Math: Data Analysis

2nd Semester

C Nature of Probability and Statistics

1
Introduction to Statistics

 Statistics: The science of collecting, organizing, summarizing,

analyzing, and drawing conclusions from data.

 Uses of Statistics:

o Analyzing survey results.

o Decision-making in scientific research.

o Used in fields like sports, public health, education, and

business.

 Importance of Studying Statistics:

1. Understand statistical studies in various fields.

2. Conduct research, design experiments, and analyze data.

3. Make informed decisions as consumers and citizens.

1. Descriptive and Inferential Statistics

Descriptive Statistics

 Summarizes and describes the main features of a dataset.

 Focuses on presenting data without making inferences.

 Example:

o A company records test scores of 100 students.

o Descriptive statistics include:

 Mean (Average): 75

 Median: 78

 Standard Deviation: 10

 25% of students scored below 70

Math: Data Analysis
2nd Semester

o These describe the dataset but do not generalize beyond it.

Inferential Statistics

 Makes inferences from samples to populations.

 Includes hypothesis testing, determining relationships, and making

predictions.

 Example:

o Using test scores from 100 students to estimate the average

math score of all students in a district.

o A confidence interval (e.g., 95% confidence that the district’s

average score is between 73 and 77).

o Hypothesis testing to check if the average score significantly

differs from 80.

o Generalizing results from a sample to a larger group.

2. Variables and Types of Data

Definition of Key Terms

 Variable: A characteristic or attribute that can assume different

values.

 Data: The values (measurements or observations) that variables

assume.

 Random Variable: A variable whose values are determined by

chance.

 Data Set: A collection of data values.

 Datum: A single value in a dataset.

Types of Variables

1. Quantitative Variables

o Numerical and can be ordered or ranked.

o Types:
Math: Data Analysis
2nd Semester

 Discrete Variables: Countable values (e.g., number of

students, books on a shelf).

 Continuous Variables: Measurable values, including

fractions and decimals (e.g., height, weight,
temperature).

2. Qualitative Variables

o Non-numerical; categorized based on characteristics.

o Examples: Gender, religion, nationality, eye color.

Levels of Measurement

1. Nominal Level:

o Data categorized without ranking.

o Examples: Gender, blood type, nationality, car brands.

2. Ordinal Level:

o Data can be ranked, but differences between ranks are not

equal.

o Examples: Educational levels, customer satisfaction ratings,

job performance ratings.

3. Interval Level:

o Data is ordered with equal intervals, but no true zero.

o Examples: Temperature (°C, °F), IQ scores, calendar years.

4. Ratio Level:

o Data has equal intervals and a true zero.

o Examples: Height, weight, income, distance traveled.

3. Data Collection and Sampling Techniques

Methods of Data Collection

1. Telephone Survey:

o Less costly, more honest responses.

Math: Data Analysis
2nd Semester

o Some people may not answer or have unlisted numbers.

2. Mailed Questionnaire:

o Covers a larger geographic area, maintains anonymity.

o Low response rates, potential for misunderstood questions.

3. Personal Interview:

o In-depth responses, but costly and may introduce interviewer

bias.

Sampling Techniques

1. Random Sampling:

o Every member of the population has an equal chance of

selection.

o Uses chance methods or random number generators.

2. Systematic Sampling:

o Selecting every kth member from the population.

o Example: Choosing every 40th subject from a population of

2000.

3. Stratified Sampling:

o Population divided into subgroups (strata), then random

samples taken from each.

o Example: Selecting students from different grade levels.

4. Cluster Sampling:

o Population divided into groups (clusters), then entire clusters

are selected randomly.

o Example: Selecting all residents from randomly chosen

apartment buildings.

Other Sampling Methods

 Convenience Sampling: Uses readily available subjects (e.g., mall

surveys).
Math: Data Analysis
2nd Semester

 Volunteer Sampling: Respondents choose to participate (e.g., call-

in surveys).

Types of Sampling Errors

1. Sampling Error:

o Occurs when a sample does not perfectly represent the

population.

o Example: A survey estimates 55% support for a candidate, but

actual votes show 52%.

2. Non-Sampling Error:

o Errors in data collection, recording, or survey design.

o Example: Biased survey questions, misreported income, or

excluding certain groups.

4. Experimental Design

Types of Studies

1. Observational Study:

o Researcher observes subjects without manipulation.

o Types:

 Cross-Sectional Study: Data collected at one time.

 Retrospective Study: Uses past records.

 Longitudinal Study: Data collected over time.

o Example: Studying smoking habits and lung cancer over 10

years.

2. Experimental Study:

o Researcher manipulates variables to observe effects.

o Example: Studying effects of exercise on stress levels with

control and experimental groups.

Advantages & Disadvantages

Math: Data Analysis
2nd Semester

 Observational Study:

o ✅ Natural setting, ethical for sensitive topics.

o ❌ Cannot establish cause-and-effect, expensive.

 Experimental Study:

o ✅ Researcher controls variables, can determine cause-and-

effect.

o ❌ May not apply to real-world settings, subjects may change

behavior due to observation (Hawthorne effect).

5. Uses and Misuses of Statistics

Common Misuses of Statistics

1. Suspect Samples:

o Small, convenience, or volunteer samples may not represent

the population.

2. Ambiguous Averages:

o Different measures of average (mean, median, mode) can be

used to mislead.

3. Changing the Subject:

o Using different values to represent the same data to influence

perception.

o Example: "3% budget increase" vs. "$6 million increase."

4. Detached Statistics:

o Claims without comparisons.

o Example: "This drug is 50% more effective" (compared to

what?).

5. Implied Connections:

o Suggests relationships without proof.

o Example: "Eating fish may lower cholesterol."

Math: Data Analysis
2nd Semester

6. Misleading Graphs:

o Improperly drawn graphs can exaggerate trends.

7. Faulty Survey Questions:

o Poorly worded questions influence responses.

o Example: "Do you support raising taxes to build a stadium?"

vs. "Should a new stadium be built?"

Summary

 Statistics helps collect, analyze, and interpret data.

 Two branches: Descriptive (summarizing data) and Inferential

(drawing conclusions).

 Data types: Quantitative (discrete, continuous) and Qualitative.

 Measurement levels: Nominal, Ordinal, Interval, Ratio.

 Sampling techniques: Random, Systematic, Stratified, Cluster.

 Research methods: Observational vs. Experimental studies.

 Beware of statistical misuse through biased sampling, misleading

graphs, and ambiguous claims.
Math: Data Analysis
2nd Semester

C Frequency Distribution and Graphs

2
1. Frequency Distribution

 Data collected in original form is called raw data.

 Nominal – or ordinal-level data that can be placed in categories is

organized in categorical frequency distributions.

 A frequency distribution is a table that organizes data into classes

or groups, showing the number of observations in each category.

 Purpose:

o Organizes large data sets into a manageable format.

o Makes patterns and trends easier to identify.

o Helps in data analysis and interpretation.

Components of a Frequency Distribution Table

1. Class Intervals – The specific ranges into which the data is

grouped.

2. Frequency (f) – The number of values falling within a class interval.

3. Class Boundaries – The actual limits of a class interval that

separate it from adjacent intervals.
Math: Data Analysis
2nd Semester

4. Class Width – The difference between the lower boundaries of

consecutive classes.

5. Midpoint – The central value of a class interval, calculated as:

Lower Class Limit +Upper Class Limit

midpoint =
2

6. Relative Frequency – The proportion of total observations that fall

into a class, given by:
Class Frequency
Relative Frequency=
Total Frequency

7. Cumulative Frequency – The running total of frequencies,

indicating how many values are below a particular class boundary.

2. Types of Frequency Distributions

1. Ungrouped Frequency Distribution:

o A simple count of occurrences for each individual data point.

o Used for small data sets or discrete data.

2. Grouped Frequency Distribution:

o Data is grouped into class intervals for better readability.

o Used for larger data sets or continuous data.

3. Relative Frequency Distribution:

o Expresses class frequencies as proportions or percentages.

o Useful for comparing different data sets of varying sizes.

4. Cumulative Frequency Distribution:

o Displays cumulative totals, showing how frequencies build up

over intervals.

3. Constructing a Grouped Frequency Distribution

Math: Data Analysis
2nd Semester

The following data represent the record high temperatures for each of the
50 states. Construct a grouped frequency distribution for the data using 7
classes.

112 100 127 120 134 118 105 110 109 112

110 118 117

4. Graphical Representations of Frequency Distributions

 Graphs help in visualizing frequency distributions effectively.

 Types of Graphs:

A. Histogram

 A bar graph representing frequency distribution.

 Characteristics:

o No gaps between bars (unlike bar charts).

o X-axis represents class intervals.

o Y-axis represents frequencies.

o Heights of bars indicate the frequency of observations.

B. Frequency Polygon

 A line graph connecting midpoints of class intervals.

 Steps to construct:

1. Plot midpoints on the X-axis.

2. Plot frequencies on the Y-axis.

3. Connect points with straight lines.

C. Ogive (Cumulative Frequency Graph)

 A line graph that represents cumulative frequency.

Math: Data Analysis
2nd Semester

 Types:

1. Less than Ogive – Shows cumulative frequency below each

class boundary.

2. Greater than Ogive – Shows cumulative frequency above

each class boundary.

 Usage:

o Helps determine median and percentiles.

D. Bar Graph

 Represents categorical data using rectangular bars.

 Bars can be vertical or horizontal.

 Spacing: Bars are separated (unlike histograms).

E. Pie Chart

 A circular graph divided into proportional segments.

 Represents relative frequency of categories.

F. Dot Plot

 Uses dots to show individual data points.

 Suitable for small data sets.

G. Stem-and-Leaf Plot

 Represents data while maintaining original values.

 Splits numbers into stems (leading digits) and leaves (trailing

digits).

4. Choosing the Right Graph

DATA TYPE RECOMMENDED GRAPH

Math: Data Analysis
2nd Semester

QUANTITATIVE Histogram, Frequency Polygon,

(CONTINUOUS) Ogive

CATEGORICAL Bar Graph, Pie Chart

SMALL DATA SETS Dot Plot, Stem-and-Leaf Plot

5. Summary

 Frequency distributions help in organizing data systematically.

 Graphs make it easier to visualize and interpret data.

 Choice of graph depends on the type of data being analyzed.