Random sampling distributions in NumPy - Step-by-Step Execution

Concept Flow - Random sampling distributions

Choose distribution type

↓

Set parameters (mean, std, etc.)

↓

Generate random samples

↓

Calculate sample statistics

↓

Visualize or analyze samples

↓

Repeat for multiple samples

↓

Observe sampling distribution behavior

This flow shows how to pick a distribution, generate random samples, and analyze their statistics to understand sampling distributions.

Execution Sample

NumPy

import numpy as np
samples = np.random.normal(loc=0, scale=1, size=5)
mean_sample = np.mean(samples)
print(samples, mean_sample)

Generate 5 random samples from a normal distribution and calculate their mean.

Execution Table

Step	Action	Code/Operation	Result/Value
1	Import numpy	import numpy as np	numpy module ready
2	Generate 5 samples from normal distribution	samples = np.random.normal(loc=0, scale=1, size=5)	[0.5, -1.2, 0.3, 1.1, -0.7] (example)
3	Calculate mean of samples	mean_sample = np.mean(samples)	Mean = 0.0 (example)
4	Print samples and mean	print(samples, mean_sample)	[0.5, -1.2, 0.3, 1.1, -0.7] 0.0
5	End of execution	N/A	Sampling and mean calculation done

💡 All steps executed; samples generated and mean calculated.

Variable Tracker

Variable	Start	After Step 2	After Step 3	Final
samples	None	[0.5, -1.2, 0.3, 1.1, -0.7]	[0.5, -1.2, 0.3, 1.1, -0.7]	[0.5, -1.2, 0.3, 1.1, -0.7]
mean_sample	None	None	0.0	0.0

Key Moments - 3 Insights

Why do the random samples change every time we run the code?

Because np.random.normal generates new random numbers each run, the samples differ. This is shown in execution_table step 2 where samples are created.

Is the mean of the samples always exactly zero for a normal distribution with mean 0?

No, the mean of a small sample varies due to randomness. The execution_table step 3 shows the calculated mean from the sample, which can differ from zero.

What does the 'size' parameter control in np.random.normal?

It controls how many random samples are generated at once, as seen in step 2 where size=5 means 5 samples are created.

Visual Quiz - 3 Questions

Look at the execution_table step 2. What does the 'samples' variable contain?

A A list of 5 random numbers from a normal distribution

B A single random number

C The mean of the samples

D An empty list

💡 Hint

Check the 'Result/Value' column in step 2 of execution_table.

At which step is the mean of the samples calculated?

A Step 1

B Step 3

C Step 2

D Step 4

💡 Hint

Look for the action 'Calculate mean of samples' in execution_table.

If we increase the 'size' parameter to 1000, what changes in the execution_table?

A The samples will be all zeros

B The mean calculation step will be skipped

C The samples array will have 1000 numbers instead of 5

D The numpy import will fail

💡 Hint

Refer to the 'size' parameter effect in step 2 of execution_table.

Concept Snapshot

Random sampling distributions:
- Use numpy.random functions (e.g., normal, uniform)
- Specify parameters like mean (loc), std (scale), and sample size
- Generate samples with np.random.normal(loc, scale, size)
- Calculate sample statistics (mean, std) with numpy
- Sampling distributions show variability in sample stats
- Useful for understanding data randomness and inference

Full Transcript

This lesson shows how to generate random samples from a distribution using numpy. First, we import numpy. Then, we generate 5 random numbers from a normal distribution with mean 0 and standard deviation 1. Next, we calculate the mean of these samples. Finally, we print the samples and their mean. Each run produces different samples because of randomness. The mean of a small sample can vary from the true mean. The size parameter controls how many samples are generated. This process helps us understand how sample statistics vary in random sampling.