HYPOTHESES DEVELOPMENT & TESTING

The Beginning
Some of the methods that are included for research formulation are Where does the problem origination or discovery begin?
Previous Experience Triggered Interest Potential problem fields

Criteria of problems and problem statement Goals & Planning Search, Explore & Gather the Evidence Generate creative and logical alternative solutions Making the educated guess-the hypothesis!

Definitions of hypothesis
Hypotheses are single tentative guesses, good hunches assumed for use in devising theory or planning experiments intended to be given a direct experimental test when possible. (Eric Rogers, 1966) A hypothesis is a conjectural statement of the relation between two or more variables. (Kerlinger, 1956) Hypothesis is a formal statement that presents the expected relationship between an independent and dependent variable.(Creswell, 1994) A research question is essentially a hypothesis asked in the form of a question.
3

Nature of Hypothesis
The hypothesis is a clear statement of what is intended to be investigated. It should be specified before research is conducted and openly stated in reporting the results. This allows to:
Identify the research objectives Identify the key abstract concepts involved in the research Identify its relationship to both the problem statement and the literature review

A problem cannot be scientifically solved unless it is reduced to hypothesis form It is a powerful tool of advancement of knowledge, consistent with existing knowledge and conducive to further enquiry
4

Nature of Hypothesis
It can be tested verifiable or falsifiable Hypotheses are not moral or ethical questions It is neither too specific nor too general It is a prediction of consequences It is considered valuable even if proven false
5

An Example
Imagine the following situation: You are a nutritionist working in a zoo, and one of your responsibilities is to develop a menu plan for the group of monkeys. In order to get all the vitamins they need, the monkeys have to be given fresh leaves as part of their diet. Choices you consider include leaves of the following species: (a) A (b) B (c) C (d) D and (e) E. You know that in the wild the monkeys eat mainly B leaves, but you suspect that this could be because they are safe whilst feeding in B trees, whereas eating any of the other species would make them vulnerable to predation. You design an experiment to find out which type of leaf the monkeys actually like best: You offer the monkeys all five types of leaves in equal quantities, and observe what they eat. There are many different experimental hypotheses you could formulate for the monkey study. For example:
When offered all five types of leaves, the monkeys will preferentially feed on B leaves.

This statement satisfies both criteria for experimental hypotheses. It is a Prediction: It predicts the anticipated outcome of the experiment Testable: Once you have collected and evaluated your data (i.e. observations of what the monkeys eat when all five types of leaves are offered), you know whether or not they ate more B leaves than the other types.

An Example (Cont)
Incorrect hypotheses would include: When offered all five types of leaves, the monkeys will preferentially eat the type they like best.
This statement certainly sounds predictive, but it does not satisfy the second criterion: there is no way you can test whether it is true once you have the results of your study. Your data will show you whether the monkeys preferred one type of leaf, but not why they preferred it (i.e., they like it best). I would, in fact, regard the above statement as an assumption that is inherent in the design of this experiment, rather than as a hypothesis.

When offered all five types of leaves, the monkeys will preferentially eat B leaves because they can eat these safely in their natural habitat.
This statement is problematic because its second part ('because they can eat these safely in their natural habitat') also fails to satisfy the criterion of testability. You can tell whether the monkeys preferentially eat baobab leaves, but the results of this experiment cannot tell you why.

An Example (Cont)
In their natural habitat, howler monkeys that feed in B trees are less vulnerable to predation than monkeys that feed on A, C, D, or E. This is a perfectly good experimental hypothesis, but not for the experiment described in the question. You could use this hypothesis if you did a study in the wild looking at how many monkeys get killed by predators whilst feeding on the leaves of A, B etc. However, for the experimental feeding study in the zoo it is neither a prediction nor testable. When offered all five types of leaves, which type will the monkeys eat preferentially? This is a question, and questions fail to satisfy criterion #1: They are not predictive statements. Hence, a question is not a hypothesis.

Types of Hypotheses
NULL HYPOTHESES
Designated by: H0or HN Pronounced as H oh or H-null

ALTERNATIVE HYPOTHESES
Designated by: H1or HA

The alternative hypothesis is a statement of what a hypothesis test is set up to establish.

Opposite of Null Hypothesis. Only reached if H0is rejected. Frequently alternative" is actual desired conclusion of the researcher!

The null hypothesis represents a theory that has been put forward, either because it is believed to be true or because it is to be used as a basis for argument, but has not been proved.
Has serious outcome if incorrect decision is made!
10

EXAMPLE
In a clinical trial of a new drug, the null hypothesis might be that
the new drug is no better, on average, than the current drug. We would write H0: there is no difference between the two drugs on average.

The alternative hypothesis might be that:

the new drug has a different effect, on average, compared to that of the current drug. We would write H1: the two drugs have different effects, on average.

The new drug is better, on average, than the current drug.

We would write H1: the new drug is better than the current drug, on average.

11

We give special consideration to the null hypothesis This is due to the fact that the null hypothesis relates to the statement being tested, whereas the alternative hypothesis relates to the statement to be accepted if / when the null is rejected. The final conclusion, once the test has been carried out, is always given in terms of the null hypothesis. We either 'reject H0in favor of H1' or 'do not reject H0'; we never conclude 'reject H1', or even 'accept H1'. If we conclude 'do not reject H0', this does not necessarily mean that the null hypothesis is true, it only suggests that there is not sufficient evidence against H0in favor of H1; rejecting the null hypothesis then, suggests that the alternative hypothesis may be true.
12

Formulating a hypothesis
is important to narrow a question down to one that can reasonably be studied in a research project. The formulation of the hypothesis basically varies with the kind of research project conducted: QUALITATIVE QUANTITATIVE
13

Hypothesis can also be divided into: Inductive

Observation Pattern Tentative hypothesis Theory

Deductive
Theory Hypothesis Observation Confirmation
14

Qualitative Approach
The use of Research Questions as opposed to objectives or hypothesis, is more frequent. Characteristics
Use of words-what or how. Specify whether the study: discovers, seeks to understand, explores or describes the experiences. Use of non-directional wording in the question. These questions describe, rather than relate variables or compare groups. The questions are under continual review and reformulation-will evolve and change during study. The questions are usually open-ended, without reference to the literature or theory. Use of a single focus.

15

The rules of Qualitative research

Kleining offers four rules for a scientific and qualitative process of approaching understanding to reality. Rule 1 (refers to subject / researcher) "Prior understandings of the phenomenon to be researched should be seen as provisional and should be transcended with [the discovery of] new information with which they are not consistent."(1982: 231) Rule 2 (refers to the object of study) "The object is provisional; it is only fully known after the successful completion of the process of discovery."(1982: 233) Rule 3 (refers to action in relation to the subject of research, hence to data collection) "The object should be approached from "all" sides; rule of the maximum variation of perspectives."(1982: 234) Rule 4 (refers to the evaluation of information gathered, hence to data analysis) "Analysis of the data for common elements."(1982: 237)
16

Quantitative Approach
In survey projects and experiments the use of research questions and objectives is more frequent comparison between variables Represent relationship between variables Characteristics
The testable proposition to be deduced from theory. Independent and dependent variables to be separated and measured separately. To be either writing-questions, or objectives or hypotheses, but not a combination. Consider the alternative forms for writing and make a choice based on the audience for the research

17

Generation of Research Hypothesis

Problem statements become research hypotheses when constructs are operationalized
Initial Ideas (often vague and general)

Initial observations

Search of existing research literature

Statement of the problem

Operational definitions of constructs

Research hypothesis (a specific deductive prediction)

18

Example
Consider the example of a simple association between two variables, Y and X.
Y and X are associated (or, there is an association between Y and X). Y is related to X (or, Y is dependent on X). As X increases, Y decreases (or, increases in values of X appear to effect reduction in values of Y).
19

 The first hypothesis provides a simple statement of association between Y and X. Nothing is indicated about the association that would allow the researcher to determine which variable, Y or X, would tend to cause the other variable to change in value. The second hypothesis is also a simple statement of association between Y and X, but this time it may be inferred that values of Y are in some way contingent upon the condition of the X variable. The third hypothesis is the most specific of the three. Not only does it say that Y and X are related and that Y is dependent on X value, but it also reveals something more about the nature of the association between the two variables.

20

Hypothesis testing
Null hypothesis is that there is no systematic relationship between independent variables (IVs) and dependent variables (DVs). Research hypothesis is that any relationship observed in the data is real.

21

Hypothesis testing
Whereas research hypothesis tends to be imprecise about numerical differences between groups (e.g., difference in reaction times), null hypothesis states very specifically that difference should be zero.

22

Testing the null hypothesis

A statistical test assesses the probability of obtaining a given sample or samples of scores, assuming the null hypothesis is correct.

23

Testing the null hypothesis

If the probability is low enough (e.g., p<.05), then the null hypothesis is rejected in favour of the alternative (research) hypothesis, and the IV is deemed to have a systematic effect. If the probability is not sufficiently low (e.g., p>.05), then the null hypothesis is not rejected but retained, and the IV is deemed to have no effect (i.e., the observed changes are due to chance).

24

Statistical significance
Statistical significance refers to the probability of the data obtained, given that the null hypothesis is true. A statistically significant result does not mean that the null hypothesis is doubtful. There is an ongoing gap between statistical significance and substantive significance.

25

Errors in hypothesis testing

Given the gap between statistical and substantive significance, a decision based on probability to retain or reject the null hypothesis can be wrong.

26

When null hypothesis is true (Type I error)

When null hypothesis is true, and it is rejected, this decision is called a Type 1 error. The probability of making such an error is designated alpha (E) and is equivalent to the significance level (e.g., p<.05).

27

When null hypothesis is true (Type I error)

If null hypothesis is true and alpha level is set at .05, then the null hypothesis will be rejected 5% of time even though it is true. One way to safeguard against a Type I error is to set a more stringent alpha level (e.g., p<.01).

28

When null hypothesis is false (Type II or III errors)

When alternative hypothesis is true, and the statistic (mean) from alternative distribution falls within cut-off points (i.e., p>.05), then null hypothesis would be retained.

29

Type II error
Retaining null hypothesis when alternative hypothesis is true is called a Type II error. The probability of making a Type II error usually is symbolized as beta (F). The probability of beta depends on how much the alternative hypothesis sampling distribution overlaps the retention region of the null hypothesis sampling distribution.

30

Type III error

It is also possible to make a Type III error, by rejecting a null hypothesis but inferring the incorrect alternative hypothesis. The probability of making a Type III error usually is symbolized as gamma (K) and is equivalent to whatever percentage of scores in the alternative distribution falls in the far end of the null hypothesis distribution. The probability of making a Type III error is usually quite small.
31

The power of a test

The probability of rejecting a false null hypothesis and correctly inferring the position or direction of the alternative hypothesis with respect to the null hypothesis. Factors affecting power and error rates

32

Power is affected by significance (alpha) level

Setting a less stringent significance level increases the discriminatory power of the statistical test and increases power.

33

Power is affected by sample size

An increase in sample size increases the power of the test. This is because as sample size increases, the standard error of the mean decreases, thus reducing the overlap between the null and alternative hypotheses.

34

Effect size
In order to gauge the effect of the IV, it makes sense to contrast the difference between the population mean for the null hypothesis and the population mean for the alternative hypothesis.

35

Effect size formula

Effect_ size !
Q 0  Q1

where W is standard deviation of population of dependent measure scores.

36

Judging effect sizes

According to Cohen (1988)
.20 = small effect size .50 = medium effect size .80 = large effect size

37

Do we really need the null hypothesis?

A significant test of the null hypothesis does not mean the data are not a product of chance. The significant result may simply be a Type I error (falsely rejecting null hypothesis).

38

Do we really need the null hypothesis?

Better to test research hypothesis, if know size and direction of effect. Even better report combination of outcome values (e.g., effect sizes, confidence intervals, strength of relationship).

39

One-tailed versus two-tailed tests

Conventionally reject null hypothesis if obtained z-score or t-score falls beyond certain values in either tail of the relevant sampling distribution (i.e., a two-tailed test). In specific contexts, a one-tailed test might seem appropriate (e.g., reject null hypothesis only if test statistic fell in 5% left-hand tail of distribution.

40

One-tailed versus two-tailed tests

Generally, two-tailed tests are preferred to one-tailed tests. The IV may have an effect in opposite direction to the one predicted.

41