You are on page 1of 17

Writing a hypothesis

1. Introduction
2. Origin of the word “Hypothesis”
3. Definitions of hypothesis
4. Characteristics of hypothesis
5. The functions of hypothesis
6. Types of hypothesis
7. Research variables and their types
8. How to write a hypothesis
9. Errors in hypothesis
10. How we test the hypothesis statistically
11. The difference between hypothesis and thesis statement
12. The difference between qualitative and quantitative
research
13. Summary

1. Introduction

meaning "to put under" or "to suppose". good hunch – assumed for use in devising theory or planning experiments intended to be given a direct experimental test when possible”. 1994)  Creswell(1994) states that a research question is essentially a hypothesis asked in the form of a question. Turabian(2007) states that to start a storyboard.”(Creswell. stated objectives or Hypothesis(Perrin. 2. we have to state at the top of its first page our question and working hypothesis as exactly as we can. The English word hypothesis comes from the ancient Greek word ὑπόθεσις. hypothesis provides clarity so that we can focus on a research problem. It is a . The significance of a hypothesis lies in its ability to bring direction to our research work. (Kerlinger. even we have only one or two. we have to present our ideas in one of three alternative ways: thesis statements. It is always good to construct a hypothesis as it will help to narrow down our focus of research. One of the most important considerations when beginning our research work and formulating the research problem is constructing the hypothesis. ( Hilborn:1997) 3. Generally. (Eric Rogers. 1956)  “Hypothesis is a formal statement that presents the expected relationship between an independent and dependent variable. Definitions of hypothesis  “Hypothesis is a single tentative guess. We have to put at the top of separate pages each reason that might support our best hypothesis. 1966)  “A hypothesis is a conjectural statement of the relation between two or more variables”. Origin of the word “Hypothesis” A hypothesis (plural hypotheses) is a proposed explanation for a phenomenon. 2012). To clarify the central goal of our writing.

yet.”(Sarantakos. Formulating a hypothesis that cannot be verified will lead to nowhere.  “A hypothesis can be defined as a tentative explanation of the research problem.”(Macleod Clark J and Hockey L 1981)  “Hypothesis is written in such a way that it can be proven or disproven by valid and reliable data. or a guess about the research outcome.”  “An hypothesis is a statement or explanation that is suggested by knowledge or observation but has not. we can see that a hypothesis is based on a tentative proposition and its validity is unknown. However. Characteristics of hypothesis As researchers. There must be techniques to verify our hypothesis. tentative prediction about the nature of the relationship between two or more variables. a possible outcome of the research.” Grinnell (1988) From these definitions. Turabian(2007) mentions that working hypothesis need not to close our mind to a better one. A working hypothesis is a risk only if it blinds us to a better one or if we cannot give it up when the evidence says we should. been proved or disproved. we should keep in mind some important considerations when constructing a hypothesis for our research work such as: (a) A Hypothesis must be capable of verification In our research work. in some cases. 4. there must be methods and techniques used for data collection and analysis. 1993)  “Hypothesis is always in declarative sentence form which relates variable to another variable. researchers may .

This criterion can only be achieved if the hypothesis has its foundation in existing knowledge. we need to equip ourselves well in the literature review of our subject area. Enhance the objectivity and purpose of a research work. The functions of hypothesis A hypothesis has several functions: 1. (b) A Hypothesis Needs to be Precise. 2. Why do you think so? Your reasons are the general statements that you offer to support your answers: Well. the stories distorted facts to emphasize what become . develop new techniques to verify their hypotheses during the research process. hence providing focus on the study. Help a researcher in designing data collection. Enable the formulation of theory for a researcher to specifically conclude what is true and what is not. first. and your friend asks. Indicate the type of the research design. Simple and Specific To be able to develop a good hypothesis. 4. 5. (b) A Hypothesis must be Related to the Existing Body of Knowledge. 6. Provide a research with focus and tells a researcher the specific scope of a research problem to investigate. You say. 5. 3. Provide clarity to the research problem and research objectives. Imagine explaining your project to a friend. 7. This is crucial in academic research methodology. You must ensure that the hypothesis we construct emerges from an existing body of knowledge and adds to it. The hypothesis should be able to test one relationship at a time. Direct the research study process. I want to show that Alamo stories helped develop a unique Texan identity.

the story were first used to show that Texas (and the Wild West) was a new kind of frontier.2007) Each reason needs support.central to Texan identity. (Turabian. A list of reasons. second. is the best framework to guide our research and focus our thinking and certainly better than no reason at all. Types of hypothesis . so for each reason.……and so on. third. ask why do I think that? What evidence will I need to prove it? That will help us focus our search for evidence. no matter how speculative. 6.

.

1 Research hypothesis 6. For example: Two hourly positions.1. The statement shows that there exists a relationship between 2 hourly positioning and bedsore prevention. there exist a relationship between the independent variable and dependent variable.1 simple hypothesis predicts that. .changing of a fully bedridden patient will prevent bedsore. In the above example 2 hourly position changing is independent variable and bedsore prevention is dependent variable.6.

the independent variable is the experimental or treatment variable.1. 6. For example: . B) building up of body resistance.1.6. B) 2 hourly back care.4 Causal Hypothesis predicts a cause and effects relationship or interaction between the independent variable and dependent variable. three independent variable are:- A) 2 hourly position changing. In this hypothesis. And three dependent variable are: A) promotion of blood circulation. 6.2 Complex Hypothesis predicts that there exists relationship between two or more independent and dependent variable. In the above example. For example: Teacher student relationship influence student’s learning. This hypothesis predicts the effect of the independent variable on the dependent variable. 6. C) prevention of bed sore.3 Non -directional Hypothesis predicts the relationship between the independent variable and the dependent variable but does not specific the directional of the relationship. High quality of nursing education will lead to high quality of nursing practice skills.1. will promote blood circulation and will prevent bedsore.2 Directional Hypothesis predicts the direction of the relationship between the independent and dependent variable. C) high protein diet. The dependent variable is the outcome variable . 2 hourly back care and a high protein diet will build up body resistance. For example: For a fully bed ridden patent 2 hourly position changing. For example.1.

5 Associative Hypothesis predicts an associative relationship between the independent variable and the dependent variable. The null hypothesis predicts that. . there is no relationship between the independent variable and dependent variable.2. dyspnea. In the above example. alcoholism. mumps or chicken pox. For example: Nasogastric tube feeding does not alter body temperature.3 Causal null Hypothesis For example: High intake of fluid does not cause tissue oedema. 6. 6.2 Null Hypothesis is called statistical hypothesis because this type of hypothesis is used for statistical testing and statically interpretation. The associative relationship between the independent and dependent variables may have either Positive association or negative association. 6.2.1. the independent variable that is. bed rest does not have any causal relationship with the dependent variable that is. have no relationship in the occurrence of malaria. drug abuse. When there is a change in any one of the variables. Early postoperative ambulation will lead to prompt recovery. 6.1 Simple null hypothesis For example: Bed rest will not relives dyspnea. tobacco use etc.2 Complex null Hypothesis For example: smoking. changes also occurs in the other variable. 6.2.

7. that is. etc.2. For example. behaviors. properties. tissue oedema.3 The testable hypothesis predicts relationship between the independent variable and the dependent variable and theses variable are testable or measurable. situations. Research variables and their types They are defined as qualities. attributes etc. characteristics.1 Independent variable is the quality or property that can be manipulated by the researcher to cause an effect on the dependent .4 Associative null Hypothesis For example: Increased does in antibiotics will not reduce body temperature. 6. activities. high fluid intake does not have any causal relationship with the dependent variable such as. objects. 7. Increase in patient’s body temperature causes increase in patient’s pulse rate. the independent variable. whether individuals or group. of people. 6.In the above example.

2 Dependent variable is the quality or property or behavior or outcome that the researcher predicts and that occurs in response to the manipulation. patient’s state of anxiety may be increased. administration by face mask cause an effect on the dependent variable.3 Extraneous variables exist in all type of research studies but the researcher does not include them for the research purpose. For examples: O2 administration to a highly nervous patient by a face mask instead of a nasal canula will cause less anxiety to the patient. It is also called experimental variable or treatment variable. the independent variable that is methods of O2. that is patient’s state of anxiety. experimentation or treatment of the independent variable. 7. In this the independent variable that is methods of O2 administration is manipulated.variable. may also be administration by a nasal canula and this may cause an influence on the dependent variable or there may be a different outcome such as. For example: A clam and quite environment at bedtime at night will allow sound sleep to a patient in a general ward. The researcher makes an attempt to identify those extraneous variables before the research study is initiated and thereby control the influence of extraneous variables on the research study through a specific research design or through statistical manipulation. Because O2. It is also called outcomes variable. . These are the variable which confuse or mix up the relationship between the variable and also interfere with the rational or causal relationship between the independent and the dependent variables. In this above example. instead of face mask. 7.

7. we are not supposed to do the data analysis first and then decide on the hypotheses afterwards. It is assumed to be true unless there is strong evidence to the contrary – similar to how a person is assumed to be innocent until the guilty is proven. These variables are climate. the researcher makes no attempt to control or alter the environmental variables. movement. The other hypothesis. height. These variable are also called the sample characteristics such as age. gender. In a descriptive or correlation research study where the study is conduct in a natural setting and where it is necessary to study the subjects’ behavior in a natural setting. Both the null and alternative hypothesis should be stated before any statistical test of significance is conducted. these variable are also some type of extraneous variable. speech. For example: . 7.sleep of patient at night. religion. weight. hearing. is referred to as the alternative hypothesis and is often symbolized by HA or H1. In other words. marital status etc.4 Environmental variable are the variables which compose a research setting where the research study is conducted. institution setup. How to Write a Hypothesis The hypothesis that we want to test is usually given the symbol H0.In the above example. the independent variable.5 Demographic variable are the qualities or property or characteristics of the subject under the research study and which are collected to describe sample. 8. social background. and it is commonly referred to as the null hypothesis. vision. build. family background.clam and quite environment will have an effect on the dependent variable. which is assumed to be true when the null hypothesis is false. community setup. education setup etc.

we know that the first hypothesis indicates there is no difference between both genders and this is called a null hypothesis. (b) A total of 70 percent of male and 30 percent of female in this study are IT literate. A researcher may have some fundamental knowledge about the community IT education exposure and he/she is likely to . From this example. and (d) There are twice as many male IT educated as female IT educated in this study population. and μ2 = the mean of population 2. (c) A greater proportion of male than female are IT literate in this population. μ1 = the mean of population 1. The following hypotheses could be constructed: (a) There is no significant difference in the proportion of male and female with IT literacy in the community population. suppose you want to do a research on the IT literacy pattern in a community in relation to gender differences. Given the test scores of two random samples of men and women. Another example can illustrate the matter. does one group differ from the other? A possible null hypothesis is that the male score is the same as the female score: H0: μ1 = μ2 where H0 = the null hypothesis. which is also sometimes referred to as Ho.

speculate on almost the exact outcome in a quantitative unit. that is. a researcher stipulates that there will be a difference but does not specify its magnitude. The third hypothesis states that there is a difference in the proportion of male and female IT education exposure. 9. Errors in Hypothesis Type I Error: A type I error occurs when the null hypothesis (H0) is wrongly rejected. Type II Error: A type II error occurs when the null hypothesis H0. Z-tests : comparing means under stringent conditions . One-sample tests : a sample is being compared to the population . This hypothesis is known as hypothesis of difference. Two-sample tests : comparing two samples . This hypothesis is widely known as hypothesis of association. Looking at the second hypothesis in the example. though the extent of the difference is not specified. there is no difference between the two drugs on average. T-test : is appropriate for comparing means under relaxed conditions . A type II error would occur if it were concluded that the two drugs produced the same effect. For example. In this type of hypothesis. 10. when in fact they produced different ones. How we test the hypothesis statistically . For example. the proportion is 70:30 and this type of hypothesis is known as hypothesis of point prevalence. is not rejected when it is in fact false. A type I error would occur if we concluded that the two drugs produced different effects when in fact there was no difference between them. The fourth hypothesis implies on the extent of the relationships in the study population as prevalence of a phenomenon in different population groups.

direct sentence that summarizes the main point or claim of an essay or research paper. qualitative. .. A thesis statement is a short. It is more subjective because it describes a problem or condition from the point of view of those experiencing it and it is a text-based research. It is typically used in quantitative research and predicts the relationship between variables. and explained in the body of the essay or research report by means of examples and evidence. 12. The difference between qualitative and quantitative research Qualitative Research is primarily exploratory research. It is more objective than qualitative research because it provides observed effects (interpreted by researchers) of a program on a problem or condition and it is number-based. and motivations. opinions. Quantitative Research is used to quantify the problem by way of generating numerical data or data that can be transformed into useable statistics. supported. It provides insights into the problem or helps to develop ideas or hypotheses for a quantitative research.F-tests : used when deciding whether groupings of data by category are meaningful 11.chi-squared test : can be used to attempt rejection of the null hypothesis . and mixed methods research. The difference between hypothesis and thesis statement Both the hypothesis statement and the thesis statement answer the research question of the study. Whereas. A thesis statement is developed. It is seen in quantitative. A hypothesis is a statement that can be proved or disproved. It is used to gain an understanding of underlying reasons.

Peacock Publishers. (1978).  A hypothesis is generally a speculative statement that needs to be verified in a research work. (1988). New York: The Free Press. it is important to keep the statement simple. Itasca: Illinois. .13. E. Grinnell. precise and clear. K. F. Summary  Hypothesis is important to help researchers focus on their research study and to provide clarity.  During hypothesis formulation.). D. References Bailey. and derive it from an existing body of knowledge. Social work research and evaluation.  Hypothesis could be proved or disproved by statistical methods. Methods of social research (3rd ed.

Oxford English Dictionary (OED. A Manual for writers of Research Paper. Turabian.(2012). Oxford University Press. Mangel. Pocket Guide to APA Style. (Internet Sources) . https://en. Ray.wikipedia.Kate. The Ecological Detective: Confronting Models with Data. Princeton University Press.Hilborn. Marc (1997).(2007).com). Perrin. Robert.org/wiki/Hypothesis.