BELOW IS MY DISCUSSION POST FOR MY STATISTICS COURSE. AT THE BOTTOM IS A REPLY TO MY POST. I NEED HELP RESPONDING TO IT. CAN SOMEONE PLEASE HELP ME....

BELOW IS MY DISCUSSION POST FOR MY STATISTICS COURSE. AT THE BOTTOM IS A REPLY TO MY POST. I NEED HELP RESPONDING TO IT. CAN SOMEONE PLEASE HELP ME.

Describe the chi-square goodness-of-fit test.

The chi-square test is applied when there is one categorical variable from a single population. We use it to determine if the sample data and the hypothesized distribution are consistent with each other. 

Provide a detailed explanation of what this test measures, and how it is similar to and different from the independent t-test and the chi-square test of independence.

The goodness of fit test determines if distributions approximates well with another specific distribution. The test of independence tests if two variables are related or dependent to each other. Chi square test of independence tests to see if two variables are associated or related to each other. A contingency table is constructed, then, using the observed frequencies, expected frequencies are totaled by adding the product of the sum of the row and column divided by the grand sum. There is a similarity to t tests because only two groups or variables are involved and the chi test for the dependence or independence of two variables. The differences between the types of tests is that a chi square test only uses frequencies which count numbers whereas a t test include continuous variables. 

How do you know when to use one analysis over the other? Provide a real-world example

Choosing which analysis depends on what you are trying to find out. The variables on hand are usually a good indication on which analysis on which test to use. 

If you had a medical study that involved 100 individuals, and measured 10 different characteristics such as height, weight, cholesterol to name a few. Each patient is then monitored for specific symptoms over a period. A multivariate analysis would be used to see which characteristics correlate with which symptoms. 

REPLY-NEED HELP ANSWERING THIS:

Hi Kristi -

I like how you clearly differentiated between the goodness-of-fit test and the test of independence. Indeed, the latter is better suited for looking at relationships among two or more categorical variables. I would also add that chi-square tests allow us to compare mutually exclusive groups. The difference with t-tests is that the t-test compares a categorical variable to a variable measured on an interval or ratio scale. In other words, we compare means instead of frequencies. In your example you suggest looking at medical patients and a number of different variables. How might you convert this example so that you are able to make a similar comparison using a chi-square test? What would change?