Definition

Lets start with a definition:

Plagiarize \'pla-je-,riz also j - -\ vb -rized; -riz ing vt [plagiary] : to steal and
pass off (the ideas or words of another) as one's own : use (a created
production) without crediting the source vi: to commit literary theft: present as
new and original an idea or product derived from an existing source -
pla gia riz er n
FROM: Webster's New Collegiate Dictionary 9th ed, (Springfield, Ma:
Merriam 1981, p. 870).
What to do
Now what does this mean for you?
1. First, it is unacceptable to copy something out of a book, newspaper, journal or
any other printed source. The most blatant example of this is to directly copy
something word for word. It does not matter if it is only a phrase. If it is not
yours, either do not use it or place it in quotes and reference it. There are
different methods for doing this. The important thing is that the reader can tell
what is yours, and what is someone else's.
a. For short quotes, use quotation marks in the sentence. An example is
"CFC's: These substances are also of concern in connection with the
destruction of stratospheric ozone" [Bunce, N. Environmental
Chemistry (Winnipeg: Wuerz, 1994, p. 19)]
b. b. For longer quotes it is appropriate to indent the entire passage:
Chlorofluorocarbons, CFCs: These substances are also of concern in
connection with the destruction of stratospheric ozone (Chapter 2). Like N2O,
they have no tropospheric sinks, but are infrared absorbers. Up to 1984, the
tropospheric concentrations of three of the major commercial CFCs...
[Bunce, N. Environmental Chemistry (Winnipeg: Wuerz, 1994, p. 19)]
2. Another reason to use references is to show where you get information from.
When you state a fact, unless it is "general knowledge," you should say where
it comes from. Otherwise, a careful reader will have no way to verify your
statement. It may be subjective to decide what is "general knowledge" but keep
in mind who is your audience. As an example what is your reaction to the
statement:
Wetlands emit 150 million tons of methane each year [Bunce,
N. Environmental Chemistry (Winnipeg: Wuerz, 1994, p. 18)].
Without the reference, why should you believe me?
3. The above examples may seem obvious. If you use something word for word
it MUST be acknowledged. Things start to get a bit gray when you paraphrase.
There is one simple solution to this dilemma. DO NOT PARAPHRASE! Only
use someone else's writing when it serves a purpose. Only use someone else's
writing when you want to quote precisely what they wrote. If this is not your
goal, USE YOUR OWN WORDS.
a. This avoids any ambiguity about who wrote it. After all, you do not want
someone to accuse you of plagiarism.
b. You need to learn how to write in your own style. You may be
influenced by authors that you find clear and easy to understand, but
your writing needs to be YOUR writing. Mimicking someone else is not
a productive exercise. You just learn to cut and paste.
c. An instructor who is reading or grading your work is interested in
YOUR understanding of an idea. I am not interested in your ability to
copy explanations from the textbook. I know that the author of the book
understands it, which is why I picked the textbook. I need to know if
YOU understand it.
d. Understanding and learning is more than just replaying something you
have heard. Writing is a valuable exercise that tests your ability to
explain a topic. I often think I understand something, until I try to write
it out. This is an important part of learning.
What is citation?
A "citation" is the way you tell your readers that certain material in your work came from another
source. It also gives your readers the information necessary to find that source again, including:
1. information about the author
2. the title of the work
3. the name and location of the company that published your copy of the source
4. the date your copy was published
5. the page numbers of the material you are borrowing


Importance Of Citation
There are various reasons of plagiarism and one of the top most reasons is the improper referencing. Therefore, the need
of following proper method of citation is there and many rules and the patterns are designed to achieve this goal. Most of
the critiques believe that the first thing to avoid plagiarism is to give the proper references. There are some of the
following reasons which are making the citation important part of any intellectual work.
1. Citation is very important for the readers who have the keen interest in getting more and more information about
the related topics

2. There is a variety of information available on the Internet and many people only download the authentic
information. Therefore, in order to provide information to such people citation is very important.

3. Citation also show the efforts you made in the research and it also exhibit the originality of your research without
any plagiarism.

4. Citation gives an external support to your ideas and also increases your arguments strength.

Why should I cite sources?
Giving credit to the original author by citing sources is the only way to use other people's work
without plagiarizing. But there are a number of other reasons to cite sources:
1. citations are extremely helpful to anyone who wants to find out more about your ideas and where they came from.
2. not all sources are good or right -- your own ideas may often be more accurate or interesting than those of your
sources. Proper citation will keep you from taking the rap for someone else's bad ideas.
3. citing sources shows the amount of research you've done.
4. citing sources strengthens your work by lending outside support to your ideas.
Your reference list should appear at the end of your paper. It provides the information necessary
for a reader to locate and retrieve any source you cite in the body of the paper. Each source you
cite in the paper must appear in your reference list; likewise, each entry in the reference list must
be cited in your text.
Your references should begin on a new page separate from the text of the essay; label this page
"References" centered at the top of the page (do NOT bold, underline, or use quotation marks for
the title). All text should be double-spaced just like the rest of your essay.
Basic Rules
- All lines after the first line of each entry in your reference list should be indented one-half inch
from the left margin. This is called hanging indentation.
- Authors' names are inverted (last name first); give the last name and initials for all authors of a
particular work for up to and including seven authors. If the work has more than seven authors,
list the first six authors and then use ellipses after the sixth author's name. After the ellipses, list
the last author's name of the work.
- Reference list entries should be alphabetized by the last name of the first author of each work.
- If you have more than one article by the same author, single-author references or multiple-
author references with the exact same authors in the exact same order are listed in order by the
year of publication, starting with the earliest.
- Capitalize all major words in journal titles.
- When referring to books, chapters, articles, or Web pages, capitalize only the first letter of the
first word of a title and subtitle, the first word after a colon or a dash in the title, and proper
nouns. Do not capitalize the first letter of the second word in a hyphenated compound word.
- Italicize titles of longer works such as books and journals.
- Do not italicize, underline, or put quotes around the titles of shorter works such as journal
articles or essays in edited collections.
- Please note: While the APA manual provides many examples of how to cite common types of
sources, it does not provide rules on how to cite all types of sources. Therefore, if you have a
source that APA does not include, APA suggests that you find the example that is most similar to
your source and use that format. For more information, see page 193 of the Publication Manual
of the American Psychological Association, sixth edition
A problem statement is a concise description of the issues that need to be addressed by a
problem solving team and should be presented to them (or created by them) before they try to
solve the problem. When bringing together a team to achieve a particular purpose provide them
with a problem statement. A good problem statement should answer these questions:
1. What is the problem? This should explain why the team is needed.
2. Who has the problem or who is the client/customer? This should explain who needs the
solution and who will decide the problem has been solved.
3. What form can the resolution be? What is the scope and limitations (in time, money,
resources, technologies) that can be used to solve the problem? Does the client want a
white paper? A web-tool? A new feature for a product? A brainstorming on a topic?
The primary purpose of a problem statement is to focus the attention of the problem solving
team. However, if the focus of the problem is too narrow or the scope of the solution too limited
the creativity and innovation of the solution can be stifling.
In project management, the problem statement is part of the project charter. It lists what's
essential about the project and enables the project manager to identify the project scope as well
as the project stakeholders.
[1]

A research-worthy problem statement is the description of an active challenge (i.e. problem)
faced by researchers and/or practitioners that does not have adequate solutions available
including the argumentation for its viability based on solid peer-reviewed sources as well as
theoretical foundation. The research-worthy problem statement should address all six
questions: what, how, where, when, why, and who. On the other hand, a statement of the
problem is one or two sentences claim that outlines the problem that the study addresses. The
statement of the problem should briefly address the question: What is the problem that the
research will address
Hypotheses
An hypothesis is a specific statement of prediction. It describes in concrete (rather than
theoretical) terms what you expect will happen in your study. Not all studies have hypotheses.
Sometimes a study is designed to be exploratory (see inductive research). There is no formal
hypothesis, and perhaps the purpose of the study is to explore some area more thoroughly in
order to develop some specific hypothesis or prediction that can be tested in future research. A
single study may have one or many hypotheses.
Actually, whenever I talk about an hypothesis, I am really thinking simultaneously about two
hypotheses. Let's say that you predict that there will be a relationship between two variables in
your study. The way we would formally set up the hypothesis test is to formulate two hypothesis
statements, one that describes your prediction and one that describes all the other possible
outcomes with respect to the hypothesized relationship. Your prediction is that variable A and
variable B will be related (you don't care whether it's a positive or negative relationship). Then
the only other possible outcome would be that variable A and variable B are not related. Usually,
we call the hypothesis that you support (your prediction) the alternative hypothesis, and we call
the hypothesis that describes the remaining possible outcomes the null hypothesis. Sometimes
we use a notation like H
A
or H
1
to represent the alternative hypothesis or your prediction, and H
O

or H
0
to represent the null case. You have to be careful here, though. In some studies, your
prediction might very well be that there will be no difference or change. In this case, you are
essentially trying to find support for the null hypothesis and you are opposed to the alternative.
A Research design is concerned with turning a research question into a testing project. The best
design depends on the research questions. Every design has its positive and negative sides. The
research design has been considered a "blueprint" for research, dealing with at least four
problems: what questions to study, what data are relevant, what data to collect, and how to
analyze the results.
[1]

Research design can be divided into fixed and flexible research designs (Robson, 1993). Others
have referred to this distinction with quantitative research designs and qualitative research
designs. However, fixed designs need not be quantitative, and flexible design need not be
qualitative. In fixed designs the design of the study is fixed before the main stage of data
collection takes place. Fixed designs are normally theory-driven; otherwise its impossible to
know in advance which variables need to be controlled and measured. Often these variables are
quantitative. Flexible designs allow for more freedom during the data collection. One reason for
using a flexible research design can be that the variable of interest is not quantitatively
measurable, such as culture. In other cases, theory might not be available before one starts the
research.
Contents
[hide]
- 1 Examples of fixed (quantitative) designs
o 1.1 Experimental design
o 1.2 Non-experimental research designs
o 1.3 Quasi experiment
- 2 Examples of flexible (qualitative) research designs
o 2.1 Case study
o 2.2 Ethnographic study
- 3 References
[edit] Examples of fixed (quantitative) designs
[edit] Experimental design
See also Design of experiments.
In an experimental design, the researcher actively tries to change the situation, circumstances or
experience of participants (manipulation), which may lead to a change in behaviour of the
participants of the study. The participants are (randomly) assigned to different conditions, and
variables of interest are measured. The researcher tries to keep the other variables as similar as
possible. Experiments are normally highly fixed before the data collection starts. In a good
research design, a few things are of great importance. First of all, it is necessary to think of a
proper way to operationalise the variables that you want to measure. Do you want to measure
your variable with a questionnaire? Do you measure it physically? Secondly, the statistical
analysis has to be taken into account. What are your expectations? How do you want to analyse
this? Thirdly, in a design you have to think of the practical limitations. Can you find enough
participants for your study? Are the participants that you want to include in your study
representative for the population? The most important thing is that when you want to execute a
good research, you think of all these questions beforehand (Adr, Mellenbergh & Hand, 2008).
Read more about experiental research designs here Experiment.
[edit] Non-experimental research designs
Non-experimental research is almost the same as experimental research, the only difference is
that non-experimental research does not involve a manipulation of the situation, circumstances or
experience of the participants. Non-experimental research designs can be split up in three
designs. First, relational designs, in which a range of variables is measured. These designs are
also called correlational studies, since the correlation is most often used analysis. The second
type is comparative designs. These designs compare two natural groups. The third type of non-
experimental research is a longitudinal design. See Longitudinal study.]
[edit] Quasi experiment
Quasi research designs are research design that follow the experimental procedure, but do not
randomly assign people to (treatment and comparison) groups. See Quasi-experiment and natural
experiment for more details.
[edit] Examples of flexible (qualitative) research designs
[edit] Case study
In a case study, one single unit is extensively studied. that can be a case of a person,
organization, group or situation. Famous case studies are for example the descriptions about the
patients of Freud, who were thoroughly analysed and described. Read more on case study. Bell
(1999) states a case study approach is particularly appropriate for individual researchers
because it gives an opportunity for one aspect of a problem to be studied in some depth within a
limited time scale.
[edit] Ethnographic study
This type of research is involved with a group, organization, culture, or community. Normally
the researcher shares a lot of time with the group. Read more on Ethnography.
by Janet Waters
Planning the Observation:
Plan as much as you can before you begin your observation. Choose the age group, (e.g. a
particular child, adolescent or adult), or a behaviour setting (e.g. a playground, school or home).
Then choose a topic which you wish to observe. Before the observation, read about the topic you
are studying (the applicable chapter in your text), & plan your observations. Think about the
behaviours you will be looking for that are within your topic area. You may wish to prepare a
checklist of target behaviours within your topic in advance. (Make sure you leave a column titled
"misc" for behaviours you hadn't anticipated). Also, check that your audio/video recorder, if you
will be allowed to use one, is working properly.
Guidelines for Conducting the Observation: Some guidelines for carrying out an observation:
Be unobtrusive: Because people behave differently in the presence of others, it's important to
make sure your participants don't notice you. If observing children, & you can't remain unseen,
you may wish to spend some time before the observation sitting quietly in a corner to allow the
children to get used to your presence. (If a child tries to engage you in conversation, you could
explain you are doing some work, & can't play or talk now).
Be objective: Your language should be clear, accurate, & formal. Focus on the behaviour, not on
your interpretation of it. Keep your language objective, avoid hyperbole or descriptive language,
which may exaggerate the behaviour or mislead the reader. For example, "the kids were
bouncing off the walls" would be overly descriptive, as well as vague. A better description would
be: "The children were excited; two boys were energetically chasing each other, while two of the
other children were wrestling and shouting."
Be specific: Your observations should describe behaviour as specifically as possible.
Generalities are vague & don't give a clear picture. For example, an observation that "the five
children were each engaged in gender biased behaviour" is too general, it doesn't specifically
identify what the children were doing. "As the observation began, two of the three girls were
sitting quietly at the crafts table, while the third girl pretended to cook dinner in the play kitchen.
All three boys were building a fort with large wooden blocks." This gives a more accurate
picture to your reader of the specific behaviours you are typing as "gender-biased".
Be scientific: Your observations should be accurate; they should be thorough & complete; &
should include nothing but your observations. (That is, unless you observed it, avoid speculations
about the possible sugar consumption that may have preceded the children's excitement).
Beginning the Observation:
As you begin your observation, record the following:
Setting: Describe the setting (e.g. in the kitchen of the child's home). Indicate roughly what the
setting was like, size, facilities, number of people. In other words, include anything that might
have an influence on the behaviour you are going to observe.
On-going Action: Indicate what is happening, & who is involved in the action at the time you
begin your observation.
Description of the child: Describe the child or children, indicating their number, age and
gender, & any notable features (e.g. disabilities). You will include the description of your setting
& your participants in the Method section of the research report.
During your observation:
Record as full a description of the child's or children's behaviour & responses to that behaviour
as possible. It's a good idea to make notes every thirty seconds, even if you are recording with
video or audio equipment. You can use your prepared checklist, or write a narrative of the
behaviour - you can invent your own shorthand for notes during the observation, then expand on
your shorthand notes as you transcribe the notes soon after. Be as thorough & complete as
possible.
Analyzing the Observation:
Once you have finished the observation, you will have to make some sense of your data, &
present your results in the Results section of your report. If you had a checklist, you would total
the columns & present the totals for each variable (or type of behaviour) in a table form. You
may wish to convert these totals into percentages in some cases. If you are typing behaviour into
a stage or category according to a theory (e.g. Piaget's cognitive development, or Kohlberg's
moral development), list the behaviours that typify each category or stage, & identify why you
think so. Then present these in a table. If you have a narrative, you would code it for specific
behavioural patterns or themes, total these, & present them in a table.
As an example, you are interested in observing child-initiated interactions with an adult. You
have a good narrative record of your observations of all the child-initiated interactions that took
place within the hour's observation. You could then code your observations according to the
following criteria, then total each type and present in a table:
I: Child Approaches to Adult - a) type of approach: P (physically), V (verbally), O (Other
e.g. body language, eye gaze, etc).
b) content of child's approach: includes the following subcategories: request to adult; question;
wants to show adult something; wants to involve adult in play; expression of emotion or physical
state; aggression; complaint; etc. (List as many types as you find).
c) valence of approach: + (positive), - (negative), n (neutral).
d) intensity of approach: quiet vs loud, etc.
II: Response by Adult to Child: a) type of response: as above
b) content of adult response: includes the following subcategories: complies with request;
answer to question; expression of empathy; reprimand/ discipline; etc. (List as many types as you
find).
c) valence of response: + (adult responds verbally, smiles, picks up child, etc.); negative - (adult
refuses child's approach verbally or non-verbally); n (neutral - approach not noticed or ignored).
d) intensity of response: as above
III: Response by Child to Adult's Response: as above.
Sampling Plan
1. How big should a sample be?
It is frequently a matter of concern as to the size of a sample drawn, and the notion is that if the
sample size is not "large enough", the sampling results are likely to be inaccurate.
"It is sometimes presumed that a sample should be based on some agreed percentage of the
population from which it is taken. The view that there is a constant percentage, often thought to
be around 10 per cent, which can be applied when sampling populations of all kinds and sizes is
quite wrong". (Ref. Chisnall, Peter M., Marketing Research, Maidenhead, UK, McGraw-Hill,
1986)
Some researchers base the sample size on the margin of error that can be tolerated or the
precision required of estimates. However, most survey studies are designed to make a variety of
estimates - not just a single estimate. It is also highly improbable that a researcher can specify the
acceptable margin of error in advance. (Ref. Fowler, Jr., Floyd J. Survey Research Methods -
Applied Social Research Methods Series - Volume 1. California: 1984)
In general, the sample size decision must be made on a case-by-case basis, considering the
variety of goals to be achieved by a particular study and taking into account numerous other
aspects of the research design. The size of a sample depends upon the basic characteristics of the
population. If there is complete homogeneity, a sample size of 1 would be sufficient, while a
larger sample is obviously required where the required characteristics display wide
heterogeneity.
One of the ways of dealing with heterogeneity is to break the population into sub-groups or
strata, which display homogeneity among the sample units. This is known as stratified (random)
sampling, which is statistically more efficient than simple random sampling. However, strictly
speaking, we need a sample frame such as a list of all students in a college from which to draw a
sample. Where we are sampling from a very much larger population, as in say, a city, we require
a complete list of all the households in the city from which to randomly select a given sample,
subject to certain characteristics such as age, income etc., which might be set as "quotas". It is
also necessary to ensure that the smallest sub-group or stratum should contain "sufficient"
sampling units so that accurate and reliable estimates can be found of the population stratum.
"Samples in the US range from 1500 to 2000 for national surveys, unless minority sub-sampling
is involved when larger samples would be used. In the UK, national surveys of housewives
buying habits are frequently about 2000, and this figure is also relevant for Europe". (Chisnall,
ibid)"
The error of the sample is inversely proportional to the square root of the sample size. This
means that although a sample of 8000 is four times as large as a sample of 2000, it can only be
twice as accurate, since the square root of 4 is 2.
The important fact to remember is that a sample size is a balancing act between precision (or
reliability) and cost of the survey.
Daniel and Terrel have suggested a formula for calculation of sample size when we have a fixed
budget for a sample study. (See Daniel, Wayne W., and Terrel, James C., BUSINESS
STATISTICS for Management and Economics, Boston, USA, 1992 Houghton Mifflin)
The budget represents the total cost C for a sampling study, which can be broken into two parts -
the fixed cost C
f
and the variable cost per sampling unit, C
u
.
The sample size n is given by the formula:

Let us assume that the budget available for a sample survey is Rs.800,000; the cost per
questionnaire charged by the Market Research firm is Rs.150, and the fixed costs associated with
the study (mainly supervision and management costs) are Rs.1,50,000. Then we have:

from which we find that the required sample size

Use natural and familiar language
Use language that is understandable to the type of respondents whom you are targeting. Consider
the age of your respondents, their educational level, and any other relevant cultural
characteristics of your respondents when deciding how to phrase your questions.
Types of Survey Questions
Survey questions vary according to what type of information they are trying to collect from the
respondents, and how this information will apply to the goals of the survey. There are two basic
types of survey questions: Open-ended and Closed-ended.
Open-ended
This type of question allows participants to respond in any way they choose. Open-ended
questions provide primarily qualitative data, and are frequently used in exploratory research.
Example
What is your current marital status?
A: [Participants provide answers in their own words]
Closed-ended
In contrast to open-ended questions, closed-ended questions require participants to choose from a
limited number of responses predetermined by the researcher. There are 5 basic types of closed-
ended questions: Multiple-choice; Categorical; Likert-scale; Numerical; and Ordinal. Closed-
ended questions provide primarily quantitative data, and are frequently used in confirmatory
research.
Multiple Choice

Use a multiple-choice question when you want your respondents to choose the best possible
answer among all options presented.
Example

What is your current marital status? (Select one.)
Single
Married
Divorced
Separated
Widowed
Categorical

Use a categorical question when the possible answers are categories, and the respondent must
belong to one category.
Example

What is your gender?
Male
Female
Likert-Scale

Use a Likert-scale question when you are trying to determine respondents attitudes or feelings
about something.
Example

How important do you think SAT scores are to a college students success? (select one):
Not very important 1 2 3 4 5 Extremely important
Ordinal

Sometimes you may want your respondents to rank order their responses. A ranking indicates the
importance assigned by a participant to an attitudinal object.
Example

Please rank the importance of the following qualities in a team leader. (Please fill in your rank
order in the spaces provided using the numbers 1 through 5)
A team leader that is sincere
A team leader that gets resources for the team
A team leader that is an advocate for the team
A team leader that is a strong disciplinarian
A team leader that is a good motivator
Numerical

When the answer must be a number, ask a numerical question.
Example

What is your current age? (select one)
Less than 18
18 to 29
30 to 39
40 to 49
50 or older
Remember: How you develop your questions depends on why you are conducting your survey,
and how you plan to apply the data from your survey to your survey problem. Educate yourself
on the various types of survey questions, and what purpose they serve before developing
questions for your own survey project.
Field Survey
Ashley Bowers
Field Survey The term field is used in survey research to refer to the geographical setting where
data collection takes place. Typically this refers to in-person interviewing and thus the name,
field survey. One of the key decisions when designing a survey is the choice of the mode of data
collection. Field interviewing is one of three traditional modes of survey data collection (along
with telephone and mail). In field surveys, which are also referred to as face-to-face or personal-
visit surveys, an interviewer visits the respondent's home or office (or another location) and
conducts the interview. This entry outlines the major advantages and disadvantages of field data
collection and the variations that are found in modern survey research and concludes with a brief
overview of the development of present-day field surveys. Field surveys have several advantages
over other modes of data collection. Lengthy,...
A research library is a library which contains an in-depth collection of material on one or
several subjects (Young, 1983; p.188). A research library will generally include primary sources
as well as secondary sources. Large university libraries are considered research libraries, and
often contain many specialized branch research libraries.
Research libraries can be either reference libraries, which do not lend their holdings, or lending
libraries, which do lend all or some of their holdings. Some extremely large or traditional
research libraries are entirely reference in this sense, lending none of their material; most
academic research libraries, at least in the U.S., now lend books, but not periodicals or other
material
Statistical hypothesis testing
From Wikipedia, the free encyclopedia
This article is about frequentist hypothesis testing which is taught in introductory statistics. For Bayesian
hypothesis testing, see Bayesian inference.
A statistical hypothesis test is a method of making decisions using data, whether from a
controlled experiment or an observational study (not controlled). In statistics, a result is called
statistically significant if it is unlikely to have occurred by chance alone, according to a pre-
determined threshold probability, the significance level. The phrase "test of significance" was
coined by Ronald Fisher: "Critical tests of this kind may be called tests of significance, and when
such tests are available we may discover whether a second sample is or is not significantly
different from the first."
[1]

Hypothesis testing is sometimes called confirmatory data analysis, in contrast to exploratory
data analysis. In frequency probability, these decisions are almost always made using null-
hypothesis tests (i.e., tests that answer the question Assuming that the null hypothesis is true,
what is the probability of observing a value for the test statistic that is at least as extreme as the
value that was actually observed?)
[2]
One use of hypothesis testing is deciding whether
experimental results contain enough information to cast doubt on conventional wisdom.
A result that was found to be statistically significant is also called a positive result; conversely, a
result that is not unlikely under the null hypothesis is called a negative result or a null result.
Statistical hypothesis testing is a key technique of frequentist statistical inference. The Bayesian
approach to hypothesis testing is to base rejection of the hypothesis on the posterior
probability.
[3]
Other approaches to reaching a decision based on data are available via decision
theory and optimal decisions.
The critical region of a hypothesis test is the set of all outcomes which cause the null hypothesis
to be rejected in favor of the alternative hypothesis. The critical region is usually denoted by the
letter C.
General Description
There are two types of statistical inferences: estimation of population parameters and hypothesis
testing. Hypothesis testing is one of the most important tools of application of statistics to real
life problems. Most often, decisions are required to be made concerning populations on the basis
of sample information. Statistical tests are used in arriving at these decisions.
There are five ingredients to any statistical test :
(a) Null Hypothesis
(b) Alternate Hypothesis
(c) Test Statistic
(d) Rejection/Critical Region
(e) Conclusion
In attempting to reach a decision, it is useful to make an educated guess or assumption about the
population involved, such as the type of distribution.
Statistical Hypotheses : They are defined as assertion or conjecture about the parameter or
parameters of a population, for example the mean or the variance of a normal population. They
may also concern the type, nature or probability distribution of the population.
Statistical hypotheses are based on the concept of proof by contradiction. For example, say, we
test the mean () of a population to see if an experiment has caused an increase or decrease in .
We do this by proof of contradiction by formulating a null hypothesis.
Null Hypothesis : It is a hypothesis which states that there is no difference between the
procedures and is denoted by H
0
. For the above example the corresponding H
0
would be that
there has been no increase or decrease in the mean. Always the null hypothesis is tested, i.e., we
want to either accept or reject the null hypothesis because we have information only for the null
hypothesis.
Alternative Hypothesis : It is a hypothesis which states that there is a difference between the
procedures and is denoted by H
A
.
Table 1. Various types of H0 and HA
Case Null Hypothesis H
0 Alternate Hypothesis H
A
1
1
=
2

1
`
2

2
1
<
2

1
>
2

3
1
>
2

1
<
2

Test Statistic : It is the random variable X whose value is tested to arrive at a decision. The
Central Limit Theorem states that for large sample sizes (n > 30) drawn randomly from a
population, the distribution of the means of those samples will approximate normality, even
when the data in the parent population are not distributed normally. A z statistic is usually used
for large sample sizes (n > 30), but often large samples are not easy to obtain, in which case the
t-distribution can be used. The population standard deviation o is estimated by the sample
standard deviation, s. The t curves are bell shaped and distributed around t=0. The exact shape on
a given t-curve depends on the degrees of freedom. In case of performing multiple comparisons
by one way Anova, the F-statistic is normally used.It is defined as the ratio of the mean square
due to the variability between groups to the mean square due to the variability within groups.
The critical value of F is read off from tables on the F-distribution knowing the Type-I error
oand the degrees of freedom between & within the groups.
Rejection Region : It is the part of the sample space (critical region) where the null hypothesis
H
0
is rejected. The size of this region, is determined by the probability (o) of the sample point
falling in the critical region when H
0
is true. o is also known as the level of significance, the
probability of the value of the random variable falling in the critical region. Also it should be
noted that the term "Statistical significance" refers only to the rejection of a null hypothesis at
some level o.It implies only that the observed difference between the sample statistic and the
mean of the sampling distribution did not occur by chance alone.
Conclusion : If the test statistic falls in the rejection/critical region, H
0
is rejected, else H
0
is
accepted.
Go to Table of Contents

Types of Tests
Tests of hypothesis can be carried out on one or two samples. One sample tests are used to test if
the population parameter () is different from a specified value. Two sample tests are used to
detect the difference between the parameters of two populations (
1
and
2
).
Two sample tests can further be classified as unpaired or paired two sample tests. While in
unpaired two sample tests the sample data are not related, in paired two sample tests the sample
data are paired according to some identifiable characteristic. For example, when testing
hypothesis about the effect of a treatment on (say) a landfill, we would like to pair the data taken
at different points before and after implementation of the treatment.
Both one sample and two sample tests can be classified as :
One tailed test : Here the alternate hypothesis H
A
is one-sided and we test whether the test
statistic falls in the critical region on only one side of the distribution.
1. One sample test: For example, we are measuring the concentration of a lake and we need
to know if the mean concentration of the lake is greater than a specified value of 10mg/L.
Hence, H
0
: ` 10 mg/L, vs, H
A
: > 10 mg/L.
2. Two sample test: In Table1, cases 2 and 3 are illustrations of two sample, one tailed tests.
In case 2 we want to test whether the population mean of the first sample is lesser than
that of the second sample.
Hence, H
0
:
1
`
2
, vs, H
A
:
1
<
2
.
Two tailed test : Here the alternate hypothesis H
A
is formulated to test for difference in either
direction, i.e., for either an increase or a decrease in the random variable. Hence the test statistic
is tested for occurrence within either of the two critical regions on the two extremes of the
distribution.
1. One sample test: For the lake example we need to know if the mean concentration of the
lake is the same as or different from a specified value of 10 mg/L.
Hence, H
0
: ` 10 mg/L, vs, H
A
: = 10 mg/L.
2. Two sample test: In Table 1, case 1 is an illustration of a two sample two tailed test. In
case 1 we want to test whether the population mean of the first sample (
1
) is the same as
or different from the mean of the second sample (
2
).
Hence H
0
:
1
=
2
, vs, H
A
:
1
`
2
.
Given the same level of significance the two tailed test is more conservative, i.e., it is more
rigorous than the one-tailed test because the rejection point is farther out in the tail. It is more
difficult to reject H
0
with a two-tailed test than with a one-tailed test.
The diagram associated with the link illustrates the critical region(s) for one and two tailed tests.

one and two tailed tests

Go to Table of Contents

Error
When using probability to decide whether a statistical test provides evidence for or against our
predictions, there is always a chance of driving the wrong conclusions. Even when choosing a
probability level of 95%, there is always a 5% chance that one rejects the null hypothesis when it
was actually correct. This is called Type I error, represented by the Greek letter o.
It is possible to err in the opposite way if one fails to reject the null hypothesis when it is, in fact,
incorrect. This is called Type II error, represented by the Greek letter |. These two errors are
represented in the following chart.
Table 2. Types of error
Type of decision H
0
true H
0
false
Reject H
0
Type I error (o) Correct decision (1-|)
Accept H
0
Correct decision (1-o) Type II error (|)
A related concept is power, which is the probability of rejecting the null hypothesis when it is
actually false. Power is simply 1 minus the Type II error rate, and is usually expressed as 1-|.
When choosing the probability level of a test, it is possible to control the risk of committing a
Type I error by choosing an appropriate o.
This also affects Type II error, since they are are inversely related: as one increases, the other
decreases. To appreciate this in a diagram, follow this link:

Choice of o

There is little control on the risk of committing Type II error, because it also depends on the
actual difference being evaluated, which is usually unknown. The following link leads to a
diagram that illustrates how at a fixed o value, the | value changes according to the actual
distribution of the population:

Changes in |

The consequences of these different types of error are very different. For example, if one tests for
the significant presence of a pollutant, incorrectly deciding that a site is polluted (Type I error)
will cause a waste of resources and energy cleaning up a site that does not need it. On the other
hand, failure to determine presence of pollution (Type II error) can lead to environmental
deterioration or health problems in the nearby community.
Go to Table of Contents

Steps in Hypothesis Testing
1

Identify the null hypothesis H
0
and the alternate hypothesis H
A
.

2

Choose o. The value should be small, usually less than 10%. It is important to
consider the consequences of both types of errors.

3

Select the test statistic and determine its value from the sample data. This value is
called the observed value of the test statistic. Remember that a t statistic is usually
appropriate for a small number of samples; for larger number of samples, a z
statistic can work well if data are normally distributed.

4

Compare the observed value of the statistic to the critical value obtained for the
chosen o.

5

Make a decision.
If the test statistic falls in the critical
region:

Reject H
0
in favour of H
A
.
If the test statistic does not fall in the
critical region:

Conclude that there is not enough evidence to reject H
0
.
Go to Table of Contents

Practical Examples
A) One tailed Test
An aquaculture farm takes water from a stream and returns it after it has circulated through the
fish tanks. The owner thinks that, since the water circulates rather quickly through the tanks,
there is little organic matter in the effluent. To find out if this is true, he takes some samples of
the water at the intake and other samples downstream the outlet, and tests for Biochemical
Oxygen Demand (BOD). If BOD increases, it can be said that the effluent contains more organic
matter than the stream can handle.
The data for this problem are given in the following table:
Table 3. BOD in the stream
One tailed t-test :
Upstream Downstream
6.782 9.063
5.809 8.381
6.849 8.660
6.879 8.405
7.014 9.248
7.321 8.735
5.986 9.772
6.628 8.545
6.822 8.063
6.448 8.001

1. A is the set of samples taken at the intake; and B is the set of samples taken downstream.
o H
0
:
B
<
A

o H
A
:
B
>
A

2. Choose an o. Let us use 5% for this example.
3. The observed t value is calculated
4. The critical t value is obtained according to the degrees of freedom
The resulting t test values are shown in this table:
Table 4. t-Test : Two-Sample Assuming Equal Variances

Upstream Downstream
Mean 6.6539 8.6874
Variance 0.2124 0.2988
Observations 10 10
Pooled Variance 0.2556

Hypothesized Mean Difference 0

Degrees of freedom 18

t stat -8.9941

P(T<t) one-tail 2.22 x 10
-08


t Critical one-tail 1.7341

P(T<t) two-tail 4.45 x 10
-08


t Critical two-tail 2.1009


5) Make a decision.... Is the effluent polluting the stream? See Answer
B) Two tailed Test
Let us asume that an induced bioremediation process is being conducted at a contaminated site.
The researcher has obtained good cleanup rates by injecting a mixture of nutrients into the soil in
order to maintain an abundant microbial community. Someone suggests using a cheaper mixture.
The researcher tries one patch of land with the new mixture, and compares the degradation rates
to those obtained from a patch treated with the expensive one to see if he can get the same
degradation rates.
The data for this problem are shown in the following table: