Chebyshev's lemma, weak law of large numbers, central limit theorem for i.i.d. variables, standard errors - Question Bank

1. The Weak Law of Large Numbers is a statement about the behavior of the sample mean as the sample size approaches infinity. It states that the sample mean converges to the population mean:
A) With certainty
B) In probability
C) In distribution
D) In variance
2. Which of the following is a direct consequence of Chebyshev's lemma?
A) The sample mean will always be within one standard deviation of the population mean.
B) The probability of a random variable being far from its mean is bounded.
C) The distribution of any random variable is normal.
D) The variance of any random variable is zero.
3. The Central Limit Theorem allows us to approximate the sampling distribution of the sample mean with a normal distribution. This approximation improves as:
A) The sample size decreases
B) The population variance increases
C) The sample size increases
D) The population mean deviates further from zero
4. What is the standard error of the difference between two independent sample means (X̄₁ - X̄₂), assuming equal variances σ²?
A) √(σ²/n₁ + σ²/n₂)
B) √(σ²/n₁)
C) √(σ²/n₂)
D) σ * √(1/n₁ + 1/n₂)
5. If X₁, X₂, ..., Xn are i.i.d. random variables with mean μ and variance σ², the distribution of the sample mean X̄n for large n is approximately:
A) Normal with mean μ and variance σ²
B) Normal with mean μ and variance σ²/n
C) Uniform with mean μ
D) Binomial with parameters n and μ/σ²
6. The Weak Law of Large Numbers is essential for the concept of statistical estimation. It provides theoretical justification for:
A) Using a single data point to estimate a parameter.
B) Using the sample mean to estimate the population mean.
C) Using the population mean to estimate the sample mean.
D) Using the variance to estimate the mean.
7. Chebyshev's lemma is a general result. Compared to the actual distribution of the sum of random variables, the bound provided by Chebyshev's lemma is typically:
A) More precise
B) Less precise
C) Equally precise
D) Only applicable for specific values of k
8. The standard error of the sample mean is calculated as σ/√n. If the sample size is quadrupled, how does the standard error change?
A) It remains the same.
B) It is halved.
C) It is doubled.
D) It is quadrupled.
9. If the sample size is small, and the population standard deviation is unknown, which distribution is typically used for inference regarding the population mean?
A) Normal distribution
B) t-distribution
C) Chi-squared distribution
D) F-distribution
10. What is the primary condition under which the Central Limit Theorem applies to the sum of *non-identically* distributed random variables?
A) Their means must be equal.
B) Their variances must be equal.
C) The Lyapunov condition or Lindeberg condition must be met.
D) They must be drawn from a normal distribution.
11. The Weak Law of Large Numbers implies that for a large sample, the sample mean is a 'good' estimator of the population mean. What does 'good' mean in this context?
A) It is guaranteed to be exactly equal to the population mean.
B) It is likely to be close to the population mean.
C) It is the only possible estimator.
D) It has zero variance.
12. Consider a random variable X with mean μ. Chebyshev's inequality states P(|X - μ| ≥ k) ≤ Var(X)/k². If we set k = 3 and Var(X) = 9, what is the maximum probability that X is outside the interval (μ-3, μ+3)?
A) 1/9
B) 1/3
C) 1
D) 0
13. Which of the following statements about standard error is FALSE?
A) It decreases as the sample size increases.
B) It measures the precision of a sample statistic as an estimate of a population parameter.
C) It is the same as the standard deviation of the population.
D) It is used in constructing confidence intervals.
14. If a sample of size n is drawn from a population with mean μ and standard deviation σ, the standard error of the sample mean is:
A) Directly proportional to σ
B) Inversely proportional to σ
C) Directly proportional to n
D) Inversely proportional to σ²
15. What is the role of the Central Limit Theorem in statistical inference?
A) It allows us to approximate probabilities for sums/averages of random variables using the normal distribution.
B) It guarantees that the population is normally distributed.
C) It provides exact distributions for small sample sizes.
D) It eliminates the need for hypothesis testing.
16. For the Weak Law of Large Numbers to hold, is it sufficient for the random variables to be independent but not identically distributed?
A) Yes, independence is sufficient.
B) No, they must also be identically distributed or satisfy certain moment conditions.
C) Yes, if their means are all zero.
D) No, they must be normally distributed.
17. The Strong Law of Large Numbers (SLLN) is a stronger result than the Weak Law of Large Numbers (WLLN). What type of convergence does the SLLN guarantee?
A) Convergence in probability
B) Convergence in distribution
C) Almost sure convergence
D) Convergence in mean square
18. Chebyshev's lemma provides a bound that is:
A) Tight for all distributions
B) Generally loose but universally applicable
C) Only applicable to normal distributions
D) Dependent on the sample size
19. In the context of the Central Limit Theorem, what does 'i.i.d.' stand for?
A) Independent and Identically Distributed
B) Internal and Independent Data
C) Integrated and Distributed
D) Independent and Intuitively Distributed
20. What is the standard error of a regression coefficient in linear regression?
A) It measures the variability of the coefficient estimate across different samples.
B) It is always equal to the standard deviation of the dependent variable.
C) It is solely determined by the sample size.
D) It is the same as the standard error of the mean.
21. If Z is a standard normal random variable, and X̄n is the sample mean of n i.i.d. random variables with mean μ and standard deviation σ, which of the following is approximately true for large n?
A) X̄n ≈ μ + σZ/√n
B) X̄n ≈ μ + Z/√n
C) X̄n ≈ σ + Z/√n
D) X̄n ≈ μ + σZ
22. The Central Limit Theorem is often stated for sums of random variables. For a sum S_n = X₁ + ... + Xn of i.i.d. random variables with mean μ and variance σ², the standardized sum Z_n = (S_n - nμ) / (σ√n) converges in distribution to:
A) A uniform distribution
B) A standard normal distribution
C) A t-distribution with n-1 degrees of freedom
D) A chi-squared distribution
23. Consider a sequence of random variables Xn such that E[Xn] = 0 for all n and Var(Xn) = 1/n. Does this sequence converge in probability to 0?
A) Yes, by Chebyshev's inequality.
B) No, because the variance does not converge to 0.
C) Yes, because the mean is 0.
D) No, because the distribution is not specified.
24. The Weak Law of Large Numbers guarantees convergence in probability. What is the key difference between convergence in probability and almost sure convergence?
A) Almost sure convergence is a stronger form of convergence.
B) Convergence in probability implies almost sure convergence.
C) They are equivalent statements.
D) Almost sure convergence requires finite variance.
25. Chebyshev's lemma can be used to derive a bound for the error in approximating the population mean by the sample mean. If we want the probability of the sample mean being within ε of the population mean to be at least 0.9, what is the maximum possible value for σ/ε?
A) √10
B) 1/√10
C) 10
D) 1/10
26. Which statistical concept is most directly related to the standard error of a statistic?
A) Bias
B) Variance of the sampling distribution
C) Point estimate
D) Hypothesis testing
27. The concept of standard error is crucial for constructing confidence intervals. A wider confidence interval is associated with:
A) A smaller standard error
B) A larger standard error
C) A larger sample size
D) A higher confidence level and a smaller standard error
28. What is the standard error of the sample proportion (p̂) in a large sample, assuming the population proportion is p?
A) √(p(1-p))
B) √(p(1-p)/n)
C) p(1-p)/n
D) √(p/n)
29. If we have a sample of size n = 100 from a population with standard deviation σ = 10, what is the standard error of the sample mean?
A) 10
B) 1
C) 0.1
D) 100
30. When the population standard deviation (σ) is unknown, how is the standard error of the sample mean typically estimated?
A) By using the sample standard deviation (s) in place of σ.
B) By using the population mean (μ).
C) By using the sample size (n).
D) By assuming the population standard deviation is 1.
31. The standard error quantifies the variability of a sample statistic. For the sample mean, what does the standard error represent?
A) The standard deviation of the population.
B) The typical deviation of sample means from the population mean.
C) The variance of the population.
D) The distance between the sample mean and the population mean.
32. What is the standard error of the sample mean (X̄n)?
A) σ
B) σ / √n
C) σ² / n
D) μ / √n
33. The CLT is powerful because it allows us to make inferences about population parameters using sample statistics, even when the population distribution is unknown. Which distribution is typically used for hypothesis testing and confidence intervals when the CLT applies?
A) Chi-squared distribution
B) t-distribution
C) Normal distribution (or standard normal)
D) F-distribution
34. The Central Limit Theorem is often stated for the sum S_n = X₁ + X₂ + ... + Xn. As n becomes large, what distribution does S_n approximate?
A) A normal distribution with mean nμ and variance nσ²
B) A normal distribution with mean μ and variance σ²
C) A uniform distribution with mean nμ
D) A Poisson distribution with mean nμ
35. What is the variance of the sampling distribution of the sample mean X̄n, according to the Central Limit Theorem, for i.i.d. random variables with variance σ²?
A) σ²
B) μ²
C) σ²/n
D) σ²/n²
36. What is the mean of the sampling distribution of the sample mean X̄n, according to the Central Limit Theorem, for i.i.d. random variables with mean μ?
A) μ / n
B) μ
C) σ²
D) μ / σ
37. For the Central Limit Theorem to apply to a sequence of i.i.d. random variables X₁, X₂, ..., Xn, what is the crucial condition related to the individual variables?
A) They must be normally distributed.
B) They must have finite variance.
C) They must have a known probability density function.
D) They must be discrete random variables.
38. The Central Limit Theorem (CLT) is a cornerstone of statistics. What does the CLT state about the distribution of the sum or average of a large number of independent random variables?
A) The sum/average will follow the distribution of the individual variables.
B) The sum/average will approach a normal distribution, regardless of the original distribution.
C) The sum/average will approach a uniform distribution.
D) The distribution of the sum/average will be a Cauchy distribution.
39. A common proof of the Weak Law of Large Numbers utilizes Chebyshev's inequality applied to the sample mean. What property of the sample mean is essential for this proof?
A) Its mean is equal to the population mean.
B) Its variance is finite and decreases as n increases.
C) Its distribution is normal.
D) Its median is equal to the population mean.
40. The Weak Law of Large Numbers is a fundamental result in probability theory because it justifies the use of sample averages to estimate population parameters. What does it imply about large samples?
A) The sample average will be exactly equal to the population mean.
B) The sample average is likely to be close to the population mean.
C) The sample average will deviate significantly from the population mean.
D) The distribution of the sample average approaches a uniform distribution.
41. Mathematically, the Weak Law of Large Numbers states that for a sequence of i.i.d. random variables X₁, X₂, ..., Xn with E[Xᵢ] = μ and Var(Xᵢ) = σ², the sample mean X̄n converges in probability to μ. This is expressed as:
A) lim (n→∞) P(|X̄n - μ| < ε) = 1 for any ε > 0
B) lim (n→∞) P(|X̄n - μ| ≥ ε) = 0 for any ε > 0
C) lim (n→∞) P(|X̄n - μ| = 0) = 1
D) lim (n→∞) E[|X̄n - μ|] = 0
42. What are the typical conditions required for the Weak Law of Large Numbers to hold for a sequence of independent and identically distributed (i.i.d.) random variables?
A) Finite variance
B) Finite mean
C) Finite third moment
D) Infinite variance is allowed
43. The Weak Law of Large Numbers (WLLN) states that under certain conditions, the sample mean converges to the population mean. In what sense does this convergence occur?
A) Convergence in probability
B) Convergence in distribution
C) Almost sure convergence
D) Convergence in mean square
44. Consider a random variable X with mean μ and standard deviation σ. According to Chebyshev's lemma, what is the maximum probability that X falls outside the interval (μ - 2σ, μ + 2σ)?
A) 1/2
B) 1/4
C) 3/4
D) 1
45. Chebyshev's lemma is particularly useful when the distribution of the random variable is:
A) Known and normal
B) Unknown or non-normal
C) Uniform
D) Symmetric
46. What is the primary implication of Chebyshev's lemma regarding the concentration of probability around the mean?
A) It guarantees that all probability mass is within k standard deviations.
B) It provides an upper bound on the probability of a value being far from the mean.
C) It states that the probability of being close to the mean approaches 1.
D) It is only applicable to normally distributed random variables.
47. In Chebyshev's lemma, what does 'k' represent in the inequality P(|X - μ| ≥ kσ) ≤ 1/k²?
A) A constant greater than 1
B) A constant greater than 0
C) The standard deviation
D) The expected value
48. Chebyshev's lemma provides a bound on the probability that a random variable deviates from its expected value. What is the form of this inequality?
A) P(|X - μ| ≥ kσ) ≤ 1/k²
B) P(|X - μ| ≥ kσ) ≥ 1/k²
C) P(|X - μ| < kσ) ≤ 1 - 1/k²
D) P(|X - μ| < kσ) ≥ 1 - 1/k²