Course Objectives By the end of the course the student will: Define research Describe various types of research Describe the research process Carry out a simple research
Course outline Definition Types of research Identifying research problem Objectives of the research Statement of hypothesis Operational definition Literature review Methodology Research setting and population Sampling method Data collection, tools/methods, limitations Dissemination of research report
What is Research? Research means to search again or carefully examine (Langford 2001)
Research defined Research is systematic inquiry that uses disciplined methods to answer questions or solve problems. (Polit and Beck, 2010). Characteristics of nursing research It demands a clear statement of the problem It requires a plan, order and control It builds on existing data Based on theory of empiricism Generalisation
Purpose of conducting research Description Exploration Explanation Prediction Types of research 1. Basic 2. Applied research. Basic research Also called Fundamental or pure research Studies are designed to seek knowledge without specifying application of the knowledge Ex: examining xtics of a cell. Applied research Concerned with using knowledge to solve immediate problems facing an organization. Ex. Using to solve patient care difficulties, educational concerns and administrative issues. The nurse investigator contribute to some modification of the present practices
Quantitative Research Originated in the natural sciences such as biology, chemistry, physics, geology This is that is concerned with investigating things which we could observe and measure in some way.
Qualitative research Origin: social sciences like psychology & nursing. Involves study of human behaviour & the social world inhabited by human beings; Answers the why and how questions. Definition of nursing research Nursing research is the systematic inquiry designed to develop knowledge about issues of importance to the nursing profession, including nursing practice, education, administration, and informatics.
(Polit and Beck, 2010) Importance of Nursing Research 1. To promote evidence-based nursing practice: nursing care must be based on accurate knowledge. 2. To ensure credibility of the nursing profession 3. Provide accountability for nursing practice 4. Document the Cost Effectiveness of Nursing Care: Sources of nursing knowledge Tradition Authority Trial and error Logical reasoning: comprises inductive and deductive reasoning Scientific research The research process 1. Review of existing literature 2. Research questions 3. Method 4. Analysis 5. Presenting our findings
Chapter Two Selecting a Research Topic Chapter objectives Enumerate the sources of nursing research problems List the various steps required to select a research topic Describe the criteria for prioritising a research problem Select their own research topic that is relevant to nursing
Introduction What is a problem? A situation that lends itself to be addressed through application of the research process Sources of research problem Experience from clinical practice Nursing literature Ideas from external sources colleagues Procedure for identifying research problem Select a broad topic of interest Refine/narrow down Evaluate significance of topic
Identifying research problem Select broad topic area Write down general area of interest E.g. cancer patients in pain Selecting Research Problem Refine/narrow down the topic Ask questions Review literature Talk to people Is your topic significant? A research topic must meet the following conditions 1. The should be perceived difference betweenwhat exist and the ideal or planned situation 2. The reason(s) for the difference shd be unclear 3. There should be more than one possible answer to the question or solution to the problem.
Prioritising Research: Criteria 1. Significance of the problem: Is the problem an important one? Will patients, nurses etc. benefit from the evidence that will be produced? Will the results lead to practical applications? Will the study help to alter nursing practices or policies?
Prioritising Research: Criteria 2. Researchability of the problem Not all problems are amenable to a research through a scientific study Example include problems that relate to moral or ethical nature Ex. Observing how often couples use condoms during sexual intercourse
Prioritising Research: Criteria 3. Feasibility Time and Timing Availability of study participants Cooperation of others (e.g. seeking the consent of parents if children) Interest to the researcher Avoidance of duplication Applicability of possible research findings Ethical acceptability
Characteristics of a good research topic 1. Interesting 2. Researchable 3. Significant 4. Manageable 5. Ethical Chapter Three Analysing & Stating Research Problem Learning objectives Use the problem analysis diagram to analysis a research problem Describe the importance of a clear statement of a problem Enumerate the points that should be included in the statement of a problem Analyse and state their own research problem
Introduction
Adequately analysing the problem will help you include all possible contributory factors from different sectors Analysing the problem Analysis focus on: Factors that may have contributed to the problem The relationship between the problem and the contributing factors Analysing the problem Contributing factors grouped into: Service- related factors: e.g. distance to clinic Disease related factors e.g. seriousness of patients condition Socio- cultural factors e.g. occupation & marital status Analysing the problem STEPS IN PROBLEM ANALYSIS Identify and write down the core problem Identify possible contributing factors Determine relationship between the problem and the contributing factors Regroup the contributing factors into broad categories where appropriate Decide on the focus and scope of the research
Stating the Research Problem Problem statement is an expression of the dilemma or disturbing situation that needs investigation. Stating the Research Problem It has six components: 1. Problem identification: what is wrong with the current situation? 2. Background: what is the nature of the problem, the context of the situation that readers need to understand? 3. Scope of the problem: how big a problem is it; how many people are affected? 4. Consequences of the problem: what is the cost of not fixing of not fixing the problem? 5. Knowledge gaps: what information about the problem is lacking? 6. Proposed solution: what is the basis that the proposed study would contribute to the solution of the problem?
CHAPTER FOUR Study Purpose, Aim or Objectives At the end of the lesson, students should be able to Explain the relationship between the terms: purpose, aims and objective Differentiate between general and specific objectives Formulate specific objectives
Study purpose, aims and objectives are synonymous terms and are therefore used interchangeably Study purpose, aims & Objective Assumed to mean the same thing It answers the question what does the researcher wish to achieve? It is the overall impact of the study Statement of objectives Research objectives are the steps you are going to take to answer your research questions or a specific list of tasks needed to accomplish the goals of the project. While aims are broad in nature, objectives are focused and practical. Statement of objectives Define the focus of your study Clearly identify variables to be measured Indicate the various steps to be involved Establish the limits of the study Avoid collection of any data that is not strictly necessary General Objectives These are normally the aims/goals of the study, Are broad statements of what is to be achieved by the study. That is, what is the purpose of research?
Specific Objectives These are measurable statements on the specific questions to be answered. They are more specific and are related to the problem situation Refer to example 4.1 in lecture notes How to state the objectives Research objectives should: cover different aspects of the problem and its contributing factors be clearly expressed in measurable terms be realistic considering local conditions meet the purpose of the study use action verbs that are specific enough to be measured
Characteristics of Objectives (SMART)
Specific
be precise about what you are going to do
Measurable
you will know when you have reached your goal
Achievable
dont attempt too much. Realistic
do you have the necessary resources to achieve the objective?
Time Constraint
determine when each stage needs to be completed. Examples of strong verbs for objectives To determine To compare To verify To describe To establish To produce To revise
To find out To collect To construct To classify To develop To devise To measure To select To synthesise
Avoid the use of weak, vague non- action verbs such as: To appreciate, To consider, To enquire, To learn, To know, To understand, be aware of to listen, to perceive
Chapter Five Research Questions, Hypothesis & Variables At the end of this lesson, the student should be able to: Explain the need for developing a research question and hypothesis Formulate research questions and hypothesis. Differentiate between dependent & independent variables Explain the need for operationalizing variables State operational definition of variables
Introduction After deciding on your research topic, the next thing to do is to state a research question that will help focus your research study. This will be followed by the making a scientific guess as to the possible outcome of the research study. What is Research Question? This is a clear, focused, concise, complex and arguable question around which you centre your research. The question provides a path through the research and writing process. Characteristics of research questions Clear Focused Complex i.e., should not be answerable with a simple yes or no or by easily- found facts. Refer to examples 5.1 & 5.2 Research questions, rather than hypothesis, are normally used in qualitative research and in descriptive- survey studies. Variables-what youre measuring A variable is a characteristic that varies between individuals and can be measured, such as weight, age and gender.
Refers to Qualities, properties, or characteristics of persons, things, or situations that change or vary
(Burns & Grove, 2007, p.125).
Examples of variables A person's age. This variable can take on different values, such as, 20 years old, 30 years old, and so on. Marital status single, married, divorced & widowed
Other examples: height, weight, job satisfaction Types of variables Five main types 1. Dependent variable 2. Independent variable 3. Demographic variable 4. Descriptive variable 5. Extraneous variables
Dependent vs. Independent variables Nursing researchers may be interested in answering the following questions Does a nursing intervention cause improvements in patient outcome? Does smoking cause lung cancer? The presumed cause is the independent variable, and the presumed effect is the dependent variable Dependent vs. Independent variables
Independent variable Dependent variable
intervention, influence or exposure outcome
Activity-determine the variables 1. A researcher wants to know whether a hospitalised childs anxiety level during painful procedure would lessened if a parent were present during the procedure. 2. You are interested in the effect of daily exercise on glucose levels in adolescents with type I diabetes Activity-determine the variables 2. A researcher asked: What is the effect of heart failure self-management education on a patients knowledge level and readmission rate to the hospital? 3. For term, stable infants, is there a relationship* between immediate skin-to-skin contact after birth and exclusive breastfeeding at 2 months of age?
Demographic variables These are attributes or characteristics of the subjects in a study. Examples: Age Gender Diagnosis Socioeconomic information
Extraneous Variables Also called nuisance variables. Not usually of primary interest but are believed to be related to the independent and/or dependent variables. Their effects need to be controlled in order to obtain meaningful results. Examples include: Transportation Literacy In doing a research, you need to identify and control them if possible.
Hypothesis A hypothesis attempts to answer a question which has emerged from a research problem. They are scientifically reasonable predictions that go further than a research question and predict an outcome. Hypothesis A hypothesis states the relationship between two or more variables that suggest an answer to the research question. Simple VS. complex hypothesis Simple hypothesis expresses an expected relationship btn one independent and one dependent variable. Complex hypothesis Expresses a relationship btn two (or more) independent variables and/or two (or more) dependent variables.
Directional vs. Non-directional Hypothesis Directional hypothesis: specifies not only the existence but the expected direction of the relationship between variables. Example The risk of falling increases with the age of the patient. In the above example, there is an explicit prediction that older patients are at greater risk of falling than younger ones.
Directional vs. Non-directional Hypothesis Non-directional hypothesis: does not stipulate the direction of the relationship. Example: There is a relationship between the age of a patient and the risk of falling. This hypothesis do not stipulate whether the researcher thinks that older patients or younger ones are at greater risk.
Alternate VS. Null Hypothesis Alternative hypotheses (H I ) This hypothesis normally suggests a relationship and a potential outcome in a research study. can be directional or non-directional Example: Children with high IQ will exhibit more anxiety than children with low IQ-directional There is a difference in the anxiety level of the children of high IQ and those of low IQ- non- directional
Alternate VS. Null Hypothesis A null hypothesis (H O ) is a statement that there is no actual relationship between variables. predicts no difference between the groups of events or observations under study. Example: There is no significant difference in the anxiety level of children of High IQ and those of low IQ. There is no relationship between age of adolescents and occurrence of unwanted pregnancy.
Refer to examples in the handout Chapter 5 Literature Review Learning objective After reading this chapter, student should be able to: Describe the reasons for reviewing available literature Describe the literature resources that are available for carrying out review Systematically review a literature on a given topic
Introduction A literature review summarises, interprets, and critically evaluates existing "literature" establish current knowledge of a subject establish what knowledge and ideas have been established on a specific topic Purpose of literature review Refer to lecture notes
Types of literature Primary literature e.g. articles published in reputable journals. Secondary literature e.g. textbooks and review articles. Grey literature e.g. government reports, conference proceedings and theses. Web sites : sites other than those associated with mainstream academic literature. Steps in the review of literature Initial search a cursory examination of available publication Secondary search in-depth & critical evaluation of publications Involves: Electronic searching Manual searching Steps in the review of literature Electronic searching Databases contain large quantities of information Examples of databases: Cochrane library Web of science Google scholar CINAHL PubMed/Medline Steps in the review of literature Manual Searching not all journals are available on databases; important information may be missed. Ideal to combine manual and computerised search. This include: Hand searching journals Searching reference list Author searching Keeping Record A systematic method for recording important information and the search strategy: prevent duplicating effort by doing the same search twice missing out a significant and relevant sector of literature Information such as authors name, date of publication, title of article and name of journal or book can be entered on a separate card Writing the review Final task: organise and report the material covered Outline an introduction, a body, a conclusion
Writing the review Your review should: well-organized and critical summary of current state of knowledge Studies with comparable findings often can be summarised together. in your own words. point out both consistencies and contradictions in the literature as well as offer possible explanations for the inconsistencies. CHAPTER SEVEN Research Methods Learning objective After completing this chapter, the student should be able to: Differentiate between quantitative and qualitative research methods Describe and understand the various components of the methods section in a research proposal Explain the cyclical nature of the different steps in designing the methodology
Introduction Not all research methods can be used to answer every research questions E.g. a nurse interested in the accuracy of thermometers in assessing fever will use a quantitative a nurse interested in the experience of fever from the patients perspective will use a qualitative approach Definitions Research Methodology is the science of studying how research is done scientifically. Research methods are generalized and established ways of approaching research questions (e.g., qualitative vs. quantitative methods). Research Design involves determining how a chosen method (qualitative or quantitative) will be applied to answer your research question. Includes methodology, sample selection, data collection process, instruments
Quantitative Research Design Based on the measurement of quantity or amount. Results can be: a number or a set of numbers presented in tables and graphs.
Types of quantitative research Two main types Interventional (experimental) research Non-interventional (non-experimental) research Types of quantitative research 1. Interventional (experimental) research The researcher manipulates objects He then measures the outcome of his manipulation. Two main types: experimental and quasi-experimental studies. Types of quantitative research Non-interventional (non-experimental) research: the researcher just describes or analyses variables without intervening in anyway. The main types are correlational studies and descriptive studies.
Interventional Research: Experimental The researcher provides a specific treatment to one group and withholds it from the other. He then determines how both groups scored on an outcome. Interventional Research: Experimental Characteristics of experimental design Manipulation: involves doing something to study participants. Control: the experimenter introduces controls over the experimental situation, including the use of a control group Randomization: the experimenter assigns subjects to a control or experimental group on a random basis.
Interventional Research Quasi-experimental Undertaken when randomization not possible. The design introduces some form of treatment or manipulation but does not utilize randomization or control group. Quasi-experimental therefore lack either randomisation or a control group
Non-interventional research Non-interventional research Generally present-oriented. describe what exist. variables are not deliberately manipulated, the setting controlled Non-interventional research Examples 1. Explorative studies: explores new phenomena to enhance the researchers understanding. normally of short duration and carried out on small scale.
Non-interventional research Examples 2. Descriptive studies description of phenomena in real life situation. It is designed to provide an accurate account of characteristics of particular individuals, situations or groups. It answers the question: what is? e.g. what factors influence mother-infant bonding? Non-interventional research Examples 4. Correlational studies investigates relationship btnx or among variables. 5. Surveys provides a quantitative description of trends, attitudes, or opinions of a population by studying a sample of that population. It can either be cross-sectional or longitudinal.
Qualitative research design Quali is a way of looking at the world from the point of view of people. It enquires about what people feel, think, understand and believe. It is more concern with describing and understanding human experiences from the point of view of the people who have had, or are having, the experience. Qualitative research E.g. a patients who are experiencing chronic pain. Quantitative research would be concerned with the level of pain patient experience that these people were experiencing, and Qualitative research would be concerned with what it means to be living with chronic pain. Examples of qualitative Grounded theory, action research, historical, ethnographic, philosophical and phenomenological
Selecting a research method Refer to section 7.6 CHAPTER EIGHT Data Collection Learning objective After completing this chapter, the student should be able to: Define key terms used in data collection Mention the data collection techniques and tools Differentiate between data collection techniques and tools Mention the characteristics of a good interview Design and administer a questionnaire for a simple study
Definition and types of data Data pieces of information obtained in a study It can exist as: Numeric values Quantitative Narrative descriptions Qualitative
Types of data Primary data collected afresh & for the first time original in character. Secondary data data collected by someone else & already been passed through the statistical process.
Data Collection Techniques Data are collected using the ff means: Interviewing Administering questionnaire Observing participants using existing data using focus group discussions Historical data and records
Data collection tools These are the recording forms. consists of : observation schedule interview guide, interview schedule, questionnaire, rating scale, check list etc.,
Data collection technique Data collection tool Using existing data Checklist, data collection forms Observing Eyes and other senses, pen and paper, watch, scales etc Interviewing Interview schedule, questionnaire, tape reorder Administering written questionnaire questionnaire Interview Definition it is a data-collection technique that involves oral questioning it is a two way systematic conversation between an investigator and an informant Interview: characteristics 1. Interviewer and respondent are strangers; proper introduction needed. 2. The relationship btnx participants and interviewer must have a fixed beginning and termination points. 3. Interview is conversation with a specific purpose 4. Interview needs not to be face-to-face only 5. Although interview is usually a conversation between two persons, it need not be limited to a single respondent. Advantages of interviews improves the percentage of responses & quality of information received than other method supplemental information like economic level, living conditions etc. can be gathered The accuracy and dependability of the answers given by the respondent can be checked by observation and probing. Interview is flexible and adaptable to individual situations. Disadvantages of interviews 1. Results are often adversely affected by interviewer's mode of asking questions & interactions 2. Certain types of personal and financial information may be refused in face-to-face interview 3. Interview poses the problem of recording information obtained from the respondents 4. Lack of training for the person who conduct interview. 5. Interview is costly both in terms of money and time.
Types of interview 1. Structured or directive interview same questions put to all the respondents and in the same order. Each question is asked in the same way in each interview. 2. Unstructured or non-directive interview Respondent encouraged to talk freely about a given topic with a minimum of prompting or guidance.
Interview process 1. Preparation e.g.Prepare interview schedule 2. Researcher properly introduces self 3. Establish rapport with respondent 4. Carrying the interview forward by asking questions 5. Recording the interview 6. Closing the interview Questionnaire Definition Consist of a number of questions printed or typed in a definite order on a form or set of forms. Advantages of questionnaire Questionnaires: are relatively simple to administer not to be a time-consuming are inexpensive. facilitate the collection of large amount of data in a short period of time. can be relatively anonymous, Disadvantages Questionnaire prevents personal contact with respondents. does not allow respondents to qualify ambiguous questions Poorly worded or direct questions might arouse antagonism or inhibitions on the part of respondents
Types of questionnaires Three basic types of questionnaire: closed-ended; open-ended; combination of both Types of questionnaires Closed-ended questionnaires used to generate statistics in quantitative research. Questionnaires follow a set format Open-ended questionnaires Contain blank section for the respondent to write in an answer. E.g. closed-ended questionnaires might be used to find out how many people use a service, open-ended questionnaires might be used to find out what people think about a service.
Types of questionnaires Combination of both Combination of open-ended and close-ended questions Many questionnaires begin with a series of closed questions, with boxes to tick or scales to rank, and then finish with a section of open- questions for more detailed response.
Refer to example of questionnaire Designing effective questionnaire Questionnaire design go through: Planning Composing a draft questionnaire Sequencing questionnaire Formatting the questionnaire Piloting and revising the questionnaire Designing effective questionnaire Planning make a list of research objectives/variables determine information required to achieve objectives Make a list of all the questions that could go into the questionnaire. The best way to do this is to turn the objectives to questions. Review literature to identify tested questionnaires. Designing effective questionnaire Composing a draft question; POINTS TO NOTE!. Avoid leading questions: questions should not be worded in such a way that it lead the respondent into an answer. E.g. Wouldnt you say that, Isnt it fair to say Designing effective questionnaire Composing a draft question; POINTS TO NOTE!. Be specific. Avoid words like regularly, often, or locally as everyones idea of what is regular, often or local will be different.
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Keep your questions short & simple as possible. Avoid multiple ideas or two questions in one will confuse and be misunderstood E.g. How many cups of coffee or tea do you drink in a day? To make the question simple, separate the it into two: How many cups of coffee do you drink during a typical day? How many cups of tea do you drink during a typical day?
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Make sure question and answer options match. Example: Have you had pain in the last week? [ ] Never [ ] Seldom [ ] Often [ ] Very often Solution Reword either question or answer to match. The questions should be: How often have you had pain in the last week? [ ] Never [ ] Seldom [ ] Often [ ] Very Often
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Encourage the respondent to consider each possible response to avoid the uncertainty of whether a missing item may represent either an answer that does not apply or an overlooked item. Example: Which one of the following do you think increases a persons chance of having a heart attack the most? (Check one.) [ ] Smoking [ ] Being overweight [ ] Stress See solution on next page
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Solution: Which of the following increases the chance of having a heart attack? Smoking: [ ] Yes [ ] No [ ] Dont know Being overweight: [ ] Yes [ ] No [ ] Dont know Stress: [ ] Yes [ ] No [ ] Dont know
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Avoid branching as much as possible to avoid confusing respondents. Example :( 1) Do you currently have a life insurance policy? (Circle: Yes or No) If no, go to question 3. (2) How much is your annual life insurance premium?
Designing effective questionnaire Composing a draft question; POINTS TO NOTE! Solution: If possible, write as one question. How much did you spend last year for life insurance? (Write 0 if none).
Designing effective questionnaire Desensitise questions by using response bands. Questions which ask women about their age are best presented as a range of response bands. Example instead of asking the respondent to write down her age, you can give a range of ages such as 20-29, 30-39 etc.
Designing effective questionnaire Do not use jargon or specialist language Avoid questions which require participants to perform calculations Avoid offensive questions or insensitive questions which could cause embarrassment Avoid asking difficult questions, e.g. where the respondent may struggle to answer (people hate to look stupid by not knowing the answer). Sequencing of questionnaire Three major sections in a questionnaire: The basic information sought The socio-demographic information useful in obtaining the profile of the respondent The identification sections to be used by the interviewer Sequencing of questionnaire Points to consider Put the most important items in first half of questionnaire. Dont start with awkward or embarrassing questions respondents may just give up. Start with easy and non-threatening questions. Go from the general to the particular.
Sequencing of questionnaire Points to consider Go from factual to abstract questions. Go from closed to open questions. Leave demographic and personal questions until last Arrange questions in logical order. Sudden changes in subject confuse the respondent and cause indecision.
Formatting the questionnaire Appearance of your questionnaire matters! The questionnaire should be clear and easy to read. It should be easy for the interviewer to navigate around. Provide adequate space for respondents to answer open-ended questions. Formatting the questionnaire Use clear headings and numbering if appropriate. Questionnaire should be legible It is important not to split the question, or question and response categories between two pages. Questions must be numbered (1,2,etc) and sub- sections clearly labelled (e.g. 1a, 1b, etc). Piloting & revising the questionnaire Pre-testing administering questionnaire to a limited number of potential respondents Helps identify potential problems Respondents should be informed that they are being interviewed for a pilot study How to administer the questionnaire ways of administering questionnaires: self-administered (sent by post, email, or electronically online). Interview administered ( administered by telephone, skype or face to face
Advantages of self-administered questionnaires 1. Cheap and easy to administer 2. Preserve confidentiality 3. Can be completed at respondents convenience 4. Can be administered in a standard manner
Advantages of interview administered questionnaires Allow participation by illiterate people. Allow clarification of ambiguity
Participant observation the researcher is involved in the situation being measured; E.g., a nurse who would be washing his or her hands, along with the other staff. The nurse researcher might do this covertly (secretly)- ethical concerns Non-participant observation The researcher is not involved directly in the practice being measured. Both participant and non-participant observation can raise concerns about something called the Hawthorne effect (or sometimes performance bias). The Hawthorne effect is where the behaviour of those being watched changes because they know they are being watched. Using existing data It is also possible to take existing data and subject those data to analysis. E.g. use of existing hospital records. It would be a waste of time collecting new data when existing data are available. An important and relatively new way of using existing data is in the meta-analysis associated with systematic reviews. CHAPTER NINE SAMPLING A POPULATION Learning objective After completing this chapter, the student should be able to: Define common concepts used in sampling Explain the term sampling Enumerate the steps involved in the development of a sample design Describe the two main types of sampling designs
Definitions Research setting The environment in which research is carried out. E.g. laboratory or a 'real' setting such as hospital A research population/Target population a large collection of individuals or objects that is the main focus of a scientific query. Study Population This is the population from which the sample actually was drawn. Subset of target population
Sampling Process of selecting a portion of the population to represent the entire population. a subset of the entire population. must be representative Reasons for Sampling Less costs Less field time More accuracy When its impossible to study the whole population
Steps involved in sample design 1. Define target population 2. Decide on the Sampling Unit e.g. geographical area such as a village 3. Decide on the sampling frame (list of units from which the sample is to be selected) 4. Determine the sample size. 5. Decide on sampling Procedure Types of sampling design Two main types: Probability sampling Non-probability sampling Probability (random) sampling
Each member has an equal chance of being selected. It ensures representativeness Types 1. Simple random, 2. Stratified random, 3. Cluster sampling 4. Systematic sampling.
Simple random sampling Individuals have an equal and independent chance of being selected for the sample. Used when the population is uniform or has similar characteristics in all cases. Refer to examples in the handbook
Stratified sampling Applied to a population that is not homogeneous The population is divided into several sub- populations that are individually more homogeneous these sub populations are called strata A simple random sample is then taken from each group. Example, dividing the population into males and females and then doing a simple random sampling of each strata Cluster/multistage sampling Used for large-scale surveys, when the population represents broad geographic areas or large numbers of people. The process of sampling moves through stages until the final sample has been selected. E.g. to sample all nursing students in the Ghana, you would proceed as follows: Prepare a list of regions and draw a random sample. Prepare a list of nursing schools in those selected regions and take a random sample of the schools. Then prepare a list of students from these schools and make a random selection of a sample of students.
Systematic sampling Involves the selection of every kth case from a list or group, such as every 10th person on a patient list. Procedure; 1. Establish the desired sample size (n) 2. Determine the size of the population (N). 3. Calculate the sampling interval (K) = N/n 4. E.g. a sample of 200 from a population of 40,000,then our sampling interval would be as follows K=40,000/200 = 200 5. Every 200th element on the list would be sampled. 6. The first element should be selected randomly 7. If number 73 is selected from a table. The people corresponding to numbers 73, 273, 473, 673, and so forth would be sampled.
Non-probability (non-random) Each member does not have an equal chance of being selected as a participant in the study. Units of the sample are chosen on the basis of personal judgment or convenience. Other name: deliberate sampling, purposive sampling and judgment sampling. Advantages ease of recruitment, easier monitoring and follow-up, higher response rates Non-probability sampling Convenience sampling Researcher includes whoever happens to be available or participants that are easiest to obtain. It is also called accidental or haphazard sampling. Example: distributing questionnaires to nursing students in a class Disadvantage: available subjects might be atypical of the population of interest
Snowball sampling also called network sampling or chain sampling Its a variant of convenience sampling. Researcher ask participants to suggest or refer someone else who might be eligible Snowball samples are useful when certain people are hard to contact, for example a person trying to contact drug users might use a snowball sample
Purposive/Judgmental sampling Based on the belief that researchers knowledge about the population can be used to hand-pick sample members. subjects sampled may be: typical of the population or particularly knowledgeable about the issues under study Sampling methods Probability sampling Simple random Systematic
cluster stratified Non- probability convenience Snow -balling Purposive quota Quota Sampling The researcher identifies population strata and determines how many participants are needed from each stratum. Ensures the inclusion of representatives from certain elements in the population. For example ensuring that all tribes are represented in a study. DATA PROCESSING AND ANALYSIS Isaac Amankwaa 157 Key topics Data processing Tabulation of data Analysing quantitative data the student should be able to: Mention the processes involve in processing research data Mention the importance of tabulating data Explain how quantitative data is analysed
Editing Data It is a process of examining the collected raw data to detect errors and omissions and to correct these when possible. It involves a careful scrutiny of the completed questionnaires.
Editing Data Purpose of editing For consistency between and among responses. For completeness in response To better utilize questions answered out of order. To facilitate the coding process.
Data Processing Types of Editing Field Editing Done on the same day as the interview to catch technical omissions, check legibility of handwriting, and clarify responses Office Editing Performed by a central office staff; often done more rigorously than field editing Coding of data It involves assigning of numbers to each response of the question. Purpose to translate raw data into numerical data, which may be counted and tabulated. E.g. the variable sex can be represented as: 1 = Male 2 = Female. Missing values can be entered as a code 9 or 99 or 999 instead of entering it as blank.
Coding of data Pre-coding This is when codes are entered on the questionnaires (or checklists) themselves. For each questionnaire a box is inserted in the right margin of the page. These boxes should not be used by the interviewer. They are only filled in afterwards during data processing. Summarizing (classification) of data Data can be summarized using: Data master sheets; manual compilation or compilation by computer
Summarizing (classification) of data Data Master Sheets All the answers from individual respondents are entered by hand onto the data master sheet.
Summarizing (classification) of data Data Master Sheets In a study carried out by students of a nursing school about the smoking habits of the inhabitants of their town. The questionnaire had only 17 questions, of which 9 were asked of everyone, 4 exclusively to smokers and 4 exclusively to non-smokers. The data was processed by hand as seen in the next slide No Q1 Sex Q2 Age Q6 No. of Cig Q7 Age of onset Q 9 Tried to Q 14 Cough > 2 weeks Q 14 Coug h /chest pain reduce stop Yrs Cat No Cat Yrs Cat yes No Yes No Yes No Yes N o 1 M 18 10 12 1x 2 M 35 30 20 NR 1x 3 M 54 15 14 10x 3x Etc. total 31 AV 35 Av 20 Av 20 26 4 + 1 NR 19 12 5 26 11 2 0 Summarizing (classification) of data Compilation by hand (without using master sheets) Used for a small sample (e.g.< 30) This can be done by manual sorting tally counting
Summarizing (classification) of data Compilation by hand (contd) Manual Sorting (Procedure) Take one question at a time, for example, use of health facility, Sort the questionnaires into different piles representing the various responses to the question, (e.g., hospital/ health centre/ traditional practitioners) then count the number in each pile
Summarizing (classification) of data Compilation by hand (contd) Tally counting (Procedure) One member of the compiling team reads out the information while the other records it in the form of a tally (e.g., /// representing 3 subjects, //// representing 4 subjects who present a particular answer). After tally counting, add the tallies and record the number of subjects in each group. Summarizing (classification) of data Compilation by hand (contd) After doing either manual or tally counting, check the total number of subjects/responses in each question to make sure that there has been no omission or double count. Computer Compilation The computer should not be used For small samples if data is mainly generated by open questions (qualitative data) The larger the sample, the more beneficial in general the use of a computer will be.
Computer Compilation Steps in Computer Choosing an appropriate computer program (e.g. STATA, SPSS, ect) Data entry Verification or validation of the data Programming (if necessary) Computer outputs/prints
Computer Compilation-steps 1. Choosing an appropriate computer program You need to identify an appropriate statistical package Examples include Epi Info, SPSS, STATA, etc. 2. Data entry First develop a data entry format This is followed by coding of information on the data collection instrument e.g., Male: M or 1, Female: F or 2 Computer Compilation-steps 3. Verification This is done to correct mistakes that occurred during data entry E.g. of mistakes that can seen on a print out included exceptionally long or short lines, blanks that should not be there, alphabetic codes where numbers are expected. Computer Compilation-steps 4. Programming A certain amount of basic knowledge of computer programming is needed to give the appropriate commands. Computer Compilation-steps 5. Computer outputs This involves printing the analysis generated by the computer This is followed by a careful scrutiny of the individual tables, graphs, and statistical tests to ensure they make sense Classification of data This involves putting the collected data into groups that have common features This helps convey a meaning to the researcher. Classification is done in two ways: 1. Classification according to attributes. 2. Classification according to the class intervals
Classification according the attributes Data is classified on the basis of common characteristics that can be: Descriptive e.g. sex, marital status Numeral e.g. weight and height
Classification on the basis of the interval The numerical feature such as income, age and weight can be measured quantitatively classified by way of intervals.
Tabulation of Data Tabulation is the process of summarizing raw data and displaying it in the form of statistical table for further analysis This can be done manually (small study) or by the use of computers (large numbers)
Advantages of Tabulation It simplifies complex data. It facilitates comparison and summarisation. It facilitates computation. It presents facts in minimum possible space. Facilitates detection of errors and omissions Tabulated data are good for references and they make it easier to present the information in the form of graphs and diagrams.
Basic Principles of Tabulation 1. Tables should be clear, concise & adequately titled. 2. Every table should be distinctly numbered for easy reference. 3. Column headings & row headings of the table should be clear & brief. 4. Units of measurement should be specified at appropriate places. 5. Explanatory footnotes concerning the table should be placed at appropriate places. 6. Source of information of data should be clearly indicated. 7. Abbreviations should be avoided.
Analyzing Quantitative Data Quantitative studies normally produce numbers In quantitative study, data that describe both the characteristics of the participants and the findings of the study. This can be presented in two main ways: Descriptive analysis Inferential analysis Descriptive Analysis Descriptive analysis describes the main characteristics of a collection of data. Four main areas of descriptive statistics are: Frequencies Averages Charts Variability
Descriptive Analysis Frequency counts An enumeration of how often a certain measurement or a certain answer to a specific question occurs. Example, asking 100 nurses working in SDA hospital whether they had experienced any back pain in the past six months. Responses to be given include: Severe, Minor and None. The number of responses to each of the possible answers can be presented as follows:
Possible answer Frequency of answer severe 7 respondents answered YES minor 45 respondents answered YES none 48 respondents answered YES Diagnosis Frequency % Arrested hydrocephally 1 4.2 Brain trauma 3 12.5 Brain damage 2 8.3 Brain damage (RTA) 1 4.2 Cerebral palsy 1 4.2 Chicken pox encephalitis 1 4.2 Congenital abnormality 1 4.2 Downs syndrome 6 25.0 Dysgenic features 1 4.2 Microcephaly 2 8.3 Multiple handicap birth 1 4.2 Not recorded 1 4.2 Williams syndrome 3 12.5 total 24 100.0 FREQUENCIES OF TYPES OF LEARNING DISABILITIES Descriptive Analysis Percentages Allow us to quickly summarize and put some meaning behind our findings. In percentage terms, 25 per cent of our sample has been diagnosed with Downs syndrome. Averages/ Measures of Central Tendencies It give the reader a good idea of some of the central, or average, values of a set of data. The three types of averages are Mean mode median E.g. a nurse consultant interested in how long patients are seen at the OPD Possible answer Frequency of answer 10 minutes 3 patients 20 minutes 1 patient 30 minutes 40 minutes 50 minutes 60 minutes 1 patient Charts: visual presentation of data Variables can be represented as charts. Examples of charts are the bar chart, the histogram and the pie chart. These charts help present data graphically. Bar charts and pie charts tend to be used for categorical-type data, and histograms tend to be used for continuous-type data.
Bar chart
Mainly used for categorical-type data Frequencies of variables appear here Variables appear here Pie Chart This is a circular chart divided into segments, illustrating the different frequencies, proportional to the size of the frequency to all the other frequencies.
Discussing your Research Finding Key topics Interpreting the findings Contextualising the findings Evaluating the study and making recommendations After reading this topic, the student must be able to: offer a good interpretation of research results discuss research findings in relation to existing literature make recommendations based on study findings
Introduction This is the most difficult part of the research process. It involves: interpreting your results and what they mean Looking for opportunities to point out the importance of your findings Pointing out the issues that arose out of your study Introduction Discussion therefore involves interpreting the findings, contextualising the findings and the study in relation to the literature, evaluating the study and making recommendations. Interpretation of Results Provide a brief summary of the findings do not repeat the statistics nor repeat verbatim quotes in the results section and do not come up with new findings not already covered in the results. Explain why certain trends were obtained. Contextualising the findings and the study in relation to the literature Clearly define whether the data confirm your hypotheses (quantitative study) or whether a new theory has been generated (qualitative studies). If a hypothesis was not supported by the data, are there any alternative ideas for further re- search and further hypotheses? Could any anomalous findings in a quantitative study lead to an exploratory qualitative study to try to explain such anomalies? Contextualising the findings and the study in relation to the literature It is essential that you provide suggestions for future studies in the area Provide proposals for more effective designs and alternative methods of analysis. Mention the limitations.
Evaluating the study and making recommendations Summarise the general strengths and limitations of the study so you can make clearer to the reader the main points you are trying to convey. Provide recommendations that might apply to: developments in policy, changes to nursing practices future recommendations for researchers to further study in this area. Finally there should be one or two sentences that summarise your overall findings and main conclusion.
Reporting/Disseminating Research Finding Findings of research must be communicated especially if they have the potential to impact nursing practice and patient care. Common forums for communication of study findings include publication in various nursing journals, oral and poster presentations at professional meetings/conferences, and/or in the workplace. Research Reports A research report should have the ff sections: An abstract or summary An introduction Methodology or method Results/findings Discussion