Take-Home Assignment

About this document

This document covers the foundations of quantitative data analysis. You will work with a real dataset in R and move through six sections, step by step:

Importing and preparing the data
Basic statistical concepts
Descriptive statistics and tables
Graphs
The normal distribution
Standard score transformations

How it works. Each section starts with a short explanation and some R code. Copy the code into R, run it, and answer the questions at the end of the section. When all answers in a section are correct, the next section opens. If an answer is wrong, you will get a hint that sends you back to the part you should review. You can try as many times as you need.

Answer rules

Use a dot as the decimal separator (for example 28.55).
Round as the question asks. Do not round in the middle of a calculation, only at the end.
Your answers and progress are saved in this browser. If you come back later, use the same browser and computer.

👤 Your information (optional)

Full nameStudent IDUniversity / institutionProgramme / departmentEducation levelResponse dateResponse code (if you were given one)

All fields are optional, and the date is filled in automatically. They are saved in this browser and appear on your results page. They are sent only if you press Submit at the end of the document.

🔑 Solutions

Solutions are locked. When you receive the password, enter it here to open every section and see all solutions.

Section 1: Importing and preparing the data

In this document we use the sat.act dataset from the psych package. It contains self-reported test scores of 700 people on the ACT and the SAT, together with their gender, education level and age.

Variable	Description
`gender`	1 = male, 2 = female
`education`	Self-reported education, coded 0 to 5 (higher codes mean more education)
`age`	Age in years
`ACT`	ACT composite score
`SATV`	SAT Verbal score
`SATQ`	SAT Quantitative score

Step 1. Install the psych package (only once) and load it.

install.packages("psych")

library(psych)

Step 2. Load the data and make a working copy called dat.

data(sat.act)
dat <- sat.act
head(dat)

Step 3. Prepare the categorical variables. gender becomes a factor with labels, and education becomes an ordered factor.

dat$gender    <- factor(dat$gender, levels = c(1, 2), labels = c("male", "female"))
dat$education <- factor(dat$education, levels = 0:5, ordered = TRUE)
str(dat)

Step 4. Check the size of the data and the missing values.

dim(dat)
table(dat$gender)
colSums(is.na(dat))
which(is.na(dat$SATQ))

Questions for Section 1

Q1How many observations (rows) are there in dat?

Q2How many female students are in the data?

Q3How many missing values does SATQ have?

Q4In which row number is the first missing value of SATQ?

Q5What is the ACT score of the student in the 10th row of dat (that is, dat[10, ])?

🔒 Solution (locked)