1 of 10

CSE 163

Statistical Learning

​

Arpan Kapoor�Summer 2026��

​

​

2 of 10

Announcements

  • Homework 5: Mapping released, due Friday, August 14th
  • Programming Practice 6 due Thursday, August 6th
  • Project Part 3 (Report & Code) released, due Sunday, August 16th
    • Remember to include your project repository link in your EDA submission!

3 of 10

What is Statistics?

“The study of models to gather, understand, and draw conclusions from real-world data.”

- Hunter Schafer, 2020 (and probably other people too)

  • Applications of statistics:
    • Predicting disease outbreaks
    • Product testing
    • Sports analytics
    • Machine learning
    • …and many more

4 of 10

Statistics 101

  • Summary Statistics
    • Number of values in our data set
    • Mean - the “average” value
    • Median - the value in the middle of our data set
    • Standard deviation - how spread out our values are
    • Min, max, mode, range, etc.
  • Distributions
    • How are values in our data set distributed?
    • Uniform distribution
    • Normal distributions
    • Other types of distributions (e.g. bimodal)

5 of 10

Uniform Distribution - everything equally likely

  • Coin flip - Heads or Tails
  • Dice roll - all sides
  • Perfect random number generator

6 of 10

Normal Distribution - bell curved, mean centered

  • Height
  • IQ
  • Grades

7 of 10

Central Limit Theorem

Distribution of sample means approaches a normal distribution as number of samples increases!

8 of 10

Hypothesis Tests

  • Null Hypothesis is the hypothesis that supports the pre-existing expectations of probability (e.g. the status quo)
  • Alternative Hypothesis is the hypothesis that something is different, one that if true, would allow us to reject the null hypothesis.
  • Our p-value is the chance that this situation would happen in a world bound by the null hypothesis
    • If our p-value is lower than a given significance level (usually 0.05), it is significant enough to reject the null hypothesis
    • Be mindful of “p-hacking” - misusing data analysis techniques or data in the hopes of getting significant results
    • A non-significant result is still valuable and should be reported!

9 of 10

Type 1 and Type 2 Errors

Accept = “fail to reject”

10 of 10

Type 1 and Type 2 Errors

You visited Hall Health Center to check if you have the flu. Your doctor says you don’t have it, while you actually have the flu. What type of error did the doctor make?

Null hypothesis

You don’t have the flu