Skip to content

Statistics -- Diagnostic Tests

Statistics — Diagnostic Tests

Unit Tests

Tests edge cases, boundary conditions, and common misconceptions for statistics.

UT-1: Identifying Skew from Quartile Positions

Question:

For a dataset, the quartiles are Q1=42Q_1 = 42, Q2=55Q_2 = 55And Q3=70Q_3 = 70.

(a) Determine whether the data is positively skewed, negatively skewed, or symmetric.

(b) A student argues: “Since Q2Q1=13Q_2 - Q_1 = 13 and Q3Q2=15Q_3 - Q_2 = 15The data is positively skewed because Q3Q2>Q2Q1Q_3 - Q_2 \gt Q_2 - Q_1.” Is this reasoning correct?

(c) If the interquartile range is IQR=28IQR = 28State the outlier boundaries using the 1.5×IQR1.5 \times IQR rule.

[Difficulty: hard. Tests interpretation of quartile positions to identify skewness and outlier detection.]

Solution:

(a) The distances from the median are:

  • Q2Q1=5542=13Q_2 - Q_1 = 55 - 42 = 13
  • Q3Q2=7055=15Q_3 - Q_2 = 70 - 55 = 15

Since Q3Q2>Q2Q1Q_3 - Q_2 \gt Q_2 - Q_1The right tail is longer than the left tail, indicating positive skew.

(b) The student”s reasoning is correct in principle: positive skew means the right tail is longer. However, the student should note that this is a heuristic — formal skewness is measured by the moment coefficient 1n(xixˉs)3\frac{1}{n}\sum\left(\frac{x_i - \bar{x}}{s}\right)^3Not just quartile differences. The quartile-based test is a quick check, not definitive proof.

(c) Lower fence: Q11.5×IQR=4242=0Q_1 - 1.5 \times IQR = 42 - 42 = 0. Upper fence: Q3+1.5×IQR=70+42=112Q_3 + 1.5 \times IQR = 70 + 42 = 112.

Outliers are values below 00 or above 112112.


UT-2: PMCC with Coded Data

Question:

A dataset has the following coded values. The coding is y=x5010y = \frac{x - 50}{10}:

y=45,y2=285,n=9\sum y = 45, \quad \sum y^2 = 285, \quad n = 9

(a) Find xˉ\bar{x} and sxs_x (the standard deviation of xx).

(b) A student computes sy=285925=31.6725=6.67s_y = \sqrt{\frac{285}{9} - 25} = \sqrt{31.67 - 25} = \sqrt{6.67} and concludes sx=sys_x = s_y. Explain why this is wrong.

[Difficulty: hard. Tests coded data transformations and the effect on mean and standard deviation.]

Solution:

(a) yˉ=459=5\bar{y} = \frac{45}{9} = 5.

Since y=x5010y = \frac{x - 50}{10}We have x=10y+50x = 10y + 50:

xˉ=10yˉ+50=10(5)+50=100\bar{x} = 10\bar{y} + 50 = 10(5) + 50 = 100

For the standard deviation: sx=10sys_x = 10s_y.

sy=y2nyˉ2=285925=31.6725=6.672.58s_y = \sqrt{\frac{\sum y^2}{n} - \bar{y}^2} = \sqrt{\frac{285}{9} - 25} = \sqrt{31.67 - 25} = \sqrt{6.67} \approx 2.58

sx=10×2.58=25.8s_x = 10 \times 2.58 = 25.8

(b) The student’s error is concluding sx=sys_x = s_y. The coding y=x5010y = \frac{x-50}{10} scales by a factor of 110\frac{1}{10} and shifts by 5050. Scaling by cc multiplies the standard deviation by c|c|So sx=10sys_x = 10s_yNot sys_y. The student forgot to account for the scaling factor. Additionally, the student used 285931.67\frac{285}{9} \approx 31.67 and then subtracted 2525 (where 25=5225 = 5^2), which is correct for computing sys_yBut then incorrectly applied the result to sxs_x.


Integration Tests

Tests synthesis of statistics with other topics.

IT-1: Least Squares Regression and Summation (with Algebra)

Question:

Given five data points (xi,yi)(x_i, y_i) with \sum x_i = 15$$\sum y_i = 20$$\sum x_i^2 = 55$$\sum x_iy_i = 68And yi2=90\sum y_i^2 = 90:

(a) Find the equation of the least squares regression line of yy on xx in the form y=a+bxy = a + bx.

(b) Find PMCC (Pearson product-moment correlation coefficient).

(c) Predict the value of yy when x=5x = 5.

[Difficulty: hard. Combines regression computation with correlation analysis.]

Solution:

(a)

b=nxiyixiyinxi2(xi)2=5(68)15(20)5(55)225=340300275225=4050=0.8b = \frac{n\sum x_iy_i - \sum x_i \sum y_i}{n\sum x_i^2 - (\sum x_i)^2} = \frac{5(68) - 15(20)}{5(55) - 225} = \frac{340 - 300}{275 - 225} = \frac{40}{50} = 0.8

a=yˉbxˉ=2050.8×155=42.4=1.6a = \bar{y} - b\bar{x} = \frac{20}{5} - 0.8 \times \frac{15}{5} = 4 - 2.4 = 1.6

Regression line: y=1.6+0.8xy = 1.6 + 0.8x.

(b)

r=nxiyixiyi[nxi2(xi)2][nyi2(yi)2]r = \frac{n\sum x_iy_i - \sum x_i\sum y_i}{\sqrt{\big[n\sum x_i^2 - (\sum x_i)^2\big]\big[n\sum y_i^2 - (\sum y_i)^2\big]}}

=340300(275225)(450400)=4050×50=4050=0.8= \frac{340 - 300}{\sqrt{(275 - 225)(450 - 400)}} = \frac{40}{\sqrt{50 \times 50}} = \frac{40}{50} = 0.8

(c) When x=5x = 5: y=1.6+0.8(5)=1.6+4=5.6y = 1.6 + 0.8(5) = 1.6 + 4 = 5.6.

Overview

This content page provides comprehensive coverage of Maths content for the Ib qualification, with detailed explanations, worked examples, and practice questions aligned to the specification.

Content Structure

This page includes:

  • Key Definitions: Precise explanations of essential concepts
  • Core Concepts: Detailed treatment of fundamental principles
  • Worked Examples: Step-by-step solutions demonstrating application
  • Practice Questions: Examination-style questions with mark schemes
  • Common Pitfalls: Frequent errors and how to avoid them
  • Exam Tips: Strategies for maximising marks

How to Use This Content

  1. Read through the introductory material to establish context
  2. Study the definitions and core concepts carefully
  3. Work through the worked examples, following each step
  4. Attempt the practice questions independently
  5. Review your answers against the provided solutions
  6. Note any areas requiring further revision

Key Concepts

  • Foundational definitions and terminology
  • Application of principles to examination contexts
  • Connections to related topics within the specification
  • Assessment objective alignment

Revision Strategies

  • Active Recall: Test yourself on the material rather than passively re-reading
  • Spaced Repetition: Review this content at increasing intervals
  • Interleaving: Mix this topic with others during study sessions
  • Elaborative Interrogation: Ask yourself why each concept works

Exam Preparation

Practise applying these concepts under timed conditions. Focus on understanding what each question is asking and how marks are allocated. Review examiner reports to learn from common mistakes made by other students.