2-Var Quant. Data
Experimental Design
Inference for Proportions
Probability
100

What does a positive correlation mean?

As x increases, y increases.

100

What is a control group? Why is it important?

A group used for comparison; helps establish causality.

100

State the conditions for constructing a 1-prop z-interval.

Random, 10%, Large Counts (np ≥ 10, n(1−p) ≥ 10)

100

What is meant by “mutually exclusive” events?

Events that cannot occur together (P(A and B) = 0).

200

A correlation r = 0.92 is found. Interpret its strength and direction.

Strong positive linear association.

200

Define replication in an experiment.

Repeating the treatment on many units to reduce variation.

200

A 95% CI for a population proportion is (0.42, 0.58). Interpret this interval.

We are 95% confident the true proportion is between 0.42 and 0.58.

200

P(A or B) = P(A) + P(B) − P(A and B). When do you use this?

When events overlap (not mutually exclusive).

300

What is the slope in a least-squares regression line? What does it mean?

Predicted change in y for each 1-unit increase in x.

300

What is the difference between an observational study and an experiment?

Only experiments assign treatments and can establish causation.

300

What does the p-value represent in a 1-prop z-test?

The probability of getting results as extreme or more if H₀ is true.

300

A bag has 3 red, 2 blue, 5 green marbles. What’s P(red or green)?

(3 + 5)/10 = 0.8

400

Calculate the residual if observed = 10 and predicted = 8.5

Residual = 10 − 8.5 = 1.5

400

Explain the purpose of blocking in an experiment.

Grouping similar subjects to reduce variability within treatments.

400

Calculate the standard error: p̂ = 0.6, n = 100

SE = √(0.6×0.4/100) = 0.049

400

You toss a coin 5 times. What’s P(all tails)?

(0.5)^5 = 0.03125

500

If a regression line has R² = 0.64, interpret this.

64% of the variation in y is explained by the model.

500

Describe a double-blind experiment and its benefits.

Neither subject nor evaluator knows treatment; reduces placebo and bias.

500

A test gives p = 0.003. What decision should you make at α = 0.05?

Since p < α, reject H₀; evidence supports alternative.

500

What’s the expected value of a game where you win $10 with P=0.2 and lose $2 with P=0.8?

E(X) = 10×0.2 + (−2)×0.8 = 2 − 1.6 = 0.4