Scribd
Upload
65 views3 pages

Chi Square Distribution

The document discusses Chi Square distribution, which is a non-parametric test used to compare observed data with expected frequencies in one or more categories. It provides three key points: 1) Chi Square is used to test independence and fit between observed and expected data in contingency tables. It can be used to test proportions, means, and distributions. 2) There are certain conditions for using Chi Square, including that no expected frequency is below 5 and the total sample size is large. 3) An example problem demonstrates how to calculate Chi Square test statistics and compare it to the critical value to determine if the null hypothesis that observed and expected frequencies are the same should be rejected.

Uploaded by

Amara Prabasari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
65 views3 pages

Chi Square Distribution

The document discusses Chi Square distribution, which is a non-parametric test used to compare observed data with expected frequencies in one or more categories. It provides three key points: 1) Chi Square is used to test independence and fit between observed and expected data in contingency tables. It can be used to test proportions, means, and distributions. 2) There are certain conditions for using Chi Square, including that no expected frequency is below 5 and the total sample size is large. 3) An example problem demonstrates how to calculate Chi Square test statistics and compare it to the critical value to determine if the null hypothesis that observed and expected frequencies are the same should be rejected.

Uploaded by

Amara Prabasari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Ni Luh Putu Amara Prabasari

119211078
Accounting IC
CHI SQUARE DISTRIBUTION

CHI SQUARE DEFINITION


Chi Square is also known as Kai Squared. Chi Square is one type of non-parametric
comparative test that is carried out on two variables, where the data scale of the two variables is
nominal. (If of 2 variables, there is 1 variable with a nominal scale, then the chi square test is
carried out by referring that the test must be used at the lowest degree).

CHI SQUARE TEST CONDITIONS


The chi square test is the most widely used non-parametric test. However, it is necessary
to know the requirements of this test are: the frequency of respondents or samples used is large,
because there are several conditions in which the chi square can be used, namely:
 There is no cell with a reality frequency value or also known as Actual Count (F0) of 0
(Zero).
 If the contingency table is 2 X 2, then there should not be just 1 cell that has the expected
frequency or also known as the expected count (“Fh”) less than 5.
 If the table form is more than 2 x 2, for example 2 x 3, then the number of cells with an
expected frequency of less than 5 cannot be more than 20%.

CHI SQUARE DISTRIBUTION BENEFITS


The following are the benefits of this chi-square distribution, including:
 Test proportions for multinomal data
 Test the mean similarity of the Poisson data
 Independent testing of two factors in contingency
 Testing the suitability of the observed data with the distribution model from
which the data is thought to have been taken, and
 Test the distribution model based on observational data.

CHI SQUARE FORMULATION


Before discussing further, we must get to know several types of chi-square formulas,
including:
1. Pearson Chi-Square,
2. Continuity Correction / Yates Correlation / Yates Correction,
3. Fisher Exact Test,
4. Likelihood Ratio.

The formula for Chi Square is like the following formula.

Information:
χ2 = Chi Square
fo = Frequency of observation
fh = Frequency expected

TERMS OF USE CHI SQUARE (χ2)


In order for hypothesis testing with Chi Square to be used properly, the following
conditions should be considered:

 The sample size must be large enough to convince us that there is a similarity between
the theoretical distribution and the Chi Square sampling distribution.
 Observations must be independent (unpaired). This means that one subject's answer has
no effect on the answers of other subjects or that one subject is only used once in the
analysis.
 Chi Square test can only be used on descriptive data (frequency data or categorical data)
or continuous data that has been grouped into categories.
 The number of expected frequencies must be equal to the number of observed
frequencies.
 At degrees of freedom equal to 1, there cannot be an extremely small expected value.

In general, if the expected value lies in one cell is too small (<5), Chi Square should not
be used because it can cause an over estimate so that many hypotheses are rejected except with
the correction from Yates. If it is not big enough, then having an expectation value smaller than 5
will not have much effect on the desired result. In the Chi Square test with many categories, if
there is more than one expected value less than 5, then the expected values can be combined with
the consequence that the number of categories will decrease and the information obtained is also
reduced.
EXAMPLE PROBLEM AND SOLUTION CHI SQUARE
1. Researchers have conducted a survey of 1600 coffee drinkers asking how much coffee
they drink in order to confirm previous studies. Previous studies have indicated that 72%
of Americans drink coffee. The results of previous studies (left) and the survey (right) are
below. At α = 0.05, is there enough evidence to conclude that the distributions are the
same?
Answer:

1) The null hypothesis H0:the population frequencies are equal to the expected
frequencies (to be calculated below).
2) The alternative hypothesis, Ha: the null hypothesis is false.
3) α = 0.05.
4) The degrees of freedom: k − 1 = 4 − 1 = 3.
5) The test statistic can be calculated using a table:

6) From α = 0.05 and k − 1 = 3, the critical value is 7.815.


7) Is there enough evidence to reject H0? Since χ 2 ≈ 8.483 > 7.815, there is enough
statistical evidence to reject the null hypothesis and to believe that the old
percentages no longer hold.

You might also like