Psychology 123 Lectures 5-8 PDF
Document Details
Uploaded by Deleted User
University of the Western Cape
Tags
Summary
These lecture notes cover topics related to research methods in psychology at the University of the Western Cape. It details data collection, levels of measurement, and different research methods. These notes are designed for undergraduate psychology students.
Full Transcript
lOMoARcPSD|42337356 Psychology 123 lectures 5 - 8 Intro To Research Methods 123 (University of the Western Cape) Scan to open on Studocu Studocu is not sponsored or endorsed by any college or university Downloaded by Emihle Mz...
lOMoARcPSD|42337356 Psychology 123 lectures 5 - 8 Intro To Research Methods 123 (University of the Western Cape) Scan to open on Studocu Studocu is not sponsored or endorsed by any college or university Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Data Collection: Lecture 5 Psy123 Data collection is a systematic gathering of information for research or practical purposes. Examples are: (a) surveys, (b) interviews, (c) laboratory experiments, and (d) psychological testing. Before data is collected some critical decisions will have been made about the research topic. Formulate the research question: EXAMPLE: wherever applicable: consider variables to be measured / what are the conceptual and operational definitions/ how to generate hypotheses Decided on a research design Perform the appropriate sampling Now you are on track to gather information / collect the data for your study Levels of Measurement This step involves gathering data from the participants It may also include: o aspects of quantifying variables, o levels of measurement and o the appropriate techniques for gathering data o When a researcher decided to use quantitative research methods o He/she may select from TWO types of levels/scales of measurement. viz.: CATEGORICAL/ DISCRETE (data is usually fixed): Nominal scale or Ordinal scale CONTINUOUS (data can be measured): interval cale or Ratio scale When we quantify/ rank/rate variables, we can choose between FOUR levels or scales of measurement: 1. Nominal 2. Ordinal 3. Interval 4. Ratio 1. Nominal Scales. (Categorial scale) We simply classify variables into mutually exclusive groups, or we provide categories and assign labels in the form of numbers to them. Example: male/ female, young, middle-aged, old, happy/ sad Example: 1= male; 2= female; 1= young; 2= middle-aged; 3= old 1= happy; 2= sad 2. Ordinal scales (categorial scales To go a step further, we can use ordinal scales to assign variables in the form of numbers so that one variable can be placed in relation to another variable in terms of the number of relevant attributes they possess. Example: assigning numbers to examination/test marks to categorise them as follows: (0- 40%) = 0 (40-50%) = 1 (50-60%) = 2 (60-70%) = 3 (70+ %)= 4 3. Interval or rating scales (Continuous scales) Interval scales build on the ordinal scale Interval scales show the distance between measures An interval scale assigns numbers in a way that the size or the difference between any two numbers correspond to the size of the difference in the attribute being measured. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 (Classifies data in orders, categories and establish equal differences) Example: the difference scale in temperature; i.o.w. distance is meaningful - measures the difference in temperature, but it is not the absolute/true zero the difference between an IQ score of 90 and 95 is the same as a difference between a score of 110 and 115. Most measures in Behavioural Science uses interval measures/ scales. 4. Ratio Scales: A ration scale is like an interval scale except that a ratio scale has a true zero value. Example: Age: a person cannot be less than 0 years old and a person who is 10 years old is twice as old as someone who is 5 years old. More examples: weight and height Methods for gathering data 1. Questionnaires A questionnaire is a text that ask specific questions on a specific order. Precise way in which answers can be given. Commonly uses Likert-type scale. Each item, the scale is given a number of choices (usually between 3 and 10). Ideally suited for quantitative studies. Questionnaires can be used in structured interviews or can be used in situations when there are little or no direct contact between researcher and participant. Self-administered questionnaires are those that are completed by the participants without the researcher being present. 2. Observational Studies Information can also be obtained by merely observing people. Non-participant observation involves a researcher observing people without interacting with them. Drawback: people may behave differently to the way they normally would, because they know that they are being watched. This option is used to understand a phenomenon by entering the community or social system involved, while staying separate from the activities being observed. EXAMPLE: Observing group members' behavioural reactions at different times throughout the workday. Participant observation: when the researcher becomes part of the group and covertly observes people’s behaviour. the observer participates in ongoing activities and records observations. Participant observation extends beyond naturalistic observation because the observer is a "player" in the action. EXAMPLE: for example, living in a commune, becoming a firefighter, enrolling in flight training school, working in a mental hospital 3. Interviews Interviewing involves the researcher asking questions, listening and analysing the responses. Process of gathering information for research using verbal interaction. Begin by giving a brief explanation of him/herself and describe the purpose of the study. Participant’s consent must be obtained. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Structured interview: interviewer follows a set of listed questions in a certain sequence. Unstructured interview: (open-ended) the researcher tries to remain focused on an issue of study and uses predetermined questions. Semi-structured interview: researcher ensure that certain questions are covered, but there is no fixed sequence or format. 5 Focus Groups Focus group interviews entail a group discussion that explores a certain topic. Usually has a moderator that facilitates the discussion. The researcher can gather information in the instance where participants are interacting with one another. Focus groups needs to be large enough to generate rich discussion (6-8 people). Offers the researcher the opportunity to gather information in a situation where participants are interacting with one another. Needs to be large enough to generate rich in-depth discussion, but not too large that some members are left out of the discussion. Qualitative Data Analysis: Lecture 6 Qualitative data refers to nonnumerical data. Qualitative data often takes the form of interview transcripts. Qualitative data also takes the form of documents (e.g., government reports, books, newspaper articles), open-ended survey responses and the interpretation of images and videos. The analysis involves sifting through transcripts in a systematic way so that conclusions may be reached. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 There are several methods for analysis qualitative data which all revolve around the analysis of meaning. Qualitative research is significantly different from quantitative research and therefore has its own verification processes What is qualitative data analysis? (QDA) The range of processes where we move from: (a) the qualitative data that have been collected, (b) into some form of explanation, (c) understanding, or (d) interpretation of: the (a) people and (b) situations we are investigating. Use of Qualitative Research: understanding underlying reasons; opinions and motivations. (b) provides insight into a problem. When analysing qualitative data: the researcher needs to look at (a) depth; (b) detail and (c) complexity CONTEXT is CRUCIAL: i.o.w. what connection to the social world does the participants have? e.g., Giving a student an “award” or “comment” [researcher needs to look at what was the student’s experience like at university?] negative/positive? Transcription of Data Interviews and focus groups: 1) Are always audio-taped. 2) Researchers must then transcribe these interviews into a written format (this is a very time-consuming process, but necessary). Audiotapes: 1) should be described word for word into an electronic document. REMEMBER: 1) You as the researcher should always insert comments, symbols that denote hesitation, pauses, laughs or sighs. 2) Transcribe entire interviews rather than what you want to select. 3) As the researcher transcribes the interviews, he or she must make notes about possible interpretations. Qualitative Data Analysis The six most popular qualitative data analysis methods are: o Qualitative content analysis [read additional notes on Ikamva] o Narrative analysis o Discourse analysis o Thematic analysis o Grounded theory (GT) [read additional notes on Ikamva] o Interpretive phenomenological analysis (IPA) [read additional notes on Ikamva) Narrative Analysis is a technique that approaches the transcript as if it were a story following a particular sequence. The word narrative is always interchangeable used with the word “story”. A narrative always responds to the question: ‘And then what happened?’ Narrative analysis is useful for a study that changes over time. Used to explain how participants in a study make sense and meaning of themselves and their actions. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Example: A narrative of learners’ lives, establishes the importance of stories, provides an illustrative example of the analysis of an adult learner's story Discourse analysis Discourse simply emphasises the written or spoken language. Discourse includes the relationships we have with other people, as well as with power. Discourse is a process of reasoning about things in social realities. i.o.w. Reasoning about where you fit in in your own society. The researcher typically tries to draw attention to dominant meanings of phenomenon, as well as how such meaning may be ambivalent or contradictory Discourse analysis entails analysing language in a political or social cultural context. I. o. w. analysing language such as a conversation, a speech, a book or any text in the society we live in. Discourse analysis wants to investigate the functions of language (i.o.w. what is language used for), how meaning is constructed in different contexts, which include social, cultural, political, and historical background of the discourse. Discourse analysis is socially constructed which makes it unique. Read in additional notes on “Gender as Social Construction Thematic analysis Thematic analysis is the most used method of qualitative data analysis (QDA). TA looks at patterns of meaning in the transcripts from interviews and focus group discussions Audio-taped transcriptions are first broken down into units of meaning. The researcher then uses a technique to place such units into categories. Most common themes are systematically identified. Discussions of large information sections are broken down into similarities – in other words, they are divided into themes. From the themes: insight into issues being studied can be drawn. In other words, we make meaning of the content of these themes. Statistical software: are now used to assist in the thematic analysis (TA) process (e.g. Atlas Ti). What is data verification of qualitative research? Verification is the process of checking and confirming. I.o.w the strategies used to ensure reliability, validity and therefore the rigour of the study during the research process. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Several debates about the rigor of qualitative research around questions, viz: How can we trust the authenticity of qualitative research? How can we be sure that such research is reliable and valid? There are many different perspectives on how to make sure that qualitative data is trustworthy and rigorous. Correspondence checks is frequently used: this involves the use of: (a) colleague and (b) other researchers to analyse the data independently. Analysis is then compared with that of the primary researchers to check for correspondence. Also: take the analysed data back to the participants to find out what they think of the analysis. NOTE WELL: Always remember the goals, theory and method of study when interpreting the data Final analysis: the researcher should provide enough information to allow others to assess: (a)the merits and (b) trustworthiness of the work. How to verify qualitative data and promote rigour: Triangulation: check out if stories are consistent- ask questions from two/ more different persons/sources. Reflective Journal: A dairy kept by the researcher to provide personal thoughts and insights on what happened during the study, also noting personal biases, etc Data Saturation: This is a tool frequently used for ensuring that adequate and quality data are collected to support the study. Member checking/ Respondent validation: Take data analyses back to the members of the group and confirm the data. Self-disclosure (Reflexivity): Researcher should not be too critical. i.o.w. better to use more than one investigator. Meticulous record-keeping: demonstrating a clear decision trail and ensure interpretations of data are consistent and transparent. STEP5: REPORTING FINDINGS: Lecture 7 What is rigor? In quantitative language rigor refers to the reliability and validity of a study Rigor, in qualitative terms, is a way to establish trust or confidence in the findings of a research study. Research errors and biases How do you know that your research findings are true and accurate? The nature of qualitative data makes it difficult, if not impossible, for the person undertaking the research and conducting the analysis to separate themselves from the data. This can contribute to potential errors and biases. To enhance the rigor, it is important to ensure that efforts are made to reduce errors and biases. What is a bias? Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 A bias is “any deviation from the truth in data collection, data analysis, interpretation and publication which can cause false conclusions”. Types of bias : Forms of Participant Bias 1. Agreement bias or acquiescence bias occurs when a research participant agrees with every aspect of an interview regardless of whether it matches their opinion. 2. Social desirability bias happens when the research participant answers questions not based on their true opinions but on how they believe others will view their responses. It involves under reporting socially unacceptable behaviour and over reporting socially desirable behaviours. People are more likely to respond inaccurately on personal or sensitive topics. How to reduce participant bias: You can word your questions carefully You can choose to combine different ways to collect data during your study. For example, in a face-to-face interview, you can allow the respondents to provide their answers to highly sensitive questions after the session via anonymous self-administered mode. This way, the respondents will not feel pressured or embarrassed as they’re allowed their own space to provide their responses. Bias from the researcher Interviewer bias: the way in which a researcher interacts with participants during an interview can influence their responses. A researcher may: ask questions in a hostile, disinterested or insensitive way, suggest to participants how to respond, record answers incorrectly. Analyst bias: this entails inaccurately capturing data, coding data incorrectly or choosing the incorrect method of analysis for the data. Confirmation bias: the tendency to interpret the data in a way that confirms the researchers existing perspectives, opinions and attitudes. Hindsight bias (“knew-it-all-along” phenomenon): occurs when a researcher looks back at their research and concludes that they knew the outcome all along. Funding bias: refers to any potential influence from funders of a research project. How to reduce researcher bias & promote rigor? Verification continued & expanded: Triangulation: entails using different data sources, researchers and methods of data collection. (I) Data triangulation refers to using multiple data sources in time (gathering data in different times of the day or at different times in a year), space (collecting data on the same phenomenon in multiples sites or test for cross site consistency) and person (gathering data from different types or level of people e.g. individuals, their family members and clinicians) (II) Researcher triangulation is concerned with using two or more researchers to make coding, analysis and interpretation decisions. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 (III) Method triangulation means using multiple methods of data collection (e.g. interviews & observation). Audit Trail: Transparently describing the research steps taken from the start of a research project to the development and reporting of the findings. The records of the research path are kept throughout the study. Keeping records of the raw data, field notes, transcripts, and a reflexive journal can help researchers systemize, relate, and cross reference data, as well as ease the reporting of the research process. These are all means of creating a clear audit trail. Reflexivity: Examining one’s own conceptual lens, explicit and implicit assumptions, preconceptions and values, and how these affect research decisions in all phases of qualitative studies. Keeping a reflexive journal is one way of being reflexive and promoting rigor Respondent validation or member checking includes inviting participants to comment on the interview transcript and whether the final themes and concepts created adequately reflect the phenomena being investigated. This process strengthens the data, especially because researcher and respondents look at the data with different eyes. A research report is organised into sections 1.Abstract 2.Introduction 3.Methodology 4.Results 5.Discussion 6.Limitations 7.Conclusion 8.References What is the purpose of the abstract? An abstract is an executive summary of all the sections of a research report (such as a journal article or thesis). It serves the following main functions: 1. To provide the reader with an overview of the report 2. To help potential readers determine the relevance of the report to their own research 3. To communicate key findings that may be of relevance to the field Abstracts usually have keywords at the end. This makes it easier to find the article when a researcher types key words into a search engine. Since the abstract is the first thing any reader sees, it’s important that it clearly and accurately summarises the content of your report. The introduction The introduction is a road map that helps the reader to understand: 1.What the research is about? 2.Why the research is important? 3.What has been done before on the topic? 4.What is not known about the topic? 5.How will the current research advance new knowledge on the topic? The Methodology or Method Section The method section provides information about how the study was conducted. Subheadings are used to structure this section. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 The method section typically includes information about the: site of the study (i.e. where the study was conducted), participants and the characteristics of the participants (e.g. age and gender), measures/instruments that were used in the study (if it was a quantitative study) or the types of questions that were asked of participants (if it was a qualitative study) procedures for data collection (e.g., interviews, survey, FGDs), method of data analysis (e.g., thematic analysis, IPA, quantitative analysis, etc.) and ethical considerations. Results The results section is where the findings of the research are reported based upon the methodology [or methodologies] applied to gather information. The results section should state the findings of the research arranged in a logical sequence without bias or interpretation. Discussion The discussion section typically begins by reminding the reader of the purpose of the study. Thereafter, a summary and interpretation of the results of the study is provided. The purpose of the discussion is to interpret and describe the significance and implications of the findings considering what was already known about the research problem being investigated and to explain any new understanding or insights that emerged as a result of the study of the problem. The discussion section compares the findings to existing research. Limitations This section can be presented separately with its own heading, or it can be included in a paragraph at the end of the Discussion section. The limitations of the study are those characteristics of design or methodology that impacted or influenced the interpretation of the findings from the research. They are also the constraints on generalizability or rigor of the study. Conclusion The conclusion is intended to help the reader understand why your research should matter to them after they have finished reading the paper. A conclusion is not merely a summary of the main topics covered or a re-statement of your research problem, but a synthesis of key points and, if applicable, where you recommend new areas for future research. References All the references or citations used in the research report need to be included at the end of the report in alphabetical order. The purpose of the reference list is to acknowledge all the sources used in the paper and allows readers to confirm the sources for your arguments. Citing other people's words and ideas demonstrates that you have conducted a thorough review of the literature on your topic. Referencing styles may vary. In Psychology, we typically use the conventions of the American Psychological Association (APA). Other referencing styles include the Harvard referencing style and the Chicago referencing style. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 STEP 6: THEORY BUILDING & ETHICS IN RESEARCH Lecture 8 What is a theory? A theory is a big idea that organizes many other ideas with a high degree of explanatory power. Theories are formulated to explain, predict, and understand phenomena and, in many cases, to challenge and extend existing knowledge. In addition to psychological theories, there are also social theories, organisation theories and economic theories that are used to define concepts and explain phenomena. We can think about theory in three ways, namely as: A paradigm which underpins research A“lens” or theoretical framework through which the researcher understands the phenomenon under investigation New knowledge, which may emerge from the study A theory as a Paradigm Paradigm: is a basic belief with assumptions about ontology and epistemology, an approach to how we undertake research Ontology: philosophical assumptions about what constitutes social reality. o What is reality? Single reality, multiple reality or reality that is constantly negotiated o Realism versus relativism o How do we classify what is real? Ontology: is a description of things, relationships, and their characteristics, usually in a well bounded domain (e.g. psychology, medicine, physics, astronomy, biology, etc.) Epistemology: philosophical assumptions related to the study of knowledge, what we know and how we know it. A way of understanding and explaining how we know what we know. A theory as a theoretical Framework: Is the “blueprint” for the entire research inquiry. Eisenhart defined a theoretical framework as: “a structure that guides research by relying on a formal theory…constructed by using an established, coherent explanation of certain phenomena and relationships” (1991, p. 205). Thus, the theoretical framework consists of the selected theory (or theories) that undergirds your thinking with regards to how you understand and plan to research, your Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 topic, as well as the concepts and definitions from that theory that are relevant to your topic. Theoretical and conceptual frameworks Theoretical framework: A theoretical framework is a single formal theory or theories. When a study is designed around a theoretical framework, the theory is the primary means in which the research problem is understood and investigated. Conceptual framework: A conceptual framework includes one or more formal theories (in part or whole) as well as other concepts and empirical findings from the literature. It is used to show relationships among these ideas and how they relate to the research study. Conceptual frameworks are commonly seen in qualitative research in the social and behavioural sciences, for example, because often one theory cannot fully address the phenomena being studied. What are examples of theoretical frameworks used by qualitative researchers? 1.Phenomenology: focuses on understanding lived experience. 2.Interactionism: understands social processes (such as conflict, cooperation, identity formation) as emerging from human interaction. 3.Critical race theory: can be used to scrutinize the ways in which race and racism directly and indirectly affect certain groups of people. It is concerned with racial subordination, prejudice, and inequity. 4.Feminist theory: explores inequality in gender relationships and how gender is constructed. Theory as new knowledge Adaptation, revision or confirmation of existing theory Generation of new theory What is research ethics? A way of conducting research such that the fundamental principles of research ethics are upheld. Ethical research must conform with the national and international accords and prescripts. KEY HUMAN RESEARCH ETHICS POLICIES AND REGULATIONS IN SA Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Unethical Research in Psychology John Watson is known as the “Father of Behaviourism” and often used orphans in his various experiments. In one well known and unethical experiment, Watson used a nine-month-old orphan known as Little Albert. At first, Little Albert was exposed to a variety of sights and sounds, including rabbits, monkeys, burning newspaper, and masks of all sorts. In the experiment’s second phase, Watson introduced Little Albert to a white rat. As with the other things, Little Albert didn’t show any fear of the rat. That is, until Watson began making loud noises with a steel bar anytime Albert touched the animal. Not surprisingly, the presence of the rat turned distressing. Soon, Little Albert expressed fear over anything fluffy and/or white, ultimately proving Watson’s hypothesis that fear could be conditioned. Another way of looking at research ethics is by looking at unethical research Deception (issues of full disclosure): Withholding information about the aim of the study or misleading participants about the risks inherent in participating in the study Plagiarism: academic dishonesty & wrongful appropriation Misinterpretation of results Not providing details of theories and methods that might be relevant in the interpretation of research findings. Fabrication or falsification of data Not respecting the right to privacy, anonymity and confidentiality Not respecting rights of vulnerable groups: Children, mentally handicapped individuals, the elderly, prisoners, illiterate, those with low social status, those who have experienced traumatic life events Not having due consideration for the environment conduct Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 ETHICAL REQUIREMENTS 1.Informed consent 2.Confidentiality 3.Anonymity (e.g. using a pseudonym or made up name to refer to participants) 4.Referral: if participants become distressed during the research process, an appropriate referral for psychological support must be made. 5.Discontinuance 6.Research with vulnerable populations 7.Quality 8.Analysis and Reporting 9.Reporting and Publication Informed consent Consent given by well-informed participants about the nature of the research procedure, its purpose, and about the risks and benefits of the study. Informed consent is given without subjecting the potential participant to coercion, intimidation or undue influence. Participant’s understanding of the research aims and objectives must be addressed by laying out the details out in the language the participant understands, in a culturally acceptable way. INTRODUCTION TO STATISTICS: Lecture 9 WHAT IS STATISTICS The science of collecting, organizing, presenting, analyzing, and interpreting data to assist in making more effective decisions. Statistical analysis is used to describe, summarize, and investigate data, so that useful decision-making information is created. Why study statistics? Data is everywhere. Statistical techniques are used to make many decisions that affect our lives. No matter what your career, you will make professional decisions that involve data. An understanding of statistical methods will help you make these decisions effectively. The importance of statistics in Psychology Statistics allows us to make sense of and interpret a great deal of information. o Consider the following questions: o How many hours did you have good night’s sleep this past week? o How many Psy123 students live near you? o How many first-year psychology students feel anxious about studying statistics? Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 o How many students have passed the Psy123 module with distinction over the past three years? o What factors motivate students to pursue a career in clinical psychology? By using statistics, we can organize and interpret all this information or data in a meaningful way. How do we get data? Through surveys/questionnaires We use data sets for statistical analysis To undertake statistical analysis, we need a data set. What is a data set? A data set is basically a collection of numbers or values regarding a particular subject. A statistical data set is collection of data/information in an organized form. For example, the test scores of all students who took Test 1 of Psy123 is a dataset. Statistics allows psychologists to do the following: Organize and Describe Data: When dealing with an enormous amount of information, it is all too easy to become overwhelmed. o Statistics allow psychologists to present data in ways that are easier to comprehend and more meaningful. Using statistics, we can accurately describe the information that has been gathered in a way that is easy to understand. o Descriptive statistics provide a way to summarize what already exists in a given population, such as how many people are currently employed, how many people live with a disability, or in our example, how many students experience anxiety before an exam period. Make Inferences Based on the Data: By using what's known as inferential statistics, researchers can infer things about a given sample or population. o Psychologists can use the data they have collected to test a hypothesis or a guess about what they predict will happen. Using this type of statistical analysis, researchers can determine the likelihood that a hypothesis should be either accepted or rejected. How to enter data into a database: Step 1: Collect your data Step 2: Create a codebook Step 3: Code your data: Coding is the process of assigning a numerical value to different levels of a variable. Each code describes a different attribute of a variable. Research question: How anxious do students feel before the exam period? Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 RESPONSES Step 1: Assign numerical values to the participant’s responses. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 When statistical analyses are performed, often two broad types of data are produced: Descriptive statistics refers to data that is used to describe or summarise a study sample. o This can include the total number of individuals in the sample, the number of males and females or the age range of those in the sample. o The origins for the term descriptive is describe which means to give a detailed account of something. And this descriptive information is often expressed or displayed in tables and graphs Inferential statistics refers to data that can be generalised from the sample to the population. o The origins for the word inferential is inference which means a conclusion reached based on evidence and reasoning. o This type of data can be used to test hypotheses and therefore draw conclusions on the sample which can be applied to a population being studied Well-known statistical programs that can be used for statistical analysis: o 1.SPSS (Statistical Package for the Social Science) o 2.BMDP (Bio-medical computer programs) o 3.SAS (Statistical Analysis System) Descriptive data analysis Describes data by examining the distribution of scores for each variable. It gives the researcher an initial picture of how people scored on each variable and how their scores are related to the scores of others Under the branch of descriptive statistics, we can find out the overall frequency of each activity (distribution), the averages for each activity (central tendency), and the spread of responses for each activity (variability) Descriptive data analysis cannot, however, be used to come to any definitive conclusions based on the information provided. Frequency Distributions After collecting data, the first task for a researcher is to organize and simplify the data so that it is possible to get a general overview of the results. This is the goal of descriptive statistical techniques. One method for simplifying and organizing data is to construct a frequency distribution. How frequently does something occur Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Frequency of occurrence → the number of times at which something happens. The symbol f (F) is used to indicate frequencies. The symbol N is used to indicate the total number of items in a sample. For example, the total number of students who completed a survey N = 322. Frequency Distribution Graphs The graphs help us to understand the collected data in an easy way. The graphical representation of a frequency distribution can be shown using the following: Bar Graphs: Bar graphs represent data using rectangular bars of uniform width along with equal spacing between the rectangular bars. Histograms: A histogram is a graphical presentation of data using rectangular bars of different heights. In a histogram, there is no space between the rectangular bars. Pie Chart: A pie chart is a type of graph that visually displays data in a circular chart. It records data in a circular manner and then it is further divided into sectors that show a particular part of data out of the whole part. Frequency Polygon: A frequency polygon is drawn by joining the mid-points of the bars in a histogram. Frequency Distribution Tables Ungrouped frequency distribution: It shows the frequency of an item in each separate data value rather than groups of data values. Grouped frequency distribution: In this type, the data is arranged and separated into groups called class intervals. The frequency of data belonging to each class interval is noted in a frequency distribution table. The grouped frequency table shows the distribution of frequencies in class intervals. A frequency distribution table shows the frequency of each of the items in a data set. It indicates the frequency with which each value (or category) occurs. Let’s use a straightforward example to understand how to make a frequency distribution table: You buy a big box of smarties, and it comes in different colours: red, green, blue, brown, yellow, orange, purple, etc. To know the exact number of smarties of each colour, we need to classify the smarties into categories. Pick the smarties one by one and count how many smarties there are of each colour. Then, indicate the frequency for each item (smartie) in the table. Ungrouped Frequency Distribution is a type of frequency distribution that displays the frequency of each individual data value instead of groups of data values. In this type of frequency distribution, we can directly see how often different values/categories occurred in the table. Grouped Frequency Distribution Grouped Frequency Distribution Table: To arrange a large number of observations or data, we use grouped frequency distribution table. For example: The marks obtained by students in Psy123 Test 1 are as follows: 5, 10, 20, 15, 5, 20, 20, 15, 15, 15, 10, 10, 10, 20, 15, 5, 18, 18, 18, 18. Grouped frequency distribution means we make class intervals (i.e., groups of marks). Thus, we will make class intervals of marks ranging from: 0 - 5, 6 - 10, 11 - 15, and so on. Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 With grouped frequency distribution, the different levels of, or scores associated with a variable are grouped into different classes together with the frequency for each class. To prevent a large uninformative table, it is better to use a grouped frequency distribution where the values are grouped into classes How to group scores into classes: Basic rules for making groups or class intervals Class intervals or grouping: Range of each group of data (e.g., 1-5; 6-10, etc.) You could following a pre-assigned categorization (e.g. if we had age as a variable we could use the various life stages as a guide to group age) Child = 5-12 yrs. Adolescent = 13-19 yrs. Adult = 20-39 yrs. Middle Age Adult = 40-59 yrs. Non-overlapping (same number must not be present in two or more groups) o 1-5 o 6-10 o 11-15 All groups should be able to include all the data we have. Class interval must be the same. The class limit is the difference between the upper and lower limit (highest score and lowest score) o 5-1 = 4 o 10-6 = 4 o 15-11= 4 Basic rule for making class intervals Step 1: To get started, put the numbers in order Step 2: Find the smallest and largest values in your data, Step 3: Calculate the range → highest score minutes lowest score. o This is also known as the upper and lower limit. o Psy123 Test 1 marks (N = 23): 5, 10, 10, 10, 10, 15, 15, 15, 18, 18, 18, 18, 20, 20, 20,22 25, 25, 25, 27, 29, 35, 40. o Smallest: 5; Highest 40 Range = 35 Step 4: Select the number of classes that you want. o There should be between 5 and 20 classes. In this case, let’s say we want 5 classes. Step 5: Calculate the interval size (i.e., the number of scores that will fall into each class) by dividing the range by the number of classes. o Divide the range (e.g., 35) by the number of classes (e.g., 35/5 = 7) 0-7; 8-15; 16- 23; 24-31; etc Relative frequencies and cumulative relative frequencies A relative frequency indicates how often a specific kind of event occurs within the total number of observations. It is a type of frequency that uses percentages, proportions, and fractions. o Manchester United won 9 out of 12 soccer matches o The frequency of winning is 9 o The relative frequency of winning is 9/12 = 0.75 or 75% Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 Cumulative frequency is used to know the number of observations that lie above (or below) a particular frequency in a given data set. Cumulative relative frequency is used to show what percent of the data is below a particular value. Disadvantages of frequency tables Since the data is organised into groups, it is impossible to read exact values. For example, although we know that 70 students obtained marks between 31-35, we do not know how many students obtained 31, 32, 33, 34 and 35. 2 You can only use this method with continuous data. Stem and Leaf Display Stem-and-leaf display is as an alternative to frequency distribution with data sorted into stems (leading digits) and leaves (trailing digits) The basic idea behind this plot is to divide each data point into a stem and a leaf. The stem of the number includes all but the last digit. The leaf of the number will always be a single digit. A stem and leaf plot also called a stem and leaf diagram is a way of organizing data into a form that makes it easy to observe the frequency of different types of values. It is a graph that shows numerical data arranged in order. Each data value is broken into a stem and a leaf. How to create a stem and leaf diagram A stem and leaf plot is represented in form of a special table where each first digit or digit of data value is split into a stem and the last digit of data in a leaf. Data: 5, 10, 20, 15, 20, 15, 45, 15, 10, 11, 13, 20, 18, 18, 23, 25, 39, 37 Organize from lowest to highest (this makes it easier to see the spread and F): 5, 5, 5, 10, 10, 11, 13, 15, 15, 15, 18, 18, 20, 23, 25, 37, 39, 45 The stem of the number includes all but the last digit. The leaf of the number will always be a single digit. Key: 3|4 means 34 mins Downloaded by Emihle Mzomba ([email protected]) lOMoARcPSD|42337356 How many students took the multiple choice test? Each Leaf represents 1 student = 17 students How long did it take the student who completed the test in the longest amount of time? 75 min How long did it take the student who completed the test in the shortest amount of time? 34min Downloaded by Emihle Mzomba ([email protected])