Statistics Mastery Quiz — Quiz

Sampling, confidence intervals, regression, A/B tests, chi-square, ANOVA and Bayesian basics. · 10 questions

Question 1 of 10

Which sampling method guarantees every city is represented in proportion to its size?

aConvenience samplingbSnowball samplingcStratified samplingdSelf-selected online survey

Question 2 of 10

If you quadruple the sample size, what happens to the standard error of the mean?

aIt halvesbIt quarterscIt doublesdIt stays the same

Question 3 of 10

Ice-cream sales and AC sales are highly correlated across months. What is the most likely explanation?

aIce cream causes AC purchasesbAC purchases cause ice-cream salescThe correlation must be a data errordA confounder: hot weather drives both

Question 4 of 10

Which test checks whether two categorical variables, such as city and payment method, are related?

aOne-way ANOVAbChi-square test of independencecPearson correlationdPaired t-test

Question 5 of 10

Which statement correctly interprets a 95% confidence interval of [₹462, ₹510] for the mean bill?

a95% of bills lie between ₹462 and ₹510bThere is a 95% probability the sample mean is in this rangecThe method produces intervals that contain the true mean in about 95% of repeated samplesdThe true mean is exactly ₹486

Question 6 of 10

A one-way ANOVA across four campaigns gives p = 0.002. What can you conclude?

aAt least one campaign mean differs; use a post-hoc test to find whichbAll four means are different from each othercCampaign D is the bestdThe data are normally distributed

Question 7 of 10

What does this code estimate?

a = rng.beta(1 + 540, 1 + 11460, 100_000)
b = rng.beta(1 + 624, 1 + 11376, 100_000)
print((b > a).mean())

aThe p-value of a z-testbThe required sample sizecThe posterior probability that B's conversion rate exceeds A'sdThe standard error of the difference

Question 8 of 10

In `smf.ols('sales ~ ad_spend + store_size', data=df).fit()`, the ad_spend coefficient is 2.0 (both in ₹ thousand). What does it mean?

aAd spend explains 2% of salesbEach extra ₹1,000 of ads is associated with about ₹2,000 more sales, holding store size fixedcAds double salesdAds definitely cause ₹2,000 more sales in every store

Question 9 of 10

An analyst checks an A/B test every morning and stops as soon as p < 0.05. Why is this a problem?

aIt makes the test less sensitivebZ-tests cannot be run more than oncecIt reduces the sample ratiodRepeated peeking inflates the false-positive rate well above 5%

Question 10 of 10

A test planned a 50/50 split but recorded 51,800 vs 48,200 users. What should you do first?

aInvestigate a sample ratio mismatch before trusting any resultbDeclare the larger group the winnercReweight the results and continuedIgnore it; splits never match exactly