Denunciar

Compartilhar

Seguir

•3 gostaram•76 visualizações

•3 gostaram•76 visualizações

Denunciar

Compartilhar

Baixar para ler offline

MELJUN CORTES research lecture series.

Seguir

- 2. RESEARCH WHAT IS RESEARCH? The systematic , rigorous investigation of a situation or problem in order to generate new knowledge or validate existing knowledge. It is a careful, critical, disciplined inquiry, varying in technique and method according to nature and conditions of the problem identified toward clarification or resolution of a problem (Good, p. 464)
- 3. Fundamental Goals of Research To satisfy man’s craving for more understanding, To improve his judgement To add to his power To reduce the burden of work To relieve suffering To increase satisfaction in multitudinous ways
- 4. Types of Research 1. Basic Research seeks to contribute to knowledge through the development of a theory or concept. The main motivation is to expand man’s knowledge, not to create or invent something. There is no obvious commercial value to the discoveries that result from basic research. 2. Applied Research seeks to provide solutions to problems through the development and evaluation of processes, policies and other activities that require specific courses of action.
- 5. 3. Correlational Research refers to the systematic investigation or statistical study of relationships among two or more variables, without necessarily determining cause and effect. 4. Descriptive Research refers to research that provides an accurate portrayal of characteristics of a particular individual, situation or group. This is also known as statistical research. 5. Ethnographic Research refer to the investigation of a culture through an in depth study of the members of the culture ; it involves the systematic collection, description, and analysis of data for development of theories of cultural behaviour.
- 6. 6. Experimental Research is an objective, systematic, controlled investigation for the purpose of predicting and controlling phenomena and examining probability and causality among selected variables. 7. Exploratory Research is a type of research conducted for a problem that has not been clearly defined. 8. Historical Research is research involving analysis of events that occurred in the remote or recent past. 9. Phenomenological Research an inductive, descriptive research approach developed from phenomenological philosophy; its aim is to describe an experience as it is actually lived by the person.
- 7. Research are classified into two groups: Qualitative research is research dealing with phenomena that are difficult or impossible to quantify mathematically, such as beliefs, meanings, attributes and symbols. The qualitative methods investigates the why and how of decision making, not just what, where, and when. Quantitative Research refers to the systematic empirical investigation of any phenomena via statistical, mathematical or computational techniques. The objective of quantitative research is to develop and employ mathematical models, theories and/or hypotheses pertaining to phenomena.
- 8. RESEARCH OUTLINE 1. Abstract of the Study 1.1 Objectives 1.2 Major hypotheses 1.3 Methodology 1.4 Findings 1.5 Conclusions 1.6 Recommendations
- 9. 2. Chapter 1 2.1 Introduction of the Study 2.2 Background of the Study Description of the general context in which the problem is to be viewed and discussed Description of the situation in and the process by which the problem arose and developed Reasons for choosing the topic 2.3 Theoretical/Conceptual Framework
- 10. Theoretical Framework It is important that you cite existing theories and ideas that are relevant to your chosen topic within the theoretical framework. This includes defining key terms from your statement of the problem and research questions and hypothesis. It consists of theories that seem to be interrelated. It can be used to answer descriptive research questions. (diagram )
- 11. Conceptual Framework It is the researcher’s own position on the problem and gives direction to the study. it may be an adaptation of a model used in a previous study, with modifications to suit the inquiry., through the conceptual framework, the researcher can be able to show the relationships of the different constructs that he wants to investigate. (diagram)
- 12. 2.4 Statement of the Problem There should be a general statement of the whole problem followed by the specific questions or sub problems into which the general problem is broken up. It provides direction and focus to the study. Consider the ff: 1. The research problem is written in question form and identifies specific area. 2. The topic is phrased in workable and manageable manner.
- 13. 3. The scope is limited to realistic parameters that are not too narrow nor too broad. 4. The words used are unbiased, objective, and not emotional-laden. 5. The relationship between variables to be studied are clearly cited. 6. The phrases and wordings are measurable and can be empirically proven. 7. The problems identify the data and techniques to answer the questions.
- 14. Assumptions and Hypotheses The hypotheses formulated are testable, that is, they can be accepted or rejected. Hypotheses are not proved, they are only determined as true or not. If the findings from the data do not conform to the hypotheses, the latter are rejected. If the findings conform to the hypotheses, the latter are accepted as true and valid.
- 15. 2.5 Significance of the Study The importance of the whole study must contain explanations or discussions of any of the following: 1. The rationale, timeless and relevance of the study to the existing conditions must be explained or discussed. 2. Who are to be benefitted and how they are going to be benefitted. 3. Possible contribution to the fund of knowledge. 4. Possible implications
- 16. 2.6 Scope and Limitation The statement of the research problem requires a detailed explanation of the study’s parameters and limitations. It should indicate study coverage with concrete reference to: variables, sources of data, methods, analysis, timeframe and constraints that might be encountered in the conduct of the study.
- 17. 2.7 Definition of Terms Terms should be defined either lexical or operational as it is used in the study.
- 18. Chapter 2 Review of Related Literature and Studies Thematic approach - literature and studies organized around a topic or issue, rather than the progression of time . However progression of time may still be an important factor in a thematic review. Synthesis
- 19. Chapter 3 Methodology Research Design Research design appears to be the schema that maps out the sources of data, type of data to be collected, how the data will be collected, and the methods to be used in data analysis. A good research design must also set time constraints within which the research problem should be answered.
- 20. Sampling Sampling is the process of choosing adequate and representative elements from the population. Sampling makes the scope of the study manageable because of the small number of respondents to be covered, and increases the likelihood of obtaining more reliable and accurate result.
- 21. The adequate number of elements to be taken as samples is based on the desired confidence level (alpha : α) and room for error (e) in selecting the correct sample. In the academe, the most common confidence levels employed in thesis and dissertation sample size computations are : 0.01 ; 0.05; 0.10. The higher the confidence level desired, the bigger sample size should be..
- 22. Statistics books contain different formulae in determining the sample size , the common is Slovins formula. Formula : n = N / (1+Ne2) if N = 350 ; e = .05 n = 187
- 23. Sampling Designs Sampling designs are commonly classified into probability and non probability sampling. Probability is used when inferences about the population are required , as in thesis, dissertation or other academic researches. Non probability sampling is usually adopted when immediate information feedback is needed, as in marketing research studies, such as product launching.
- 24. Probability Non – Probability – Random Quota – Systematic Judgement – Stratified Convenience – Cluster Accidental – Area Snowball – Double Purposive – Multi – Stage
- 25. Methods of Data Analysis Data analysis involves the application of the appropriate statistical tools to generate results which can be interpreted meaningfully to answer the research problems posed at the beginning of the study/investigation. The most common problem of a researcher at this stage of the research process is choosing the most appropriate statistical tools for data analysis.
- 26. HOW IMPORTANT STATISTICS IN RESEARCH In theory they are very important. Without statistics it is almost impossible to come to an informed conclusion in any piece of research. The use of statistics is wide ranging in the field of research and without the sue of statistics , it is virtually impossible to interpret a true meaning of what the research shows. Not to exaggerate ... statistics is the BACKBONE OF RESEARCH.
- 27. Dangers of (mis)using statistics Statistics, no matter how carefully collected, can always be flawed e.g. without a sample of thousands of people (ensuring they are representative of the whole population), you cannot be certain that the results can be wholly generalized. Statistical information can be easily manipulated to show very different results.
- 28. Levels of Measurement NOMINAL – uses categories or classifications; order is meaningless. Categories are mutually exclusive ; lowest level of data measurement since data cannot be transformed. Examples: gender; form of ownership; civil status and etc. INTERVAL – categories are ordered or ranked using equality of distance. Classes are mutually exclusive . Higher level of data and measurement than nominal and ordinal. Zero point has no true value.
- 29. Examples: Age; Average monthly income; number of years RATIO – categories are exclusive and are in equidistant orders. Possess the characteristics of the nominal, ordinal, and interval. Possess true zero point. Data can be transformed. And highest level of data measurement. Examples: net income per year ; return of investment; average no. of tardiness and absences.
- 30. Statistical Treatment Descriptive : Frequency or percentage – usually used to determine the profile of respondents engage in the study. Weighted Mean - summarizing the data in terms of measures of central tendency. It is a kind of average. Instead of each data point contributing equally to the final mean, some data points contribute more weight than others.
- 31. Weighted Mean = Sum of weighted terms Number of Terms 2. Inferential test - use to test the research hypothesis. - a technique that relies on the probability distribution, for reaching the conclusion concerning the reasonableness of the hypothesis. These hypothetical testing are classified into :
- 32. 1. Parametric Test if data has an assumption or information about the population parameter. the distribution is normal refers to interval and ratio data mean is known the information about the population is completely known applicable only to variables
- 33. Tests used are: 1.1 One Sample Mean – test of significant difference between sample mean and population mean 1.1.1 Z – test (n >30) 1.1.2 t – test ( n < 30 )
- 34. 1.2 Two sample Means - two independent sample means of significant difference 1.2.1. t – test 1.2.2 Z – test 1.2.3 Pearson Product Moment Correlation – to measure strength of association or relationship between two variables.
- 35. 1.3 k - independent Sample Means 1.3.1 One Way Analysis of Variance , ANOVA 1.3.2 Two way Analysis of Variance - two or more sample variances.
- 36. 2. Non Parametric Tests - used in the case of non parametric independent variables. - distribution is arbitrary - the data use nominal and ordinal - use median as measure of central tendency. - information about the population is unavailable - applicable only to variable and attributes
- 37. 2.1 One Sample Mean 2.1.1 Chi Square 2.1.2 Kolmogorov – Smirnov 2.1.3 Runs 2.1.4 Binomial 2.2 Two Independent Sample Means 2.2.1 Chi Square 2.2.2 Mann – Whitney / U test 2.2.3 Median Test
- 38. 2.2.4 Kolmogorov Smirnov 2. 2.5 Kruskal Wallis Test 2.3 Paired Samples 2.3.1 Sign Test 2.3.2 Wilcoxon Test 2..3.3 McNemar Test 2.3.4 Chi Square Test 2.3.5 Cochran’s Q Test
- 39. Conclusion To make a choice between parametric and non parametric test is not easy for a researcher conducting statistical analysis. For performing hypothesis, if the information about the population is completely known, by way of parameters, then the test is said to be parametric test, whereas, if there is no knowledge about a population and it is needed to test the hypothesis on population. then the test conducted is considered as non parametric test.
- 40. Parametric Inference 1. To test significance of difference between 1.1 One Sample and Population Mean - t test ; Z – test The mean number of students in a day in a local university is 100. Taguig City University is one of the local university in Taguig . The researcher would want to know if the said university has the same mean as the population mean in other university in Taguig.
- 41. Ho : There is no significant differences to the mean number of students in other city university. Ha: There is significant difference to the mean number of students in other university.
- 42. 1.2 Two Independent Sample Mean - t test ; Z- test If the researcher would also want to know if PUP has the same mean number of students in TCU. Ho: There is no significant difference between the mean number of students in TCU and PUP. Ha: There is a significant difference between the mean number of students in TCU and PUP.
- 43. 1.3k - Independent Sample Means - One Way ANOVA The manager would want to know if there is any difference in applying three different measurements of the fragrance chemical in the perfume products. A total of 30 formulations were made ( 10 per each measurement), and 30 prospective customers were asked to rate the scent of the perfumes.
- 44. Ho: There is no significant difference in the mean of the customers on the three formulations. Ha: There is no significant difference in the mean of the customers on the three formulations.
- 45. Non Parametric Inference 1. To test significance of difference 1.1 One sample mean and population mean. The marketing manager will pursue the TV commercial if public acceptability is at least 75%. A sample survey was done to determine this and a sample population market acceptability was measured to test the following:
- 46. Ho : Proportion of public acceptance is at least 75%. Ha : Proportion of public acceptance is less than or greater than 75%.
- 47. 1.2 Proportions of two related or dependent random samples. McNemar Test ( n>30) The President of the Philippines wanted to know if there is any difference in people’s satisfaction rating after his one year of presidency. A survey was done among the people before and after his one year of presidency whether they are generally satisfied or not. ( paired nominal data)
- 48. Ho: The proportion of satisfied people is the same before and after. There is no significant difference in the proportion of satisfied people before and after. Ha: The proportion of satisfied people after is significantly different before his one year of presidency.
- 49. 1.3 Proportion of K - dependent random samples: Cochran’s Q Test Using the example above : The president wanted to know the proportion of satisfied people among the members of the society: above average , average and the poor or below average.
- 50. 1.4 two independent random samples Mann – Whitney / U test or Sum of Ranks A company ranked its salespeople based on sales and it was noted that many in the top ranks came from Metro Manila and Visayas. The sales manager wanted to know if there was any difference between those from M.M and Visayas
- 51. 1.5 k - independent random samples - Kruskal Wallis Test A company tested its computer product with three different specifications . Customers were asked to rate the computer product. the ratings were then ranked on the overall across the three different specifications
- 52. Statistical Treatment of Data The following statistical tests were used to analyse the gathered data: frequency and percentage, weighted mean Frequency and Percentage. This was used to describe the profile of the respondents. The formula is: % = f x 100 N
- 53. where: % = percentage, f = frequency of responses, and N = total number of respondents Weighted Mean. This was computed to determine the average response of the respondents on the various factors considered in the study.
- 54. Formula : – ∑WF WM = N where: WM = weighted mean, W = weights assigned, F = frequencies for each option, ∑WF = sum of all weighted scores obtained by a sample, and N = number of respondents in the sample
- 55. Likert Scale Method For verbal interpretation of the computed weighted means, the following intervals was used: Weight Limits Verbal Interpretation 5 4.50 – 5.00 Strongly Agree SA 4 3.50 – 4.49 Agree A 3 2.50 – 3.49 Moderately Agree MA 2 1.50 – 2.49 Disagree DA 1 1.00 – 1.49 Strongly Disagree SA
- 56. Pearson Product Moment Correlation. This is used to determine the significance of relationship among the given variables such as students’ performance in the basic education and the teaching competencies of teachers. Analysis of Variance . This is used to test the significance of difference of means of two or more groups that are to be determined at one time. t – Test . This is used to test the significant of difference between two independent variables.
- 57. Decision of Hypothesis If the computed results of the test of statistics is lower than the critical value of the test statistics , the null hypothesis is accepted at 0.05 level of significance. If the computed results of the test statistics is greater than the critical value of the test statistics , the null hypothesis is rejected at 0.05 level of significance.
- 58. In reporting statistical tests of significance, include information concerning the value of the test, the degree of freedom, the probability level and the direction of the effect. The findings are compared and contrasted with that of other previous studies and interpretations are made thereof.
- 59. Chapter 4 Analysis, Presentation and Interpretation of Data Analysis is the process of breaking up the whole study into its constituent parts of categories according to the specific questions under the statement of the problem. Presentation the process of organizing data into logical , sequential and meaningful categories and classification to make them amenable to study and interpretation.
- 60. Textual presentation uses statement with numerals or numbers to describe data. The aim is to focus attention to some important data and to supplement tabular presentation. Tabular presentation Graphical presentation
- 61. Chapter 5 Summary of Findings, Conclusions and Recommendations Summary of Findings There should be a brief statement about the main purpose of the study, the population or respondents, period of the study, method of research used, research instrument and sampling design. The findings should be in textual form . The specific questions should follow the order they are given under the SOP.
- 62. No deduction, nor inference nor interpretation should be made otherwise it will be duplicated in the conclusion. Only important findings, the highlights of the data, should be included in the summary, especially those upon which the conclusions should be based. Findings are not explained nor elaborated upon anymore. It should be stated concisely. No new data should be introduced.
- 63. Conclusion Conclusions are inferences, deductions, abstractions, implications, interpretations, general statements and/or generalization based upon the findings. They should not contain any numerals because numerals generally limit the forceful effect or impact and scope of generalization. No conclusion should be made that are not based upon the findings.
- 64. It should appropriately answer the specific questions in the SOP It should be formulated concisely, brief, and short, to convey all the necessary information resulting from the study. It should not be a repetitions of any statements anywhere in the study.
- 65. Recommendations Recommendations are appeal to people or entities concerned to solve or help solve the problem discovered in the inquiry. No recommendations should be made for a problem , or any thing that has not been discovered or discussed in the study. It should aim for the ideal but they must be feasible, practical and attainable and should be logical and valid.
- 66. It should be addressed to the persons, entities, agencies or offices who or which are in position to implement them. Last, there should be recommendation for further research on the same topic in other places and other variables to verify, amplify or negate the findings of the study.
- 67. Bibliography This contains a complete list of references used in the study. The format is APA Manual of 1964. Appendices This contains all the supplementary materials of the study.
- 68. QUALITIES OF A GOOD RESEARCH Research Oriented Efficient Scientific Effective Active Resourceful Creative Honest Economical Religious
- 69. Every great accomplishment starts with the decision to try. THANK YOU !