Week 12: Lecture/Tutorial 12 Chi-Square, Referencing and Review BCPC 301: RESEARCH METHODS 1st Semester, 2019 Lecture outline The following are covered in this lecture: • Chi-square • What is Referencing • Reasons for Referencing • APA referencing Style – In-text referencing – References list – Using Mendeley to in-text referencing and referencing list • Course review Learning outcomes By the end of this lecture/tutorial you should be able to: 1. Understand chi-square test and the interpretation of results 2. Explain why referencing is important is research 3. Understand how to do in-text referencing and reference list 4. Understand how to use Mendeley to do in-text referencing and reference list CHI-SQUARE What is chi-square? • Karl Pearson in 1900 developed Static procedure for testing the significance of the discrepancy between experimental values and theoretical values obtained under some theory or hypothesis. • This test is known as x2 (Chi-square) test. • It is used to find whether the deviation between observation (survey/experiment) and theory may be attributable to chance (fluctuations in sampling) or any other factor. • Chi-square test is applicable to categorical or nominal data and not to data collected on continuous scale Conditions for validity of chi-square test • Chi-square test can be used only if the following conditions are satisfied: – N, the total number of frequency should be reasonably large, say greater than 50 – The observations in the sample should be independent. This means that no individual item should be included twice or more in the sample – No theoretical frequency should be small. Preferably, each theoretical frequency should be larger than 10 but should not be less than 5 Application of chi-square test 1. chi-square test of goodness of fit or chi-square with a priori hypothesis. – That is, how far an observed frequency distribution fits well with the expected frequency distribution based on some theory or hypothesis – In this case, null hypothesis (H0) is “there is no difference between observed frequency and expected frequency”. – The alternate hypothesis (HA) is “there is difference between observed frequency and expected frequency” Application of chi-square test 2. chi-square test for association between attributes or independence of attributes or chi-square test without a priori hypothesis. – This is used to find whether two characters have the tendency to remain together or remain independently. E.g curing a disease and drug – Null hypothesis is ”there is no association between curing a disease and drug taken”. – Alternative hypothesis is “there is an association between curing a disease and drug taken” Application of chi-square test 3. chi-square test to test the quality of proportions. – Chi-square test enables one to find out the significance of difference between two or more population proportions. – If an investigator is interested in finding out whether the proportion of married men is same in four major cities. – The null hypothesis (H0) is “The proportion of married men is the same in four major cities. – The alternate hypothesis (HA)is “The proportion of married men is not the same in four major cities”. Application of chi-square test 4. Chi-square test of homogeneity – Sometimes we need to compare samples taken from two populations differing in some characters. – E.g., samples are drawn from two populations namely “normal” and “liver disease patients” – These two samples are then classified into two: persons with hepatitis and persons without hepatitis – Chi-square is can be used to find out whether the two populations from where the samples are drawn are homogenous or not. – In this case the null hypothesis (H0) is “The two populations from where the samples are drawn are homogenous”. – The alternate hypothesis is “The two populations from where the samples are drawn are not homogenous”. Running a Chi-square test • Although, four different applications are given for test, all these tests are basically the same • They find whether the observed frequency fits well with expected frequency, but the statement of null hypothesis differs. 1. 2. 3. 4. 5. 6. 7. Procedure To Carry Out Chi-Square Test Propose Null and Alternate hypothesis Calculate expected frequencies Find the deviations between expected and observed frequencies Square the deviations and divide by respective expected frequencies Substitute in the formula Write the degrees of freedom Refer the tabulated test values for the specified degrees of freedom at 0.05 (or 0.01) probability level 8. Compare calculated chi-square values with tabulated chi-square values 9. Interpret the results. Interpreting chi-test results from spss Goodness of Fit for a Categorical Variable • Example 1 It is believed that the general human population in a region consists of 10% Hispanic, 10% Asian, 10% African–American and 70% White folk. In a sample survey it was recorded that there were 24 Hispanic, 11 Asians, 20 African–American and 145 White folk. Test whether the observed frequencies differ significantly from the hypothesized values. • Null and alternate hypotheses: – H0 There is no difference between observed and expected frequencies. – HA There is real difference between observed and expected frequencies. SPSS output/results SPSS output/results • • • The observed and expected frequencies are given in the first table. In the second table, the Chi-square value is 5.029 for 3 df and asymptotic significance is 0.170, (i.e., p-value) Since, the p-value 0.170 is greater than 0.05 (p > 0.05), the difference between observed frequencies and expected frequencies is insignificant. • Therefore, the null hypothesis (H0), i.e., there is no difference between observed and expected frequencies is accepted at 5% level of significance. • The answer to our problem is that the racial composition of our sample does not differ significantly from the hypothesized values for human population in that region. Interpreting chi-test results from spss Chi-square Test for Independence of Attributes • • As noted, this test is used to find out whether two categorical variables are associated with each other. number of categories). Example 2 • A group of students were classified in terms of gender (male and female) and blood group (A, B, AB and O). • Find whether there is association between gender and blood group. Interpreting chi-test results from spss Hypothesis and SPSS output/results • Null and alternate hypotheses – H0 There is no association between gender and blood group. – HA There is real association between gender and blood group. Hypothesis and SPSS output/results SPSS output/results • The first table gives the frequencies of blood groups in male and female in the table form (Cross tabulation). • The second table shows 3 degrees of freedom i.e., [(r – 1) (c - 1)] = [(2 – 1) (4 – 1)] = 3, • The p-value 0.852 is greater than 0.05. • The difference is considered insignificant. • The null hypothesis is accepted and therefore, there is no association between sex and blood group. Example 3 • Two groups A and B consist of 100 people each having a particular disease. A drug is given to group A and not to group B. Otherwise both are treated identically. It is found that in group A and B, 80 and 65 persons have recovered from the disease. • Test the hypothesis that the drug helps to cure the disease at 0.05 level of significance. • Null and alternate hypothesis – H0 The drug is not effective in curing the disease. – HA The drug is effective in curing the disease. Step SPSS output/results SPSS output/results Pearson’s for 1 degrees of freedom, i.e., [(r – 1) (c – 1)] = [(2 – 1) (2 – 1)] . The p-value 0.018 is less than 0.05. Therefore, null hypothesis is rejected and the drug is effective in curing the disease (p < 0.05). REFERENCING Conceptualising Social research Epistemology Theoretical Framework Methodology Methods See Crotty (1998, p4) Referencing (Crotty 1998) What is Referencing? • It is about showing and acknowledging all sources of information or ideas that you have used in your research or assignment • When a researcher/student uses another person words or ideas without acknowledging them it is referred to as Plagiarism 26 Why do we do Referencing? • To avoid plagiarism by giving credit to the original source of an idea, piece of information or resource • To avoid plagiarism – Learn good note-taking techniques – Paraphrase appropriately – Summarise correctly and efficiently – Use direct quotations appropriately – Organise your sources – Reference your sources correctly 27 Why do we do Referencing cont’d? • To support your work with the authoritative work of another author • To demonstrate your knowledge and familiarity with a topic that you have researched • To help readers of your work to find the original source of information or ideas that you have used 28 Types/Parts of Referencing Referencing is in two parts: 1. The in-text referencing which is normally done in the text and 2. List of references which is normally at the end of the report. There are two ways of listing the references a. List of references: This refers to sources of materials cited in the text. Any material used for the preparation of the report but was not cited in the text cannot be part of the list of references b. Bibliography: This refers to all sources of informational materials used for the presentation of the whether cited in the text or not. 29 Referencing Styles • There are many different referencing styles. Each style includes the same basic information, but organizes it slightly differently. Some of the known formats/styles are: 1. American Psychology Association (APA) 2. Modern Language Association (MLA) 3. Harvard Type 4. Oxford format 5. Chicago format etc 30 APA Referencing Style • The APA reference style uses the Author-Date format. • It is used by psychologist, sociologist and other social scientist • The APA format requires short notes, or citations, put in parenthesis with the text instead of footnotes or endnotes • The complete format can be found in the publication manual of the American Psychological Association available http://student.ucol.ac.nz/library/onlineresources/Documen ts/APA_guide_2015.pdf 31 In-text Referencing • In-text referencing can take two form: 1. Direct quotation: use quotation marks around the quote and include page numbers in the Last name and publication date 2. Indirect quotation: Identify source material that you are paraphrasing by citing the author’s last name and the publication date, either in your sentence or in parenthesis. You do not have to cite page number(s) for paraphrases. 32 Examples of Direct Quotation Samovar and Porter (1997) point out that "language involves attaching meaning to symbols" (p.188). Alternatively, “Language involves attaching meaning to symbols" (Samovar & Porter, 1997, p.188). 33 Notes on Direct Quotation • Shorter quotations (fewer than 40 words) should be incorporated within your paragraph with quotation marks: they should not be indented separately but should have page numbers preceded by p. or pp. • Longer quotation (over 40 words) should be blockindented five spaces from the left margin and typed without quotation marks 34 Examples of Indirect Quotation 1. If you mention the author’s name and the publication date in your sentence, you will not need any additional citation. Example: In 1983 study, Deborah Mayo began to question the scientific validity of experience involving laboratory animals. 2. If you mention the author’s last name in your sentence, place the date of publication in parentheses right after the name. Example: Mayo (1983) questioned the scientific validity of experiments involving laboratory animals 35 Examples of Indirect Quotation cont’d 3. If you do not mention the author’s name or the publication date in your sentence, put both parentheses with comma between them (Kofi, 2001) 4. If you cite two works by one author published in the same year, distinguish them by placing an (a) and a (b) after the date within the parenthesis e.g. (Kofi, 2001a) 5. If you cite authors with the same last name, use their first and middle initials within the parentheses (Salifu, A. 2016); Salifu, J. 2016) 36 Examples of Indirect Quotation cont’d 6. If a work has two authors, combine the names with “and” in your sentence. Use an ampersand “&” instead of “and” in a parenthetical citation. (Kofi & Ama, 2001) 7. If a work has no author, cite it by the first two or three words of the article, starting with the first important word and placing these two words or three words in quotation marks (”Business Ranking”, 2011) 8. If you use a quotation from an indirect source, precede the source information in the parenthetical citation with the words “as cited in”. In the reference list include an entry only for the secondary source. Chang (as cited in Polit & Beck, 2008) outlined the four main concepts… 37 Examples of Indirect Quotation cont’d 9. If you cite two or more works by different authors in one parenthetical citation, give the work in alphabetical order and separate them with semicolons (;) e.g. (Adam, 2003; Kofi, 2001; Taku, 2005) 10.If a work has more than two to five authors, cite all of them in your sentence or parenthetical citation in the first instance and in all other subsequent references use the last name of the first author followed by “et al.” (Taku, Toyu, & Naam, 2001) Taku et al. (2001) 38 Examples of Indirect Quotation cont’d 11.If a work had six or more authors, use et al. after the first authors last name in all references in the text e.g. (Adam et al., 2003) 39 Reference list (examples by type of publication) • Alphabetize entries in the list of references by authors last names • If a work has no author, alphabetize it by its title • The first element of each entry is important because citations in the text of the paper refer to it and readers will be looking for it in the alphabetized list. Make sure the first element of each entry corresponds with your in-text citations • The date of publication appears immediately after the first element of the citation, followed by titles 40 Reference list (examples by type of publication cont’d) 1. Book with one author King, M. (2000). Wrestling with the angel: A life of Janet Frame. Auckland, New Zealand: Viking. N.B. The first letter of the first word of the main title, subtitle and all proper nouns have capital letters. 2. Book with two to five authors Krause, K. L., Bochner, S., & Duchesne, S. (2006). Educational psychology for learning and teaching, (2nd ed.). South Melbourne, Vic., Australia: Thomson. N.B. Use & between authors’ names, except when paraphrasing in text. 41 Reference list (examples by type of publication cont’d) 3. Edited Book: use (Ed.). Before the date. e.g. DeGenova, M.K. (Ed.). (1997). Families in cultural context: Strength and challenges in diversity. Mountain View, CA: Mayfield 4. Edition other than the first: place the edition number in parenthesis after the title; for a revised edition, use Rev. ed. e.g. Bennett, L., Jr.(1984). Before the Mayflower: A history of Black America (5th ed.). Harmondsworth, England: Penguin Books. 5. Books by a corporate Author or Group: e.g. U.S Bureau of the Census. (1999). Statistical abstract of the United states, 1999 (11th ed.) Washington, DC: Government Printing Office 42 Reference list (examples by type of publication cont’d) 6. Books without an author or editor: e.g. The control of the campus: a report on the governance of higher education. (1982). Lawrenceville, NJ: Princeton University Press 7. Multivolume work: e.g. The entire set: Neather, C.A., & Richardson, G.F. (1930). A course in English for engineers (vols. 1-2). Boston:Ginn. One volume: Battle, K.P. (1912). History of the university of North Carolina: vol. 2. Raleigh, NC: Edwards and Broughton. If the volume has it own title, include it after the volume number. 43 Reference list (examples by type of publication cont’d) 9. Essay or Article in a Book: e.g. Wilkinson, D. (1997). American families of African descent. In M.K. DeGenova (Ed.), Families In Cultural Context (p. 35-51). Mountain View, CA: Mayfield. The selection title is written without quotation marks and with lower-case letters (except for the first letter of the title, of proper names and of a subtitle after a colon). The book title is in the same lowercase format but is italicized. Place the page numbers for the complete title. 44 Reference list (examples by type of publication cont’d) Citing from Reports, Documents and Dissertation Government documents, research report, monograph U.S Census Bureau. (1999, September). Money income in the united states. Current population reports (p60-206).Washington, DC: author. Kreshner, L., Addams, B., & Winestein, C. (2001). Use of manipulatives in teaching mathematics in grades four through six (Report No. 6). New Orleans: state Mathematics Service A report or document number, if there is one should appear in parentheses immediately after the number. 45 Reference list (examples by type of publication cont’d) Dissertation Fredericks, C. (1999). HIV testers and non-testers at a university students health centre: A study of college students sexual risk taking (Doctorial dissertation, University of South California, 1999) Dissertation Abstracts International, 60 (02A), 0346. 46 Reference list (examples by type of publication cont’d) Articles in a scholarly journal paginated by year or volume • The entire year’s issues are paginated as a unit • Battaglia, D. M., Datteri, D., & Lord, C. (1998). Breaking up is (relatively) easy to do: A script for the dissolution of close relationships. Journal of social and personal Relationships, 15, 829-845 • Do not italicise the title of the article, and do not capitalize it (except for the first word, proper names and the first word after a colon. • Capitalise and italicise the title of the journal. Underline the volume number. It is followed by a comma and the complete page numbers of the article. 47 Reference list (examples by type of publication cont’d) Article in a scholarly journal paginated by issue Each issue begins with page 1. Blanton, J.S. (2000). Why consultants don’t apply psychological research. Consulting psychological journal: practice and research, 52 (4), 235-247 Underline the volume number. It is followed by the issue number in parentheses (not underline), a comma, and the complete page numbers of the articles. 48 Reference list (examples by type of publication cont’d) Internet Article Based on a Print Source • O’Barr, W., & Conley, J. (2000). When cultures collide: Social security and the Market [electronic version]. Journal of psychology and Financial Market, 1, 92-100 • Article in an Internet-only Journal • Wagner, L. (2001). Virtual Advertising: Delivering Student services. Online journal of Distance Learning Administration, 4(3). Retrieved June 1, 2002, from http://www.westga.edu/distance/main11.htm • World Wide Web Site • International Society for Mental Health Online. (n.d.). Children and trauma: Reflections on the World Trade Centre disaster. Retrieved October 15, 2001, from http://www.ismho.org 49 Using Mendeley as a referencing tool Course Review Positivism Objectivism Research problem/topic/issue/question Epistemology Literature review Theories Constructionism Subjectivism/ interpretivism Theoretical Framework Methodology Sampling Data collection Method Data analysis Ethics Exam (suggested topics) 1. Case study--- test your understanding of the entire research process. 2. Literature review 3. Methodology/research design 4. Methods for data collection 5. Sampling 6. Qualitative data analysis 7. Quantitative data analysis (chi-square, conditions, statement of hypothesis and interpretation) 8. Referencing 52