Introduction to Probability and Proportions

TL;DR

Probability helps us quantify uncertainty by assigning a number between 0 and 1 to how likely an event is. Proportions are simply the fraction of a group that has a specific characteristic. We often use proportions from samples to make educated guesses about larger populations, but there's always some chance our sample isn't perfectly representative.

1. The Mental Model

Imagine you have a big bag of marbles, some red and some blue. If you pick one without looking, probability tells you how likely it is to be red. A proportion is just the fraction of red marbles in the bag.

2. The Core Material

Probability is all about chance. It's a numerical measure of the likelihood that an event will occur. Think of it as a scale:
* 0 means an event is impossible (e.g., rolling a 7 on a standard six-sided die).
* 1 means an event is certain to happen (e.g., the sun will rise tomorrow).
* 0.5 means an event is equally likely to happen or not happen (e.g., flipping a fair coin and getting heads).

You calculate probability by looking at the number of favorable outcomes (the ones you're interested in) divided by the total number of possible outcomes.

Understanding Events and Outcomes

Photo by Markus Winkler on Pexels

An experiment is any process with well-defined outcomes. For example, flipping a coin, rolling a die, or asking someone if they prefer coffee or tea.
An outcome is a single result of an experiment (e.g., getting "heads" when flipping a coin).
An event is a set of one or more outcomes (e.g., getting an even number when rolling a die means outcomes 2, 4, or 6).

Example: What's the probability of rolling an even number on a fair six-sided die?
* Favorable outcomes (even numbers): {2, 4, 6} → 3 outcomes
* Total possible outcomes: {1, 2, 3, 4, 5, 6} → 6 outcomes
* Probability = 3/6 = 0.5 or 50%

Introducing Proportions

Photo by https://kaboompics.com/ on Pexels

A proportion is essentially a fraction or a percentage that describes a part of a whole. In statistics, we often use proportions to describe the characteristics of a population or a sample.

Let's say you have 100 students in a school, and 60 of them prefer chocolate ice cream.
The proportion of students who prefer chocolate ice cream is 60/100 = 0.60.
You can also express this as a percentage: 0.60 * 100% = 60%.

Why are proportions important?
Often, we can't survey everyone in a large group (the population). So, we take a smaller group (a sample) and find the proportion for that sample. We then use this sample proportion to estimate the population proportion. This is a fundamental idea in statistics!

Relationship Between Probability and Proportion

Photo by DS stories on Pexels

You might notice that the way we calculate probability (favorable outcomes / total outcomes) looks a lot like calculating a proportion (part / whole). And you're right! They're very closely related.

Think of it this way:
* If you have a population where 60% of people prefer chocolate, the population proportion is 0.60.
* If you randomly pick one person from that population, the probability that they prefer chocolate is also 0.60.

This connection is key to understanding how we make inferences from samples to populations.

Here's a simple flow of how we often think about these concepts:

graph LR
    A["Real-world situation: What's the chance of X?"] --> B["Identify all possible Outcomes"]
    B --> C["Identify Favorable Outcomes (for Event X)"]
    C --> D["Calculate P(X) = (Favorable Outcomes) / (Total Outcomes)"]
    D --> E{"Is P(X) related to a 'part of a whole'?"}
    E -- Yes --> F["This 'part of a whole' is a Proportion"]
    E -- No --> G["It's just a Probability of a single random pick"]
    F --> H["Proportions help estimate Population Characteristics"]
    G --> H

3. Worked Example

Let's say a local high school has 500 students. We want to know the proportion of students who own a smartphone. We randomly survey 50 students and find that 40 of them own a smartphone.

1. Calculate the sample proportion:

   • Number of students in sample with smartphones = 40
   • Total students in sample = 50
   • Sample proportion (denoted as $\hat{p}$) = 40/50 = 0.80

2. Interpret the sample proportion:

   • This means 80% of the students in our sample own a smartphone.

3. Relate to probability:

   • If you were to randomly pick one student from our sample, the probability that they own a smartphone would be 0.80.

4. Estimate the population proportion:

   • We can use this sample proportion (0.80) as our best guess for the true proportion of all 500 students in the high school who own a smartphone. This is an inference. We're using a small group to say something about a larger group. We know this isn't perfect, but it's our best estimate based on the data we have.

4. Key Takeaways

• Probability quantifies uncertainty, telling you how likely an event is on a scale from 0 (impossible) to 1 (certain).
• Proportions describe the fraction of a group that shares a specific characteristic or trait.
• You calculate probability by dividing favorable outcomes by total possible outcomes.
• A sample proportion is an estimate of a population proportion, used when studying an entire population is too difficult.
• The probability of randomly selecting an item with a specific characteristic from a group is numerically equal to the proportion of that characteristic in the group.
• Understanding probability and proportions is foundational for making educated guesses about larger populations based on smaller samples.

Common Mistakes to Avoid:

• Confusing a sample proportion with the true (often unknown) population proportion – the sample proportion is just an estimate!
• Assuming a small sample perfectly reflects a large population – there's always variability.
• Calculating probability as a percentage without converting it to a decimal or fraction first (e.g., saying 50 probability instead of 0.50).
• Not ensuring all possible outcomes are accounted for when calculating total outcomes.

5. Now Try It

Imagine a deck of 52 playing cards.

1. What is the probability of drawing a red card?
2. What is the proportion of red cards in the entire deck?
3. If you draw 10 cards and 7 of them are red, what is your sample proportion of red cards?
4. Based on your sample, what would you estimate the proportion of red cards in the entire deck to be?

Success looks like calculating three different numerical values (two probabilities and one proportion) and then stating your estimate for the population proportion clearly.