This action might not be possible to undo. Are you sure you want to continue?

BooksAudiobooksComicsSheet Music### Categories

### Categories

### Categories

Editors' Picks Books

Hand-picked favorites from

our editors

our editors

Editors' Picks Audiobooks

Hand-picked favorites from

our editors

our editors

Editors' Picks Comics

Hand-picked favorites from

our editors

our editors

Editors' Picks Sheet Music

Hand-picked favorites from

our editors

our editors

Top Books

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Audiobooks

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Comics

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Sheet Music

What's trending, bestsellers,

award-winners & more

award-winners & more

Welcome to Scribd! Start your free trial and access books, documents and more.Find out more

Science mainly consists of two main factors on which its working depends first is the body of the knowledge and the other one is the method of the inquiry. The body of knowledge involves the various laws, theories, hypothesis etc. and the other factor of inquiry methodology consists of the various mechanisms that help a great deal in the addition of the theories etc to the body of the knowledge.

Hypothesis and the theories are generally responsible for the movement of knowledge from the unknown to the known. Hypotheses play a very important and a critical role in the assertion of a particular thing, as they are able to describe certain facts and are also able to explain the various relationships between these facts. As a result of this, hypotheses help a great deal in the investigation operations or activities. On the institution of the problem to be answered in the process of the research, the researcher forms various tentative or possible solutions to these problems these proposed answers or the solutions are referred to as the hypothesis. But a very critical and essential point to be kept in mind here is that these propositions are not at all verified in nature. So Hypothesis can be referred to as the interpretation of certain facts which is just a possible solution or a tentative answer to a problem and is completely or partly unverified in nature. Then afterwards on its establishment, it ceases to be a hypothesis and then finally becomes a theory or a principle. The word ‗Hypothesis‘ has come from the Greek word hypo (means under)and tithenas (means to place) together these words indicate towards the support they provide to each other on the placement of the hypothesis under the evidence, which acts as a foundation.

1

According to George A Luniberg, hypothesis can be defined as a ‗tentative generalization, the validity of which remains to be tested. In this elementary stage, the hypothesis may be very hunch, guess, imaginative data, which becomes the basis for an action or an investigation.‘ A very vital point that should be kept in mind about the hypotheses is that these are not theories these only have some linkage to the theory but hypothesis is not that much elaborated as the theory is. But it can be said that the hypothesis is derived from the theory. A researcher uses hypothesis testing to support beliefs about comparisons (i.e., variables or groups). Basically, it is how we empirically test our research hypotheses for "accuracy." We NEVER prove beyond the shadow of a doubt that a comparison is true. Rather, we conclude that, based on some collected data and assumptions, the probability of the comparison being true is very high (i.e., around 95 – 99% sure). In all hypothesis testing, the hypothesis being tested is a hypothesis about equality. The researcher thinks the equality hypothesis is NOT true, and by showing how the data do not fit it, the equality hypothesis can be rejected.We call this equality hypothesis the null hypothesis , and its symbol is: H0. The null hypothesis is a statement comparing two statistics (usually two means).This difference hypothesis is the alternative hypothesis , and its symbol is: Ha or H1. The alternative hypothesis is a statement comparing two statistics or groups, suggesting there is a difference.

2

**CHAPTER 2: CHARACTERISTICS OF A GOOD HYPOTHESIS
**

A good hypothesis must be based on a good research question. It should be simple, specific and stated in advance Hypothesis should be simple A simple hypothesis contains one predictor and one outcome variable, e.g. positive family history of schizophrenia increases the risk of developing the condition in first-degree relatives. Here the single predictor variable is positive family history of schizophrenia and the outcome variable is schizophrenia. A complex hypothesis contains more than one predictor variable or more than one outcome variable, e.g., a positive family history and stressful life events are associated with an increased incidence of Alzheimer‘s disease. Here there are 2 predictor variables, i.e., positive family history and stressful life events, while one outcome variable, i.e., Alzheimer‘s disease. Complex hypothesis like this cannot be easily tested with a single statistical test and should always be separated into 2 or more simple hypotheses. Hypothesis should be specific A specific hypothesis leaves no ambiguity about the subjects and variables, or about how the test of statistical significance will be applied. It uses concise operational definitions that summarize the nature and source of the subjects and the approach to measuring variables (History of medication with tranquilizers, as measured by review of medical store records and physicians‘ prescriptions in the past year, is more common in patients who attempted suicides than in controls hospitalized for other conditions). This is a long-winded sentence, but it explicitly states the nature of predictor and outcome variables, how they will be measured and the research hypothesis. Often these details may be included in the study proposal and may not be stated in the research hypothesis. However, they should be clear in the mind of the investigator while conceptualizing the study.

3

This will help to keep the research effort focused on the primary objective and create a stronger basis for interpreting the study‘s results as compared to a hypothesis that emerges as a result of inspecting the data. The habit of post hoc hypothesis testing (common among researchers) is nothing but using third-degree methods on the data (data dredging). This leads to overrating the occasional chance associations in the study. 4 . to yield at least something significant. Hypothesis should be stated in advance The hypothesis must be stated in writing during the proposal state.

Helps in the determination of the most suitable type of research.CHAPTER 3 : ROLE AND FUNCTIONS OF THE HYPOTHESIS Helps in the testing of the theories. Is very helpful in carrying out an enquiry of a certain activity. Results of the research and development department. Provides guidance to the research work or study. Provides knowledge about the required sources of data. Serves as a great platform in the investigation activities. Research becomes focused under the direction of the hypothesis. Helps in reaching conclusions. 5 . if it is correctly drawn. Knowledge obtained from the functional executives. Develops the theory. Provides a relationship between phenomena in such a way that it leads to the empirical testing of the relationship. Hypothesis sometimes suggests theories. Helps in knowing the needs of the data. Also acts as a bridge between the theory and the investigation. Explains social phenomena. Analogies. Experience of the investigator. Helps in knowing the most suitable technique of analysis. SOURCES OF HYPOTHESIS Observations made in routine activities. Theories based on the scientific approach.

occurred by chance. the health of all subjects was measured and it was found that the mean level of health (on a 10-point scale with higher numbers indicating better health) was 6 for the enhanced control group and 4 for the non-enhanced group. After six weeks. To compare the benefits of this enhanced control. it is possible that some of the relationships that we observe might be due to chance. conducted in McGregor Hospital. What is needed is a way to evaluate the likelihood that relationships. 6 . They could specify when they would have their meals. there are many numbers of relationships that we could examine to learn more about their workings. rather than chance?" It might be that simply by chance the people who were chosen for the enhanced control group were somewhat healthier before the experiment than those assigned to the other group. rather than some benefit of control over living conditions.CHAPTER 4: WHY USE HYPOTHESES IN SOCIAL SCIENCE RESEARCH? In examining phenomena of the social world. The establishing and testing of hypotheses is such a method. ten people in the chronic care ward were sampled and given "enhanced control" over their schedule and living conditions. In this experiment. though their routines were not altered. However. such as those in the study in the hospital described above. Or it might be that these differences were due only to chance. and which programs they could watch on television. rather than some relationship between two variables. which hours they could receive visitors. an additional ten patients of the chronic care ward were chosen. Perhaps the first question that should be asked is: "Can we be sure that the enhanced sense of control is responsible for the difference between the groups. For instance. consider a hypothetical experiment that is designed to evaluate whether enhancing hospital patients' "sense of control" influences their health.

and sexmatched ―control‖ patients hospitalized for other diagnoses). By starting with the proposition that there is no association. hypotheses are classified by the way they describe the expected difference between the study groups. The alternative hypothesis cannot be tested directly. it does not specify the direction. (The word tails refers to the tail ends of the statistical distribution such as the familiar bell-shaped normal curve that is used to test a hypothesis. The proposition that there is an association — that patients with attempted suicides will report different tranquilizer habits from those of the controls — is called the alternative hypothesis. it is accepted by exclusion if the test of statistical significance rejects the null hypothesis. One tail represents a positive effect or association.CHAPTER 5: TYPES OF HYPOTHESIS For the purpose of testing statistical significance. One. the other. The prediction that patients with attempted suicides will have a different rate of tranquilizer use — either higher or lower than control patients — is a two-tailed hypothesis. a negative effect. statistical tests can estimate the probability that an observed association could be due to chance.and two-tailed alternative hypotheses A one-tailed (or one-sided) hypothesis specifies the direction of the association between the predictor and outcome variables. The prediction that patients of attempted suicides will have a higher rate of use of tranquilizers than control patients is a one-tailed hypothesis.) A one-tailed hypothesis has the 7 . A two-tailed hypothesis states only that an association exists. Null and alternative hypotheses The null hypothesis states that there is no association between the predictor and outcome variables in the population (There is no difference between tranquilizer habits of patients with attempted suicides and those of age. The null hypothesis is the formal basis for testing statistical significance.

it would lack statistical rigor. PROBLEMS FACED DURING HYPOTHESIS FORMULATION Formulating a hypothesis is not at all an easy process and is faced with a large number of difficulties. One other major difficulty in the formulation of the hypothesis is the lack of clear theoretical background. otherwise. in fact. the possibility that the drug has fewer side effects than the placebo is not worth testing. some investigators believe that they should never be used. Because of this problem of unclear and indefinite background of theory one is not able to arrive to a conclusion easily. 8 . But with time answers to all such problems are available and these difficulties that arise during the hypothesis formulation can be easily removed by having complete and accurate information about the concepts of the subjects involved. Whatever strategy is used. as sometimes it becomes impossible to gather the complete information about a particular scientific method. Unfortunately. Also the hypothesis should not be very long and should be timely in nature. However. they are appropriate when only one direction for the association is important or biologically meaningful. An example is the one-sided hypothesis that a drug has a greater frequency of side effects than a placebo. one-tailed hypotheses are not always appropriate. it should be stated in advance. Data dredging after it has been collected and post hoc deciding to change over to one-tailed hypothesis testing to reduce the sample size and P value are indicative of lack of scientific integrity.statistical advantage of permitting a smaller sample size as compared to that permissible by a two-tailed hypothesis. the various difficulties faced during the formulation of the hypothesis generally include the lack of the knowledge about the scientific approach of the method involved. According to Goode and Hatt.

there is always the possibility of committing an error. Difficulty in meeting assumptions The tests used in the testing of hypothesis. when it comes to comparing several population means at the same time. t-tests and ANOVA have some fundamental assumptions that need to be met.. The following cases illustrate some of the limitations of this type of test: Multiple Comparisons z and t tests are very useful when comparing two population menas. 9 . Table 8 shows the resulting overall if multiple t tests are conducted. Since we are conducting three such tests. For each test. The samples are drawn randomly from a population in which the data are distributed normally distributed. viz. Assume that each k value represents the number of populations to be compared.CHAPTER 6: LIMITATIONS FOR ENVIRONMENTAL SAMPLING Although hypothesis tests are a very useful tool in general. the overall error probability would exceed the acceptable ranges. for the test to work properly and yield good results. However. this method is not very appropriate. The primary assumptions underlying the a t-test are: 1. they are sometimes not appropriate in the environmental field. and we could not feel very confident about the final conclusion. The main assumptions for the t-test and ANOVA are listed below.

2. 10 . with each observation independent of all other observations and the groups independent of each other. The samples represent populations in which the data are normally distributed. In the case of a two sample t-test. Each group is obtained randomly. Like the t-test.Therefore it is assumed that 2 s12 and s22 both estimate a common population variance. the measurements in sample 1 are independent of those in sample 2. assumption is called the homogeneity of variances . In the case of a two sample t-test.2. Assumptions of ANOVA are that: 1. This 3. analysis of variance is based on a model that requires certain assumptions. 1 2 = 2 2 .

that is assumed to be true. The null hypothesis (H0). in hypothesis testing. When a defendant is on trial. the jury starts by assuming that the defendant is innocent. For the children watching TV example. We will test whether the value stated in the null hypothesis is likely to be true. 11 . This is stated in the null hypothesis. This is a starting point so that we can decide whether this is likely to be true. stated as the null. The basis of the decision is to determine whether this assumption is true. we state the null hypothesis that children in the United States watch an average of 3 hours of TV per week.1: Step 1: State the hypotheses. Step 2: Set the criteria for a decision. similar to the presumption of innocence in a courtroom. such as the population mean. Step 1: State the hypotheses. Step 3: Compute the test statistic. In this section. The null hypothesis is a starting point. Step 4: Make a decision. is a statement about a population parameter. Likewise. is likely to be true. we describe the four steps of hypothesis testing that were briefly introduced in Section 8. which we presume is true. The basis of the decision is to determine whether this assumption is likely to be true. We begin by stating the value of a population mean in a null hypothesis. we start by assuming that the hypothesis or claim we are testing is true. such as the mean.CHAPTER 7: FOUR STEPS TO HYPOTHESIS TESTING The goal of hypothesis testing is to determine the likelihood that a population parameter.

Jurors decide whether the evidence presented shows guilt beyond a reasonable doubt (this is the criterion).Keep in mind that the only reason we are testing the null hypothesis is because we think it is wrong. or not equal to the value stated in the null hypothesis. To set the criteria for a decision. Likewise. In a similar way. 12 . based on the likelihood of selecting a sample mean from a population (the likelihood is the criterion). we may have reason to believe that children watch more than (>) or less than (<) 3 hours of TV per week. then we conclude that the sample we selected is too unlikely and so we reject the null hypothesis. When the probability of obtaining a sample mean is less than 5% if the null hypothesis were true. in hypothesis testing. An alternative hypothesis (H1) is a statement that directly contradicts a null hypothesis by stating that that the actual value of a population parameter is less than. which is needed for Step 2. since the defendant is assumed to be innocent (this is the null hypothesis so to speak). we collect data to show that the null hypothesis is not true. Step 2: Set the criteria for a decision. placing the burden on the researcher to conduct a study to show evidence that the null hypothesis is unlikely to be true. This is similar to the criterion that jurors use in a criminal trial. In a courtroom. greater than. Regardless. For the children watching TV example. The alternative hypothesis is needed for Step 2. we assume the null hypothesis is true. The alternative hypothesis states what we think is wrong about the null hypothesis. the burden is on a prosecutor to conduct a trial to show evidence that the defendant is not innocent. When we are uncertain of the direction. We state what we think is wrong about the null hypothesis in an alternative hypothesis. The likelihood or level of significance is typically set at 5% in behavioral research studies. we always make a decision about the null hypothesis (that it is likely or unlikely to be true). we can state that the value in the null hypothesis is not equal to (≠) 3 hours. we state the level of significance for a test.

refers to a criterion of judgment upon which a decision is made regarding the value stated in a null hypothesis. Specifically. the criterion or level of significance is typically set at 5%. or significance level. the further the distance. We use a test statistic to determine this likelihood. or both tails (not equal to 3). 13 . meaning that there is less than a 5% probability of obtaining a sample mean that is beyond 2 SD from the population mean. Figure 8. a test statistic tells us how far. if the population mean stated by the null hypothesis (3 hours per week) is true. a sample mean is from the population mean. the lower tail (less than 3). or how many standard deviations. The empirical rule tells us that at least 95% of all sample means fall within about 2 standard deviations (SD) of the population mean. a sample mean is from the population mean stated in the null hypothesis. Remember that we know that the sample mean will equal the population mean on average if the null hypothesis is true. Step 3: Compute the test statistic. Suppose we measure a sample mean equal to 4 hours per week that children watch TV. All other possible values of the sample mean are normally distributed (central limit theorem). or number of standard deviations. The value of the test statistic is used to make a decision in Step 4.Level of significance. For the children watching TV example.2 shows that the alternative hypothesis is used to determine which tail or tails to place the level of significance for a hypothesis test. The alternative hypothesis establishes where to place the level of significance. When the probability of obtaining a sample mean is less than 5% if the null hypothesis were true. we need to evaluate how likely this sample outcome is. The larger the value of the test statistic. we can look for the probability of obtaining a sample mean beyond 2 SD in the upper tail (greater than 3). To make a decision. In behavioral science. then we reject the value stated in the null hypothesis. The criterion is based on the probability of obtaining a statistic measured in a sample if the value stated in the null hypothesis were true.

If the probability of obtaining a sample mean is less than 5% when the null hypothesis is true. In Step 2.The test statistic is a mathematical formula that allows researchers to determine the likelihood of obtaining sample outcomes if the null hypothesis were true. given that the value stated in the null hypothesis is true. which is typically set at 5% in behavioral research. The sample mean is associated with a low probability of occurrence when the null hypothesis is true. We use the value of the test statistic to make a decision about the null hypothesis. Retain the null hypothesis. 2. The value of the test statistic is used to make a decision regarding the null hypothesis. Reject the null hypothesis. given that the value stated in the null hypothesis is true. The sample mean is associated with a high probability of occurrence when the null hypothesis is true. Step 4: Make a decision. The p value is a probability: It varies between 0 and 1 and can never be negative. we compare the p value to the criterion we set in Step 2. To make a decision. is stated by the p value. we stated the criterion or probability of obtaining a sample mean at which point we will decide to reject the value stated in the null hypothesis. The decision is based on the probability of obtaining a sample mean. In sum. and are compared against alpha to determine whether to reject the null hypothesis or not. then the decision is to retain the null hypothesis. P-values are the actual probabilities calculated from a statistical test. then the decision is to reject the null hypothesis. there are two decisions a researcher can make: 1.The p value for obtaining a sample outcome is compared to the level of significance. 14 . If the probability of obtaining a sample mean is greater than 5% when the null hypothesis is true. given that the value stated in the null hypothesis is true. A p value is the probability of obtaining a sample outcome. The probability of obtaining a sample mean.

alpha = 0. we reach significance.008. When the p value is less than . we retain the null hypothesis.110. we reject the null hypothesis. The decision to reject or retain the null hypothesis is called significance. reject null hypothesis calculated p-value = 0. the decision is also to reject the null hypothesis. When the null hypothesis is retained. do not reject null hypothesis Significance.Example: alpha = 0.05.05.05. calculated p-value = 0.05). we fail to reach significance. the decision is to retain the null hypothesis. although note that when p = . we reach significance. the decision is to reject the null hypothesis. When the null hypothesis is rejected.05. When the p value is less than 5% (p < . describes a decision made concerning a value stated in the null hypothesis.05. We will refer to p < .05).05 as the criterion for deciding to reject the null hypothesis. or statistical significance. When the p value is greater than . 15 . When the p value is greater than 5% (p > . we fail to reach significance.

that is. than the current drug. then a random sample selected from a given population will have a sample mean equal to the value stated in the null hypothesis. 2. the probabilities of all other possible sample means we could select are normally distributed. Hence.In a hypothesis test. a type I error occurs when the null hypothesis is rejected when it is in fact true. To locate the probability of obtaining a sample mean in a sampling distribution. we must know (1) the population mean and (2) the standard error of the mean Each value is entered in the test statistic formula computed in Step 3. on average. In hypothesis testing. we showed three characteristics of the mean. i. a randomly selected sample will have a mean equal to that in the population. 16 . Using this distribution. the null hypothesis might be that the new drug is no better.e.CHAPTER 8: HYPOTHESIS TESTING AND SAMPLING DISTRIBUTIONS The logic of hypothesis testing is rooted in an understanding of the sampling distribution of the mean. we can therefore state an alternative hypothesis to locate the probability of obtaining sample means with less than a 5% chance of being selected if the value stated in the null hypothesis is true. H0 is wrongly rejected. the sampling distribution of the sample mean is normally distributed. two of which are particularly relevant in this section: 1. we begin by stating the null hypothesis. We expect that. thereby allowing us to make a decision in Step 4. in a clinical trial of a new drug. if the null hypothesis is true. MAKING A DECISION: TYPES OF ERROR TYPE I ERROR. For example. Regardless of the distribution in the population. On average. The sample mean is an unbiased estimator of the population mean.

the higher the risk of the other.In a hypothesis test. This probability of a type I error can be precisely computed as P(type I error) = significance level = The exact probability of a type II error is generally unknown. the null hypothesis might be that the new drug is no better. i. type I and type II errors are inversely related. The hypothesis test procedure is therefore adjusted so that there is a guaranteed 'low' probability of rejecting the null hypothesis wrongly.A type I error is often considered to be more serious. than a type II error. on average. and therefore more important to avoid. For example. in a clinical trial of a new drug.e. 17 .If we do not reject the null hypothesis. Types of error Type of decision Reject H0 Accept H0 Correct decision (1H0 true H0 false Correct decision (1- TYPE II ERROR. H0: there is no difference between the two drugs on average. Table 2. is not rejected when it is in fact false.For any given set of data. this probability is never 0. it may still be false (a type II error) as the sample may not be big enough to identify the falseness of the null hypothesis (especially if the truth is very close to hypothesis).A type I error can also be referred to as an error of the first kind. the smaller the risk of one. 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.H0: there is no difference between the two drugs on average. than the current drug. a type II error occurs when the null hypothesis H0.

The strength of evidence in support of a null hypothesis is measured by the P-value. 18 . statisticians describe these decision rules in two ways . there is no difference between the two drugs on average. The decision to reject the null hypothesis could be correct. The decision to retain the null hypothesis could be incorrect. The probability of a type II error is generally unknown. For example. it is possible that a conclusion may be wrong. 4. P-value. Because we are observing a sample and not an entire population. On the other hand. we decide whether to retain or reject the null hypothesis.e. The consequences of these different types of error are very different. failure to determine presence of pollution (Type II error) can lead to environmental deterioration or health problems in the nearby community The analysis plan includes decision rules for rejecting the null hypothesis. 3. i.with reference to a P-value or with reference to a region of acceptance. The Pvalue is the probability of observing a test statistic as extreme as S. if one tests for the significant presence of a pollutant. but is symbolized by and written P(type II error) = A type II error can also be referred to as an error of the second kind.A type II error would occur if it was concluded that the two drugs produced the same effect. Suppose the test statistic is equal to S. In practice. 2. 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. when in fact they produced different ones. The decision to reject the null hypothesis could be incorrect. A type II error is frequently due to sample sizes being too small. there are four decision alternatives regarding the truth and falsity of the decision we make about a null hypothesis: 1. The decision to retain the null hypothesis could be correct.

In such cases. others use the region of acceptance approach.assuming the null hypothesis is true. DECISION: RETAIN THE NULL HYPOTHESIS When we decide to retain the null hypothesis. While it‘s an error. The incorrect decision is to retain a false null hypothesis. In this decision. the null hypothesis is not rejected. The region of acceptance is defined so that the chance of making a Type I error is equal to the significance level. 19 . null results alone are rarely published in behavioral research. we reject the null hypothesis. Some statistics texts use the P-value approach. or b error. In subsequent lessons. Region of acceptance. This decision is called a null result or null finding. With each test we make. this tutorial will present examples that illustrate each approach. we decide to retain previous notions of truth that are in fact false. If the test statistic falls within the region of acceptance. If the test statistic falls within the region of rejection. there is always some probability that the decision could be a Type II error. We can always go back and conduct more studies. This is usually an uninteresting decision because the decision is to retain what we already assumed: that the value stated in the null hypothesis is correct. we still did nothing. The region of acceptance is a range of values. we retained the null hypothesis. The set of values outside the region of acceptance is called the region of rejection. the null hypothesis is rejected. If the P-value is less than the significance level. These approaches are equivalent. we can be correct or incorrect. The correct decision is to retain a true null hypothesis. For this reason. This decision is an example of a Type II error. we say that the hypothesis has been rejected at the α level of significance.

Type I error is the probability of rejecting a null hypothesis that is actually true.05 (a = . With each test we make. It is the largest probability of committing a Type I error that we will allow and still decide to reject the null hypothesis. This criterion is usually set at . is the largest probability of committing a Type I error that we will allow and still decide to reject the null hypothesis.Type II error. This decision is an example of a Type I error. we assume the null hypothesis is true when beginning a hypothesis test. we control for Type I error by stating a level of significance.05). There is always some probability that we decide that the null hypothesis is false when it is indeed false. Making this type of error is analogous to finding an innocent person guilty. there is always some probability that our decision is a Type I error. To minimize this error. Researchers directly control for the probability of committing this type of error. When the probability of a Type I error is less than 5% (p < . is the probability of retaining a null hypothesis that is actually false. The correct decision is to reject a false null hypothesis. The incorrect decision is to reject a true null hypothesis. An alpha (a) level is the level of significance or criterion for a hypothesis test. we assume a defendant is innocent when beginning a trial.05). called the alpha level (symbolized as a).we decide to reject the null hypothesis. This decision is called the power of the decision-making process. to minimize making a Type I error. or beta (b) error. Similarly. we can be correct or incorrect. It is called 20 . we retain the null hypothesis. The level we set. A researcher who makes this error decides to reject previous notions of truth that are in fact true. and we compare the alpha level to the p value. Since we assume the null hypothesis is true. otherwise. DECISION: REJECT THE NULL HYPOTHESIS When we decide to reject the null hypothesis.

Specifically. Null Hypothesis (Treatment A = Treatment B) POPULATION True (No difference) Decision Based on Inferential Statistical Test Accept H0 (No difference) Reject H0 (Difference) Correct Decision Type I Error (alpha () error) False (Difference) Type II Error (beta () error) Correct Decision Power (1-) 21 . inasmuch as we learn the most about populations when we accurately reject false notions of truth. it is the probability that a randomly selected sample will show that the null hypothesis is false when the null hypothesis is indeed false. This decision is the most published result in behavioral research. The power in hypothesis testing is the probability of rejecting a false null hypothesis. Remember that we are only testing the null hypothesis because we think it is wrong. is the power. Deciding to reject a false null hypothesis.power because it is the decision we aim for. then.

which equals -10. A researcher might ask: What is the probability of rejecting the null hypothesis if the true population mean is equal to 90? In this example.The power of a statistical hypothesis test measures the test's ability to reject the null hypothesis when it is actually false . usually expressed as: Power = 1 . to make a correct decision. The effect size is the difference between the true value and the value specified in the null hypothesis. suppose the null hypothesis states that a population mean is equal to 100. AND SAMPLE SIZE EFFECT SIZE To compute the power of the test. POWER The probability of not committing a Type II error is called the power of a hypothesis test.100. POWER. Ideally we want a test to have high power. Effect size = True value . the power of a hypothesis test is the probability of not committing a type II error.Hypothesized value For example. close to 1. the effect size would be 90 . It is calculated by subtracting the probability of a type II error from 1. assuming that the null hypothesis is false.CHAPTER 9: EFFECT SIZE.P(type II error) = The maximum power a test can have is 1. 22 .In other words. the minimum is 0. one offers an alternative view about the "true" value of the population parameter.that is.

FACTORS THAT AFFECT POWER The power of a hypothesis test is affected by three factors. The higher the significance level. is that its value can be used to determine the power of detecting an effect in hypothesis testing. As a result. if the null hypothesis is false. In this section. The likelihood of detecting an effect. we describe how effect size and sample size are related to power.. One advantage of knowing effect size. That is. the greater the effect size. the higher the power of the test. the greater the power of the test. If you increase the significance level. you reduce the region of acceptance. Hence. Sample size (n). you are more likely to reject the null hypothesis. Significance level (α).e. the greater the power of the test. 23 . the power of the test is increased. the greater the sample size. less likely to make a Type II error. called power. Other things being equal. The "true" value of the parameter being tested. This means you are less likely to accept the null hypothesis when it is false. i. d. is critical in behavioral research because it lets the researcher know the probability that a randomly selected sample will lead to a decision to reject the null hypothesis. the greater the power of the test. The greater the difference between the "true" value of a parameter and the value specified in the null hypothesis.

10 alpha level if you are doing a pilot study. Would that affect the alpha error you choose? The alpha error tells you what your chances are of concluding the drug is effective when it's really not. It's not going to hurt anybody. but if you have good reasons for increasing or decreasing it by all means do so. you may want to have a . you may want to have a .2.10. What if this drug is for a horrific disease. you don't want to do an experiment that causes you to miss the good drug. the drug has no harmful side effects. So.001 alpha level if the drug has nasty side effects. a crippling disease or a life threatening disease? Well.8 to . what if you're researching a drug.CHAPTER 10: FACTORS AFFECTING THE CHOICE OF ALPHA AND POWER Now.9 maybe . because it has nasty side effects. You've got a chance to do something about it. It doesn't matter if you misapply this drug. On the other hand. You want to reduce the chance of your falsely concluding this is a good drug when it's not. If the drug has really nasty side effects would you want to increase or decrease your alpha? Would you want to set it higher than 5% or lower than 5%? You'd want to lower your alpha to under 5%.01 a point . Well you could try to reduce the beta error. the 5% is the convention. on the one hand. That is increase your power from . then you may want to increase your alpha level to say . and you want to know whether the drug is effective and the drug has nasty side effects. That is. It tells you what your chances of a false positive are. Or. So. if in starting a new program of research.95.1 instead of . whatever it takes to do that kind of 24 . and you want to reduce the chances of missing an important effect especially since at this point your procedures may be relatively unrefined. to . Assume it is a very devasting disease. your experiment is designed in a way that you have a 10% chance of a false positive. So you want to make sure that if the drug works you don't miss it.

The figure below shows what alpha. beta and power look like in a graph and illustrates some of the relationships between them. the area to the right of 107. not the statisician. Of course. respectively. alpha and beta represent the probabilities of Type I and Type II Errors. Remember. You are the person who knows these issues. power (1 . You'll be interacting with the statistician on these kinds of issues.5 under the right curve represents your power in this experiment. beta and power are closely related. but you'll have to use your medical knowledge to decide these sorts of things. so that is one of your alternatives.thing. increasing alpha increases power. Figure 3. In particular. Because only you know the medical aspects of the treatments that you're using.3: Alpha and Beta Errors Since power is 1-beta. Then the statistician builds an experiment to guarantee your alpha level is what you want it to be and your beta error or your power is what you want it to be. how devastating the disease is. When you do this. It should be apparent from the graph that alpha. So these numbers are important for you to interpret. you can see that reducing alpha is equivalent to moving the vertical line between the two sample means to the right. 25 . alpha decreases. or how painful the side effects might be.beta) decreases.

if one is true. 26 . That is. The population distribution is normal. The sampling distribution is moderately skewed. The sample is drawn from a normal or near-normal population. unimodal. when the following conditions are met: The sampling method is simple random sampling. State the Hypotheses Every hypothesis test requires the analyst to state a null hypothesis and an alternative hypothesis. To put it another way.and beta increases. (3) analyze sample data. The sample size is greater than 40. the sampling distribution will be approximately normally distributed if any of the following conditions apply. and the sample size is between 16 and 40. increases power. and vice versa. On the other hand moving that same vertical line to the left increases alpha. (2) formulate an analysis plan. increases in alpha increase power and decreases in alpha decrease power. CHAPTER 11: HYPOTHESIS TEST FOR A MEAN This chapter explains how to conduct a hypothesis test of a mean. without outliers. Generally. the other must be false. and (4) interpret results. and the sample size is 15 or less. and decreases beta. without outliers. unimodal. This approach consists of four steps: (1) state the hypotheses. without outliers. The hypotheses are stated in such a way that they are mutually exclusive. The sampling distribution is symmetric.

Each makes a statement about how the population mean μ is related to a specified value M. researchers choose significance levels equal to 0.01. It should specify the following elements. Often. but any value between 0 and 1 can be used. Formulate an Analysis Plan The analysis plan describes how to use sample data to accept or reject the null hypothesis. or 0.05. 27 . conduct a one-sample t-test. (In the table. Significance level. since an extreme value on either side of the sampling distribution would cause a researcher to reject the null hypothesis. Test method. and the P-value associated with the test statistic.10. test statistic. Use the one-sample t-test to determine whether the hypothesized mean differs significantly from the observed sample mean. The other two sets of hypotheses (Sets 2 and 3) are one-tailed tests. Analyze Sample Data Using sample data. degrees of freedom. since an extreme value on only one side of the sampling distribution would cause a researcher to reject the null hypothesis. the symbol ≠ means " not equal to ". This involves finding the standard error. 0.The table below shows three sets of hypotheses.) Set 1 2 3 Null hypothesis μ=M μ>M μ<M Alternative hypothesis μ≠M μ<M μ>M Number of tails 2 1 1 The first set of hypotheses (Set 1) is an example of a two-tailed test.

1. Thus. given the degrees of freedom computed above.) Interpret Results If the sample findings are unlikely. 28 . and rejecting the null hypothesis when the P-value is less than the significance level. SE = s * sqrt{ ( 1/n ) * ( 1 . Compute the standard error (SE) of the sampling distribution. Since the test statistic is a t-score. The P-value is the probability of observing a sample statistic as extreme as the test statistic. this involves comparing the P-value to the significance level. When the population size is much larger (at least 10 times larger) than the sample size. DF = n . The degrees of freedom (DF) are equal to the sample size (n) minus one. use the t Distribution Calculator to assess the probability associated with the tscore. t = (x . given the null hypothesis.1 ) ] } where s is the standard deviation of the sample. N is the population size. Standard error.n/N ) * [ N / ( N . and n is the sample size. Typically.μ) / SE where x is the sample mean. P-value. The test statistic is a t-score (t) defined by the following equation. (See sample problems at the end of this lesson for examples of how this is done. Test statistic. and SE is the standard error. the standard error can be approximated by: SE = s / sqrt( n ) Degrees of freedom. the researcher rejects the null hypothesis. μ is the hypothesized population mean in the null hypothesis.

Another important point to remember is that we cannot ‗prove‘ or ‗disprove‘ anything by hypothesis testing and statistical tests. 29 . The acceptable magnitudes of type I and type II errors are set in advance and are important for sample size calculations. This uncertainty can be of 2 types: Type I error (falsely rejecting a null hypothesis) and type II error (falsely accepting a null hypothesis).CHAPTER 12: CONCLUSION Hypothesis testing is the sheet anchor of empirical research and in the rapidly emerging practice of evidence-based medicine. We can only knock down or reject the null hypothesis and by default accept the alternative hypothesis. ipso facto. empirical research and. If we fail to reject the null hypothesis. However. hypothesis testing have their limits. we accept it by default. At the best. The empirical approach to research cannot eliminate uncertainty completely. it can quantify uncertainty.

It does not mean that this difference was caused by the independent variable.CHAPTER 13: RECOMMENDATIONS Here are some things you should remember about hypothesis testing: Hypotheses are never about the samples. Data are not significant. when we do a hypothesis test. That means 5%. and conclude that means are "significantly different. usually . the hypothesis is about the population. or 1 in 20. as follows: o You may conclude that the null hypothesis is false when. DIFFERENCES are significant. What's true or false in the sample does not prove anything about the population.) A significant difference means that the observed difference in some statistic between two (or more) samples is PROBABLY NOT DUE TO RANDOM CHANCE. in fact. it is true. We can see what's true in the samples. in fact true. Never. A hypothesis test may lead you to the wrong conclusion in two ways." THAT is a statement about the samples. This is called a Type I error. Results are not significant." On the other hand. the probability of committing a Type I error is determined by (and equal to) the alpha level. Hypotheses are always about the population or "general case. We've only seem a small piece of it--the sample. EVER say that the hypothesis has been proven as the result of a single hypothesis test. reject the null hypothesis. and it most certainly does not "prove" that the groups are different or that the hypothesis is correct. meaning that the effect indicates a significant difference. (Sometimes we also say that effects are significant. A significant difference (or effect) "supports" or "confirms" the experimental hypothesis. and we have not seen the population. If the null hypothesis is. true null hypotheses end up being rejected by hypothesis tests! 30 . Remember.05. The analysis is not significant.

If you decrease the alpha level of a test in order to avoid making a Type I error. There is nothing you can do about it (other than lower the alpha level. that one is very likely a Type I error. You can't have it both ways. This is called a Type II error. which has other unfortunate consequences).That's the nature of the beast. Type I and Type II errors are generally traded off. Small sample sizes generally mean small power. Sample size DOES NOT affect the Type I error rate. you may claim not to see an effect that is really there. The ability of a hypothesis test to find an effect that is really there is called the power of the test and is equal to 1-beta. the more likely you are to commit a Type I error on at least one of them. it is false. 31 . If you conduct more than one hypothesis test at alpha=. in fact. the overall (or "family wise") Type I error rate obeys the simple laws of probability. in fact. If the null hypothesis is. then the probability of committing a Type II error is called beta. false.05. That is. You are NOT more likely to make a Type I error because of a small sample size. The more tests you conduct. The most important thing you can do to increase the power of a test is to increase the sample size. decrease the power of the test to find an effect that really is there. o You may conclude that the null hypothesis is true when. you will generally increase beta and. therefore. If you do 20 tests and find only 1 significant difference.

com www.CHAPTER 14: WIBLIOGRAPHY Websites or the links referred are as follows: http://www.gazhoo.00.in/circular/So testing hypothesisI.net www.2636557.com/testing/stories/main/0.eprimers.zdnet.scribd.org http://nrega.ht ml http://www.slideshare.com/doc/201105281211242104/Project+Repor t+on+hypothesis testing www.nic.pdf 32 .10475.

...

...

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

We've moved you to where you read on your other device.

Get the full title to continue

Get the full title to continue listening from where you left off, or restart the preview.

scribd