Data Analysis
Chapter 4
Statistical Analysis
Dr. Mahmoud Elsabagh
Contents
Chapter 1: Introduction to Data Analysis
Chapter 2: Data Collection & Preparation
Chapter 3: Exploratory Data Analysis (EDA)
Chapter 4: Statistical Analysis
Chapter 5: Predictive Data Analysis
Chapter 6: Data Analysis Tools & Software
Chapter 7: Communicating Results
Chapter 8: Applications & Future Trends
Chapter 4: Statistical Analysis
3
1. Introduction to Statistical Analysis
➜ Definition:
Statistical analysis is the process of collecting, exploring, organizing, and interpreting data
using statistical methods to uncover patterns, test hypotheses, and support decision-making.
➜ Why It Matters in Data Analysis:
○ Helps summarize large datasets into meaningful insights.
○ Provides tools for comparing groups, predicting outcomes, and identifying
relationships.
○ Essential for evidence-based decisions in business, healthcare, education, research,
and AI.
➜ Analogy:
Think of statistics as the microscope of data — it allows us to see patterns and relationships
that are invisible to the naked eye.
2. Types of Statistics
- A. Descriptive Statistics
➜ Goal: Summarize and describe the main features of a dataset.
➜ Key Measures:
○ Measures of Central Tendency: Mean, Median, Mode.
○ Measures of Dispersion: Range, Variance, Standard Deviation, Interquartile
Range (IQR).
○ Data Distribution: Histograms, frequency tables, percentiles.
➜ Example: Average exam score of students in a class.
2. Types of Statistics
- B. Inferential Statistics
➜ Goal: Make predictions or generalizations about a population based on a sample.
➜ Key Concepts:
○ Hypothesis testing.
○ Confidence intervals.
○ Regression analysis.
○ ANOVA (Analysis of Variance).
➜ Example: Using a survey of 500 people to estimate the political preferences of a
country.
Tip: Use a diagram showing “Population → Sample → Inferential Statistics →
Generalization.”
3. Levels of Measurement in Data
➜ Nominal: Categories without order (e.g., gender, blood type).
➜ Ordinal: Categories with order but unequal intervals (e.g., satisfaction ratings).
➜ Interval: Ordered, equal intervals, no true zero (e.g., temperature in Celsius).
➜ Ratio: Ordered, equal intervals, true zero (e.g., weight, income).
Important: The level of measurement determines which statistical techniques can be
applied.
4. Descriptive Statistics in Detail
A. Central Tendency
➜ Mean (average) = Σx / n.
➜ Median = middle value when data is sorted.
➜ Mode = most frequent value.
➜ Example: Test scores: 60, 70, 70, 80, 90.
○ Mean = 74.
○ Median = 70.
○ Mode = 70.
4. Descriptive Statistics in Detail
B. Dispersion
➜ Range = Max – Min.
➜ Variance = average squared deviation from the mean.
➜ Standard Deviation (SD) = square root of variance → shows spread.
➜ Coefficient of Variation (CV) = SD / Mean × 100.
➜ Example: If average income is $2000 with SD = $200 → most incomes lie between $1800–
$2200.
5. Inferential Statistics in Detail
➜ A. Hypothesis Testing
➜ Steps:
○ State null hypothesis (H₀) and alternative hypothesis (H₁).
○ Select significance level (α, usually 0.05).
○ Collect sample data.
○ Calculate test statistic (t-test, z-test, chi-square, etc.).
○ Compare with critical value → Accept or reject H₀.
➜ Example: Testing whether a new teaching method improves student performance compared
to the old method.
5. Inferential Statistics in Detail
B. Confidence Intervals (CI)
➜ Definition: Range of values likely to contain the true population parameter with a given
probability (e.g., 95% CI).
➜ Example: If average student GPA = 3.2, 95% CI = (3.0, 3.4) → We are 95% confident the
true average GPA lies between 3.0 and 3.4.
5. Inferential Statistics in Detail
C. Regression Analysis
➜ Definition: Examines relationship between independent variable(s) and dependent variable.
➜ Types:
○ Simple Linear Regression (Y = a + bX).
○ Multiple Regression (Y = a + b₁X₁ + b₂X₂ + …).
➜ Example: Predicting sales based on advertising spending and product price.
5. Inferential Statistics in Detail
D. Correlation
➜ Definition: Measures strength and direction of relationship between two variables.
➜ Correlation Coefficient (r): Ranges from –1 to +1.
○ r > 0: Positive correlation.
○ r < 0: Negative correlation.
○ r = 0: No correlation.
➜ Example: Hours studied vs. exam scores (likely positive correlation).
5. Inferential Statistics in Detail
E. ANOVA (Analysis of Variance)
➜ Definition: Compares means across three or more groups.
➜ Example: Testing if students’ average grades differ across three different teaching methods.
6. Visualizing Statistical Data
➜ Charts for Descriptive Stats:
○ Histograms (distribution).
○ Pie charts (categories).
○ Boxplots (spread and outliers).
○ Scatterplots (relationships).
You should learn when to use each visualization.
7. Common Mistakes in Statistical Analysis
➜ Misinterpreting correlation as causation.
➜ Using the wrong test for the data type.
➜ Ignoring outliers.
➜ Overgeneralizing from small samples.
➜ P-hacking (running many tests until one shows significance).
8. Practical Applications
➜ Healthcare: Analyzing clinical trial results to test drug effectiveness.
➜ Business: A/B testing for digital marketing campaigns.
➜ Education: Comparing student performance across teaching methods.
➜ AI/ML: Statistical foundations of algorithms (e.g., probability, regression).
Summary
➜ Two main branches: Descriptive (summarize data) and Inferential (draw conclusions).
➜ Core tools: Mean, Median, Mode, SD, Variance, CI, Hypothesis Testing, Correlation,
Regression, ANOVA.
➜ Statistical analysis turns raw data into knowledge.
➜ Always ensure proper method selection, avoid bias, and interpret results carefully.
Thanks!
Any questions?
19