Descriptive statistics aims to summarize and present the features of a given dataset, while inferential statistics leverages sample data to make estimates or test hypotheses about a larger population.

Descriptive Statistics

Descriptive statistics describe the key aspects or characteristics of a dataset:

• Measures of Central Tendency: Identify central or typical values in the dataset, typically using the mean, median, or mode.
• Measures of Spread or Dispersion: Indicate the variability or spread around the central value, often quantified by the range, standard deviation, or variance.
• Data Distribution: Categorizes the data distribution as normal, skewed, or otherwise and assists in visual representation.
• Shape of Data: Describes whether the data is symmetrical or skewed and the extent of that skewness.
• Correlation: Measures the relationship or lack thereof between two variables.
• Text Statistics: Summarizes verbal or written data using word frequencies, readabilities, etc.

Inferential Statistics

In contrast, inferential statistics extends findings from a subset of data (the sample) to make inferences about an entire population.

• Hypothesis Testing: Allows researchers to compare data to an assumed or expected distribution, indicating whether a finding is likely due to chance or not.
• Confidence Intervals: Provides a range within which the true population value is likely to fall.
• Regression Analysis: Predicts the values of dependent variables using one or more independent variables.
• Probability: Helps measure uncertainty and likelihood, forming the basis for many inferential statistical tools.
• Sampling Techniques: Guides researchers in selecting appropriate samples to generalize findings to a wider population.

Visual Representation

Descriptive statistics are often visually presented through:

• Histograms
• Box plots
• Bar charts
• Scatter plots
• Pie charts

Inferential statistics might lead to more abstract visualizations like:

• Confidence interval plots
• Probability distributions
• Forest plots
• Receiver operating characteristic (ROC) curves

Code Example: Descriptive vs. Inferential Stats

Here is the Python code:

import pandas as pd
from scipy import stats

# Load example data
data = pd.read_csv('example_data.csv')

# Perform descriptive statistics
print(data.describe())

# Perform inferential statistics
sample = data.sample(30)  # Obtain a random sample
t_stat, p_val = stats.ttest_1samp(sample, 10)
print(f'T-statistic: {t_stat}, p-value: {p_val}')