Practice 50 chapter-wise MCQs covering statistical modeling, linear relationships, correlation, experimental design, population and sample, statistics, data visualization, summary statistics, data cleaning and computational data-analysis tools.
A) Study relationships in data and use them to make predictions or recommendations B) Replace all data collection C) Store files without analysis D) Design computer hardware
2. In a statistical model, a variable is:
A) A fixed computer program B) A characteristic or quantity that can take different values C) Only a chart D) A database table
3. A linear relationship between two variables can be represented by:
A) x = y² B) x + y = 0 only C) y = mx + c D) y = x³ only
4. In y = mx + c, m represents the:
A) Intercept B) Dependent variable C) Data set size D) Slope
5. In y = mx + c, c represents the:
A) Intercept B) Slope C) Correlation coefficient D) Sample size
6. The slope of a straight line indicates:
A) The number of observations B) The rate at which y changes with x C) The sample size D) The type of graph
7. A positive slope generally indicates that:
A) As x increases, y always decreases B) There is no relationship C) As x increases, y tends to increase D) Both variables are constant
8. A negative slope generally indicates that:
A) Both variables increase together B) There is perfect correlation C) The intercept is zero D) As x increases, y tends to decrease
9. The correlation coefficient is used to describe:
A) The strength and direction of a linear association between two variables B) The number of rows in a database C) Only the slope D) The colour of a graph
10. A correlation coefficient close to +1 indicates:
A) A strong negative linear association B) A strong positive linear association C) No linear association D) A categorical variable
11. A correlation coefficient close to -1 indicates:
A) A strong positive association B) No association C) A strong negative linear association D) A random sample
12. A correlation coefficient close to 0 generally indicates:
A) Perfect positive correlation B) Perfect negative correlation C) A causal relationship D) Little or no linear association
13. Correlation by itself does not prove:
A) Causation B) Association C) Variation D) Measurement
14. A statistical model can be used to:
A) Guarantee future events B) Make predictions based on observed relationships in data C) Eliminate uncertainty completely D) Replace every experiment
15. A good choice of statistical model depends partly on:
A) The computer brand B) The colour of the data C) The nature of the data and the question being investigated D) The size of the monitor
16. Linear regression is used to model:
A) Only categorical labels B) Only database keys C) Only images D) A linear relationship between variables
17. A fitted regression line is intended to:
A) Represent the relationship between variables in a data set B) Show every observation exactly C) Replace the original data D) Prove causation
18. A residual is commonly the:
A) Slope of a regression line B) Difference between an observed value and its predicted value C) Intercept of a line D) Number of variables
19. A model should be evaluated using:
A) Only its appearance B) Only the number of equations C) Evidence about how well it represents or predicts the data D) Only its file size
20. A recommendation based on statistical findings should consider:
A) Only the highest value B) Only the average C) Only the graph title D) The quality, context and limitations of the evidence
21. An experiment is useful in data science because it can help:
A) Distinguish possible causal effects from simple associations B) Eliminate all variation C) Avoid collecting data D) Guarantee a desired result
22. An observational study differs from a designed experiment because researchers:
A) Always control every variable B) Observe existing conditions without assigning the treatment in the same way as an experiment C) Never collect numerical data D) Cannot study relationships
23. A survey is commonly used to:
A) Build a computer processor B) Compile a program C) Collect information from people using structured questions D) Create a regression line automatically
24. A controlled experiment typically involves:
A) No variables B) No measurements C) Only historical data D) Manipulating a factor and observing its effect under controlled conditions
25. The population in statistics is:
A) The complete group of interest in a study B) A small subset selected from a group C) Only the people who answer first D) The mean of a data set
26. A sample is:
A) The entire population B) A subset of the population selected for study C) A type of graph D) A regression equation
27. A parameter describes:
A) Only a sample B) Only a graph C) A characteristic of a population D) A computer model
28. A statistic describes:
A) Only the population B) A database schema C) A graph axis D) A characteristic calculated from a sample
29. Random sampling is useful because it can:
A) Reduce selection bias when properly carried out B) Guarantee a perfect prediction C) Remove all measurement error D) Make a population smaller
30. A confounding variable is one that:
A) Is always the dependent variable B) Can affect the apparent relationship between variables and make interpretation difficult C) Must be categorical D) Is never measured
31. Central tendency describes:
A) The number of variables B) The shape of a database C) A typical or central value in a data set D) The colour of a chart
32. The mean is calculated by:
A) Selecting the most frequent value B) Selecting the middle value C) Subtracting the smallest from the largest D) Adding values and dividing by the number of values
33. The median is:
A) The middle value when data are ordered, with appropriate handling for an even number of observations B) Always the largest value C) Always the mean D) The difference between extremes
34. The mode is:
A) The middle value B) The most frequently occurring value C) The arithmetic average D) The range
35. The range is:
A) The average value B) The most common value C) The difference between the maximum and minimum values D) The number of observations
36. A measure of spread tells us about:
A) Only the mean B) Only the mode C) Only the sample size D) How dispersed or variable the data are
37. A histogram is especially useful for showing:
A) The distribution of a numerical variable B) A database relationship C) A program's source code D) Only categorical labels
38. A bar chart is commonly used to compare:
A) Only continuous distributions B) Values across categories C) Regression residuals only D) Database tables
39. A pie chart is commonly used to show:
A) A time series with many points B) The exact slope of a regression line C) Parts of a whole as proportions D) Only continuous measurements
40. A scatterplot is useful for examining:
A) Only category names B) Only database records C) Only one constant value D) The relationship between two numerical variables
41. A boxplot can show:
A) The centre, spread and possible outliers of a numerical data set B) Only the mean C) Only the sample size D) Only categorical frequencies
42. A line graph is especially useful for showing:
A) A database schema B) Changes or trends across an ordered variable such as time C) Only proportions of a whole D) Only individual categories
43. An outlier is:
A) The average value B) The most frequent observation C) An observation unusually far from the rest of the data D) A variable name
44. Data visualization helps because it:
A) Eliminates the need for data analysis B) Guarantees correct conclusions C) Makes every relationship causal D) Can reveal patterns, trends and unusual observations
45. A data set consists of:
A) Collected observations and their associated variables B) Only graphs C) Only averages D) Only database commands
46. Data cleaning may involve:
A) Adding random values B) Handling missing, duplicated or inconsistent data appropriately C) Deleting every unusual observation D) Changing all values to the mean
47. A spreadsheet tool such as Excel or Google Sheets can be used to:
A) Only write essays B) Only browse websites C) Analyze data and create charts D) Only compile Python programs
48. A data visualization should have:
A) Unlabelled axes B) Misleading scales C) Random categories D) Clear labels and a suitable chart type for the data
49. A model's prediction should be interpreted with:
A) Awareness of uncertainty, assumptions and limitations B) Absolute certainty C) No reference to the data D) Only the graph colour
50. A multiple linear regression model uses:
A) Only one numerical value B) More than one predictor variable to model a response variable C) Only categorical charts D) No dependent variable
These MCQs are prepared with reference to the FBISE HSSC-I Computer Science Assessment Framework and the National Curriculum of Pakistan 2022–23. Chapter 4 covers SLO CS-11-D-01 on model building and real-world applications, CS-11-D-02 on experimental design in data science, and CS-11-D-03 on analyzing pre-existing data sets to create summary statistics and data visualizations. Topics include linear relationships and correlation, population and sample, parameter and statistic, experimentation, surveys and observational studies, central tendency and spread, and visualizations such as bar charts, pie charts, line graphs, boxplots, histograms and scatterplots.