Как писать на экзамене (чтобы не облажаться)
Пиши ровно так:
1. z для 60 = (60-70)/10 = -1
z для 80 = (80-70)/10 = +1
2. Из Z-таблицы: P(Z ≤ 1.00) = 0.8413
P(Z ≤ -1.00) = 1 - 0.8413 = 0.1587
3. Вероятность между = 0.8413 - 0.1587 = 0.6826 (68.26%)
The t-test is a statistical test that compares means (averages) to see if
there is a significant difference.
It uses the t-distribution (from your Week 4 PDF slide on “t-Distribution
– When the Sample Is Small”).
Why do we need the t-test?
• When your sample is small (usually n < 30)
• When you do NOT know the population standard deviation (σ)
• When your data are roughly normal (bell-shaped)
In these cases, you cannot use the z-test (normal distribution). You
must use the t-test instead.
The t-distribution has heavier tails than the normal curve — this gives
us more “room” for error when the sample is small.
Three Main Types of t-Tests (you must know all three)
1. One-sample t-test
– Compares your sample mean to a known population value (e.g., “Is
the average exam score really 70?”)
2. Independent two-sample t-test
– Compares means of two different groups (e.g., males vs females,
Group A vs Group B)
3. Paired t-test
– Compares means of the same group before and after (e.g.,
students’ scores before and after a course)
Exam Example 1: One-Sample t-Test (Most Common on Your Exam)
Problem
A teacher claims the average exam score in the class is 70.
You randomly test 15 students:
Sample mean x = 73
Sample standard deviation s = 9
Is the true average significantly different from 70? (α = 0.05, two-tailed)
Step-by-Step Solution (write exactly this way)
Step 1: State hypotheses
H₀: μ = 70 (no difference)
H₁: μ ≠ 70 (there is a difference)
Step 2: Calculate t-statistic
Step 3: Degrees of freedom
df = n – 1 = 15 – 1 = 14
Step 4: Find critical value from t-table
For df = 14, α = 0.05 (two-tailed), critical t = ±2.145
(Go to df = 14 row, 0.025 column in the t-table)
Step 5: Decision
|1.291| < 2.145 Fail to reject H₀
Conclusion: The sample mean is not significantly different from 70 (p
> 0.05).
Exam Example 2: Independent Two-Sample t-Test
Problem
Compare exam scores of two teaching methods.
Group A (n₁ = 20): mean = 78, s₁ = 10
Group B (n₂ = 20): mean = 72, s₂ = 8
Is there a significant difference? (α = 0.05, two-tailed, assume equal
variances)
Step-by-Step Solution
Step 1: Hypotheses
H₀: μ₁ = μ₂
H₁: μ₁ ≠ μ₂
Step 2: Calculate t
Step 3: df
df = 20 + 20 – 2 = 38
Step 4: Critical value
For df ≈ 38 (use df=30 or 40 row), α=0.05 two-tailed critical t ≈ ±2.021 (or
±2.024)
Step 5: Decision
|2.098| > 2.021 Reject H₀
Conclusion: There is a significant difference between the two teaching
methods.
Exam Example 3: Paired t-Test (Before-After)
Problem
10 students took a test before and after a course.
Before: mean = 65, s = 12
After: mean = 78, s = 10
Difference mean = 13, s_difference = 8
Is the course effective? (α = 0.05)
Steps (same as one-sample, but use the differences):
t = 13 / (8 / √10) ≈ 5.14
df = 9
Critical t ≈ ±2.262
5.14 > 2.262 Reject H₀ Course significantly improved scores.
This value is small, so the difference between the two means
is not statistically significant.
This means the variability in School A is 2.25 times larger than in
School B.
Answer: About 68% of students scored between 60 and 80.
2. Binomial Distribution
Problem:
A coin is flipped 5 times. What is the probability of getting exactly 3
heads?
Formula:
Solution:
3. Poisson Distribution
Problem:
On average, 2 buses arrive per hour. What is the probability that exactly
3 buses arrive in one hour?
Formula:
4. Exponential Distribution
Problem:
Average waiting time for a bus = 10 minutes. What is the probability
that the wait is less than 5 minutes?
Formula:
Solution:
Answer: Probability ≈ 39%.
5. Uniform Distribution
Problem:
A fair die is rolled. What is the probability of getting a number between 2
and 5?
Solution
6. Chi Square Distribution
Problem:
We expect equal preference for 3 ice cream flavors (vanilla, chocolate,
strawberry).
Observed: Vanilla = 30, Chocolate = 50, Strawberry = 20.
Expected = 100/3 ≈ 33.3 each.
Solution:
‑