.7  62
## 9    4 140.8  95
## 10   6 167.6 123
## 11   6 167.6 123
## 12   8 275.8 180

Indexing and Subsetting IV

mtcars
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
## 12 16.4   8 275.8 180 3.07 4.070 17.40

Subset by Column (Variable)

  • Alternatively, double brackets [[]] selects a column by position
mtcars[[6]] # same thing
##  [1] 2.620 2.875 2.320 3.215 3.440 3.460 3.570 3.190 3.150 3.440 3.440
## [12] 4.070
  • Data frames can select columns by name with $
mtcars$wt
##  [1] 2.620 2.875 2.320 3.215 3.440 3.460 3.570 3.190 3.150 3.440 3.440
## [12] 4.070

Indexing and Subsetting V

mtcars
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
## 12 16.4   8 275.8 180 3.07 4.070 17.40
  • Select observations (rows) that meet logical criteria

Subset by Condition

mtcars[mtcars$wt>4,] # select obs with wt>4
##     mpg cyl  disp  hp drat   wt qsec
## 12 16.4   8 275.8 180 3.07 4.07 17.4
mtcars[mtcars$cyl==6,] # select obs with exactly 6 cyl
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
mtcars[mtcars$wt<4 & mtcars$wt>2,] # select obs where 2<wt<4
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 5  18.7   8 360.0 175 3.15 3.440 17.02
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 7  14.3   8 360.0 245 3.21 3.570 15.84
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90
mtcars[mtcars$cyl==4 | mtcars$cyl==6,] # select obs with 4 OR 6 cyl
##     mpg cyl  disp  hp drat    wt  qsec
## 1  21.0   6 160.0 110 3.90 2.620 16.46
## 2  21.0   6 160.0 110 3.90 2.875 17.02
## 3  22.8   4 108.0  93 3.85 2.320 18.61
## 4  21.4   6 258.0 110 3.08 3.215 19.44
## 6  18.1   6 225.0 105 2.76 3.460 20.22
## 8  24.4   4 146.7  62 3.69 3.190 20.00
## 9  22.8   4 140.8  95 3.92 3.150 22.90
## 10 19.2   6 167.6 123 3.92 3.440 18.30
## 11 17.8   6 167.6 123 3.92 3.440 18.90

What's To Come

  • Next class: data visualization with ggplot2

  • And then: data wrangling with tidyverse

  • And then: literate programming and workflow management with R Markdown

  • Finally: back to econometric theory!

Data Science

  • You go into data analysis with the tools you know, not the tools you need

  • The next 2-3 weeks are all about giving you the tools you need

    • Admittedly, a bit before you know what you need them for

  • We will extend them as we learn specific models

Paused

Help

Keyboard shortcuts

↑, ←, Pg Up, k Go to previous slide
↓, →, Pg Dn, Space, j Go to next slide
Home Go to first slide
End Go to last slide
Number + Return Go to specific slide
b / m / f Toggle blackout / mirrored / fullscreen mode
c Clone slideshow
p Toggle presenter mode
t Restart the presentation timer
?, h Toggle this help
Esc Back to slideshow