Descriptive Stats Inferential Stats
Makes conclusions about what
Describes what is
could be
Based on whole data (or Based on sample → applied to
sample) population
Involves generalization and
No generalization
uncertainty
Descriptive statistics is a branch of statistics that focuses on summarizing and
describing the main features of a dataset. It helps us understand the basic
characteristics of data through numerical summaries, tables, and graphs, without
making any predictions or inferences.
Descriptive statistics organize and simplify large amounts of data, making it
easier to interpret. It’s useful for quickly getting a snapshot of what the data is
saying without analyzing relationships or making predictions.
Key Components of Descriptive Statistics:
1. Measures of Central Tendency – describe the center of the data:
o Mean (average)
o Median (middle value)
o Mode (most frequent value)
2. Measures of Dispersion (Spread) – describe variability:
o Range (max - min)
o Variance (average squared deviation from the mean)
o Standard Deviation (square root of variance)
3. Measures of Position:
o Percentiles
o Quartiles
4. Data Distribution Visualization:
o Tables
o Histograms
o Box plots
o Bar charts
o Pie charts
Example:
Suppose we have test scores of 5 students:
Scores: 70, 85, 90, 75, 80
Descriptive Statistics:
Mean = (70 + 85 + 90 + 75 + 80) / 5 = 80
Median = Middle value = 80
Mode = No repeating values = No mode
Range = 90 - 70 = 20
Standard Deviation = ~7.91 (calculated using formula)
Visualization: You could create a bar graph or boxplot of the scores.
Inferential statistics is a branch of statistics that involves making
predictions, conclusions, or decisions about a larger population based
on a sample of data. While descriptive statistics only summarize data,
inferential statistics go a step further by generalizing the findings beyond the
observed data.
Key Concepts in Inferential Statistics:
1. Population vs. Sample
o Population: The entire group you're interested in.
o Sample: A smaller group taken from the population, used to
represent the whole.
2. Estimation
o Estimating population parameters (like mean or proportion) using
sample statistics.
3. Hypothesis Testing
o Testing assumptions or claims about the population (e.g., is the new
drug more effective?).
4. Confidence Intervals
o A range of values used to estimate the population parameter with a
certain level of confidence (e.g., 95%).
5. p-values
o Used in hypothesis testing to determine the significance of results.
Example:
Scenario:
You want to know the average height of adult women in a country, but it's
impossible to measure everyone.
Step-by-step:
1. You take a random sample of 100 women.
2. You find that their average height is 162 cm.
3. You use inferential statistics to:
o Estimate that the average height of all women in the country is
around 162 cm.
o Calculate a 95% confidence interval, e.g., "The average height is
between 160 cm and 164 cm."
o Conduct a hypothesis test to see if women are, on average,
shorter than 165 cm.
Aspect Population Sample
Definitio The entire group you want to A subset of the population,
n study. selected for study.
Size Usually large or even infinite. Smaller and more manageable.
Contains all possible Used to draw conclusions about
Purpose
observations. the population.
Cost & Often expensive and time- Faster and more cost-effective
Time consuming to study. to analyze.
200 students selected randomly
Example All students in a country.
from schools.
Real-Life Example:
Imagine you want to know the average test score of 10th-grade students in
your country.
Population: All 10th-grade students in the country.
Sample: 500 randomly selected 10th-grade students from different
schools.
You collect data from the sample, and then use inferential statistics to
estimate characteristics (like average score) of the population.
Why Use a Sample?
Studying an entire population is often impractical, so researchers take a
representative sample and make informed guesses about the population
based on that.
