93064 - Statistics

Learning outcomes

The aim of the course is to introduce the elementary concepts of descriptive statistics, probability, statistical inference, and linear regression. The course will provide students with the basic knowledge to develop applied quantitative analyses of complex social and economic phenomena such as those characterizing the modern tourism sector and the urban economy. Prerequisite is knowledge of basics of Mathematics.

Course contents

1st half

Introduction to the R language and the software RStudio. Data frames, observations, variables, computing and interpreting means.

Basics of estimating causal effects with randomized controlled trials. Randomized experiment, treatment group, control group. Examples and case studies in R. Difference-in-means estimator.

Inferring population characteristics via survey research. Sample, population, random sampling, frequency table of a variable, table of proportions, histogram of a variable, density histogram, descriptive statistics (mean, median, standard deviation, variance), z-score, correlation between two variables.

Predicting outcomes using linear regression. The linear model. Outcome and predictor variables. Fitted linear model, estimated intercept and estimated slope. Linear regression with binary outcome variables. Connection to the difference-in-means estimator.

Basics of estimating causal effects with observational data. Confounding variables.

2nd half

Basics of Probability theory. Probability distribution, Bernoulli distribution, Normal distribution, probability density function of the Normal distribution, Standard normal distribution. Sample mean. Law of large numbers and central limit theorem. Sampling distribution of the sample mean.

Quantifying uncertainty. Parameter, estimate, estimator. Sampling distribution of an estimator. Standard error of an estimator. Confidence intervals. Hypothesis testing.

Readings/Bibliography

Text book:

Data Analysis for Social Science. A friendly and practical introduction. Alena Llaudet, Kosuke Imai. (Princeton University Press)

Teaching methods

Frontal lectures with the help of slides, blackboard. You will use your own laptop in class for the practical sessions with Rstudio. The classroom is wired, so bring your own laptop at class.

Considering the nature of the activities and the teaching methods adopted, the attendance of this training activity requires all students to participate in the safety modules 1 and 2 on studying places [https://elearning-sicurezza.unibo.it/ ] in e-learning mode.

Assessment methods

Aspects evaluated in the exam

1. Understanding quantitative data presented in different formats; ability to communicate the meaning of quantitative data.
2. Understanding the theoretical foundations of quantitative reasoning (variables, constants, and estimates); understanding how inferences are drawn from quantitative analyses; recognizing the strengths and limitations of quantitative methods.
3. Understanding the practical application of quantitative data analysis; ability to choose appropriate methods to solve a specific problem; ability to accurately interpret the results.

 

Grading policy

The maximum possible score, obtained by answering all questions correctly and completely, is 30 cum laude. A minimum score of 18/30 is required to pass the exam.

Exam options:

Option A: Homework + 1st midterm + 2nd midterm. The final grade is the average of the three scores obtained in the homework, the 1st midterm, and the 2nd midterm.

Note: The 1st midterm covers the first half of the course (the first 30 hours), while the 2nd midterm covers the second half (the last 30 hours). The 1st midterm usually takes place at the end of the first half of the course, typically at the beginning of April. The 2nd midterm corresponds to the first available exam session, usually in late May or early June.

Option B: Total exam. The final grade is determined solely by the score obtained in a comprehensive exam covering both the first and second halves of the course. The dates of the Total exam are published in advance, with the first session usually taking place in late May or early June. (Of course, it is not possible to take the Total exam on the date of the 1st midterm.)

Students choosing Option A must complete the exam during the first available exam session (usually in late May or early June). This means that a student who passes the 1st midterm but does not obtain a passing grade in the 2nd midterm will have to repeat the exam by taking the Total exam.

Regarding homework, midterm, and Total exam, use of AI

Homework. Four homework assignments (HWs) will be assigned every second week (two before the 1st midterm and two after it). The homework grade is computed as the average of the four HWs and is reported on a scale from 18 to 30. Students who obtain the maximum score on every homework assignment will receive a bonus. Collaboration between students is permitted, but each student must submit their own work and receives an individual grade. Late submissions are not accepted.

The 1st midterm and 2nd midterm consist of a computer-based quiz taken in a University computer lab. The quiz includes multiple-choice questions, open-ended questions, and questions requiring the use of RStudio.

The Total exam consists of:

1. an exercise requiring the use of RStudio; and
2. a computer-based quiz taken in a University computer lab, containing multiple-choice questions and open-ended questions.
   

With regard to the midterm and Total exams, the use of AI tools is prohibited. Any use of such tools constitutes a violation of academic integrity.

For the homework assignments, limited, declared, and non-substantial use of AI tools is permitted for support activities (e.g., summarization and rephrasing). Students are required to explicitly state which exercises were completed with the assistance of AI tools.

Enrollment, grades, registration, and grade rejection

It is the student's responsibility to enroll for an exam via the AlmaEsami website.

Students will be notified by email when their grades have been published on AlmaEsami and informed of the registration date. Registration usually takes place one week after the publication of the grades.

Students who have passed the exam may reject their final grade once. To do so, they must send a request by email to the instructor no later than the registration date. The instructor will confirm receipt of the request by the same date.

Please note that grade rejection applies only to the final grade, not to individual midterm grades.

Teaching tools

Slides, blackboard, laptop for practicing Rstudio.

RStudio is based on the R language. Both R and RStudio are free softwares that are installed in lab computers, I recommend students download and install both R and RStudio in their laptops. We will use RStudio Desktop version. First install R and then RStudio Desktop.

 

To download R

https://cran.r-project.org

To download RStudio Desktop:

https://posit.co/download/rstudio-desktop/

Office hours

See the website of Massimo Ventrucci