WORKED EXAMPLES OF NON-PARAMETRIC TESTS

1. CONTINGENCY TABLES/CHI SQUARE STATISTICS

A contingency table is a table that shows the relationship between two categorical variables. The
Chi-square statistic reflects the strength of this relationship. All else equal, the greater the chi-
square statistic, the stronger the relationship. The chi square statistic is usually reported at the
bottom of a contingency table. The probability associated with the chi-square statistic indicates
the probability that you would be incorrect if you were to assert that there is a relationship between
these same two variables in the population from which you drew your sample.

What is a Chi Square?

It is a statistical technique which compares the tallies or counts of categorical

responses between two (or more) independent groups.
When do we use a Chi Square Test?
When we examine the relationship between two categorical variables
Assumptions of Chi Square
The statistics generated by the computer for chi-square are only valid if the data
meet the following qualifications:
a) Both the independent and dependent variables are categorical
b) Researchers used a random sample to collect data
c) Researchers had an adequate sample size. Generally the sample size should be at least 100
d) The number of respondents in each cell should be at least 5. If not, you can use a Fisher’s Exact
or other tests.
e) The variables you consider must be mutually exclusive
f) Data should be in a contingency table
Characteristics of the chi square statistic
It is relatively easy to interpret a chi square statistic if you know three things
•First – all else equal, the greater the chi square number, the stronger the relationship between the
dependent and independent variable
•Second – the lower the probability associated with a chi-square statistic, the stronger the
relationship between the dependent and independent variable.

1
•Third – If your probability is .05 or less, then you can generalize from a random sample to a
population, and claim the two variables are associated in the population.
Question 1
A public opinion poll surveyed a simple random sample of voters to establish whether there is a
relationship between gender and voting preference. Respondents were classified by gender (male
or female) and by voting preference (Republican, Democrat, or Independent). Results are shown
below.
Voting Preferences
Gender Republican Democrat Independent
Male 200 150 50
Female 250 300 50

a) Giving reasons, which is the best statistical test for analysing the data?
b) State and explain any three assumptions of the test statistic identified in a above
c) State the null hypothesis of the study.
d) At 0.05 significance level, does the data support the null hypothesis?
e) Report your findings.
Voting Preferences
Gender Republican Democrat Independent Total
Male 200 150 50 400
Female 250 300 50 600
Total 450 450 100 1000

O E O-E (O-E)^2 (O-E)^2/E

200 180 20 400 2.2222
150 180 -30 900 5.0000
50 40 10 100 2.5000
250 270 -20 400 1.4815
300 270 30 900 3.3333
50 60 -10 100 1.6667
16.2037

The chi square calculated is 16.2037

The degree of freedom (df) for the chi square is given by = (c-1)(r-1)=(3-1)(2-1)=2x1=2

2
At df = 2 and significance level = 0.05, the chi square critical is 5.99 form the table of critical
values of the chi square.
Since chi square calculated (16.2037) is greater than the chi square critical (5.99), we reject the
hypothesis that voting preference is not guided by gender, in deed it is
Question 2
A researcher sought to establish the relationship between stream and perception in mathematics.
The results are tabulated below.
Perception in mathematics
Stream Excellent Average Poor
3A 88.7 60.2 40.1
3B 82.6 64.2 37.3
3C 85.6 66.4 42.8
a) Giving reasons, which is the best statistical test for analysing the data?
b) State the null hypothesis to be tested.
c) At 0.05 significance level, does the data support the null hypothesis?
d) Report your findings.
Critical Values of Chi square

Level of Significance
df 0.20 0.10 0.05 0.02 0.01 0.001
1 1.642 2.706 3.841 5.412 6.635 10.828
2 3.219 4.605 5.991 7.824 9.210 13.816
3 4.642 6.251 7.815 9.837 11.345 16.266
4 5.989 7.779 9.488 11.668 13.277 18.467
5 7.289 9.236 11.070 13.388 15.086 20.515
6 8.558 10.645 12.592 15.033 16.812 22.458
7 9.803 12.017 14.067 16.622 18.475 24.322
8 11.030 13.362 15.507 18.168 20.090 26.124
9 12.242 14.684 16.919 19.679 21.666 27.877
10 13.442 15.987 18.307 21.161 23.209 29.588
11 14.631 17.275 19.675 22.618 24.725 31.264
12 15.812 18.549 21.026 24.054 26.217 32.909
13 16.985 19.812 22.362 25.472 27.688 34.528

3
 2. SPEARMAN’S RANK CORRELATION
The Spearman rank-order correlation coefficient also referred to as Spearman Correlation
Coefficient or Spearman's rho. It is typically denoted either with the Greek letter rho (ρ), or rs is
a nonparametric measure of the strength and direction of association that exists between two
variables measured on at least an ordinal scale. It is denoted by the symbol rs (or the Greek letter
ρ, pronounced rho). The test is used for either ordinal variables or for continuous data that has
failed the assumptions necessary for conducting the Pearson's product-moment correlation. For
example, you could use a Spearman’s correlation to understand whether there is an association
between exam performance and time spent revising; whether there is an association between
depression and length of unemployment; and so forth.
Assumptions of Spearman’s Rank Correlation
1. Your two variables should be measured on an ordinal, interval or ratio scale.
2. There needs to be a monotonic relationship between the two variables. A monotonic
relationship exists when either the variables increase in value together, or as one variable value
increases, the other variable value decreases. Whilst there are a number of ways to check
whether a monotonic relationship exists between your two variables, we suggest creating a
scatterplot using SPSS Statistics, where you can plot one variable against the other, and then
visually inspect the scatterplot to check for monotonicity. The following graphs illustrate
monotonic functions:

Monotonically increasing Monotonically decreasing Not monotonic

• Monotonically increasing - as the x variable increases the y variable never decreases;

• Monotonically decreasing - as the x variable increases the y variable never increases;

4
 • Not monotonic - as the x variable increases the y variable sometimes decreases and sometimes
increases.
Spearman’s correlation coefficient
Spearman’s correlation coefficient is a statistical measure of the strength of a monotonic
relationship between paired data. In a sample it is denoted by and is by design constrained as
follows: -1≤ rs≤1
And its interpretation is similar to that of Pearsons, e.g. the closer is to the stronger the monotonic
relationship. Correlation is an effect size and so we can verbally describe the strength of the
correlation using the following guide for the absolute value of rs:
.00-.19 “very weak”, .20-.39, “weak”; .40-.59, “moderate”; .60-.79, “strong”; .80-1.0, “very
strong”
Formula for calculating Spearman’s correlation coefficient

The following formula can be used to calculate this coefficient, it is

Where: d2 is the sum of the squared differences between the pairs of ranks, and n is the number of
pairs.

The advantages of this coefficient are that, if calculation is to be done by hand, it is easier to
calculate, and can be used for any data that can be ranked - which includes quantitative data.

Procedure for calculating the Spearman’s correlation coefficient

1. Create a table from your data.
2. Rank the two data sets. Ranking is achieved by giving the ranking '1' to the biggest number in
a column, '2' to the second biggest value and so on. The smallest value in the column will get
the lowest ranking. This should be done for both sets of measurements. Tied scores are given
the mean (average) rank.
3. Find the difference in the ranks (d): This is the difference between the ranks of the two values
on each row of the table.
4. Square the differences (d²) to remove negative values and then sum them ( d²).

5
5. Use the following formula below to calculate the Spearman’s correlation coefficient.

Example
A researcher sought to establish the rating whether the price of a bottle of water decreases as
distance from the Contemporary Art Museum increases. The results are tabulated below.
Convenience Store Distance from CAM (m) Price of 50cl bottle (€)
1 50 1.80
2 175 1.20
3 270 2.00
4 375 1.00
5 425 1.00
6 580 1.20
7 710 0.80
8 790 0.60
9 890 1.00
10 980 0.85

a) Which is the best test statistic suitable to analyse the data and why?
b) State the assumptions of the identified test statistic
c) State the null hypothesis to be tested
There is no significant relationship between the price of a convenience item and distance from
the Contemporary Art Museum.
d) Does the data support the null hypothesis?
Calculate the value of Spearman’s correlation coefficient using step 1 -4 above.

6
 Distance
Price of Difference
Convenience from Rank Rank
50cl between d²
Store CAM distance price
bottle (€) ranks (d)
(m)
1 50 10 1.80 2 8 64
2 175 9 1.20 3.5 5.5 30.25
3 270 8 2.00 1 7 49
4 375 7 1.00 6 1 1
5 425 6 1.00 6 0 0
6 580 5 1.20 3.5 1.5 2.25
7 710 4 0.80 9 -5 25
8 790 3 0.60 10 -7 49
9 890 2 1.00 6 -4 16
10 980 1 0.85 8 -7 49
d² =
285.5

• Calculate the coefficient (rs) using the formula:

• The answer will always be between 1.0 (a perfect positive correlation) and -1.0 (a perfect
negative correlation).
• Now to put all these values into the formula.
• Find the value of all the d² values by adding up all the values in the d² column. In our
example this is 285.5. Multiplying this by 6 gives 1713.
• Now for the bottom line of the equation. The value n is the number of sites at which you
took measurements. This, in our example is 10. Substituting these values into n(n2 – n) we
get 10(102-1)= 10(100-1) =10*99 = 990
• We now have the formula: rs = 1 - (1713/990) which gives a value for rs: 1 - 1.73 = -0.7303
What does this rs value of -0.73 mean?
The closer rs is to +1 or -1, the stronger the likely correlation. A perfect positive correlation is
+1 and a perfect negative correlation is -1. The rs value of -0.7303 suggests a fairly strong
negative relationship.

7
A further technique is now required to test the significance of the relationship. We do so by
comparing the calculated spearman rank correlation test statistic and the critical spearman rank
correlation test statistic. To get the latter, we check the value of the statistic where the level of
significance on a two or one tailed (depends of the way the Ho is stated) meet the degree of
freedom (d.f) of the spearman rank correlation.
The degree of freedom for spearman rank correlation is given by the number of pairs in your
sample minus 2 i.e. df= (n-2). In the example it is 8 i.e. (10 - 2). Our level of significance is
0.05 on a two-tailed test (Ho). In the table of critical values for Spearman's rank correlation
coefficient check for the spearman rank correlation statistic value given by the meeting point
of the level of significance 0.05 and n-2 (n=8), the test statistic is 0.738
The value is
Critical values for Spearman's rank correlation coefficient
df Two-sided
(n-2) .10 .05 .01
5 .900 -- --
6 .829 .886 --
7 .714 .786 .929
8 .643 .738 .881
9 .600 .700 .833
10 .564 .648 .794
11 .536 .618 .818
12 .497 .591 .780
13 .475 .566 .745
14 .457 .545 .716
15 .441 .525 .689
16 .425 .507 .666
17 .412 .490 .645
18 .399 .476 .625
19 .388 .462 .608
20 .377 .450 .591
21 .368 .438 .576
22 .359 .428 .562
23 .351 .418 .549
24 .343 .409 .537
25 .336 .400 .526
26 .329 .392 .515
27 .323 .385 .505
28 .317 .377 .496
29 .311 .370 .487
8
 30 .305 .364 .478

Since our Spearman's rank correlation coefficient calculated value (0.7303) is less than our
Spearman's rank correlation coefficient critical value (0.738), we accept our null hypothesis.
Example 2
Two doctors assessed the condition of eight patients suffering from particular symptoms. To do
this they ranked the patients from 1 (best) to 8 (worst): the results are tabulated.
Patient Doctor A Doctor B
1 4 5
5 1 3
3 3 1
4 2 2
5 6 6
6 5 4
7 8 7

Is the ranking significant?

Parametric testing is defined by making one or more assumptions about the population's properties.
The most common assumptions to make are that the population will be normally distributed or
have data based on an equal-interval scale

3. THE INDEPENDENT-SAMPLES T-TEST (OR INDEPENDENT T-TEST)

Introduction
The independent-samples t-test (or independent t-test, for short) compares the means between two
unrelated groups on the same continuous, dependent variable. For example, you could use an
independent t-test to understand whether first year graduate salaries differed based on gender (i.e.,
your dependent variable would be "first year graduate salaries" and your independent variable
would be "gender", which has two groups: "male" and "female"). Alternately, you could use an
independent t-test to understand whether there is a difference in test anxiety based on educational
level (i.e., your dependent variable would be "test anxiety" and your independent variable would
be "educational level", which has two groups: "undergraduates" and "postgraduates").
Assumptions of independent sample t-test
When you choose to analyse your data using an independent t-test, part of the process involves
checking to make sure that the data you want to analyse can actually be analysed using an

9
independent t-test. You need to do this because it is only appropriate to use an independent t-test
if your data "passes" six assumptions that are required for an independent t-test to give you a valid
result
1. Your dependent variable should be measured on a continuous scale (i.e., it is measured at
the interval or ratio level). Examples of variables that meet this criterion include revision time
(measured in hours), intelligence (measured using IQ score), exam performance (measured
from 0 to 100), weight (measured in kg), and so forth.
2. Your independent variable should consist of two categorical, independent groups. Example
independent variables that meet this criterion include gender (2 groups: male or female),
employment status (2 groups: employed or unemployed), smoker (2 groups: yes or no), and so
forth.
3. You should have independence of observations, which means that there is no relationship
between the observations in each group or between the groups themselves. For example, there
must be different participants in each group with no participant being in more than one group.
4. There should be no significant outliers. Outliers are simply single data points within your data
that do not follow the usual pattern. The problem with outliers is that they can have a negative
effect on the independent t-test, reducing the validity of your results.
5. Your dependent variable should be approximately normally distributed for each group of
the independent variable. We talk about the independent t-test only requiring approximately
normal data because it is quite "robust" to violations of normality, meaning that this assumption
can be a little violated and still provide valid results. You can test for normality using the
Shapiro-Wilk test of normality.
6. There needs to be homogeneity of variances. You can test this assumption using Levene’s
test for homogeneity of variances.
The independent t-test, as we have already mentioned is used when we wish to compare the
statistical significance of a possible difference between the means of two groups on some
independent variable and the two groups are independent of one another. The formula for the
independent sample t-test is:

10
 is the mean for group 1,

is the mean for group 2,

is the sum of squares for group 1,

is the sum of squares for group 2,

n1 is the number of subjects in group 1, and
n2 is the number of subjects in group 2.
The sum of squares is a new way of looking at variance. It gives us an indication of how spread
out the scores in a sample is. The t-value we are finding is the difference between the two means
divided by their sum of squares and taking the degrees of freedom into consideration.

and

We also need to know the degrees of freedom for the independent t-test which is:

Example problem using the independent t-test

Job satisfaction as a function of work schedule was investigated in two different factories. In the
first factory the employees are on a fixed shift system while in the second factory the workers have
a rotating shift system. The results are indicated in the table below.

Fixed Shift 79 83 68 59 81 76 80 74 58 49 68
Rotating Shift 63 71 46 57 53 46 57 76 52 68 73

a) Which test statistic would be most suitable to analyse the above data and why
b) Explain three assumptions of the test above
c) State the null hypothesis to be tested

11
d) Using the scores above determine if there is a significant difference in job satisfaction between
the two groups of workers
X1 X2 (X1)2 (X2)2
79 63 6241 3969
83 71 6889 5041
68 46 4624 2116
59 57 3481 3249
81 53 6561 2809
76 46 5776 2116
80 57 6400 3249
74 76 5476 5776
58 52 3364 2704
49 68 2401 4624
68 73 4624 5329
775 662 55837 40982

We can use the totals from this worksheet and the number of subjects in each group to calculate
the sum of squares for group 1, the sum of squares for group 2, the mean for group 1, the mean for
group 2, and the value for the independent t.

12
Therefore our t-calculated value is 2.209. We need to compare this with the t-critical from
statistical tables.
The degree of freedom for the t-test is given by: df = n1 + n2 - 2 = 11 + 11 - 2 = 20. The significance
level is 0.05
To know the critical value for critical t, we use the statistical tables for t-test with an alpha level
of 0.05 and a two-tailed test. Look for the column of the table under .05 for Level of significance
for two-tailed tests, read down the column until you are level with 20 in the df column, and you
will find the critical value of t which is 2.086.
Finally, compare the calculated t value (2.209) with the critical t value (2.086).That means our
result is significant if the calculated t value is greater than or equal to -2.086 or is less than or equal
to 2.086.
Since our calculated value of t (2.209) is greater than the critical value of t (2.086), we reject the
null hypothesis and accept the alternative hypothesis.
Therefore, there is a significant difference in job satisfaction between the two groups of workers
as shown by the t –test, t(20) = 2.209, p = 2.086, at 0.05.

13
Exercise
A researcher sought to establish whether two types of music, type-I and type-II, had different
effects upon the ability of college students to perform a series of mental tasks requiring
concentration? The researcher picked a fairly homogeneous subject pool of 30 college students,
randomly sorting them into two groups, A and B, of sizes Na=15 and Nb=15. (It is not essential for
this procedure that the two samples be of the same size.) He then had the members of each group,
one at a time, perform a series of 40 mental tasks while one or the other of the music types is
playing in the background. For the members of group A it is music of type-I, while for those of
group B it is music of type-II. The following table shows how many of the 40 components of the
series each subject was able to complete.

Group A 26 21 22 26 19 22 26 25 24 21 23 23 18 29 22
music of type-I
Group B 18 23 21 20 20 29 20 16 20 26 21 25 17 18 19
music of type-II

Do two types of music, type-I and type-II, have different effects upon the ability of college students
to perform a series of mental tasks requiring concentration?

4. PAIRED SAMPLES T-TESTS

The dependent t-test (called the paired-samples t-test in SPSS) compares the means between two
related groups on the same continuous, dependent variable. For example, you could use a
dependent t-test to understand whether there was a difference in smokers' daily cigarette
consumption before and after a 6 week hypnotherapy programme (i.e., your dependent variable

14
would be "daily cigarette consumption", and your two related groups would be the cigarette
consumption values "before" and "after" the hypnotherapy programme).

1. Your dependent variable should be measured on a continuous scale (i.e., it is measured at

the interval or ratio level).
2. Your independent variable should consist of two categorical, "related groups" or "matched
pairs". "Related groups" indicates that the same subjects are present in both groups. The reason
that it is possible to have the same subjects in each group is because each subject has been
measured on two occasions on the same dependent variable. For example, you might have
measured 10 individuals' performance in a spelling test (the dependent variable) before and
after they underwent a new form of computerized teaching method to improve spelling. You
would like to know if the computer training improved their spelling performance. The first
related group consists of the subjects at the beginning of (prior to) the computerized spelling
training and the second related group consists of the same subjects, but now at the end of the
computerized training.
3. There should be no significant outliers in the differences between the two related groups.
Outliers are simply single data points within your data that do not follow the usual pattern (
4. The distribution of the differences in the dependent variable between the two related groups
should be approximately normally distributed.

The formula for the dependent t is:

Where D is the difference between pairs of scores,

Notice that we subtract the score for the first X from the paired second X. This is probably so that
when we are finding the difference between the pre-test and post-test, that we subtract the pre-test
(X1) from the post-test (X2). The degree of freedom for the dependent-t test is df = n – 1 and n is
the number pairs of subjects in the study.

15
Example problem using the dependent t-test
The Beck Depression Scale (pre-test) was administered to ten adolescents undergoing anger
management therapy. After four weeks of therapy the same scale was administered again (post-
test). The results are tabulated below.
Pre-Test (X1) 14 6 4 15 3 3 6 5 6 3
Post-Test (X2) 0 0 3 20 0 0 1 1 1 0

a) What is the appropriate test statistic that will be used to analyse this data and why.
In this problem we are comparing pre-test and post-test scores for a group of subjects. At the same
time the dependent variable is in ratio while the independent variable is categorical (pretest and
posttest). This would be an appropriate situation for the dependent t-test.
b) What are the three basic assumptions of the test statistic in (a) above?
c) State the null hypothesis to be tested

Note: Our problem stated that the therapy would decrease the depression score. Therefore our
alternative hypothesis states that mu1 (the pre-test score) will be greater than mu2 (the post-test
score).
d) Does the anger management therapy significantly reduce the scores on the depression scale?
The pre-test and post-test scores, as well as D and D2 are shown in the following table
D= (X2-
Pre-Test (X1) Post-Test (X2)
X1) D2
14 0 -14 196
6 0 -6 36
4 3 -1 1
15 20 5 25
3 0 -3 9
3 0 -3 9
6 1 -5 25
5 1 -4 16
6 1 -5 25
3 0 -3 9
-39 351

16
 1. Calculate the t-value using the formula:

and the degrees of freedom for this problem is:

2. Calculate the degree of freedom of the t-test

Set the alpha level. Note: As usual we will set our alpha level at .05, we have 5 chances in 100 of
making a type I error.
3. Calculate the value of the appropriate statistic. Also indicate the degrees of freedom for
the statistical test if necessary. t = -2.623 df = n - 1 = 10 - 1 = 9 Note: We have calculated the t-
value and will also need to know the degrees of freedom when we go to look up the critical value
of t.
4. Write the decision rule for rejecting the null hypothesis. Reject H0 if t is <= -1.833 Note: To
write the decision rule we need to know the critical value for t, with an alpha level of .05 and a
one-tailed test. That means our result is significant if the calculated t value is less than or equal to
-1.833. Note: Why are we looking for a negative value of t? This is a little tricky, but we are
looking at the post-test being less than the pre-test. Now the dependent t is calculated by
subtracting the pre-test from the post-test so if the post-test is actually less than the pre-test, post-
test minus pre-test will be a negative quantity.
5. Write a summary statement based on the decision. Reject H0, p < .05, one-tailed Note: Since
our calculated value of t (-2.623) is less than or equal to -1.833, we reject the null hypothesis and
accept the alternative hypothesis.
6. Write a statement of results in Standard English. The management therapy did significantly
reduce the depression scores for the adolescents.
17
Exercise
Consider the following study in which standing and supine systolic blood pressures were
compared. This study was performed on twelve subjects. Their blood pressures were measured in
both positions.

Standing 132 146 135 141 139 162 128 137 145 151 131 143
Supine 136 145 140 147 142 160 137 136 149 158 120 150

Does the data suggest that there is no difference between the mean blood pressures in the two
populations?

5. THE ANALYSIS OF VARIANCE (ANOVA)

Analysis of variance like the t-test, tests the hypothesis that the means of OVERALL groups are
equal. One of the most important difference is that in a t-test only TWO groups are distinguished,
whereas analysis of variance usually compares three or more groups. For example, you can use
ANOVA to determine whether the means of a number of groups are equal.
Do students in Boys' only, Girls' only and Co-educational schools, on average, perform equally on
a self-efficacy questionnaire? or suppose you distinguish between age groups: young- less than 25

18
years; Middle- 25 to 45 years; and adult- over 45 years. Do all age groups, on average, spend equal
amount of time on face book? ANOVA answers these kinds of questions.
Assumptions of ANOVA

1. Interval data. ANOVA assumes an interval-level dependent. With Likert scales and other
ordinal dependents, the nonparametric Kruskal-Wallace test is preferred.
2. Homogeneity of variances. The dependent variable should have the same variance in each
category of the independent variable. When there is more than one independent, there must be
homogeneity of variances in the cells formed by the independent categorical variables. The
reason for this assumption is that the denominator of the F-ratio is the within-group mean
square, which is the average of group variances taking group sizes into account. When groups
differ widely in variances, this average is a poor summary measure. However, ANOVA is
robust for small and even moderate departures from homogeneity of variance. Still, a rule of
thumb is that the ratio of largest to smallest group variances should be 3.0 or less. The
Levene's test of homogeneity of variance is computed by SPSS to test the ANOVA
assumption that each group (category) of the independent)(s) has the same variance. If the
Levene statistic is significant at the .05 level or better, the researcher rejects the null hypothesis
that the groups have equal variances.
3. Random sampling. For purposes of significance testing, the subjects in each group are
randomly sampled.
4. Multivariate normality. For purposes of significance testing, variables follow multivariate
normal distributions. The dependent variable is normally distributed in each category of the
independent variable(s). ANOVA is robust even for moderate departures from multivariate
normality.
5. Equal or similar sample sizes. The groups formed by the categories of the independent(s)
should be equal or similar in sample size. The more the groups are similar in size, the more
robust ANOVA will be with respect to violations of the assumptions of normality and
homogeneity of variance.
ANOVA compares variance between the groups with the variance within the groups. Dividing the
former variance with the later, you get the F-statistic. Therefore instead of ANOVA, the term F-
test is also used.
Example 1
19
A manager wishes to determine whether the mean times required to complete a certain task differ
for the three levels of employee training. He randomly selected 6 employees with each of the three
levels of training (Beginner, Intermediate and Advanced). The data is summarized below.
Beginner: 56, 63, 52, 61, 65, 67
Intermediate: 41, 44, 51, 43, 41, 55
Advanced: 55, 45, 45, 60, 49, 53
a) Which is the best test static to analyse the data and why
When we want to compare the mean difference of more than two groups
b) State three assumptions of using test static
• Sample must be randomly selected
• All of the standard deviations are the same -No standard deviation is more than twice any
other.
• All of the populations are normally distributed
• The dependent variable should be interval or ratio
• More than two independent categorical groups
c) State the null hypothesis
There is no statistically significant difference in the mean times required to complete a certain
for the three levels of employee training
d) Does the data support the hypothesis?

Beginner Intermediate Advanced

56 41 55
63 44 45
52 51 45
61 43 60
65 41 49
67 55 53
60.6667 45.8333 51.1667

20
 Between column variance
N Mean d d2 N*d2
6 60.6667 8.1111 65.7901 394.7407
6 45.8333 -6.7222 45.1883 271.1296
6 51.1667 -1.3889 1.9290 11.57407
G mean 52.5556 677.4444

Between variance = 677.4444/3-1 =338.7222

Within column variance
Beg d d2 Inter d d2 Adv d d2
56 -4.6667 21.778 41 -4.8333 23.3611 55 3.8333 14.69444
63 2.3333 5.4444 44 -1.8333 3.36111 45 -6.1667 38.02778
52 -8.6667 75.111 51 5.1667 26.6944 45 -6.1667 38.02778
61 0.3333 0.1111 43 -2.8333 8.02778 60 8.8333 78.02778
65 4.3333 18.778 41 -4.8333 23.3611 49 -2.1667 4.694444
67 6.3333 40.111 55 9.1667 84.0278 53 1.8333 3.361111
60.6667 161.3333 45.8333 168.8333 51.1667 176.8333

Within column variance = (161.3333 + 168.8333 + 176.8333)/3 = 169

Calculated F-ratio = 338.7222/169 = 2.004274
Degree of freedom of the numerator = n-1 = 3-1 = 2
Degree of freedom of the denominator = (N1-1)+( N2-1)+ (N3-1) = (6-1)+(6-1)+(6-1) = 5+5+5=
15
Critical F-ratio = 3.68
Ho: There is no difference in the mean times required to complete a certain task by levels of training
Since Calculated F-ratio (2.004274) is less than the critical F-ratio (3.68) we accept the null

F Distribution critical values for P=0.05

Denominator
Numerator DF
DF 1 2 3 4 5 7 10 15 20 30 60 120 500

21
 1 161.45 199.50 215.71 224.58 230.16 236.77 241.88 245.95 248.01 250.10 252.20 253.25 254.06
2 18.513 19.000 19.164 19.247 19.296 19.353 19.396 19.429 19.446 19.462 19.479 19.487 19.494
3 10.128 9.5522 9.2766 9.1172 9.0135 8.8867 8.7855 8.7028 8.6602 8.6165 8.5720 8.5493 8.5320
4 7.7086 6.9443 6.5915 6.3882 6.2560 6.0942 5.9644 5.8579 5.8026 5.7458 5.6877 5.6580 5.6352
5 6.6078 5.7862 5.4095 5.1922 5.0504 4.8759 4.7351 4.6187 4.5582 4.4958 4.4314 4.3985 4.3731
7 5.5914 4.7375 4.3469 4.1202 3.9715 3.7871 3.6366 3.5108 3.4445 3.3758 3.3043 3.2675 3.2388
10 4.9645 4.1028 3.7082 3.4780 3.3259 3.1354 2.9782 2.8450 2.7741 2.6996 2.6210 2.5801 2.5482
15 4.5431 3.6823 3.2874 3.0556 2.9013 2.7066 2.5437 2.4035 2.3275 2.2467 2.1601 2.1141 2.0776
20 4.3512 3.4928 3.0983 2.8660 2.7109 2.5140 2.3479 2.2032 2.1241 2.0391 1.9463 1.8962 1.8563
30 4.1709 3.3159 2.9223 2.6896 2.5336 2.3343 2.1646 2.0149 1.9317 1.8408 1.7396 1.6835 1.6376
60 4.0012 3.1505 2.7581 2.5252 2.3683 2.1666 1.9927 1.8365 1.7480 1.6492 1.5343 1.4672 1.4093
120 3.9201 3.0718 2.6802 2.4473 2.2898 2.0868 1.9104 1.7505 1.6587 1.5544 1.4289 1.3519 1.2804
500 3.8601 3.0137 2.6227 2.3898 2.2320 2.0278 1.8496 1.6864 1.5917 1.4820 1.3455 1.2552 1.1586
1000 3.8508 3.0047 2.6137 2.3808 2.2230 2.0187 1.8402 1.6765 1.5811 1.4705 1.3318 1.2385 1.1342

22