Copyright © 2012 by Nelson Education Limited. Chapter 10 Hypothesis Testing IV: Chi Square 10-1

Copyright © 2012 by Nelson Education Limited.

Chapter 10Hypothesis Testing IV:

Chi Square

10-1


• Bivariate (Crosstabulation) Tables

• The basic logic of Chi Square

• Perform the Chi Square test using the five-step model

• Limitations of Chi Square

In this presentation you will learn about:

10-2


• Bivariate tables: display the scores of cases on two different variables at the same time.

Independent variableDependent variableCellsRow and column marginalsTotal number of cases (n)

Bivariate Tables

10-3


• Columns are scores of the independent variable. – There will be as many columns as there are scores on

the independent variable.

• Rows are scores of the dependent variable.– There will be as many rows as there are scores on

the dependent variable.

More on Bivariate Tables

10-4


• Cells are intersections of columns and rows.– There will be as many cells as there are scores on the

two variables combined.– Each cell reports the number of times each

combination of scores occurred.

• Marginals are the subtotals.• n is reported at the intersection of row and

column marginals.

More on Bivariate Tables (continued)

10-5


Chi Square, χ2, is a test of significance based on bivariate, crosstabulation tables.

Chi Square as a test of statistical significance is a test for independence. o Two variables are independent if the

classification of a case into a particular category of one variable has no effect on the probability that the case will fall into any particular category of the second variable.

Basic Logic of Chi Square

10-6


o Specifically, we are looking for significant differences between the observed cell frequencies in a table (fo) and those that would be expected by random chance or if cell frequencies were independent (fe):

Basic Logic of Chi Square (continued)

10-7


Formulas for Chi Square

10-8


• Is there a relationship between support for privatization of healthcare and political ideology? Are liberals significantly different from conservatives on this variable?

o The table below reports the relationship between these two variables for a random sample of 78 adult Canadians.

Computation of Chi Square: An Example

Political IdeologySupport Conservative Liberal Total No 14 29 43 Yes 24 11 35Total 38 40 78

10-9


• Use Formula 10.2 to find fe. – Multiply column and row marginals for each cell and divide by n.

• (38*43)/78 = 1634 /78 = 20.9• (40*43)/78 = 1720 /78 = 22.1• (38*35)/78 = 1330 /78 = 17.1• (40*35)/78 = 1400 /78 = 17.9

Expected frequencies (fe)

Political IdeologySupport Conservative Liberal Total No 20.9 22.1 43 Yes 17.1 17.9 35Total 38 40 78

Computation of Chi Square: An Example (continued)

10-10


• A computational table helps organize the computations.

fo fe fo - fe (fo - fe)2 (fo - fe)2 /fe

14 20.9

29 22.1

24 17.1

11 17.9

78 78


10-11


• Subtract each fe from each fo. The total of this column must be zero.


14 20.9 -6.9

29 22.1 6.9

24 17.1 6.9

11 17.9 -6.9

78 78 0


10-12


• Square each of these values


14 20.9 -6.9 47.61

29 22.1 6.9 47.61

24 17.1 6.9 47.61

11 17.9 -6.9 47.61

78 78 0


10-13


• Divide each of the squared values by the fe for that cell. The sum of this column is chi square


8 6.24 -6.9 47.61 2.28

5 6.76 6.9 47.61 2.15

4 5.76 6.9 47.61 2.78

8 6.24 -6.9 47.61 2.66

78 78 0 χ2 = 9.87


10-14


• Independent random samples• Level of measurement is nominal

– Note the minimal assumptions. In particular, no assumption is made about the shape of the sampling distribution. The chi square test is nonparametric, or distribution-free.

Performing the Chi Square Test Using the Five-Step Model

Step 1: Make Assumptions and Meet Test Requirements

10-15


• H0: The variables are independent

• Another way to state the H0, more consistently with previous tests:

H0: fo = fe

• H1: The variables are dependent

• Another way to state the H1:

H1: fo ≠ fe

Step 2: State the Null Hypothesis

10-16


• Sampling Distribution = χ2

• Alpha = .05

• df = (r-1)(c-1) = 1• χ2 (critical) = 3.841

Step 3: Select Sampling Distribution and Establish the Critical Region

10-17


• χ2 (obtained) = 9.87

Step 4: Calculate the Test Statistic

10-18


• χ2 (critical) = 3.841• χ2 (obtained) = 9.87

• The test statistic is in the Critical (shaded) Region:

– We reject the null hypothesis of independence.

– Opinion on healthcare privatization is dependent on political ideology.

Step 5: Make Decision and Interpret Results

10-19


• The chi square test tells us only if the variables are independent or not.

• It does not tell us the pattern or nature of the relationship.– To investigate the pattern, compute %’s within

each column and compare across the columns.

Interpreting Chi Square

10-20


Column Percents (%)

Political Ideology

Support Conservative Liberal No 37 73 Yes 63 27 Total 100% 100%

• This relationship has a clear pattern: people that support privatization of healthcare in Canada are more likely to be conservative, while those that oppose it are more likely to be liberal in their political ideology.

o Chi square told us that this relationship is significant (unlikely to be caused by random chance) and now, with the aid of column percents, we know how the two variables are related.

Interpreting Chi Square (continued)

10-21


1. Difficult to interpret when variables have many categories.

– Best when variables have four or fewer categories.

2. With small sample size, cannot assume that chi square sampling distribution will be accurate.

– Small sample: High percentage of cells have expected frequencies of 5 or less.

The Limitations of Chi Square

10-22


3. Like all tests of hypotheses, chi square is sensitive to sample size.

– As n increases, obtained chi square increases.

– With large samples, trivial relationships may be significant.

The Limitations of Chi Square

10-23


Important to Remember

Statistical significance is not the same thing as

substantive importance.

10-24

Documents

Copyright © 2012 by Nelson Education Limited. Chapter 10 Hypothesis Testing IV: Chi Square 10-1