Assessing Normality Preview CT-STEM

When is the sampling distribution Normal(ish)?

Let's switch gears and look at sample proportions. The main question will investigate on this page:

When can we approximate the sampling distribution for proportions as Normal?

The model below allows you to select a sample size of your choice and set the population proportion to anything you want. We can use this model to evaluate claims about sample proportions in any context. You may want to drag the slider at the top to generate your samples more quickly. Scroll down to see instructions and questions.

Something has gone wrong. Please reload the page.

Questions

Please answer the questions below.

Question 4.1

Set the model with parameters p = 0.15 and n = 5. Create an approximate sampling distribution. Describe the sampling distribution in context (Remember your SOCS!).

Question 4.2

Don't use the model yet. Make a prediction. What will happen to the sampling distribution if you make the true proportion higher (closer to p = 1)?

Question 4.3

OK, now use the model, change the proportion to something higher (like 0.8). How does the sampling distribution compare?

Question 4.4

Before using the model, make another prediction. What do you think will happen to the sampling distribution if we keep the proportion the same but increase the sample size from 5 to something higher (like 30)?

Question 4.5

Test your hypothesis by changing the sample size. How does the sampling distribution change?

Question 4.6

Which values for n and p will make the sampling distribution look the most similar to a Normal distribution? Perform some experiments using the model and report your findings here.

Question 4.7

Here's another model that can be used to explore the relationship between n and p. What are some advantages of using the NetLogo model compared to this simple model?

CLICK HERE FOR SIMPLE MODEL

Notes

These notes will appear on every page in this lesson so feel free to put anything here you'd like to keep track of.