Confidence intervals on parameters in SciPy - Mini Project: Build & Apply

Confidence Intervals on Parameters

📖 Scenario: You are a data analyst working with a small dataset of exam scores. You want to estimate the average score and understand how confident you can be about this estimate.

🎯 Goal: Build a simple Python program that calculates the 95% confidence interval for the mean exam score using scipy.

📋 What You'll Learn

Create a list of exam scores called scores with exact values

Create a variable confidence_level set to 0.95

Calculate the mean and the 95% confidence interval for the mean using scipy.stats.t.interval

Print the confidence interval in a clear format

💡 Why This Matters

🌍 Real World

Confidence intervals help us understand how precise our estimates are when working with sample data, like exam scores or survey results.

💼 Career

Data scientists and analysts use confidence intervals to report uncertainty in their findings, which is important for making informed decisions.

1

Create the exam scores data

Create a list called scores with these exact exam scores: 88, 92, 79, 93, 85, 91, 87.

SciPy

# Create the list of exam scores
# Your code here

Need a hint?

Use square brackets [] to create a list and separate numbers with commas.

2

Set the confidence level

Create a variable called confidence_level and set it to 0.95.

SciPy

scores = [88, 92, 79, 93, 85, 91, 87]
# Set the confidence level to 0.95
# Your code here

Need a hint?

Use a simple assignment statement to create the variable.

3

Calculate the confidence interval

Import scipy.stats. Calculate the mean of scores and then use scipy.stats.t.interval with confidence_level, degrees of freedom, sample mean, and standard error to find the confidence interval. Store the result in conf_interval.

SciPy

scores = [88, 92, 79, 93, 85, 91, 87]
confidence_level = 0.95
# Import scipy.stats
# Calculate mean, degrees of freedom, and standard error
# Use scipy.stats.t.interval to calculate confidence interval
# Your code here

Need a hint?

Use np.mean for the average, len(scores) - 1 for degrees of freedom, and scipy.stats.sem for standard error.

4

Print the confidence interval

Print the text "95% confidence interval for the mean score:" followed by the conf_interval variable.

SciPy

import scipy.stats
import numpy as np

scores = [88, 92, 79, 93, 85, 91, 87]
confidence_level = 0.95

mean_score = np.mean(scores)
df = len(scores) - 1
std_err = scipy.stats.sem(scores)
conf_interval = scipy.stats.t.interval(confidence_level, df, loc=mean_score, scale=std_err)
# Print the confidence interval
# Your code here

Need a hint?

Use print with a string and the variable conf_interval.