4

 import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns


# Simulate a skewed salary distribution (e.g., exponential distribution)

np.random.seed(42)

population = np.random.exponential(scale=70000, size=10000) # Skewed salaries


# Take 10 random samples, each with 50 salaries, and compute their means

sample_means = []

for _ in range(10):

sample = np.random.choice(population, size=50, replace=True)

sample_means.append(np.mean(sample))


# Plotting the sample means distribution

plt.figure(figsize=(8, 5))

sns.histplot(sample_means, bins=10, kde=True, color='skyblue', edgecolor='black')

plt.title("Sampling Distribution of Mean Salaries (10 samples of size 50)")

plt.xlabel("Sample Mean Salary")

plt.ylabel("Frequency")

plt.grid(True)

plt.tight_layout()

plt.show()

Comments

Post a Comment

Popular posts from this blog

2

 import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # Sample dataset data = { 'Satisfaction': ['Low', 'Medium', 'High', 'Low', 'Medium', 'High', 'High', 'Medium', 'Low', 'High', 'Medium', 'Low', 'High', 'Medium', 'Low', 'High', 'High', 'Medium', 'Low', 'High'], 'RepeatPurchase': ['No', 'Yes', 'Yes', 'No', 'No', 'Yes', 'Yes', 'Yes', 'No', 'Yes', 'Yes', 'No', 'Yes', 'No', 'No', 'Yes', 'Yes', 'Yes', 'No', 'Yes'] } df = pd.DataFrame(data) # Count plot to show satisfaction vs repeat purchase plt.figure(figsize=(8, 5)) sns.countplot(data=df, x='Satisfaction', hue='RepeatPurchase') plt.title('Customer Satisfaction vs Rep...
Read more

5

 import scipy.stats as stats # Given data sample_mean = 8 sample_std = 2 n = 20 mu = 0 # Hypothesized population mean # Calculate the t-statistic t_statistic = (sample_mean - mu) / (sample_std / (n ** 0.5)) # Degrees of freedom df = n - 1 # Two-tailed p-value p_value = 2 * (1 - stats.t.cdf(abs(t_statistic), df=df)) print(f"T-statistic: {t_statistic:.4f}") print(f"Degrees of freedom: {df}") print(f"P-value: {p_value:.4f}") # Conclusion if p_value < 0.05: print("Result: Reject the null hypothesis. The increase is statistically significant.") else: print("Result: Fail to reject the null hypothesis. The increase is not statistically significant.")
Read more

1

 import numpy as np # Sample dataset of house prices (in lakhs) house_prices = [45, 55, 60, 62, 68, 70, 75, 80, 85, 90, 100, 110, 125] # Calculate the 25th and 75th percentiles q1 = np.percentile(house_prices, 25) q3 = np.percentile(house_prices, 75) # Calculate the Interquartile Range (IQR) iqr = q3 - q1 # Print the results print(f"25th Percentile (Q1): {q1}") print(f"75th Percentile (Q3): {q3}") print(f"Interquartile Range (IQR): {iqr}")
Read more