Hypothesis Testing

Reject or Fail to Reject?

That is the question!
 Objectives
 Sample vs. Population
– Is there a difference?
 Null and Research Hypotheses
– What are they, what do they look like, and what do
they mean?
 A Good Hypothesis
– What are the criteria?
 Testing the Hypothesis
– The six-step program
Samples and Populations
How do we select?

Population Sample

 of
population

Inference Statistics

Parameters X of sample
Samples and Populations Contd.
 Samples must match characteristics of the
population.
 Similarity results in generalizability.
 Type of sample impacts research quality
– Systematic Sample
– Random Sample
– Sample of Convenience
– Volunteerism
 Pitfalls of Samples
 Sample Bias
– Over represent subgroups.
– Not representative of population.
 Sampling Error
– Sample group not accurate picture.
– Reduce by enlarging sample.
– Larger sample, less error.
 Standard Error
– Measure of how much sampling error likely to occur
when sample is extracted from population
– Standard deviation of values of the sampling
distribution.
Null and Research Hypotheses
 Hypothesis
– Educated guess
– Reflects the research problem being
investigated
– Determines the techniques for testing the
research questions
– Should be grounded in theory
Purposes of the Null Hypothesis

 Acts as a starting point

– State of affairs accepted as true in the
absence of any other information
– Until a systematic difference is shown,
assume that any difference observed is
due to chance
– Research job is to eliminate chance factors
and evaluate other factors that may
contribute to group differences
Null Hypothesis Purpose # 2

 Provides a benchmark to measure

actual outcomes
– How likely is it that outcomes are due to
some other factor?
– Helps define range within which observed
differences can be reasonably attributed to
chance or something other than chance
 Null Hypotheses
 Usually a statement of no differences or
no associations – an equality
– Sentence
• There will be no difference in at-home
and pre-school program children on pre-
social and pre-literacy tests.
– Symbols
• Ho:  at-home =  day-care
• Ho:  at-home –  day-care = 0
Research/Alternative Hypotheses

 A statement of a relationship between

the variables – an inequality.
 May be nondirectional (two-tailed)
 May be directional (one-tailed) which is
more powerful in research results as it
splits the p – value in half
Nondirectional Alternative Hyp.
 Reflects a difference between groups
but the direction of the difference is not
specified
– Nondirectional Sentence
• There is a difference in at-home and
pre-school program children on pre-
social and pre-literacy tests.
– Nondirectional Symbols
• Ha:  at-home   day-care
Directional Alternative Hyp.
 Reflects a difference between groups,
and the direction of the difference is
specified
– Directional Sentence
• Children in pre-school programs will
have higher pre-social and pre-literacy
scores than children who stay at home.
– Directional Symbols
• Ha:  at-home <  day-care
What Makes a Good Hypothesis?

A good hypothesis:
 is stated in
declarative form and
not as a question.
 posits an expected
relationship between
variables.
What Makes a Good Hypothesis?
A good hypothesis:
 reflects the theory or
literature on which it is
based.
 should be brief and to
the point.
 is testable, which
means that it can carry
out the intent of the
question reflected by
the hypothesis.
Six Steps of Hypothesis Testing

1. State the null hypothesis.

2. State the alternative hypothesis
3. Select a level of significance
4. Collect and summarize the sample data.
5. Refer to a criterion for evaluating the
sample evidence.
6. Make a decision to keep/reject the null.
1. State the Null Hypothesis

 States that there is no relationship

between the variables.
 Refers to the population.
Examples of the Null Hypothesis

 Written: There are no differences in the

pre, mid, and post test scores of
students who are either enrolled in
Headstart, daycare, or homecare.
 Symbols: µpre = µmid = µpost
Examples of Null Hypothesis

 Written: There are no differences in the

literacy scores between students who
either in Headstart, daycare, or
homecare.
 Symbols: µHeadstart = µdaycare= µhomecare
Examples of Null Hypothesis
 Written: The pattern of differences of
the cell µs of pre, mid, and post test
literacy scores in the first column (or
row) accurately describes the pattern of
differences among the cell µs in at least
one other column (row).
 Symbols: : jk – j’k = jk’ – j’k’, for all
rows and columns, for all combinations
of both j and j’, k and k’.
Step 2: State the Alternative
Hypothesis
 Symbolically referred to as Ha
 States the opposite of the Ho
Examples of Alternative
Hypothesis
 Written: There are differences within
the pre, mid, and post test scores of
students who are either in Headstart,
daycare, or homecare.
 Symbols:  pre   mid   post for at least
one pair. 
Example of Alternative
Hypothesis
 Written: There are differences in the
the scores between the students in
Headstart, daycare, or homecare who
either took the pre, mid, or post literacy
skills test.
 Symbols:  Headstart   daycare   homecare, for
at least one pair
Example of Alternative
Hypothesis
 Written: The pattern of differences among
the cell µs of pre, mid, and post literacy skills
scores in the first column (or first row) fails to
describe accurately the pattern of differences
among the cell µs in at least one other
column (row).
 Symbols: jk – j’k  jk’ – j’k’, for all rows and
columns, for all combinations of both j and j’,
k and k’.
Step 3: Select a Level of
Significance
 Most researchers select a small number such
as 0.001, 0.01, or 0.05.
 The most common choice is 0.05
 Otherwise known as “alpha level”, p=0.05,
=0.05
 The significance level serves as a scientific
cutoff point that determines what decision will
me made concerning the null hypothesis.
Type I and Type II Errors

 Mistakes can occur:

1. Type I Error – designates the mistake
of rejecting the Ho when the null is
actually false. When the level of
significance is set at 0.05, this means
the chance of a Type I error becomes
equal to 1 out of 20.
Type II Errors

 Designates a
mistake made if Ho is
not rejected when
the null is actually
false.
Step 4: Collection and Analysis
of Sample Data
 The summary of the sample data will
always lead to a single numerical value
which is referred to as the calculated
value. ( r, t, or f).
 The computer calculates the probability
of the above value in the form of p =
____.
Step 5: The Criterion for
Evaluating the Sample Evidence
Two Methods:
 Compare the calculated and critical
values.
 Compare the data-based p-value
against a preset point on the 0-1 scale
on which the p must fall. (Level of
Significance)
Step 6: Make a Decision!

 Reject the Null if the p-value is less than

the established level of significance.

• a statistically significant difference was

obtained
• p< 0.05
Fail to Reject the Null
Retain the Null if the
p-value is greater
than the established
level of significance.
• H0 was tenable
• The null was
retained.
• No significant
difference was found.
• The result was not
statistically
significant.
 Rejection Region

H0:  H0: 0

H1:  < 0 H1:  > 0
Reject H0 Reject H 0

 

0 Z 0 Z
Must Be Significantly Small values don’t contradict H0
Below = 0 Don’t Reject H0!
 t-Test: Unknown
 Assumptions
– Population is normally distributed
– If not normal, only slightly skewed & a large
sample taken (Central limit theorem applies)
 Parametric test procedure
 t test statistic, with n-1 degrees of
freedom X 
t
S
n
 Degrees of Freedom
• # in sample - number of parameters that must be
estimated before test statistic can be computed.
– For a single sample t-test, we must first estimate the
mean before we can estimate
f
the standard deviation.
– Once the mean is estimated, n-1 of the values are left
since we know that the nth value is equal to
n 1
nx   x i
i 1
 Example: One Tail t-Test
Does an average box of cereal
contain more than 368 grams
of cereal? A random sample of
36 boxes showed X = 372.5,
and  15. Test at the 0.01
level. 368 gm.

is not given, H0: 368

H1:  368
 Z test for proportions
• The null hypothesis for the proportion also implies
we know the variance, since the variance is just P
times (1-P).
• This is a good approximation when the sample size
is large.
• If the sample size is small, we could use the
binomial distribution to compute the exact p value
that a sample of size n would yield a sample
proportion ps given the population proportion P.
Using the normal approximation is much easier.
Example:Z Test for Proportion
•Problem: A marketing company claims
that it receives 4% responses from its
Mailing.
•Approach: To test this claim, a random
sample of 500 were surveyed with 25
responses.
•Solution: Test at the  = .05 significance
level.
The Mann-Whitney U test

 That you have acquired a set of measurements from

2 different sites.
– Maybe one is alleged to be polluted, the other clean,
and you measure residues in the soil.
– Maybe these are questionnaire returns from students
identified as M or F.
 You want to know whether these 2 sets of
measurements genuinely differ. The issue here is
that you need to rule out the possibility of the results
being random noise.
The formal procedure:
 Involves the creation of two competing explanations
for the data recorded.
– Idea 1:These are pattern-less random data. Any
observed patterns are due to chance. This is the null
hypothesis H0
– Idea 2: There is a defined pattern in the data. This is
the alternative hypothesis H1
 Without the statement of the competing hypotheses,
no meaning test can be run.
 Example
You conduct a questionnaire survey of homes in the
Heathrow flight path, and also a control population of
homes in South west London. Responses to the question
“How intrusive is plane noise in your daily life” are
tabulated:
 Noise complaints 1= no complaint, 5 = very unhappy
 Homes near airport Control site
 5 3
 4 2
 4 4
 3 1
 5 2
 4 1
 5
Stage 1: Eyeball the data!
 These data are ordinal, but not normally distributed
(allowable scores are 1, 2, 3, 4 or 5).
 Use Non-parametric statistics
 It does look as though people are less happy under the
flightpath, but recall that we must state our hypotheses
H0, H1
– H0: There is no difference in attitudes to plane noise
between the two areas – any observed differences
are due to chance.
– H1: Responses to the question differed between the
two areas.
 Now we assess how likely it is
that this pattern could occur by
chance:
 This is done by performing a calculation.
Don’t worry yet about what the calculation
entails.
 What matters is that the calculation gives an
answer (a test statistic) whose likelihood can
be looked up in tables. Thus by means of this
tool - the test statistic - we can work out an
estimate of the probability that the observed
pattern could occur by chance in random data
 One philosophical hurdle to go:
 The test statistic generates a probability - a
number for 0 to 1, which is the probability of
H0 being true.
 If p = 0, H0 is certainly false. (Actually this
is over-simple, but a good approximation)
 If p is large, say p = 0.8, H0 must be
accepted as true.
 But how about p = 0.1, p = 0.01?
 Significance

 We have to define a threshold, a boundary, and say that if p

is below this threshold H0 is rejected otherwise H1 is
accepted.
 This boundary is called the significance level. By convention
it is set at p=0.05 (1:20), but you can chose any other
number - as long as you specify it in the write-up of your
analyses.
 WARNING!! This means that if you analyse 100 sets of
random data, the expectance (log-term average) is that 5 will
generate a significant test.
The procedure:
Decide significance level
Set up H0, H1.
p=0.05

 Data
 5 3
 4 2
Test statistic Probability of
 4 4
 3 1 U = 15.5 H0 being true
 5 2 p = 0.03
 4 1
 5
Is p above critical level?
Y N

Reject H0
Accept H0
 This particular test:
 The Mann-Whitney U test is a non-parametric test
which examines whether 2 columns of data could
have come from the same population (ie “should” be
the same)
 It generates a test statistic called U (no idea why it’s
U). By hand we look U up in tables; PCs give you an
exact probability.
 It requires 2 sets of data - these need not be paired,
nor need they be normally distributed, nor need there
be equal numbers in each set.
How to do it
 1: rank all data into 2 Harmonize ranks where the
ascending order, then re- same value occurs more than
code the data set
replacing raw data with once
ranks.

 Data  Data  Data

 5 3  5 #13 3 #5  5 #13 = 12 3 #5 = 5.5
 4 2  4 #10 2 #4  4 #10 = 8.5 2 #4 = 3.5
 4 4  4 #9 4 #7  4 #9 = 8.5 4 #7 = 8.5
 3 1  3 #6 1 #2  3 #6 = 5.5 1 #2 = 1.5
 5 2  5 #12 2 #3  5 #12 = 12 2 #3 = 3.5
 4 1  4 #8 1 #1  4 #8 = 8.5 1 #1 = 1.5
 5  5 #11  5 #11 = 12
 Once data are ranked:
 Add up ranks for each column; call these rx and ry
 (Optional but a good check:
– rx + ry = n2/2 + n/2, or you have an error)
 Calculate
– Ux = NxNy + Nx(Nx+1)/2 - Rx
– Uy = NxNy + Ny(Ny+1)/2 - Ry
 take the SMALLER of these 2 values and look up in tables. If U is LESS than the
critical value, reject H0

 NB This test is unique in one feature: Here low values of the test stat. Are
significant - this is not true for any other test.
 In this case:
 Data
 5 #13 = 12 3 #5 = 5.5
 4 #10 = 8.5 2 #4 = 3.5
Ux = 6*7 + 7*8/2 - 67 = 3
 4 #9 = 8.5 4 #7 = 8.5 Uy = 6*7 + 6*7/2 - 24 =
 3 #6 = 5.5 1 #2 = 1.5 39
 5 #12 = 12 2 #3 = 3.5
 4 #8 = 8.5 1 #1 = 1.5
 5 #11 = 12
Lowest U value is 3.
 ___ ___
 rx=67 ry=24 Critical value of U (7,6) = 4 at p =
0.01.
 Check: rx + ry + 91
Calculated U is < tabulated U so
 13*13/2 + 13/2 = 91 CHECK.
reject H0.

At p = 0.01 these two sets of data

 Tails.. Generally use
2 tailed tests
2 tailed test: These
populations DIFFER.

1 tailed test: Population X is

Greater than Y (or Less than
Y).

Lower tail of distribution Upper tail of distribution

 Kruskal-Wallis: The U test’s big cousin
When we have 2 groups to compare (M/F, site 1/site 2, etc) the
U test is correct applicable and safe.

How to handle cases with 3 or more groups?

The simple answer is to run the Kruskal-Wallis test. This is run

on a PC, but behaves very much like the M-W U. It will give
one significance value, which simply tells you whether at least
one group differs from one other.
Males Females
Site 1 Site 2 Site 3

Do males differ
Do results differ
from females?
between these sites?
Wilcoxon Rank Sum Test

The Z test and the t test are “parametric

tests” – that is, they answer a question
about the difference between populations
by comparing sample statistics (e.g., X1
and X2) and making an inference to the
population parameters (μ1 and μ2).
The Wilcoxon, in contrast, allows
inferences about whole populations
Wilcoxon
Distribution A Note that
distribution B is
shifted to the right
of distribution A

μ X

Distribution B

μ X

Wilcoxon
1b. Small samples, independent
groups
Wilcoxon Rank Sum Test
– first, combine the two samples and rank order
all the observations.
– smallest number has rank 1, largest number
has rank N (= sum of n1 and n2).
– separate samples and add up the ranks for the
smaller sample. (If n1 = n2, choose either one.)
– test statistic : rank sum T for smaller sample.

Wilcoxon
1b. Small samples, independent
groups
Wilcoxon – One-tailed Hypotheses
H0: Prob. distributions for 2 sampled
populations are identical.
HA: Prob. distribution for Population A
shifted to right of distribution for
Population B. (Note: could be to the left,
but must be one or the other, not both.)

Wilcoxon
1b. Small samples, independent
groups
Wilcoxon – Two-tailed Hypotheses
H0: Prob. distributions for 2 sampled
populations are identical.
HA: Prob. distribution for Population A
shifted to right or left of distribution for
Population B.

Wilcoxon
1b. Small samples, independent
groups
Wilcoxon – Rejection region:

(With Sample taken from Population A

being smaller than sample for Population
B) – reject H0 if
T A ≥ TU or TA ≤ TL

Wilcoxon
 1b. Small samples, independent
groups
Wilcoxon for n ≥ 10 and n ≥ 10:
1 2

Test statistic:

 Z = TA – n1(n1 + n2 + 1)
 2
 n1n2(n1 + n2 + 1)
 12
Wilcoxon
Wilcoxon for n1≥ 10 and n2 ≥ 10

Rejection region:
One-tailed Two-tailed

Z > Zα │Z│ > Zα/2

Note: use this only when n1≥ 10 and n2 ≥ 10

Wilcoxon
Example 1

These are small samples, and they are

independent (“random samples of Cajun
and Creole dishes”). Therefore, we have
to begin with the test of equality of
variances.

Wilcoxon
Test of hypothesis of equal
variances
H0: 12 = 22
HA: 12 ≠ 22

Test statistic: F = S12

 S22

Rej. region: F > Fα/2 = F(6,6,.025) = 5.82

 or F < (1/5.82) = .172
Wilcoxon
Test of hypothesis of equal
variances
S2Cajun = (385.27)2 = 148432.14
S2Creole = (1027.54)2 = 1055833.33

Fobt = 148432.14 = 7.11

 1055833.33

Reject H0 – variances are not equal, so we

do the Wilcoxon.
Wilcoxon
Example 1 – Wilcoxon Rank
Sum Test
H0: Prob. distributions for Cajun and
Creole populations are identical.
HA: Prob. distribution for Cajun is shifted
to right of distribution for Creole.

Statistical test: T

Wilcoxon
Example 1 – Wilcoxon Rank
Sum Test
Rejection region:
 Reject H0 if TCajun > 66 (or if TCreole <
39)

(Note: We shall give lower heat values

lower rank values)

Wilcoxon
 Example 1 – Wilcoxon Rank
Sum Test
Cajun Creole
6.5 4.5
3500
11.5 13.53100
4200
9.5 3 4700
4100
13.5 6.5 2700
4700 2 3500
11.5
4200
8 4.5 2000
3705
9.5 1 3100
4100 1550
Σ 70 35
Wilcoxon
Example 1 – Wilcoxon Rank
Sum Test
Calculation check:

Sum of the ranks should = (n) (n+1)

 2

70 + 35 = 105 = (14)(15)

 2
Wilcoxon
Example 1 – Wilcoxon Rank
Sum Test
TCajun = 70 > 66 (and TCreole = 35 < 39)

Therefore, reject H0 – Cajun dishes are

significantly hotter than Creole dishes.

Wilcoxon
Example 2 – Wilcoxon Rank
Sum Test
H0: 12 = 22
HA: 12 ≠ 22

Test statistic: F = S12

 S22

Rej. region: F > Fα/2 = F(7,8,.025) = 4.53

 or F < (1/4.90) = .204
Wilcoxon
Example 2 – Wilcoxon Rank
Sum Test
Fobt = 4.316 = 9.38
 .46

Reject H0 – do Wilcoxon

Wilcoxon
Example 2 – Wilcoxon Rank
Sum Test
H0: Prob. distributions for females and males
populations are identical.
HA: Prob. distribution for females is shifted to
left of distribution for males.

Statistical
test: T
Rejection region: T♂ > TU = 90
 (or T♀ < TL = 54)
Wilcoxon
Example 2 – Wilcoxon Rank
Sum Test
6.4 16 2.7 3
1.7 1 3.9 10
3.2 5 4.6 12
5.9 15 3.0 4
2.0 2 3.4 6.5
3.6 8 4.1 11
5.4 14 3.4 6.5
7.2 17 4.7 13
 3.8 9
Σ 78 75
Wilcoxon
Example 2 – Wilcoxon Rank
Sum Test
T♂ = 78 < TU = 90

Therefore, do not reject H0 – no

evidence that mean distance in females is
less than that in males.

Wilcoxon
Example 3 – Wilcoxon Rank
Sum Test
H0: 12 = 22
HA: 12 ≠ 22

Test statistic: F = S12

 S22

Rej. region: F > Fα/2 = F(5,5,.025) = 7.15

 or F < (1/7.15) = .140
Wilcoxon
Example 3 – Wilcoxon Rank
Sum Test
Fobt = (7.563)2 = 57.20
 (2.04)2 4.16

 = 13.74

Reject H0 – do Wilcoxon

Wilcoxon
Example 3 – Wilcoxon Rank
Sum Test
H0: Prob. distributions for Hoodoo and
Mukluk populations are identical.
HA: Prob. distribution for Hoodoos is shifted
to right or left of distribution for Mukluks.

Statistical
test: T
Rejection region: TH > 52 or < 26

Wilcoxon
Example 3 – Wilcoxon Rank
Sum Test
Hoodoo Mukluk
2 1 6 5
6 5 8 9.5
4 2.5 7 7.5
23 12 10 11
7 7.5 8 9.5
6 5 4 2.5
Σ 33 45
Wilcoxon
Example 3 – Wilcoxon Rank
Sum Test
Check: TH + TM = 78
 (12)(13) = 78
 2

TH = 33 > 26 and < 52

Do not reject H0 – no evidence for a

significant difference between teams.
Wilcoxon
The Kruskal-Wallis (KW) Test for
Comparing Populations with Unknown
Distributions
 A nonparametric test for comparing population
medians by Kruskal and Wallis
 The KW procedure tests the null hypothesis that k
samples from possibly different populations actually
originate from similar populations, at least as far as
their central tendencies, or medians, are concerned.
The test assumes that the variables under
consideration have underlying continuous distributions.
 In what follows assume we have k samples, and the
sample size of the i-th sample is ni, i = 1, 2, . . ., k.
Test based on ranks of combined
data
 In the computation of the KW statistic, each
observation is replaced by its rank in an ordered
combination of all the k samples.
 By this we mean that the data from the k samples
combined are ranked in a single series.
 The minimum observation is replaced by a rank of 1,
the next-to-the-smallest by a rank of 2, and the largest
or maximum observation is replaced by the rank of N,
where N is the total number of observations in all the
samples (N is the sum of the ni).
Compute the sum of the ranks for
each sample
 The next step is to compute the sum of
the ranks for each of the original
samples. The KW test determines
whether these sums of ranks are so
different by sample that they are not
likely to have all come from the same
population.
 Test statistic follows
 It can be shown that if the k samples come from the same population,
that is, if the null hypothesis is true, then the test statistic, H, used in
the KW procedure is distributed approximately as a chi-square
statistic with df = k - 1, provided that the sample sizes of the k
samples are not too small (say, ni>4, for all i). H is defined as follows:

 where k = number of samples (groups)

ni = number of observations for the i-th sample or group
N = total number of observations (sum of all the ni)
Ri = sum of ranks for group i
Non-parametric Tests

 Parametric vs Non-parametric

 Chi-Square
– 1 way
– 2 way
Parametric Tests

 Data approximately normally distributed.

 Dependent variables at interval level.
 Sampling random
 t - tests
 ANOVA
Non-parametric Tests

 Do not require normality

 Or interval level of measurement

 Less Powerful -- probability of rejecting

the null hypothesis correctly is lower. So
use Parametric Tests if the data meets
those requirements.
One-Way Chi Square Test

 Compares observed frequencies within

groups to their expected frequencies.

 HO = “observed” frequencies are not

different from the “expected” frequencies.
 Research hypothesis: They are different.
Chi Square Statistic

 fo = observed frequency

 fe = expected frequency
Chi Square Statistic

( fo  fe) 2


2
 
fe
One-way Chi Square
Interpretation
 If our calculated value of chi square is less than
the table value, accept or retain Ho

 If our calculated chi square is greater than the

table value, reject Ho

 …as with t-tests and ANOVA – all work on the

same principle for acceptance and rejection of
the null hypothesis
Two-Way Chi Square

 Review cross-tabulations (= contingency

tables) from Chapter 2.
 Are the differences in responses of two
groups statistically significantly different?
 One-way = observed vs expected
 Two-way = one set of observed
frequencies vs another set.
Two-way Chi Square
 Comparisons between frequencies (rather
than scores as in t or F tests).
 So, null hypothesis is that the two or more
populations do not differ with respect to
frequency of occurrence.

 rather than working with the means as in t

test, etc.
Two-way Chi Square Example
 Null hypothesis: The relative frequency [or
percentage] of liberals who are permissive
is the same as the relative frequency of
conservatives who are permissive.
 Categories (independent variable) are
liberals and conservatives. Dependent
variable being measured is permissiveness.
 Two-Way Chi Square Example
Child-rearing Political Orientation
Practices
Liberals Conservatives Total
Permissive 13 7 20
Non-permissive 7 13 20
Total 20 20 40
Two-Way Chi Square Example
 Because we had 20 respondents in each
column and each row, our expected values
in this cross-tabulation would be 10 cases
per cell.
 Note that both rows and columns are
nominal data -- which could not be handled
by t test or ANOVA. Here the numbers are
frequencies, not an interval variable.
 Two-Way Chi Square Expected

Child-rearing Political Orientation (Expected)

Practices
Liberals Conservatives Total
Permissive 10 10 20
Non-permissive 10 10 20
Total 20 20 40
Two-Way Chi Square Example

 Unfortunately, most examples do not

have equal row and column totals, so it
is harder to figure out the expected
frequencies.
Two-Way Chi Square Example

 What frequencies would we see if there

were no difference between groups (if
the null hypothesis were true)?
 If 25 out of 40 respondents(62.5%) were
permissive, and there were no
difference between liberals and
conservatives, 62.5% of each would be
permissive.
Two-Way Chi Square Example

 We get the expected frequencies for

each cell by multiplying the row
marginal total by the column marginal
total and dividing the result by N.
 We’ll put the expected values in
parentheses.
 Two-Way Chi-Square Example
Political Orientation
Liberals Conservatives Total
Permissive 15 (12.5) 10 (12.5) 25
Not Permissive 5 (7.5) 10 (7.5) 15

Total 20 20 40
Two-Way Chi-Square Example

 So the chi square statistic, from this

data is
 (15-12.5)squared / 12.5 PLUS the same
values for all the other cells
 = .5 + .5 + .83 + .83 = 2.66
Two-Way Chi-Square Example
 df = (r-1) (c-1) , where r = rows, c
=columns so df = (2-1)(2-1) = 1

 From Table C, α = .05, chi-sq = 3.84

 Compare: Calculate 2.66 is less than

table value, so we retain the null
hypothesis.