2024-general-maths-summary-notes

Page 1: Chapter One – Investigating Data Distributions

Key Definitions

  • Mode/Modal: The most frequently occurring value or category in a dataset.

  • Mean: The average of all data values, represented as 𝑥̄.

  • Median: The middle value of a dataset, calculated using 𝑛+1/2 = median number.

  • Range: The difference between the maximum and minimum data values, calculated as Largest Data Value – Smallest Data Value.

  • IQR (Interquartile Range): The range of the middle 50% of data values, calculated as IQR = Q3 – Q1.

Univariate Data Distributions of Categorical Data

  • Frequency Table: An example can be the classification of climate types in 23 countries as ‘cold’, ‘mild’, or ‘hot’. It can be reported as:

    • 60.9% mild

    • 26.1% hot

    • 13.0% cold

Numerical Data Distributions

  • Grouped Frequency Table: Use 3 intervals to summarize the data distribution.

  • Report: Summarize context and describe a histogram in terms of shape, center, spread, and outliers.

Displaying Numerical Data

  • Dot Plot: Represents frequency of data points.

  • Stem Plot: A graphical representation of numerical data, showing frequency and intervals.

  • Histogram: Displays data in bars without gaps.

  • Bar Chart: Can be segmented to show distributions of categorical data with percentages.

Significant Figures Rules

  • First non-zero digit is significant.

  • All non-zero digits are significant.

  • Zeroes between significant digits are significant.

  • Zeroes after a decimal to the right of non-zero digits are significant.

Histograms

  • Use CAS for plotting histograms through Lists and Spreadsheets.

    • Adding data and setting up variables.

Page 2: Key Features of Data Distribution

Shape, Center, Spread, and Outliers

  • Shape: Distribution shape influences analysis and interpretation.

  • Center: Represents the middle value of the data (mean, median, mode).

  • Spread: Indicates how much variation exists within the data.

  • Outliers: Data values that are significantly different from others.

Logarithmic Scale

  • Base 10 Logarithms: Useful for large quantities and can simplify multiplication into addition.

    • Logarithmic values calculated for various numbers (Log10 of values like 0.01 to 1,000,000).

  • Properties of Logarithms:

    • Log of a number >1 is positive, <1 is negative, and log of 0 is undefined.

Measures of Center and Spread

  • IQR: More reliable measure as it is not impacted by outliers.

  • Mean: Best used with symmetric data without outliers, median preferred for skewed data.

  • Standard Deviation: Measures the amount of variation or dispersion in a set of values.

Distribution Types

  • Bimodal Distribution: Two peaks indicate potential data from two populations.

  • Skewed Distributions: Positively skewed (tail on the right) and negatively skewed (tail on the left).

Page 3: Five Number Summary and Box Plots

Five-number summary includes:

  • Minimum: Smallest value in data.

  • Quartile 1 (Q1): Value below which 25% of data fall.

  • Median (M): Middle value of sorted data.

  • Quartile 3 (Q3): Value below which 75% of data fall.

  • Maximum: Largest value in data.

Standard (z) Score

  • A z score helps determine how far a value is from the mean.

    • Positive: Above the mean.

    • Zero: Equal to the mean.

    • Negative: Below the mean.

  • Upper and Lower Fences: Used to identify outliers.

Box Plots

  • Box Plot Construction: Depicts the five-number summary, whiskers indicate min/max, outliers identified.

  • Use CAS to create box plots and analyze data.

Page 4: Investigating Associations Between Two Variables

Variable Types

  • Explanatory Variable (EV): Variable believed to predict or explain the response variable.

  • Response Variable (RV): Variable that responds to changes in the explanatory variable.

Associations Between Categorical Variables

  • Two-way Frequency Table: Display associations.

  • Examples showing percentage differences can indicate associations (e.g., gender and intention to attend university).

Associations Between Numerical and Categorical Variables

  • Parallel Box Plots & Dot Plots: Used for comparison of groups.

  • Report by comparing medians, IQRs, and identifying outliers.

Associations Between Numerical Variables

  • Scatterplots: Visual representation showing relationships.

  • Analyze the direction and form of the relationship.

    • Assess strength and non-linearity.

Page 5: Correlation Coefficient

Pearson’s Correlation Coefficient (r)

  • Measures strength and direction of linear relationships between two continuous variables.

  • Valid under conditions: both variables are numerical, association is linear, no outliers present.

Coefficient of Determination (r²)

  • Indicates the proportion of the variance in the response variable that can be explained by the explanatory variable.

  • Calculation steps involve squaring the correlation coefficient.

Interpreting Correlation Coefficient

  • r = 0: No association, r = +1: Perfectly positive, r = -1: Perfectly negative association.

Page 6: Fitting a Least Squares Regression Line

Regression Analysis Process

  1. Construct a scatterplot to visualize data.

  2. Calculate the correlation coefficient to determine strength of association.

  3. Determine the regression line using the formula y = a + bx where a is the y-intercept and b is the slope.

  4. Interpret the regression line.

  5. Use the coefficient of determination to assess prediction power.

  6. Make predictions based on the regression line.

Residuals and Linearity

  • Residuals: Differences between observed values and fitted values from the model; check for constant variance.

  • Conduct residual analysis to verify that the assumptions of linearity are valid.

Page 7: Transformations

Transformation Types

  • Squared Transformation: y = a + bx²; useful for quadratic relationships.

  • Log Transformation: y = a + b log10(x) and log10(y) = a + bx; helps normalizing right-skewed data.

  • Reciprocal Transformation: y = a + (b/x); used for hyperbolic relationships.

Implementing Transformations in CAS

  • Naming new variables for transformations.

  • Using the relevant formulas to create new datasets for analysis.

Page 8: Determining the Best Transformation

Assessing Transformations

  • Evaluate which transformation yields the best linear model by checking residual plots for linearity.

  • Coefficient of determination (r²) indicates how well the model fits the data.

Page 9: Time Series Data

Trend Analysis

  • Trend: General movement in data over time—can be increasing, decreasing, or constant.

  • Cyclic Variation: Fluctuations occurring at regular intervals longer than a year.

  • Seasonality: Patterns related to calendar periods, identifiable in a year’s cycle.

  • Structural Change: Sudden shifts in the time series trend, indicating a period change.

  • Irregular Fluctuations: Random variations arising that don’t fit systematic trends.

Smoothing Techniques

  • Calculate smoothed values using mean or averaging methods for forecasting.

Page 10: Seasonal Indices and Deseasonalising Data

Seasonal Indices Calculation

  • Seasonal indices are averages normalized to 1 or 100%, reflecting performance relative to average.

  • Deseasonalised Data: Actual figure adjusted to remove seasonal effects for analysis.

Fitting Trend Lines

  • Use least squares regression on deseasonalised data to identify trends, adjusting forecasts accordingly.

Page 11: Chapters on Finance

Key Financial Concepts

  • Basic Terminology: Principal (V₀), Future value (Vn), interest rates (r), and payments (D).

  • Simple interest calculations and methods for linear growth and decay, including flat rate depreciation.

Compound Interest and Amortization

  • Compound interest for geometric growth, understanding effective rates, and repayment plans for loans.

Page 12: Amortization Tables

Understanding Loan Repayment

  • Regular payments lead to a decrease in interest vs. an increase in principal reduction for loans.

  • Create amortization tables that track interest, principal reduction, and outstanding balance.

Calculating Interest and Principal

  • Use monthly rates to determine amounts owed, decreasing principal over time with regular payments.

Page 13: Finance Solver in CAS

Using Finance Solver

  • Inputting financial variables to calculate present and future values based on investment parameters.

  • Analyzing outcomes for common loan structures like interest-only loans and annuities.

Page 14: Matrices Summary

Types of Matrices

  • Definitions: Simple, degenerate, connected, complete, subgraph, etc.

  • Operations involving matrix addition, subtraction, and scalar multiplication.

Matrix Properties

  • Explore identity and diagonal matrices, along with concepts of equivalent and symmetric matrices.

Page 15: Matrix Multiplication and Special Rules

Matrix Operations

  • Only matrices of compatible dimensions can be multiplied.

  • The resultant matrix dimensions will match specified rules concerning the order of matrices involved.

Page 16: Dominance and Transition Matrices

Transition Matrices

  • Record transitions between conditions in a network; use for behavior model examples.

  • Compute dominance scores using one-step and two-step assessments.

Steady State Solutions

  • Systems eventually stabilize over time; ensure all columns sum to 1 for regular matrices.

Page 17: Leslie Matrices

Application of Leslie Matrices

  • Models variations in population structures using age-group specific parameters.

  • Capture birth and survival rates to forecast changes in demographic sectors over time.

Page 18: Graphs and Networks

Graph Terminology

  • Different types of graphs including simple, connected, and complete graphs.

  • Key components such as edges, vertices, and graph properties such as planar forms.

Page 19: Eulerian Trails and Circuits

Key Paths in Graph Theory

  • Understanding conditions of Eulerian trails based on vertex degree.

  • Employ Dijkstra’s algorithm for shortest path calculations on weighted graphs.

Page 20: Maximum Flow and Cuts

Flow Network Concepts

  • Identifying maximum flow based on the capacity of the weakest link and calculating cut capacities.

  • Definitions of bipartite graphs, capacities, and methodologies used in analysis.

Page 21: Precedence Tables and Scheduling

Project Management Tools

  • Use precedence tables for scheduling tasks; dummy variables may be introduced.

  • Apply critical path methods to minimize completion times.

Page 22: Total Project Duration

Calculating Minimum Completion Time

  • Assignment and analysis of float times per activity using forward and backward scheduling techniques.

Page 23: Critical Path Analysis

Project Optimization Techniques

  • Critical path identification helps streamline project management, providing cost-effective strategies for reducing completion times.