Research Hypotheses PDF

RESEARCH METHODS IN IS TOPIC 2(B): RESEARCH HYPOTHESIS(ES)  OVERVIEW  Topics Covered Introduction Characteristics of Hypothesis (es) The Null and Alternative Hypothesis (es) Examples From Real-Life Situations Types of Errors...

RESEARCH METHODS IN IS TOPIC 2(B): RESEARCH HYPOTHESIS(ES)  OVERVIEW  Topics Covered Introduction Characteristics of Hypothesis (es) The Null and Alternative Hypothesis (es) Examples From Real-Life Situations Types of Errors  Type I Error  Type II Error. 12/01/2024 Edwin Omol 2  INTRODUCTION  Hypothesis  is a tentative intelligent guess posited to direct one’s thinking towards the solution of the problem.  These may originate in the sub-problems. Often a one-to-one correspondence exists between the sub-problems and their corresponding hypotheses or questions. In this case we have as many hypotheses or questions as we have sub-problems. 12/01/2024 Edwin Omol 3  INTRODUCTION Contd.  Hypotheses  they may be directional (if a negative and a positive relationship is suggested) or non-directional (if no direction is stated).  The researcher is only able to state directional hypotheses when some information on the phenomena under study is available. Such info is derived from past experience, LR or existing theories. Some researchers don’t include hypotheses simply because their studies are exploratory. 12/01/2024 Edwin Omol 4  INTRODUCTION Contd.  Hypotheses are neither proved nor disapproved. They can only supported or not supported (rejected) by the data.  To set out to prove a hypothesis would defeat the impartiality of research. The researcher would be biased or would bias the procedure by looking only for those data that would approve/disapprove the hypothesis(es) 12/01/2024 Edwin Omol 5  INTRODUCTION Contd.  Since they have nothing to do with proof we must let the chips fall where they may.  Their acceptance or rejection is dependent on what the data (and the data alone) ultimately reveal.  If you discover that the data does not support the hypothesis, don’t let the outcome disturb you, it merely means that your educated guess about the outcome of the investigation was incorrect. 12/01/2024 Edwin Omol 6  INTRODUCTION Contd.  Examples  1. “Students who receive counseling will show a greater increase in creativity than student not receiving counseling”. 2. Automobile A is performing as well as automobile B.  NB  these hypotheses are capable of being objectively verified and tested.  Thus a hypothesis states what we are looking for and it is a proposition which can be put to test to determine its validity 12/01/2024 Edwin Omol 7  CHARACTERISTICS OF HYPOTHESIS(ES) 1. Hypothesis should be clear and precise. Otherwise the inferences drawn on its basis cannot be taken as reliable. 2. Hypothesis should be capable of being tested. It is testable if other deductions can be made from it, which in turn, can be confirmed or not confirmed by observation. 3. It should state the relationship between variables, if it happens to be a relational hypothesis. 12/01/2024 Edwin Omol 8  CHARACTERISTICS OF HYPOTHESIS(ES) Contd. 4. Should be limited in scope and must remember that narrower hypothesis are generally more testable and should develop such hypothesis. 5. Hypothesis must explain the facts that give rise to the need for explanation i.e. by using the hypotheses and other known and accepted generalizations, one should be able to deduce the original problem condition- it should have empirical reference- explain what it claims to explain. 12/01/2024 Edwin Omol 9  CHARACTERISTICS OF HYPOTHESIS (ES) Contd. 6. They should be stated as far as possible in the most simple terms so that the same is easily understandable by all concerned. But simplicity does not imply significance 7. Hypotheses must be consistent with most known facts i.e. it must be consistent with substantial body of established facts. It should be one that judges accepts as being the most likely. 8. Hypotheses should be amenable for testing within reasonable time. 12/01/2024 Edwin Omol 10  THE NULL AND ALTERNATIVE HYPOTHESIS  When we hypothesize that there is no difference between groups, no relationships between variables, or more generally, no patterns in the data, we are forming a null hypothesis  E.g. Comparing Method A with Method B and proceed to state that both of them are equally good, then this assumption is termed as the null hypothesis  Null hypothesis are used primarily during statistical analysis. The null hypothesis is the opposite of the hypothesis- probably not true-and we often set out to disapprove a null hypothesis. 12/01/2024 Edwin Omol 11  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  E.g. a team of social workers believe that one type of after-school program is good for teenagers (Program A) is more effective than another program (Program B) in terms of reducing high school dropout rates.  The teams research hypothesis is: “Teenagers enrolled in Program A will graduate from high school at a higher rate than teenagers enrolled in Program B”. 12/01/2024 Edwin Omol 12  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  Because the social workers cannot actually support their hypothesis, they instead try to reject an opposite hypothesis i.e. “There will be no difference in the high school graduation rates of teenagers enrolled in Program A and those enrolled in Program B”.  Thus if the researcher finds out that there is a substantial difference in graduation rates between the two Programs- and in particular, if the graduation rate is higher for the youth in Program A- they can reject the “no difference” hypothesis and thus by default supported their research hypothesis 12/01/2024 Edwin Omol 13  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  Alternative Hypothesis  we may think that Method A is superior or Method B is inferior, thus we are then stating what is termed as alternative hypothesis.  If the sample results do not support the null hypothesis, we should consider that something else is true. What we conclude in rejecting the null hypothesis is known as the alternative hypothesis, i.e. the set of alternatives to the null hypothesis is referred to as alternative hypothesis. 12/01/2024 Edwin Omol 14  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  If we accept the null hypothesis then we are rejecting the alternative hypothesis and the vice versa.  The null and the alternative hypothesis are chosen before the sample is drawn. The researcher must avoid the error of deriving hypothesis from the data that he/she collects and then testing the hypothesis from the same data. 12/01/2024 Edwin Omol 15  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  Conclusion (i) Alternative hypothesis is usually the one which one wishes to prove and the null hypotheses is the one which one wishes to disapprove.  Thus, a null hypothesis represents the hypothesis we are trying to reject, and alternative hypothesis represents al other possibilities 12/01/2024 Edwin Omol 16  THE NULL AND ALTERNATIVE HYPOTHESIS Contd.  Conclusion Contd. ii. Rejecting a certain hypothesis when it is actually true involves a great risk, it is taken as null hypothesis because then the probability of rejecting it when it is true is alpha (the level of significance) which is chosen to be very small see type I and II. iii. Null hypothesis should always be specific hypothesis i.e. it should not state about or approximate a certain value 12/01/2024 Edwin Omol 17  O.J. SIMPSON TRIAL: THE SITUATION  Read O.J Simpson murder trial online  In which O.J. was assumed innocent.  Evidence collected: Size 12 bruno magli bloody footprint, Bloody glove, Blood spots on white ford bronco, The knock on the wall, DNA evidence from above, motive(?), etc… 12/01/2024 Edwin Omol 18  O.J. SIMPSON TRIAL: JURY DECISIONS  In Criminal Trial  The evidence does not warrant rejecting the assumption of innocence. Behave as if O.J. is innocent.  In Civil Trial  The evidence warrants rejecting the assumption of innocence. Behave as if O.J. is guilty. Was an error made in either trial? 12/01/2024 Edwin Omol 19  ERRORS IN TRIALS Truth Jury Innocent Guilty Decision “Innocent” OK ERROR Guilty ERROR OK If O.J. is innocent, then an ERROR was made in the civil trial. If O.J. is guilty, then an ERROR was made in the criminal trial. 12/01/2024 Edwin Omol 20  ERRORS IN HYPOTHESIS TESTING Truth Null Alternative Decision hypothesis hypothesis Do not reject TYPE II OK null ERROR TYPE I Reject null OK ERROR 12/01/2024 Edwin Omol 21  TYPES OF ERRORS  There is always a chance of making one of these errors. We’ll want to minimize the chance of doing so! Type I Error  The null hypothesis is rejected when it is true (supported). Type II Error  The null hypothesis is (supported)not rejected when it is false (rejected). 12/01/2024 Edwin Omol 22  TYPE I ERROR  Type I error  also known as a “false positive”: the error of rejecting a null hypothesis when it is actually true.  In other words, this is the error of accepting an alternative hypothesis (the real hypothesis of interest) when the results can be attributed to chance.  Plainly speaking, it occurs when we are observing a difference when in truth there is none (or more specifically - no statistically significant difference). 12/01/2024 Edwin Omol 23  TYPE II ERROR  Type II error  also known as a "false negative": the error of not rejecting a null hypothesis when the alternative hypothesis is the true state of nature.  In other words, this is the error rejecting (of failing to accept) an alternative hypothesis when you don't have adequate power.  Plainly speaking, it occurs when we are failing to observe a difference when in truth there is one. 12/01/2024 Edwin Omol 24  The End 12/01/2024 Edwin Omol 25