MIT Homework1

Suppose that you want R to display ‘’Hello world!’’ Drag and drop the phrases to create the correct R input. Note that there may be multiple ways to write this in R but we want you to use this command specifically.

print ("Hello world")

## [1] "Hello world"

If you run the following code in R, what does the object my_sqrt contain?

z <- c(pi, 205, 149, -2) y <- c(z, 555, z) y <- 2 * y + 760 my_sqrt <- sqrt(y - 1)

z <- c(pi, 205, 149, -2)
y <- c(z, 555, z)
y <- 2 * y + 760
my_sqrt <- sqrt(y - 1)

a vector of length 9

Assume that you tell R to divide zero by zero, what would you get?

0/0

## [1] NaN

If you have a missing value and you try to add it to a number, what result would you get?

0/0 + 5

## [1] NaN

We have asked the age of a group of 12 students. While 10 of them provided us with this information, 2 of them did not. We have constructed the vector age that captures this information.

age <- c(12, 28, 35, 27, NA, 25, 32, 45, 31, 23, NA, 34)

If we were interested in getting the vector without the missing values, which of the following lines of code would be useful to achieve this purpose? (Select all that apply)

In order to get the vector without those missing values, we can identify the position in which they are located. We can choose then the ones without those missing values by using the code age[c(1, 2, 3, 4, 6, 7, 8, 9, 10, 12)]. We can try to simplify this, by just telling R to omit those positions where they are located, and this is possible using two different ways: age[-c(5, 11)], and age[c(-5, -11)]. We can even simplify this more, and use the is.na function, asking first where are the missing values and then using the negation symbol !. Then, we can do this by age[!is.na(age)].

Download the data “CitesforSara.csv” into RStudio. This dataset includes paper-level citations from 1969 to 1998. First, read the CSV file into R using these commands:

library(tidyverse) papers <- as_tibble(read_csv(“[YOURFILEPATH]/CitesforSara.csv”))

Great! Let’s create a simplified dataset which only keeps the following variables contained in the papers dataset in this order: journal, year, cites, title, and au1. Use the method select() to accomplish this. Set this output to the variable papers_select. Drag and drop to create the code. Note that there may be more than one way to do this but there is only one correct answer from the following drag-and-drop options.

library(tidyverse)

## Warning: package 'ggplot2' was built under R version 4.4.1

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   4.0.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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 errors

papers <- as_tibble(read_csv("/Users/trangan/Desktop/Prepare for PhD in Econ at Curtin/MIT_Data Analysis  for Social Scientists/CitesforSara.csv"))

## Rows: 4182 Columns: 22
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (5): journal, title, au1, au2, au3
## dbl (17): year, cites, female1, female2, female3, page, order, nauthor, past...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

papers_select = select (papers, journal, year, cites, title, au1)
head(papers_select, 20)

## # A tibble: 20 × 5
##    journal                   year cites title                              au1  
##    <chr>                    <dbl> <dbl> <chr>                              <chr>
##  1 American-Economic-Review  1993    31 Jeux Sans Frontieres:  Tax Compet… Kanb…
##  2 American-Economic-Review  1993     4 Changes in Economic Instability i… Jame…
##  3 American-Economic-Review  1993    28 Factor Shares and Savings in Endo… Bert…
##  4 American-Economic-Review  1993    10 Strategic Discipline in Monetary … Garf…
##  5 American-Economic-Review  1993     5 Will Affirmative-Action Policies … Coat…
##  6 American-Economic-Review  1993    21 Mergers and Market Power:  Eviden… Kim,…
##  7 American-Economic-Review  1993    45 A Search-Theoretic Approach to Mo… Kiyo…
##  8 American-Economic-Review  1993    13 An Experimental Test of the Publi… Andr…
##  9 American-Economic-Review  1993     5 A General Experiment on Bargainin… Kahn…
## 10 American-Economic-Review  1993     2 Nominal-Contracting Theories of U… Kean…
## 11 American-Economic-Review  1993     6 Is There a Peso Problem?  Evidenc… Kami…
## 12 American-Economic-Review  1993     5 Stock Options and the Strategic U… Reit…
## 13 American-Economic-Review  1993    51 What Do We Learn About Consumer D… Blun…
## 14 American-Economic-Review  1993    15 Economic Policy, Economic Perform… Harr…
## 15 American-Economic-Review  1993    16 Large-Scale Privatization in Tran… Laba…
## 16 American-Economic-Review  1993     8 The Development of Nominal Wage R… Hane…
## 17 American-Economic-Review  1993     7 Low Investment and Large LDC Debt… Cohe…
## 18 American-Economic-Review  1993     4 Entry, Dumping, and Shakeout       Clar…
## 19 American-Economic-Review  1993     1 The Relative Pricing of High-Yiel… Damm…
## 20 American-Economic-Review  1993     5 The Economics of Rotating Savings… Besl…

Let’s take a look at some of the most popular papers. Using the filter() method, how many records exist where there are greater than or equal to 100 citations?

filter(papers, cites >= 100)

## # A tibble: 205 × 22
##    journal      year cites title au1   au2   au3   female1 female2 female3  page
##    <chr>       <dbl> <dbl> <chr> <chr> <chr> <chr>   <dbl>   <dbl>   <dbl> <dbl>
##  1 American-E…  1994   117 Is I… Pers… Tabe… <NA>        0       0      NA    22
##  2 Econometri…  1971   149 Furt… Nerl… <NA>  <NA>        0      NA      NA    24
##  3 Econometri…  1971   170 The … Madd… <NA>  <NA>       NA      NA      NA    18
##  4 Econometri…  1971   155 Inve… Luca… Pres… <NA>        0       0      NA    23
##  5 Econometri…  1971   139 Some… Crag… <NA>  <NA>        0      NA      NA    16
##  6 Econometri…  1971   108 Iden… Roth… <NA>  <NA>        0      NA      NA    15
##  7 Econometri…  1972   164 Meth… Fair… Jaff… <NA>        0       0      NA    18
##  8 Econometri…  1972   150 Exis… Radn… <NA>  <NA>        0      NA      NA    15
##  9 Econometri…  1973   361 Mani… Gibb… <NA>  <NA>        0      NA      NA    15
## 10 Econometri…  1973   107 On a… Kram… <NA>  <NA>        0      NA      NA    13
## # ℹ 195 more rows
## # ℹ 11 more variables: order <dbl>, nauthor <dbl>, past5 <dbl>, aflpn90 <dbl>,
## #   spage <dbl>, field <dbl>, subfld <dbl>, aulpn90 <dbl>, aulpn80 <dbl>,
## #   aulpn70 <dbl>, lcites <dbl>

Use the group_by() function to group papers by journal. How many total citations exist for the journal “Econometrica”?

?group_by

cách 1:

summarise(group_by(filter(papers, journal == 'Econometrica'), journal), total_cites = sum(cites, na.rm = TRUE))

## # A tibble: 1 × 2
##   journal      total_cites
##   <chr>              <dbl>
## 1 Econometrica       75789

cách 2:

eco_papers = filter(papers, journal == "Econometrica")
eco_groups = group_by(eco_papers, journal)
summarise(eco_groups, total_cites = sum(cites, na.rm = TRUE))

## # A tibble: 1 × 2
##   journal      total_cites
##   <chr>              <dbl>
## 1 Econometrica       75789

How many distinct primary authors (au1) exist in this dataset? Note: do not remove NA values.

n_distinct(papers$au1, na.rm = FALSE)

## [1] 2332

Use the dplyr contains() method to create a new dataset called papers_female which contains only those columns in the papers dataframe with the string “female” anywhere in the column name . Drag and drop to create the code. Note that there may be more than one way to do this but there is only one correct answer from the following drag-and-drop options. It may be useful to type ?contains in your R console.

select(papers, contains("female"))

## # A tibble: 4,182 × 3
##    female1 female2 female3
##      <dbl>   <dbl>   <dbl>
##  1       0       0      NA
##  2       0      NA      NA
##  3       0      NA      NA
##  4       1       0      NA
##  5       0       0      NA
##  6       0       0      NA
##  7       0       0      NA
##  8       0      NA      NA
##  9       0       0      NA
## 10       0      NA      NA
## # ℹ 4,172 more rows