Download NWCA Using Statistics Exam and more Exams Technology in PDF only on Docsity!
Question 1. Which of the following best describes a nominal variable? A) It has a true zero point. B) Values can be ranked in order. C) Categories are labels with no intrinsic order. D) It measures continuous quantities. Answer: C Explanation: Nominal variables consist of categories that are names only; they cannot be ordered or quantified. Question 2. An example of an ordinal variable in a health survey is: A) Blood type (A, B, AB, O) B) Number of cigarettes smoked per day C) Pain intensity rated on a 1‑to‑5 scale D) Body temperature in Celsius Answer: C Explanation: Ordinal variables have a meaningful order (e.g., pain severity) but the intervals between ranks are not necessarily equal. Question 3. Which measurement scale possesses a true zero that allows for meaningful ratios? A) Interval B) Ordinal C) Ratio D) Nominal Answer: C Explanation: Ratio scales have a non‑arbitrary zero, enabling statements like “twice as much”.
Question 4. In a study measuring systolic blood pressure, the appropriate level of measurement is: A) Nominal B) Ordinal C) Interval D) Ratio Answer: D Explanation: Blood pressure has a true zero (no pressure) and equal intervals; thus it is ratio. Question 5. The main advantage of random sampling over convenience sampling is: A) It is faster to collect data. B) It reduces selection bias. C) It guarantees a larger sample size. D) It eliminates non‑response bias. Answer: B Explanation: Random sampling gives each population member an equal chance of selection, minimizing selection bias. Question 6. Stratified sampling is most useful when: A) The population is homogeneous. B) Researchers need to ensure representation of subgroups. C) Time constraints are severe. D) The sample size is unlimited. Answer: B Explanation: Stratified sampling divides the population into strata (e.g., age groups) and samples each proportionally.
A) They can take any value within a range. B) They are always measured on a ratio scale. C) They often require rounding for reporting. D) They include measurements such as weight and cholesterol. Answer: B Explanation: Continuous variables can be measured on interval scales (e.g., temperature in Celsius) that lack a true zero. Question 11. The mean is most appropriate as a measure of central tendency when the distribution is: A) Highly skewed. B) Bimodal. C) Symmetrical with no extreme outliers. D) Ordinal. Answer: C Explanation: The mean is sensitive to extreme values; it best represents the center of symmetric distributions. Question 12. In a right‑skewed income distribution, which statistic is the most robust measure of central tendency? A) Mean B) Median C) Mode D) Geometric mean Answer: B Explanation: The median is unaffected by extreme high incomes that pull the mean to the right.
Question 13. The mode is particularly useful for which type of data? A) Continuous interval data. B) Nominal categorical data. C) Ratio data with outliers. D) Data with a normal distribution. Answer: B Explanation: The mode identifies the most frequent category, which is meaningful for nominal data. Question 14. The range of a dataset is calculated as: A) Q3 – Q B) Maximum – Minimum C) Standard deviation multiplied by 2 D) Sum of squared deviations divided by n‑ 1 Answer: B Explanation: Range simply measures the spread between the highest and lowest observations. Question 15. Which measure of variability is expressed in the same units as the original data? A) Variance B) Standard deviation C) Interquartile range D) Coefficient of variation Answer: B Explanation: Standard deviation is the square root of variance, thus shares the original unit. Question 16. An interquartile range (IQR) is calculated as:
Question 19. A histogram with a symmetric bell shape suggests that the underlying data likely follow which distribution? A) Uniform B) Exponential C) Normal D) Poisson Answer: C Explanation: A symmetric, unimodal histogram is characteristic of a normal distribution. Question 20. In a scatter plot, the presence of a tight, upward‑sloping cloud of points indicates: A) No relationship between variables. B) A strong positive linear correlation. C) A strong negative linear correlation. D) A curvilinear relationship. Answer: B Explanation: Points clustering close to an upward line demonstrate a strong positive linear association. Question 21. The probability of an event that is certain to occur is: A) 0 B) 0. C) 1 D) Undefined Answer: C Explanation: Probabilities range from 0 (impossible) to 1 (certain).
Question 22. If two events are independent, the probability of both occurring equals: A) The sum of their individual probabilities. B) The product of their individual probabilities. C) The larger of the two probabilities. D) Zero. Answer: B Explanation: Independence implies P(A ∩ B) = P(A)·P(B). Question 23. Which of the following statements is true about the normal distribution? A) It is always positively skewed. B) Its mean, median, and mode are identical. C) It has a fixed range of 0 to 100. D) It cannot be standardized. Answer: B Explanation: In a perfectly normal distribution, the three measures of central tendency coincide. Question 24. According to the Empirical Rule, approximately what percent of data lies within two standard deviations of the mean in a normal distribution? A) 68 % B) 95 % C) 99.7 % D) 50 % Answer: B Explanation: The 68‑ 95 ‑99.7 rule states that about 95 % of observations fall within ± 2 σ. Question 25. A Z‑score of – 2.5 indicates that the observation is:
A) The two groups are randomly sampled. B) The dependent variable is measured on an interval or ratio scale. C) The variances of the two groups are exactly equal. D) The observations are independent within each group. Answer: C Explanation: Equal variances are desired but not mandatory; the Welch’s t‑test adjusts for unequal variances. Question 29. In hypothesis testing, the null hypothesis (H₀) typically states that: A) There is a significant effect. B) There is no difference or effect. C) The alternative hypothesis is true. D) The p‑value will be less than α. Answer: B Explanation: H₀ represents the status quo—no effect or no association. Question 30. A researcher obtains a p‑value of 0.03 when α = 0.05. The correct decision is to: A) Fail to reject H₀. B) Reject H₀. C) Accept H₀. D) Increase the sample size. Answer: B Explanation: Since p < α, the result is statistically significant; we reject the null hypothesis. Question 31. A Type I error occurs when: A) A true null hypothesis is incorrectly rejected.
B) A false null hypothesis is incorrectly accepted. C) The sample size is too small. D) The p‑value exceeds α. Answer: A Explanation: Type I error (false positive) is rejecting H₀ when it is actually true. Question 32. Power of a statistical test is defined as: A) The probability of making a Type I error. B) The probability of correctly rejecting a false null hypothesis. C) 1 – α. D) The sample size divided by the effect size. Answer: B Explanation: Power = 1 – β; it reflects the test’s ability to detect a real effect. Question 33. Which of the following best describes a one‑tailed hypothesis test? A) It tests for any difference, regardless of direction. B) It tests for a difference in a specific direction only. C) It always uses α = 0.01. D) It requires paired data. Answer: B Explanation: One‑tailed tests consider deviations in only one direction (e.g., > 0). Question 34. In an ANOVA table, a statistically significant F‑statistic indicates that: A) All group means are equal. B) At least one group mean differs from the others. C) The data are normally distributed.
Explanation: Correlation measures association but cannot establish cause‑effect. Question 38. The coefficient of determination (R²) of 0.64 means that: A) 64 % of the variation in the dependent variable is explained by the model. B) The correlation coefficient is 0.64. C) 36 % of the data are outliers. D) The regression line passes through 64 % of the points. Answer: A Explanation: R² = (r)²; it quantifies the proportion of variance accounted for. Question 39. In simple linear regression, the slope coefficient represents: A) The predicted value of the dependent variable when the independent variable is zero. B) The change in the dependent variable for a one‑unit increase in the independent variable. C) The correlation between the two variables. D) The variability of the residuals. Answer: B Explanation: The slope quantifies the expected change in Y per unit change in X. Question 40. A residual plot that shows a funnel shape suggests: A) Homoscedasticity (equal variance). B) Heteroscedasticity (non‑constant variance). C) Perfect linear fit. D) No relationship between variables. Answer: B Explanation: A funnel pattern indicates variance changes with the level of the predictor, violating homoscedasticity.
Question 41. Clinical significance differs from statistical significance in that: A) Clinical significance requires p < 0.01. B) Clinical significance reflects practical importance for patient care. C) Clinical significance is measured by the sample size. D) Clinical significance is always larger than statistical significance. Answer: B Explanation: Clinical significance asks whether an effect size matters in real‑world health contexts. Question 42. Relative risk (RR) of 1.5 indicates that the exposed group has: A) 50 % lower risk compared to the unexposed group. B) 1.5 times the risk of the unexposed group. C) No difference in risk. D) A 150 % increase in odds. Answer: B Explanation: RR > 1 shows increased risk; 1.5 means a 50 % higher risk. Question 43. An odds ratio (OR) of 0.7 suggests: A) The odds of outcome are 30 % lower in the exposed group. B) The odds are 70 % higher in the exposed group. C) No association between exposure and outcome. D) The relative risk is also 0.7. Answer: A Explanation: OR < 1 indicates reduced odds; 0.7 corresponds to a 30 % reduction.
A) Content validity B) Construct validity C) Criterion‑related (predictive) validity D) Face validity Answer: C Explanation: Predictive validity examines the test’s ability to forecast outcomes. Question 48. A researcher reports a statistically significant p‑value (p = 0.04) but the effect size (Cohen’s d) is 0.15. This suggests: A) A large, practically important effect. B) A small effect that may lack clinical relevance. C. That the study is under‑powered. D. That the p‑value is incorrect. Answer: B Explanation: Small effect size indicates limited practical impact despite statistical significance. Question 49. In a meta‑analysis, heterogeneity among studies is commonly quantified by: A) The p‑value. B. The I² statistic. C. The chi‑square test for independence. D. The Pearson correlation. Answer: B Explanation: I² describes the proportion of total variation due to between‑study heterogeneity. Question 50. When interpreting a research article, the term “adjusted odds ratio” indicates that: A. The OR has been corrected for confounding variables.
B. The OR has been multiplied by the sample size. C. The OR is the same as the crude OR. D. The OR is only applicable to randomized trials. Answer: A Explanation: Adjusted OR accounts for other covariates in a multivariable model, reducing confounding bias. Question 51. Which of the following is a characteristic of a discrete probability distribution? A. It can take any real value. B. Probabilities are assigned to intervals. C. The sum of all probabilities equals 1. D. It is always symmetric. Answer: C Explanation: In any probability distribution, the total probability across all possible outcomes must be 1. Question 52. The probability of drawing an ace from a standard deck of 52 cards is: A. 1/ B. 1/ C. 4/ D. 1/ Answer: C Explanation: There are 4 aces; 4/52 simplifies to 1/13, but the direct answer matching the option is 4/52.
Question 56. A researcher wishes to estimate the mean systolic blood pressure of a population with 95 % confidence and a margin of error of ±3 mmHg. Which factor will most directly reduce the required sample size? A. Decreasing the confidence level to 90 % B. Increasing the variability (standard deviation) of blood pressure measurements C. Using a one‑tailed test D. Increasing the margin of error to ±5 mmHg Answer: D Explanation: A larger allowable error (±5 mmHg) reduces the necessary n because n ∝ (Z·σ/E)². Question 57. Which sampling method is most susceptible to selection bias? A. Simple random sampling B. Stratified random sampling C. Convenience sampling D. Systematic sampling with a random start Answer: C Explanation: Convenience samples are chosen based on ease of access, often leading to non‑representative groups. Question 58. In a matched‑pairs design, the appropriate statistical test for comparing means is: A. Independent‑samples t‑test B. Paired‑samples t‑test C. One‑way ANOVA D. Chi‑square test Answer: B Explanation: Paired t‑test accounts for the dependence between matched observations.
Question 59. The term “non‑response bias” refers to: A. Errors caused by faulty measurement instruments. B. Differences between those who participate and those who do not. C. Over‑representation of certain subgroups due to sampling. D. Random variation in data collection. Answer: B Explanation: Non‑response bias occurs when non‑participants differ systematically from participants. Question 60. Which of the following is an example of a ratio scale measurement? A. Temperature in Celsius B. Likert scale rating of satisfaction (1‑5) C. Number of steps taken per day D. Gender (male/female) Answer: C Explanation: Number of steps has a true zero and equal intervals, qualifying as ratio. Question 61. The median is less affected than the mean by: A. Symmetric distributions B. Outliers C. Large sample sizes D. Interval scaling Answer: B Explanation: The median depends only on the middle order, not on extreme values.
