Chi-Square Test

The chi-square (χ2) statistic is a test that measures how well a model compares to the actual
observed data. The data used to calculate the chi-square statistic must be random, raw, mutually
exclusive, obtained from independent variables, and obtained from a sufficiently large sample.
For example, the results of tossing a fair coin meet these criteria.
Chi-square tests are often used to test hypotheses. The chi-square statistic compares the size of
any difference between the expected results and the actual results, given the sample size and
number of variables in the relationship.
For these tests, degrees of freedom are used to determine whether a specific null hypothesis can
be rejected based on the total number of variables and samples within the experiment. As with
any statistic, the larger the sample size, the more reliable the results.
 The chi-square (χ2) statistic is a measure of the difference between the observed and
expected frequency of outcomes of a set of events or variables.
 Chi-square is useful for analyzing such differences in categorical variables, especially
those that are nominal in nature.
 χ2 depends on the size of the difference between the actual and observed values, the
degrees of freedom, and the sample size.
 χ2 can be used to test whether two variables are related or independent of each other.
 It can also be used to test the goodness of fit between an observed distribution and a
theoretical distribution of frequencies.
The Formula for Chi-Square Is

where:
c=Degrees of freedom
O=Observed value(s)
E=Expected value(s)

Chi-Square Goodness of Fit

The chi-square goodness of fit test is a goodness of fit test for a categorical variable. Goodness of
fit is a measure of how well a statistical model fits a set of observations.
When the goodness of fit is high, the expected values based on the model are close to the
observed values. When the goodness of fit is low, the expected values based on the model are far
from the observed values.
Statistical models evaluated by the chi-square goodness of fit test are distributions. They can be
any distribution, from as simple as an equal probability for all groups, to as complex as a
probability distribution with many parameters.
The Chi-square goodness of fit test checks whether your sample data is likely from a certain
theoretical distribution. We have a set of data values, and an idea about how the data values are
distributed. The test gives us a way to decide if the data values have a "good enough" fit with our
idea, or if our idea is questionable.
To apply the goodness of fit test to a data set we need:

 Data values that are a simple random sample from the full population.
 Categorical or nominal data. The Chi-square goodness of fit test is not appropriate for
continuous data.
 A data set that is large enough so that at least five values are expected in each of the
observed data categories. 
Chi-square goodness of fit test example
Let's use candy bags as an example. We collect a random sample of ten bags. Each bag has 100
pieces of candy and five flavors. Our hypothesis is that the proportions of the five flavors in each
bag are the same.

Let's start by answering: Is the Chi-square goodness of fit test an appropriate way to evaluate the
distribution of flavors in candy bags?
 We have a simple random sample of 10 bags of candy. We meet this need.
 Our categorical variable is candy flavors. We have a number of each flavor in 10 bags of
candy. We meet this need.
 Each bag has 100 pieces of candy. Each bag has five flavors of candy. We expect to have
equal numbers for each flavor. This means we expect 100 / 5 = 20 pieces of candy in
each flavor from each bag. For the 10 bags in our sample, we expect 10 x 20 = 200 pieces
of candy in each flavor. This is more than the requirement of five expected values in each
category.
Based on the answers above, yes, the Chi-square goodness of fit test is an appropriate method to
evaluate the distribution of flavors in candy bags.
Let’s start by listing what we expect if each bag has the same number of pieces for each flavor. 
Above, we calculated this as 200 for 10 bags of candy.
Comparison of actual vs expected number of pieces of each flavor of candy

Flavor Number of Pieces of Candy Expected number of Pieces of

(10 bags) Candy
Apple 180 200
Lime 250 200
Cherry 120 200
Orange 225 200
Grapes 225 200
Now, we see a difference between what we observed in our data and what we expected
Difference between observed ad expected pieces of candy by flavor
Flavor Number of Pieces of Expected number of Observed-Expected
Candy (10 bags) Pieces of Candy
Apple 180 200 180-200=- 20
Lime 250 200 250-200= 50
Cherry 120 200 120-200- -80
Orange 225 200 225-200= 25
Grapes 225 200 225-200= 25
Some of the differences are positive and some are negative. If we just add them, we get zero.
Instead, we square the differences. It gives equal importance to candy flavors with fewer pieces
than expected, and flavors with more pieces than expected.
Calculation of the squared difference between Observed and Expected for each flavor of candy

Flavor Number of Expected Observed- Squared

Pieces of Candy number of Expected Difference
(10 bags) Pieces of Candy
Apple 180 200 180-200=- 20 500
Lime 250 200 250-200= 50 2500
Cherry 120 200 120-200- -80 6400
Orange 225 200 225-200= 25 625
Grapes 225 200 225-200= 25 625
Next, we divide the squared difference by the expected number:
Calculation of the squared difference/expected number of pieces of candy per flavor

Flavor Number of Expected Observed- Squared Squared

 Pieces of number of Expected Difference Difference /
Candy (10 Pieces of Expected
bags) Candy Number
Apple 180 200 180-200=- 20 500 400 / 200 = 2
Lime 250 200 250-200= 50 2500 2500 / 200 =
12.5
Cherry 120 200 120-200- -80 6400 6400 / 200 =
32
Orange 225 200 225-200= 25 625 625 / 200 =
3.125
Grapes 225 200 225-200= 25 625 625 / 200 =
3.125
Finally, we add the numbers in the final column to calculate our test statistic:
2+12.5+32+3.125+3.125=52.75

To draw a conclusion, we compare the test statistic to a critical value from the Chi-Square
distribution. This activity involves four steps:

1. We first decide on the risk we are willing to take of drawing an incorrect conclusion
based on our sample observations. For the candy data, we decide prior to collecting
data that we are willing to take a 5% risk of concluding that the flavor counts in each
bag across the full population are not equal when they really are. In statistics-speak,
we set the significance level, α , to 0.05.
2. We calculate a test statistic. Our test statistic is 52.75.
3. We find the theoretical value from the Chi-square distribution based on our
significance level. The theoretical value is the value we would expect if the bags
contain the same number of pieces of candy for each flavor.

In addition to the significance level, we also need the degrees of freedom to find this
value. For the goodness of fit test, this is one fewer than the number of categories. We
have five flavors of candy, so we have 5 – 1 = 4 degrees of freedom.

The Chi-square value with α = 0.05 and 4 degrees of freedom is 9.488.

4. We compare the value of our test statistic (52.75) to the Chi-square value. Since
52.75 > 9.488, we reject the null hypothesis that the proportions of flavors of candy
are equal.
We make a practical conclusion that bags of candy across the full population do not have
an equal number of pieces for the five flavors. This makes sense if you look at the
original data. If your favorite flavor is Lime, you are likely to have more of your favorite
flavor than the other flavors. If your favorite flavor is Cherry, you are likely to be
unhappy because there will be fewer pieces of Cherry candy than you expect.

Chart Title
300
250
250
200 225 225
200 200 200 200 200
150 180
100 120
50
0
Apple Lime Cherry Orange Grape

Expected Actual

Bar chart comparing actual vs. expected counts of candy

Statistical details
Let’s look at the candy data and the Chi-square test for goodness of fit using statistical terms.
This test is also known as Pearson’s Chi-square test.
Our null hypothesis is that the proportion of flavors in each bag is the same. We have five
flavors. The null hypothesis is written as:
H0: p1=p2=p3=p4=p5 H0: p1=p2=p3=p4=p5
The formula above uses p for the proportion of each flavor. If each 100-piece bag contains equal
numbers of pieces of candy for each of the five flavors, then the bag contains 20 pieces of each
flavor. The proportion of each flavor is 20 / 100 = 0.2.
The alternative hypothesis is that at least one of the proportions is different from the others. This
is written as:
Ha: at least one pi not equal Ha: at least one pi not equal
In some cases, we are not testing for equal proportions. Look again at the example of children's
sports teams near the top of this page.  Using that as an example, our null and alternative
hypotheses are:
H0: p1=0.2, p2=0.65, p3=0.15H0: p1=0.2, p2=0.65, p3=0.15
Ha:at least one pi not equal to expected valueHa:at least one pi not equal to expected value
Unlike other hypotheses that involve a single population parameter, we cannot use just a
formula. We need to use words as well as symbols to describe our hypotheses.
We calculate the test statistic using the formula below:

∑ni=1(Oi−Ei)2Ei∑i=1n(Oi−Ei)2Ei
In the formula above, we have n groups. The ∑∑ symbol means to add up the calculations for
each group. For each group, we do the same steps as in the candy example. The formula
shows Oi   as the Observed value and Ei  as the Expected value for a group.
We then compare the test statistic to a Chi-square value with our chosen significance level (also
called the alpha level) and the degrees of freedom for our data. Using the candy data as an
example, we set α = 0.05 and have four degrees of freedom. For the candy data, the Chi-square
value is written as:
χ²0.05,4χ²0.05,4

There are two possible results from our comparison:

 The test statistic is lower than the Chi-square value. You fail to reject the hypothesis of
equal proportions. You conclude that the bags of candy across the entire population have
the same number of pieces of each flavor in them. The fit of equal proportions is “good
enough.”
 The test statistic is higher than the Chi-Square value. You reject the hypothesis of equal
proportions. You cannot conclude that the bags of candy have the same number of pieces
of each flavor. The fit of equal proportions is “not good enough.”
 Sharmaine A. Mislang

Advanced Educational Statistics

The Chi Square Tests

Goodness of Fit