Starting your data science journey
- Guide
- Statistics
On February 12, 2025, UP Data Science Society opened its Infoseries with a set of slides on statistical variables and measures of central tendency, with content by Elaine Pelicano and Mary Arnie Aringay and design by Sebastian Merdegia and Malaya Isabela Quiambao. Statistics is one of the three pillars of data science, and these two topics are where it starts. This page keeps that first lesson and adds the stages that come after it, with free resources for each.
Stage 1: variables
A variable is a quantity that can change. In mathematics it is a symbol that stands for a number; in programming it is a named place to store data of some type. The slides sort variables two ways.
By what they hold: discrete variables are countable (you can have 0, 1, 2, or 3 siblings, never 2.5), continuous variables can take any value in a range (height can be 5.6, 5.62, or 5.621 feet), and categorical variables are labels with no natural order (gender).
By their role: the independent variable, also called the predictor or explanatory variable, is what you change or measure as input. The dependent variable, also called the response, is the outcome that depends on it. Amount of water is independent and size of leaves is dependent; age, sex, and income are independent and academic performance is dependent. In y = f(x), x is independent and y is dependent.
Resources named on the slides: What is a variable in math (SplashLearn) and What are categorical, discrete, and continuous variables (Minitab).
Stage 2: measures of central tendency
A measure of central tendency is one number that stands for the middle of a dataset. The mean is the sum of all values divided by their count: for 8, 3, 4, 9, 6 it is 30 divided by 5, or 6. The median is the middle value once the data is sorted; with an odd count it is the middle item (3, 4, 6, 8, 9 gives 6), with an even count it is the average of the two middle items (4, 8, 8, 10, 12, 15 gives 9). The mode is the most frequent value: the first set has none, the second has 8.
To go further, Khan Academy’s statistics and probability course is free and covers spread, distributions, and inference.
Stage 3: a programming language
Most data science work happens in Python or R. The official Python tutorial and Harvard’s free CS50’s Introduction to Programming with Python cover the language. For R, R for Data Science is free online. Members get DataCamp seats, which cover both languages with exercises; ask on the Facebook page for the current sign-up.
Stage 4: working with data
Learn to load, clean, and summarize tables. 10 minutes to pandas is the standard starting point in Python, and W3Schools SQL covers querying databases. Practice on real Philippine data from data.gov.ph or the finalist datasets and code in the PJDSC-Datasets repository.
Stage 5: models
Start with the scikit-learn getting started guide and the free textbook An Introduction to Statistical Learning, which has Python and R editions.
Where UP DSSoc fits
Our workshops run through these stages for members, and mentorship sessions pair you with senior members and alumni. Questions go to the UP Data Science Society Facebook page or to updatasciencesociety@gmail.com.