UNIT-III: TEST OF HYPOTHESIS AND SIGNIFICANCE

3.0 Introduction
3.1 Unit Objectives
3.2 Testing of hypothesis
3.2.1 Type I and Type II errors
3.3 Level of significance
3.4 Interpretation of P-value Goodness of fit
3.5 Confidence intervals and level of significance
3.6 One tailed and two tailed tests
3.7 Hypothesis testing
3.7.1 Means and variance based on Z
3.7.2 t-tests
3.7.3 Chi-square
3.8 Analysis of Variance
3.9 Summary
3.10 Answer to Check Your Progress
3.11 Questions and Exercises

3.0 INTRODUCTION

Normally we are not aware of the true value of population parameters. So they need to
be estimated on the basis of sample information. However, we do have hypotheses
about what the true values are.

The purpose of this unit is to deal with the methodology of hypothesis testing which
provides us to choose between two competing hypotheses about the value of a
population parameter. For example, one hypothesis might claim that the wages of men
and women are equal, while the alternative might claim that men make more than
women.

A hypothesis is defined as a statement about one or more populations. In order to test

a hypothesis, we follow the following steps: (i) Stating the hypothesis (ii) Identifying
the appropriate test statistic and its probability distribution (iii) Specifying the
significance level (iv) Stating the decision rule (v) Collecting the data and calculating
the test statistic (vi) Making the statistical decision (vii) Making the economic or
investment decision.
3.1 UNIT OBJECTIVES

The objectives of this unit are to let the students Learn the basic concept of
Hypothesis Testing, know the formulations of null hypothesis and alternative
hypothesis and understand the concept of type-1 and type-2 error. The unit also helps
the students in knowing the steps involved in the calculation of Hypothesis Testing,
work out the hypothesis testing procedures based on Z-test and t-test and in knowing
the uses of Non-Parametric Chi-Square test.

3.2 TESTING OF HYPOTHESIS

The hypothesis actually to be tested is usually given the symbol H0, and is commonly
referred to as the null hypothesis. As is explained more below, the null hypothesis is
assumed to be true unless there is strong evidence to the contrary similar to how a
person is assumed to be innocent until proven guilty. The other hypothesis, which is
assumed to be true when the null hypothesis is false, is referred to as the alternative
hypothesis, and is often symbolized by HA or H1. Both the null and alternative
hypothesis should be stated before any statistical test of significance is conducted.
e done without formulating the hypothesis

The null hypothesis, H0:

States the assumption (numerical) to be tested

Begin with the assumption that the null hypothesis is TRUE

sign

The alternative hypothesis, HA:

In general, it is most convenient to always have the null hypothesis contain an equals
sign, e.g. H0: µ = 100 against the alternative hypothesis HA: µ > 100 . The true value
of the population parameter should be included in the set specified by H0 or in the set
specified by HA. Hence, in the above example, we are presumably sure µ is at least
100. A statistical test in which the alternative hypothesis specifies that the population
parameter lies entirely above or below the value specified in H0 is a one-sided (or
one-tailed) test, e.g. H0: µ = 100 against HA: µ > 100 . An alternative hypothesis that
specified that the parameter can lie on either side of the value specified by H0 is called
a two-sided (or two-tailed) test, e.g. H0: µ = 100 against HA
use a 1-tailed or 2-tailed test depends on the nature of the problem. Usually we use a
2-tailed test. A 1-tailed test typically requires a little more theory.
An Illustration to Hypothesis Testing

For example, suppose the null hypothesis is that the wages of men and women are
equal. A two-tailed alternative would simply state that the wages are not equal
implying that men could make more than women, or they could make less. A one-
tailed alternative would be that men make more than women. The latter is a stronger
statement and requires more theory, in that not only are you claiming that there is a
difference, you are stating what direction the difference is in.

In practice, a 1-tailed test such as H0: µ = 100; HA: µ > 100 is tested the same way as
H0: µ = 100; HA: µ < 100 For example, if we conclude that µ > 100, we must also
conclude that µ > 90, µ > 80, etc.

3.2.1 TYPE I AND TYPE II ERRORS

How do we choose between H0 and HA? The standard procedure is to assume H0 is

true - just as we presume innocent until proven guilty. Using probability theory, we
try to determine whether there is sufficient evidence to declare H0 false. B. We reject
H0 only when the chance is small that H0 is true. Since our decisions are based on
probability rather than certainty, there is every possibility of committing errors. There
could be two types of errors known as type-1 and type-2 error.

Type I error - We reject the null hypothesis when the null is true. The probability of
0 |
H0
is a 5% chance that, when the null hypothesis is true, we will erroneously reject it.

Type II error - we accept the null hypothesis when it is not true. Probability of Type
II error = ß. Put another way, ß = Probability of Type II error = P (accepting H 0 | H0 is
false).
P-values
-value by comparing its value

the null hypothesis P-valu Reject H0

P- Do not reject H0

Example- Explanation for type I and type II error:

Let the null hypothesis be H0: µ = 100 and alternative hypothesis be HA

Suppose µ really does equal 100. But, suppose the researcher accepts HA instead. A
type I error has occurred. Or, suppose µ = 105 - but the researcher accepts H0. A type
II error has occurred. The following tables from Harnett help to illustrate the different
types of error.

f each other - as one increases, the other decreases.

However, increases in N cause both to decrease, since sampling error is reduced. In
this class, we will primarily focus on Type I error. But, you should be aware that Type
II error is also important. A small sample size, for example, might lead to frequent
Type II errors, i.e. it could be that your (alternative) hypotheses are right, but because
your sample is so small, you fail to reject the null even though you should.
Normally there are two types of parametric test that is in practice. One is for large
samples where n > 30. This test is known as Z-test. Another test for small sample is t-
test. It is pertinent here to mention the basic concept lying behind Z-test which is on
the basis of Z-distribution popularly known as Normal Distribution. Later on t-
distribution will be discussed in brief.

3.3 LEVEL OF SIGNIFICANCE

The validity of 0 against 1 can be tested at a certain level of significance. The

level of significance is defined as the probability of rejecting the null hypothesis 0
when it is true or the probability of type I error. Actually this is the probability of test
statistics falling in the critical region when the hypothesis true. So significance is
called size of critical region, size of the test or producers risk. It is denoted by . Is
usually expressed as a percentage such as 1%, 2%, and 5% so on.

i.e. = ( 0| 0) = ( | 0)

For instance if the hypothesis accept at 5% level, the statisticians in the long run, will
be making wrong decision 5 out of 100 cases. If the hypothesis is rejected at the same
level, he runs the risk rejecting a true hypothesis about 5% of the time.

3.4 INTERPRETATION OF P-VALUE GOODNESS OF FIT

The goodness of fit test is a statistical hypothesis test to see how well sample data fit a
distribution from a population with a normal distribution. Put differently, this test
shows if your sample data represents the data you would expect to find in the actual
population or if it is somehow skewed. Goodness-of-fit establishes the discrepancy
between the observed values and those that would be expected of the model in a
normal distribution case.If the sample findings are unlikely, given the null hypothesis,
the researcher rejects the null hypothesis.

Typically, this involves comparing the P-value to the significance level, and rejecting
the null hypothesis when the P-value is less than the significance level. The P-value is
the probability of observing a sample statistic as extreme as the test statistic.

The P-value is the probability that a chi-square statistic having 2 degrees of freedom
is more extreme than 19.58. We use the Chi-Square Distribution Calculator to find

Interpret results. Since the P-value (0.0001) is less than the significance level (0.05),
we cannot accept the null hypothesis.

3.5 CONFIDENCE INTERVALS AND LEVEL OF SIGNIFICANCE

To understand hypothesis tests a sampling distribution using probability distribution

is ploted, the t-distribution, and the variability in our data. We'll base our confidence
interval on the energy cost data set that we've been using.

When we looked at significance levels, the graphs displayed a sampling distribution

centered on the null hypothesis value, and the outer 5% of the distribution was
shaded. For confidence intervals, we need to shift the sampling distribution so that it
is centered on the sample mean and shade the middle 95%.

using our sample mean as the point estimate of the population mean. This is our 95%
confidence interval.

represents the margin of error, or the amount of uncertainty, around the point
estimate. The sample mean is the most likely value for the population mean given the
information that we have. However, the graph shows it would not be unusual at all for
other random samples drawn from the same population to obtain different sample
means within the shaded area. These other likely sample means all suggest different
values for the population mean. Hence, the interval represents the inherent uncertainty
that comes with using sample data.
You can use these graphs to calculate probabilities for specific values. However,

just as Neyman said!

WHY P VALUES AND CONFIDENCE INTERVALS ALWAYS AGREE

ABOUT STATISTICAL SIGNIFICANCE

You can use either P values or confidence intervals to determine whether your results
are statistically significant. If a hypothesis test produces both, these results will agree.

The confidence level is equivalent to 1 the alpha level. So, if your significance level
is 0.05, the corresponding confidence level is 95%.

If the P value is less than your significance (alpha) level, the hypothesis test is
statistically significant.

If the confidence interval does not contain the null hypothesis value, the
results are statistically significant.

If the P value is less than alpha, the confidence interval will not contain the
null hypothesis value.

For our example, the P value (0.031) is less than the significance level (0.05), which
indicates that our results are statistically significant. Similarly, our 95% confidence
interval does not include the null hypothesis mean of 260 and we draw the same
conclusion.

gnificance
level and confidence level work.

The significance level defines the distance the sample mean must be from the
null hypothesis to be considered statistically significant.

The confidence level defines the distance for how close the confidence limits
are to sample mean.

3.6 ONE TAILED AND TWO TAILED TESTS

The graph below displays a sampling distribution for t-values. The two shaded
regions cover the two-tails of the distribution.

Keep in mind that this t-distribution assumes that the null hypothesis is correct for the
population. Consequently, the peak (most likely value) of the distribution occurs at
t=0, which represents the null hypothesis in a t-test. Typically, the null hypothesis
states that there is no effect. As t-values move further away from zero, it represents
larger effect sizes. When the null hypothesis is true for the population, obtaining
samples that exhibit a large apparent effect becomes less likely, which is why the
probabilities taper off for t-values further from zero.

Critical Regions in a Hypothesis Test

In hypothesis tests, critical regions are ranges of the distributions where the values
represent statistically significant results. Analysts define the size and location of the
critical regions by specifying both the significance level (alpha) and whether the test
is one-tailed or two-tailed.

Consider the following two facts:

The significance level is the probability of rejecting a null hypothesis that is

correct.

The sampling distribution for a test statistic assumes that the null hypothesis is
correct.

Consequently, to represent the critical regions on the distribution for a test statistic,
you merely shade the appropriate percentage of the distribution. For the common
significance level of 0.05, you shade 5% of the distribution.
ONE TAILED TESTS

A one-tailed test is a statistical test in which the critical area of a distribution is one-
sided so that it is either greater than or less than a certain value, but not both. If the
sample being tested falls into the one-sided critical area, the alternative hypothesis
will be accepted instead of the null hypothesis. A basic concept in inferential statistics
is hypothesis testing. Hypothesis testing is run to determine whether a claim is true or
not, given a population parameter. A test that is conducted to show whether the mean
of the sample is significantly greater than and significantly less than the mean of a
population is considered a two-tailed test. When the testing is set up to show that the
sample mean would be higher or lower than the population mean, it is referred to as a
one-tailed test. The one-tailed test gets its name from testing the area under one of the
tails (sides) of a normal distribution, although the test can be used in other non-normal
distributions as well.

Before the one-tailed test can be performed, null and alternative hypotheses have to be
established. A null hypothesis is a claim that the researcher hopes to reject. An
alternative hypothesis is the claim that is supported by rejecting the null hypothesis.

A one-tailed test is a statistical hypothesis test set up to show that the sample mean
would be higher or lower than the population mean, but not both.

When using a one-tailed test, the analyst is testing for the possibility of the
relationship in one direction of interest, and completely disregarding the possibility of
a relationship in another direction.

Before running a one-tailed test, the analyst must set up a null hypothesis and an
alternative hypothesis and establish a probability value (p-value).

In the examples below, I use an alpha of 5%. Each distribution has one shaded region
of 5%. When you perform a one-tailed test, you must determine whether the critical
region is in the left tail or the right tail. The test can detect an effect only in the
direction that has the critical region. It has absolutely no capacity to detect an effect in
the other direction.

In a one-tailed test, you have two options for the null and alternative hypotheses,
which corresponds to where you place the critical region.

You can choose either of the following sets of generic hypotheses:

Example: = 67,
= 3.19.

- 67)/3.19 = - 1.82

…Consult z tabl
Example: Percentages to Z Scores

SAT Example: = 500, = 100

You find out you are at 63rd percentile

z = 33 .33

X = .33(100) + 500 = 533

Z-Table and Distribution of Means

Remember that if we use distribution of means, we

are using a sample and need to use standard error.
How do UMD students measure up on the GRE?
† = 554, = 99; M = 568, N = 90†

M = M =

Z = (M - M )/ M = (568-554) / 10.436 = 1.34

Consult z table for z …

50% + 40.99% = 90.99%

3.7.2 T-TESTS

Student's t Distribution
2
Definition. If Z ~ N(0, 1) and U (r) are independent, then the random variable:

follows a t-distribution with r degrees of freedom. We write T ~ t(r). The p.d.f.

of T is:

1(1+t2/r)(
r+1)/2

If we take a sample of n observations from a normal distribution, then the t-

distribution with degrees of freedom can be defined as the distribution of the location
of the true mean, relative to the sample mean and divided by the sample standard
deviation, after multiplying by the normalizing term . In this way, the t-distribution
can be used to estimate how likely it is that the true mean lies in any given range.

The t-distribution is symmetric and bell-shaped, like the normal distribution, but has
heavier tails, meaning that it is more prone to producing values that fall far from its
mean. This makes it useful for understanding the statistical behavior of certain types
of ratios of random quantities, in which variation in the denominator is amplified and
may produce outlying values when the denominator of the ratio falls close to zero.
The Student's t-distribution is a special case of the generalised hyperbolic distribution.
By the way, the t distribution was first discovered by a man named W.S. Gosset. He
discovered the distribution when working for an Irish brewery. Because he published
under the pseudonym Student, the t distribution is often called Student's t distribution.

The t-distribution seems to be quite similar to the standard normal distribution. Using
the formula given above for the p.d.f. of T, we can plot the density curve of
various t random variables, say when r = 1, r = 4, and r = 7, to see that that is indeed
the case:

In fact, it looks as if, as the degrees of freedom r increases, the t density curve gets
closer and closer to the standard normal curve. Let's summarize what we've learned in
our little investigation about the characteristics of the t distribution:

(1) t

(2) The probability distribution appears to be symmetric about t = 0. (It is!)

(3) The probability distribution appears to be bell-shaped. (It is!)

(4) The density curve looks like a standard normal curve, but the tails of the t-
distribution are "heavier" than the tails of the normal distribution. That is, we are
more likely to get extreme t-values than extreme z-values.

(5) As the degrees of freedom r increases, the t-distribution appears to approach the
standard normal z-distribution. (It does!)

As you'll soon see, we'll need to look up t-values, as well as probabilities

concerning T random variables, quite often in Stat . Therefore, we better make sure
we know how to read a t table.
Common Mean
Statistics
Median 0

Mode 0

Range to

Standard
Deviation
It is undefined for equal to 1 or 2.

Coefficient of Undefined
Variatio

Skewness 0. It is undefined for less than or equal to

3. However, the t distribution is symmetric
in all cases.

Kurtosis

It is undefined for less than or equal to 4.

The t distribution is used in many cases for the critical regions for hypothesis tests and
in determining confidence intervals. The most common example is testing if data are
consistent with the assumed process mean.

The t-Table:

If you take a look at following Table in the back of your text book, you'll find what
looks like a typical t table. Here's what the top of Table VI looks like (well, minus the
shading that I've added):
Example: Let T follow a t-distribution with r = 8 df. What is the probability that
the absolute value of T is less than 2.306?

Solution. The probability calculation is quite similar to a calculation we'd have to

make for a normal random variable. First, rewriting the probability in terms
of T instead of the absolute value of T, we get:

P(|T | < 2.306) = P( 2.306 < T < 2.306)

Then, we have to rewrite the probability in terms of cumulative probabilities that we

can actually find, that is:

P(|T | < 2.306) = P(T < 2.306) P(T < 2.306)

Pictorially, the probability we are looking for looks something like this:
3.7.3 CHI-SQUARE

The chi square tests in this chapter are among the most useful and most widely used
tests in statistics. The assumptions on which these tests are based are minimal,
although a certain minimum sample size is usually required. The variables which are
being examined can be measured at any level, nominal, ordinal, interval, or ratio. The
tests can thus be used in most circumstances. Besides describing these tests, we will
also discuss the chi square distribution itself. Then we will take up non parametric
APPENDIX:
 2
-E)2 /E} = 38.39
2
v = (r-1)(c-1) = (2-1)(2- 0.05 = 3.384
2
is greater than the table value. The hypothesis is rejected.
Hence quinine is useful in checking malaria.

Q.2. The figure below are (a) the frequencies of the normal distribution and (b) the
expected frequencies of the normal distribution having the same mean, standard
deviation and total frequency as in (a).

(a) : 1 12 62 220 495 792 924 792 495 220 66 12 1

(b) : 2 15 66 210 484 799 944 799 484 210 66 15 2

2 2
App test of goodness of fit. = 3.88)

5. Exercises For Practice:

3.8 ANALYSIS OF VARIANCE

The techniques of Analysis of Variance were first derived by Sir.R.Fisher. In ANOVA

testing we are dealing with comparing two population means. When more than two
experimental or fields samples are to be compared, more general method are required.
Analysis of Variance (ANOVA) is used when simultaneous comparisons are made of
measurements from more than two samples. When samples are influenced by several
kinds of effect offering simultaneously, this statistical technique is adopted to decide
which effects are important, and to estimate such effect.

The ANOVA is a procedure, which separates the variation assignable to one set of
causes from variation assignable to another set of cause. For example, four varieties of
wheat are sown in a plots and their yield per acre was recorded. We wish to test the
null hypothesis that the four varieties of wheat have same yield. This can be done by
taking all possible pairs of means and testing significance of their difference. But the
variation in yield is due to difference is in wheat seeds, fertilizers of the soil of the
various plots and the different kinds of fritzes used. Where interesting to test variation
in yields is due to differences in varieties, difference is due to fritzes or difference is in
both.

In an Anova we can estimate contributing made by each of the factor to the total
variation. Now we can split the total variation into two component (i) variation
between the samples (ii) variation within the sample. If the variance between the
sample means significantly greater the variance with in the sample, it can be
concluded that sample drawn from different population. However the total variation
may be due to experimental error and variation due to the differences in of wheat or
may be used the experimental error and the variation due to the fertilizer used.

When the data classify on the basis of variety of wheat alone it is known as one way
classification. On the other hand when we classify observation on the basis of variety
of wheat and type of fertilizer it is called two way classifications.

1. One way classification

2. Two way classification

The technique of analyzing the variance in case of one factor and two factors is
similar. In the case of one way ANOVA the total variance is divide into parts namely;
(i) variance between samples and (ii) variance with in the samples. The variance with
in the sample is also known as the residual variance. in the case of two factor analysis
the total variance divide into three parts namely (i) variance due to factor one (ii)
variance due to factor two and (iii) residual variance.

However, irrespective of three type of classification the analysis of variance is a

technique of portioning the total sum of squared deviation of all the sample
values from grand mean and is divided into two parts.

1. Sum of square between samples and

2. Sum of square with in the samples

Assumption of ANOVA

1. Population from which samples have been drawn are normally distributed

2. Population from which the samples are drawn has same variance.

3. The observation, in the sample are normally selected from the population

4. The observation is non-correlated random variables

5. Any observation is the sum of the effects of the effects of the population influencing
it.

6. The random error is normally distributed with mean 0 and Common variance 2 .
 e the mean value of each sample 1,

m the mean values of respective

samples.

the sum of squares with in the

samples,

otal obtained in the step (c) by df.

3. Calculate F ratio

Calculate F ratio

= a /
2 2
= 1 / 2

4. Compare the calculated value with F

Compare the calculated value with F within the table value of F given df at certain
critical level. If the calculated value greater than table value, it indicates the difference
in sample means are significant.

II) TWO WAY CLASSIFICATION

In one factor analysis of variance explained above the treatment constitute different
level of single factor which controlled in one experiment. However many situation in
which the response variable of interest of interest may be affected by more than one
factor. For example, sale max factor cosmetics, in addition to being affected by the
point of sale display, might be effected the price charged, the size and location of the
firm, number of competitor product in the store etc.

When it believed that two independent factor might have an effect on the response
variable in interest, it is possible to design the test so that an analysis of variance can
be used to test so that for the for the effect of two factors simultaneously. Such test is
called Two Factor Analysis of variance.

Thus with two factor analysis of variance we can two sets of hypothesis with same
data at same time. We can plan an experiment in such a way as to study the effect of
two factors in same experiment. For each factor there will be a number of classes or
levels. The procedure of Analysis of variance is somewhat different than the one way
ANOVA. The steps are follows
 0= 1 = 2 =

(b) Assume that the means of all rows are equal. Choose the hypothesis as

0= 1 = 2 =

f squares of all observations , 2/

2 2 2
1) / 1 + 2) / 2 + /
totals.
2 2 2
1) / 1+ 2) / 2 + /
column totals.

= / 1, MSR= / 1, /( 1)( 1) where C= number of column,

r= number of columns.

= / = /

n table value rejected the

null hypothesis.

3.9 SUMMARY

A hypothesis is defined as a statement about one or more populations. In order to test

a hypothesis, we follow the following steps: (i) Stating the hypothesis (ii) Identifying
the appropriate test statistic and its probability distribution (iii) Specifying the
significance level (iv) Stating the decision rule (v) Collecting the data and calculating
the test statistic (vi) Making the statistical decision (vii) Making the economic or
investment decision. The purpose of this unit is to deal with the methodology of
hypothesis testing which provides us to choose between two competing hypotheses
about the value of a population parameter. For example, one hypothesis might claim
that the wages of men and women are equal, while the alternative might claim that
men make more than women.

3.10 ANSWER TO CHECK YOUR PROGRESS

3.11 QUESTIONS AND EXERCISES

Q.1. A soap manufacturing company was distributing a particular brand of soap
through a large number of retail shops. Before a heavy campaign, the mean sales per
week per shop was 140 dozens. After the campaign a sample of 26 shops was taken
and the mean was found to be 147 dozens with standard deviation 13. Can you
consider the advertisement effective? (Ans. t=2.19)

Q.2. The average number of article produced by two machines per day are 200 and

production. Can you regard both the machines equally efficient at 1% level of
significance? (Ans. t= -4.65)

Q.3. Eleven students of class were given a test in statistics. They were given two
months special coaching and thereafter were given a second test. Marks obtained in
the two tests are given below:

Student : 1 2 3 4 5 6 7 8 9 10 11

I-Test : 23 20 19 21 18 20 18 17 23 16 19

II-Test : 24 19 22 18 20 22 20 20 23 20 18

Do the marks indicate the special coaching has benefitted the students. ( for 10
degrees of freedom at 5% level of significance, the table value of t = 2.23)
(Ans. t = 1.483)

Q.4. A manufacturer claims that at least 95% of the equipment which he supplied to a
factory conformed to the specification. An experiment of a sample of 200 piece of
equipment revealed that 18 were faulty. Test his claim at a significance level of (i) 5%
(ii) 1% (Ans. z = -2.6)

Q.5. A candidate at an election claims 90% of support of all voters in a locality.

Verify his claims if in a random sample of 400 voters from the locality, 320 supported
his candidates. Use 5% level of significance.
(Ans. z = -3.67)

Q.6. Before an increase in excise duty on tea, 400 people out of a sample of 500 were
found to be tea drinkers. After an increase in duty, 400 people were tea drinkers in a
sample of 600 people. Using standard error of proportion, state whether there is a
significant decrease in the consumption of tea.
(Ans. z = 4.81)
Q.7. In ana experiment on pea-breding Mendel obtained the following frequenciesof
seed: 315 round and yellow, 101 wrinkled and yellow, 108 round and green, 32
wrinkled and green. According to his theory of heredity the numbers should be in
proportion 9:3:3:1. Is there any evidence to doubt the theory at 5% level of
2
significance. = 0.47)

Q.8. A certain drug was administered to 456 makes put of data: 720 in a certain
locality to test its efficiency against typhoid. The incidence is shown below. Findout
the effectiveness of the drug against the disease.

Total Infection No-Infection

Admiistered the drug 456 144 312

Drug not administered 264 192 72

720 336 384

2
= 113.745)

Q.9. A study of the number of business lunches that executives in the insurance and

banking industries claim as deductible expenses per month was based on random
samples and yielded the following results: