EC 285 - 2026-09-22 - Lecture 04

EC 285 - Lecture 04 - 2026-09-22

Introductory Statistics · Zara Liaqat · SB 106

Week 3 · 16:01-17:15 · 74 min · Full transcript · Flashcards

Overview

This lecture started Chapter 3 (Probability), which is the first step toward inferential statistics. It began with why a statistics course needs probability at all. Then it covered the vocabulary of sets and Venn diagrams, practised on a die-rolling example. Next came the definition of probability, classical probability, and the counting tools (factorials, permutations and combinations) that are used to count outcomes, with two exam-style problems that combine counting with probability.

Why probability matters in statistics

This picks up the "uncertain environment" idea from Lecture 01.

Probability and uncertainty

Statisticians judge a whole population from a sample, so their conclusions can never be 100% certain. Probability lets them attach a likelihood to a claim instead of just stating it.

Why: In the lecturer's words, "we live in an uncertain environment" and "we make decisions based on incomplete information." You study probability "not by choice, just by necessity." A typical conclusion looks like this: "if I repeat my sampling, 90% of the times the population average will lie in this interval." Putting a number on uncertainty also helps with everyday decisions. A 70% chance of rain tells you more than "it's likely to rain" when you're deciding whether to carry an umbrella.

Sets and Venn diagrams

Probability is built on set theory, which is the branch of math that studies collections of objects. A Venn diagram draws those collections: a rectangle stands for the whole sample space S, and circles inside it stand for events.

Basic terms

Intersection

The intersection of A and B, written A∩B, is the set of all outcomes in S that belong to both A and B. In a Venn diagram, it is the overlapping part of the circles. Read ∩ as "and."

Why: It picks out exactly the outcomes where both events happen at once.

If the circles don't overlap, the intersection is the empty set (also called the null set), written ∅ or as empty brackets { }.

Union

The union of A and B, written A∪B, is the set of all outcomes in S that belong to either A or B. Outcomes in the overlap count too. Read ∪ as "or."

Why: Taking the union combines the two events. The whole shaded area of both circles, overlap included, is A∪B. A student asked whether the overlap counts, and the answer was yes: it includes everything in either A or B.

Mutually exclusive events

A and B are mutually exclusive if they have no basic outcomes in common, meaning they can't happen at the same time. In a Venn diagram, the two circles don't touch.

A∩B=∅

where ∅ is the empty set.

Why: To check whether two events are mutually exclusive, look at the intersection and see whether it is empty.

Collectively exhaustive events

Events are collectively exhaustive if together they cover the whole sample space. Nothing in S sits outside all of them.

E1∪E2∪⋯∪Ek=S

where E1 to Ek are the events and S is the sample space.

Why: To check whether events are collectively exhaustive, look at the union and see whether it equals S. With just two events, A and B are collectively exhaustive if A∪B=S.

Complement

The complement of A, written A¯, is every outcome in the sample space that is not in A. In a Venn diagram, it is everything inside the rectangle but outside circle A.

Why: An event and its complement split S into two pieces with nothing shared and nothing left over. So A∩A¯=∅ and A∪A¯=S. The same holds for B and B¯.

Exam

The bar over a letter is also used for averages, but "don't mix up the two." Chapter 3 has no means or averages, so here the bar always means complement.

Using the terms together

The class practised all of these terms on a single die roll.

Example: Rolling one die

S={1,2,3,4,5,6}. Event A is "number rolled is even." Event B is "number rolled is at least four."

  1. A={2,4,6} -- the even numbers in S
  2. B={4,5,6} -- "at least four" includes 4 itself
  3. A¯={1,3,5} -- everything in S that is not in A
  4. A∪B={2,4,5,6} -- everything in A or B, listing 4 and 6 only once
  5. A∩B={4,6} -- only the numbers in both
  6. A¯∩B={5} -- in B but not even
  7. A∩B≠∅ -- so A and B are not mutually exclusive
  8. A∪B={2,4,5,6}≠S -- 1 and 3 are missing, so A and B are not collectively exhaustive
  9. A∩A¯=∅ and A∪A¯=S -- an event and its complement never overlap and together cover everything

Answer: A and B are neither mutually exclusive nor collectively exhaustive. In a Venn diagram, 4 and 6 go in the overlap, 2 goes in A only, 5 goes in B only, and 1 and 3 sit outside both circles.

Exam

"This is definitely going to be on the midterm test, some MCQs or maybe even a numerical question." You should be able to explain every term in bold on these slides and answer questions with them. Also, "beware of these terms": at least four includes 4, so it is {4,5,6}. At most four also includes 4, so it is {1,2,3,4}. When setting up event B, the lecturer first said "greater than four, or at least four," and then worked it as at least four. (Strictly, "greater than four" leaves 4 out, so it would be {5,6}. Read the exact wording on a test.)

Probability

Now each event gets a number that measures how likely it is.

What probability is

Probability is the chance that an uncertain event will happen. It is a number from 0 to 1, or equivalently from 0% to 100%.

Why: The closer the number is to 1, the more likely the event is. A probability of 0 means the event is impossible, and 1 means it is certain.

0≤P(A)≤1

where P(A) is the probability of event A.

Probabilities can be assigned in different ways. A subjective probability relies on experts' opinions. Classical probability counts outcomes, and that is the one used in this chapter. The lecturer said there are very few equations here, and only two of them are on the formula sheet, so you don't have to memorise those two. The lecturer didn't say which two. The Midterm 1 formula sheet lists the permutation and combination formulas, so those are most likely the two, but check the updated sheet.

Classical probability

Classical probability assumes every outcome in the sample space is equally likely. The probability of an event is then the number of outcomes that satisfy it divided by the total number of outcomes.

Why: If every outcome is equally likely, an event's probability is just its share of all the outcomes.

P(A)=NAN

where NA is the number of outcomes that satisfy event A (the "favourable outcomes"), and N is the total number of outcomes in the sample space.
Not on any formula sheet, so memorise it.

Made-up example: Rolling at least four

Roll one die. What is the probability of getting at least four?

  1. N=6 -- the sample space is {1,2,3,4,5,6}
  2. NA=3 -- the favourable outcomes are {4,5,6}
  3. P(A)=36=0.5 -- divide favourable outcomes by total outcomes

Answer: 0.5 -- half the faces of a die are 4 or higher.

Exam

"It should be a number less than one. It's probability, so if it's more than one ... you probably made a mistake." (Strictly, a probability can equal 0 or 1 exactly, because 0≤P(A)≤1. The point is that an answer above 1, or below 0, means a mistake.)

Counting possible outcomes

Classical probability needs counts of outcomes, and these tools count them quickly.

Factorials

x! ("x factorial") is the number of ways to arrange x objects in order. You multiply x by every whole number below it, down to 1.

Why: Take the parking example. The first spot can take any of the 4 cars. The next spot has 3 cars left, then 2, then 1. Multiplying the choices at each step gives the total number of arrangements.

x!=x(x−1)(x−2)⋯(2)(1)

where x is the number of objects. By definition, 0!=1.
Not on any formula sheet, so memorise it.

Example: Parking four cars in four spots

How many ways can 4 cars be arranged in 4 parking spots?

  1. 4!=4×3×2×1 -- 4 choices for the first spot, then 3, then 2, then 1
  2. 4×3=12, 12×2=24, 24×1=24 -- multiply

Answer: 24 -- there are 24 different ways to park the cars.

Order matters or not

Permutations and combinations both count the ways to pick x objects from n. In permutations, order matters. In combinations, it does not.

Why: Picking B then C is a different arrangement from C then B, but it is the same selection. So for the same n and x, permutations are always at least as many as combinations.

How to tell which one a question wants:

Exam

The lecturer said, "I think it's useful to understand what the difference is." In the purple car question, the lecturer's first step was to settle it: "It's combinations and not permutations. So, that's established."

Permutations

A permutation is the number of possible arrangements when x objects are picked from n objects and put in order, with n−x objects left over.

Why: It is the factorial idea stopped early. There are n choices for the first position, n−1 for the second, and so on, for x positions only.

Pxn=n(n−1)(n−2)⋯(n−x+1)=n!(n−x)!

where n is the total number of objects and x is the number picked and arranged. The notation is read "n P x," for example 4P2.
On the formula sheet for: Midterm 1, Midterm 2. It is not on the final's sheet.

Example: Arranging two of the letters a, b, c, d

Two letters are picked from a, b, c, d. How many arrangements (permutations) are possible? Here n=4 and x=2.

  1. P24=4!(4−2)!=4!2! -- put the numbers into the formula
  2. 242=12 -- 4!=24 and 2!=2 (the same as 4×3)
  3. The list: ab, ac, ad, ba, bc, bd, ca, cb, cd, da, db, dc -- 12 arrangements, and this confirms the formula

Answer: 12 -- here ab and ba count as different arrangements.

Combinations

A combination is the number of possible selections of x objects from n, when order doesn't matter.

Why: Each selection of x objects can be put in order in x! ways. So you take the permutations and divide by x! to remove the repeats.

Cxn=Pxnx!=n!x!(n−x)!

where n is the total number of objects and x is the number selected. The notation is read "n C x," for example 25C4.
On the formula sheet for: Midterm 1, Midterm 2 (both sheets write it as Ckn). It is not on the final's sheet, though the final's binomial formula does contain n!x!(n−x)!.

Example: Selecting two of the letters a, b, c, d

The same letters, but now count selections (combinations). Here n=4 and x=2.

  1. C24=4!2!(4−2)!=4!2!2! -- put the numbers into the formula
  2. 242×2=244=6 -- simplify
  3. The list: ab, ac, ad, bc, bd, cd -- 6 selections, and this confirms the formula

Answer: 6 -- fewer than the 12 permutations, because bc and cb are now the same selection.

Your calculator's nPr and nCr keys do these directly, and you may use them. The keys use r where the slides use x, and it means the same thing. The lecturer's phone calculator doesn't have these keys. The exam allows a non-programmable scientific calculator, and the lecturer recommends bringing one because it saves time. Without those keys, write out the factorials and cancel them by hand.

Probability with counting

These problems use classical probability, P(A)=NA/N, with combinations counting both the favourable outcomes and the total outcomes.

Complement rule

The probability that an event does not happen is 1 minus the probability that it does.

Why: An event and its complement cover the whole sample space with no overlap, so their probabilities add to 1. This is the shortcut for "at least one" questions. "At least one" can mean many cases (1, 2, 3, …). "None" is a single case, so it is much quicker to find P(none) and subtract it from 1.

P(A¯)=1−P(A)i.e.P(A)+P(A¯)=1

where A¯ is the complement of A.
Not on any formula sheet, so memorise it.

Example: At least one purple car

A dealer has 25 cars: 10 red, 7 blue, 6 white and 2 purple. A purchasing agent receives 4 of them. What is the probability that the agent gets at least one purple car? Order doesn't matter, so use combinations. Only purple versus not purple matters, so there are 2 purple cars and 25−2=23 non-purple cars.

  1. P(at least one purple)=1−P(no purple) -- use the complement rule
  2. P(no purple)=C423×C02C425 -- favourable: all 4 cars come from the 23 non-purple and 0 from the 2 purple; total: any 4 from 25
  3. C02=2!0!2!=1 -- choosing no purple cars can happen only one way
  4. C423=23!4!19!=23×22×21×204×3×2×1=21252024=8855 -- write 23! as 23×22×21×20×19! so the 19! cancels
  5. C425=25!4!21!=25×24×23×2224=25×23×22=12650 -- the 21! cancels in the same way
  6. P(no purple)=8855×112650=0.7 -- favourable over total
  7. 1−0.7=0.3 -- subtract from 1

Answer: 0.3 -- there is a 30% chance that the agent gets at least one purple car.

Exam

Don't stop at 0.7: "you have to remember that you have to subtract that from 1." Also, "we think we know how it's done, but we make a mistake in using our calculators, so make sure you know how this is done." Rework this one yourself.

Addition rule preview

The probability of A or B is P(A) plus P(B), minus the overlap. The lecturer only sketched this in answer to a student's question and will cover it properly next time.

Why: Adding P(A) and P(B) counts the overlap A∩B twice, so you subtract it once.

P(A∪B)=P(A)+P(B)−P(A∩B)

where A∪B is "A or B" and A∩B is "A and B."
Not on any formula sheet, so memorise it.

Made-up example: The die events again

Using the die example, A is "even" ={2,4,6} and B is "at least four" ={4,5,6}. Find P(A∪B).

  1. P(A)=36, P(B)=36, P(A∩B)=26 -- count the outcomes in each set (the overlap is {4,6})
  2. P(A∪B)=36+36−26 -- put the numbers into the rule
  3. =46=23≈0.667 -- simplify

Answer: 23 -- this matches counting A∪B={2,4,5,6} directly, which is 4 of 6 outcomes.

Splitting the sample into groups

When the question asks for an exact mix from different groups, count the ways to pick from each group and multiply. The group sizes must add up to the total, and the numbers picked must add up to the number selected.

Why: Each way of choosing from one group can be paired with each way of choosing from the other, so the counts multiply.

Example: Relocating exactly one woman

From 10 officers (2 women, 8 men), 3 are picked at random to be relocated. What is the probability that exactly one of them is a woman? Order doesn't matter, so use combinations.

  1. P=C12×C28C310 -- favourable: 1 of the 2 women and 2 of the 8 men (check: 2+8=10 and 1+2=3); total: any 3 of 10
  2. C12=2!1!1!=2 -- ways to pick the woman
  3. C28=8!2!6!=8×72=28 -- ways to pick the two men
  4. C310=10!3!7!=10×9×86=7206=120 -- all possible groups of 3
  5. P=2×28120=56120≈0.4667 -- favourable over total

Answer: ≈0.4667 -- about a 46.67% chance that exactly one of the three is a woman.

Exam checklist

Admin & deadlines


Transcribed automatically from the lecture recording. Slides used: EC 285 - Ch. 03 - Probability Topics (slides).pdf. Course info used: EC 285 - Syllabus - Fall 2026.pdf. Audio archived at /mnt/porsche/configs/lectures/archive/2026-09/EC 285 - 2026-09-22 - Lecture 04.opus.