Writing a research proposal...2019/01/10 · Demonstrate writing skills by writing, a clear,...
Transcript of Writing a research proposal...2019/01/10 · Demonstrate writing skills by writing, a clear,...
Faculty of Medicine
Introduction to Research and Writing Research Proposal
31509595 By
Hatim Jaber MD MPH JBCM PhD
1-10-2019
1
According to the official website of the United Nations, this year’s theme is –
‘Youth Standing Up for Human Rights’.
• HEALTH IS A HUMAN RIGHT HEALTH IS A HUMAN RIGHT HEALTH IS A HUMAN RIGHT HEALTH IS A HUMAN RIGHT HEALTH IS A HUMAN RIGHT
2
3
4
5
Your Expectations ?????
• Have Positive Expectations!
• Have Negative Expectations!
• Previous feedback?
6
Sixth Year Including Summer Semester
• Graduation Project (Research Project)
• 31500692
• 6 hours
7
Introduction to Research and Writing Research Proposal
Course description
• This research preparedness course will review and reinforce student learning on the research process and enable students to produce a research proposal ready for implementation.
• Students will review components of research proposals and practice developing effective aims, hypotheses, background materials and analytic strategies.
• In a series of modules, the course focuses on specific aspects of doing research including: literature searching and critical appraisal; reference management; framing the research question and determining research approaches; and ethical issues.
8
Introduction to Research and Writing Research Proposal
Course description cont….
• This course allows students to prepare a research proposal, on a topic of their choice, that can be implemented during fifth year.
• In addition to preparing a complete proposal for his or her research project, each student will be required to read assigned materials, hand in reflections about readings, give status updates, conduct peer reviews, make presentations, and participate actively in class discussions.
9
Introduction to Research and Writing Research Proposal
Learning Objectives
At the end of this course students should be able to: 1. Identify and create the key components of a research proposal 2. Demonstrate the ability to conduct literature reviews and gather
the critical scientific information related to the research proposal 3. Demonstrate writing skills by writing, a clear, concise research
proposal with scientifically defensible aims, methods and conclusions
4. Develop the skills to objectively review and write a scientific critique of a colleague’s proposal
5. Describe the important concepts related to using human subjects in scientific research
6. Describe the underlying concepts and principles of scientific misconduct and plagiarism
10
Introduction to Research and Writing Research Proposal
Course Learning Outcomes
1. Identify a public health problem suitable for scientific investigation
2. Situate that problem within the relevant literature and existing evidence and identify gaps in the evidence about that problem (i.e. things worthy of further research)
3. Develop a (structured) research question which addresses a gap in the evidence about the problem
4. Plan an appropriate research design to investigate the research question
5. Use appropriate online databases of research evidence and reference management software
6. Apply ethical principles of research to shape or modify the research proposal
11
Introduction to course • Course Title : Introduction to Research and Writing
Research Proposal 31509595
• Credit Hours : 3 Credit Hours
• Calendar Description : 10 weeks/ First Semester – 5th year (2019/2020)
• Teaching Approaches : 1 Lectures (120min) per week (Tuesday 13:00 pm) for 10 weeks
12
Introduction to course (cont…)
• Method of Instruction : Lectures and discussions
Evaluation and Grading : one exam (MCQ)
• Midterm - assessment = 30% (….-11-2019)
• Project presentation = 70%
13
The Basic Elements • Competence in everything
• A GOOD idea addressing a significant problem with continuity of ideas
• Logical flow of ideas & actions – Everything fits together – Nothing is superfluous or omitted, or unrealistic
• A good fit with funding agency’s priorities
Avoid Plagiarism
• Plagiarism is presenting someone else’s ideas or words as though they were your own.
15
Introduction
Health research is a part of applied science
Aim: to advance knowledge of human health and
illness through:
i. Assessing health status
ii. Probing natural history of diseases
iii. Clinical trials help to examine the effect of new drug,
vaccine, an intervention program, etc.
iv. Determining and assessing treatment outcome
v. Identifying and assessing risk factors
16
What is a research proposal?
• A document with two major objectives: – To analyze and synthesize the existing research
about particular topic.
–Describe the researcher’s idea for a new study.
• An art which the researcher wants to sell in the market. – Buyer needs to take it from the gallery.
– Suits to buyer’s pocket.
17
Why I need a research proposal
• It is prerequisite for degree
• Needs approval from the committee to start the work
• It conceives the project
• It impresses the senior as a potential researcher
• It serves as a contract between the researcher and funder.
• Personal interest.
18
A research proposal has three main points:
• 1) Explanation of proposed research (what will be done)
• 2) Methods and techniques to be employed (how it will be done)
• 3) Novelty and/or importance of the study (why it should be done)
19
Components of a Proposal 1. Cover page 2. Summary / Abstract
3. Introduction / Statement of the Problem 4. Review of the Literature 5. Aims 6. Methodology 7. Data Analysis 8. Expected outcome (Risk/Benefit Analysis) 9. Future direction 10. Bibliography 11. Timeline 12. Budget/Cost Effectiveness 13. Appendices
20
Step 1. Choose a Topic
Choose a topic which interests and challenges you. Your attitude towards the
topic may well determine the amount of effort and enthusiasm you put into your research.
Focus on a limited aspect - narrow it down from Religion to World Religion to
Buddhism. Obtain teacher approval for your topic before embarking on full-scale
research. Select a subject you can manage. Avoid subjects that are too technical,
learned, or specialized. Avoid topics that have only a very narrow range of source materials.
A Research Guide for Research Students http://www.aresearchguide.com/1steps.html
21
Choosing a Title • The title summarizes the main idea or ideas of your
study.
• A good title contains the fewest possible words that adequately describe the contents and/or purpose of your research paper.
• The title is without doubt the part of a paper that is read the most, and it is usually read first.
• If the title is too long it usually contains too many unnecessary words, e.g., "A Study to Investigate the...." On the other hand, a title which is too short often uses words which are too general. For example, "African Politics" could be the title of a book, but it does not provide any information on the focus of a research paper.
22
• If you leave a topic broad, it will be superficial. • If your topic is narrow, you can deal with it in
depth. If your topic is broad, you will deal with it only in a shallow way.
• For example, instead of writing a history of the
development of vaccination…
• Narrow the topic to: "The effect of the combined vaccination late 1990s on prevention."
23
• The following parameters can be used to help you formulate a suitable research paper title:
• The purpose of the research
• The narrative tone of the paper [typically defined by the type of the research]
• The methods used
• The initial aim of a title is to capture the reader’s attention and to draw his or her attention to the research problem being investigated.
24
• Create a Working Title Typically, the final title you submit to your professor is created after the research is complete so that the title accurately captures what was done. The working title should be developed early in the research process because it can help anchor the focus of the study in much the same way the research problem does. Referring back to the working title can help you reorient yourself back to the main purpose of the study if you feel yourself drifting off on a tangent while writing.
25
The Final Title Effective titles in academic research papers have several
characteristics. • Indicate accurately the subject and scope of the study. • Avoid using abbreviations. • Use words that create a positive impression and stimulate reader interest. • Use current nomenclature from the field of study. • Identify key variables, both dependent and independent. • May reveal how the paper will be organized. • Suggest a relationship between variables which supports the major hypothesis. • Is limited to 10 to 15 substantive words. • Do not include "study of," "analysis of" or similar constructions. • Titles are usually in the form of a phrase, but can also be in the form of a
question. • Use correct grammar and capitalization with all first words and last words
capitalized, including the first word of a subtitle. All nouns, pronouns, verbs, adjectives, and adverbs that appear between the first and last words of the title are also capitalized.
• In academic papers, rarely is a title followed by an exclamation mark. However, a title or subtitle can be in the form of a question.
26
Project title
• The title should be descriptive and concise.
• It may need to be revised after completion of the writing of the protocol to reflect more closely the sense of the study.
27
Title
This should provide a specific summary of the proposed work
Example 1: • NO (too much detail) A three-year study of population decline in the spotted
salamander (Ambystoma maculata) following logging, road building and wetland mitigation near vernal pools in a hardwood forest of northeastern Connecticut
• YES A study of population decline in the spotted salamander
(Ambystoma maculata) following logging in northeastern Connecticut
28
Title
Example 2:
• NO (not enough detail)
Habitat models for use in rivers
• YES
Validation of in-stream habitat models for the Fenton River, Storrs, Connecticut
29
Title of the research
A good title should be short, accurate, and
concise.
It should make the central objectives of the study
clear to the reader.
It is important to specify what population will be
investigated, and where it will be conducted.
30
Simple steps to write a good research paper title
STEP 1
• Ask yourself these questions and make note of the answers: • What is my paper about? My paper studies whether X therapy improves the cognitive
function of patients suffering from dementia. • What techniques/ designs were used? It was a randomized trial. • Who/what is studied? I studied 40 cases from six cities in Japan. • What were the results? There was an improvement in the cognitive function of
patients.
31
Simple steps to write a good research paper title
STEP 2
• Use your answers to list key words.
• X therapy
• Randomized trial
• Dementia
• 6 Japanese cities
• 40 cases
• Improved cognitive function
32
Simple steps to write a good research paper title
STEP 3
• Create a sentence that includes the key words you listed.
• This study is a randomized trial that investigates whether X therapy improved cognitive function in 40 dementia patients from 6 cities in Japan; it reports improved cognitive function.
33
Simple steps to write a good research paper title
STEP 4
• Delete all unnecessary/ repetitive words and link the remaining.
• This study is a randomized trial that investigates whether X therapy improved cognitive function in 40 dementia patients from 6 cities in Japan; it reports improved cognitive function Randomized trial of X therapy for improving cognitive function in 40 dementia patients from 6 cities in Japan
34
Simple steps to write a good research paper title
STEP 5 • Delete non-essential information and reword the
title. • Randomized trial of X therapy for improving cognitive
function in 40 dementia patients from 6 cities in Japan reports improved cognitive function
• Randomized trial of X therapy for improving cognitive function in 40 dementia patients
OR Include a subtitle • X therapy improves cognitive function in 40 dementia
patients: A randomized trial
35
Be prepared for
• To make mistakes and to learn.
• To write and rewrite many times.
• To spend many hours looking for information.
• To have your writing criticized.
• To feel confuse and hopeless some times.
36
When should the research proposal be written?
• Preparation with the flying mind question
“Why”? In the first few months of this year.
• A substantial amount of work has to be done before a proposal can be written
• Some departments assume that a research proposal will be written in next two months.
• Seek advice on your draft from supervisors and peers.
37
Before start writing ……..
• Do I have the clear research question?
• Have I read broadly and deeply in that area?
• Have I discussed the topic with peers?
• Have I enough time and fund to start?
• Do I feel support from faculty and friends?
38
What it should contain? It is based on your clear research question.
• What do you want to do?
• Why do you want to do it?
• Why is it important?
• Who has done similar work?
• How are you going to do it?
• How long will it take?
39
First step: formulation of the research question.
• Subject?
• Topic?
• What I want to observe?
• How I will do this.?
• Concise and descriptive.?
• Reflects the proposal in one sentence.?
40
Cover/Title Page
Good
• Concise and clear title
Bad
• Wrong information • Short or long title
41
Cover page
42
43
44
Research Proposal Submitted to fulfill the course requirement (31509595 )
Introduction to Research and Writing Research Proposal
Faculty of Medicine
Title …………………………………………………………………………………………………………………………
Under Supervision of Dr………..
By (team) 1- 2-
Submitted To
Dr. Hatim Jaber
Date of submission …….12-2019 45
Research Plan
The Research plan should include the following items:
1. Introduction
2. Objectives
3. Review of Literature
4. Research Design and Methods. 5. Time Schedule
46
Introduction
• Definition of the problem under study.
• Magnitude of the problem.
• Major items concerning the problem, including the recent
studies trying to describe, explore its causes, solution of
the problem, etc.
• Rational of the research
- Does the study address an important health problem?
- How will scientific knowledge be advanced?
- What will be the effect of the study results on the concepts or methods
that drive this problem?
47
Introduction
• Quantitative approach – aims to accurately describe the studied
problems (Descriptive epidemiology) and to identify and explain
their causes (Analytical epidemiology)
• It addresses health problems in variables with subsequent
statistical analysis and interpretation.
• Qualitative research - produces data which is reported in the
words of the patients or clients (broad, open-ended, and
interconnected questions) and is analyzed and interpreted in the
context of their family and cultural settings
48
Research design and Methods
The following items should be overviewed in details:
1. Type of the study
2. Study population and sampling techniques
3. Study variables
4. Data collection
5. Data analysis
6. Strengths and limitations
7. Ethical consideration
49
Type of study
Observational
Descriptive
(Prevalence)
Experimental
(Intervention) Analytical
- Cross sectional
- Ecological
- Case control
- Prospective
- Randomized Controlled Trial
(RCT)
- Community intervention trial
Others: case report, case series report, Case-only studies
(Genetic epidemiology “Gene environment interaction studies),
Case-Crossover studies.
50
Arrangement of studies according to their strength in
Evidence Based Medicine (EBM)
1. Randomized Controlled Trial (RCT)
2. Prospective studies
3. Case-control studies
4. Prevalence studies
5. Ecological studies
6. Case report and case series
1
2
3
4
5,6
51
Descriptive (prevalence) What is happening right now?
Subjects selected
to the study
With
disease
Without
disease
• Advantages: - Quick and cheap
- Generate hypothesis
- Indicate the prevalence of health and disease in a community
- Deal only with survivors
• Disadvantages - Not useful in rare diseases
- Do not prove association or cause effect relationship
E
D Onset of the study
52
Case-control study What happened?
Advantages: - Not expensive
- Short period of time
- Suitable in Rare diseases
- Can examine multiple risk
factors
Disadvantages - Recall bias
- Difficult to select proper controls
- Use hospital or clinic cases only
restrict the results of the study
(Generalization)
- Misclassification of exposure
- Sophisticated statistical analysis
(Logistic regression)
53
Measure of association in case control
study (odds ratio (OR))
Exposed Non
exposed
Cases a b
Controls c d
is the odd of exposure in cases relative to that in controls (a/c)
divided by
odd of non exposure in cases relative to that in controls (b/d)
OR = a/c ÷ b/d = ad/bc OR =1 (no association)
OR > 1 (positive association)
OR < 1 (Protective effect)
OR = ad /bc
54
Prospective study What will happen?
Prospective study Advantages: - Incidence Rate and RR can
be estimated
- Cause-effect determination
- No recall bias
Disadvantages - Expensive
- Take long time
- Not suitable for rare
diseases
- Loss of follow up for some
studied persons
- Sophisticated survival
analysis (Cox regression)
55
Measure of association in prospective
(Relative Risk (RR))
Exposed Non exposed
Diseased a b
Not diseased c d
Total n1 n2
RR = a/n1 ÷ b/n2
RR is the incidence of disease in exposed (a/n1) divided by the
incidence of disease in non exposed (b/n2)
N.B.: RR is read as OR (see before). 56
Randomized Controlled Trial (RCT)
Advantages: - No bias (Randomization)
- Cause-effect
- Determine RR
Disadvantages: - Ethical consideration
- Very expensive
- Not practical when studying
behavioral risk factors
- Random allocation of
communities is not practical
Requirements:
Appropriation of the control group.
Randomized allocation.
Blinded intervention and blind
ascertainment of outcome.
Data analysis by intention-to-treat
principle. 57
Study population
i. Define target population
ii. Define study subjects: inclusion and
exclusion criteria, if any
Case control study
Definition of cases
Definition of controls
Systematic error 58
Types of Samples
59
• Probability (Random) Samples
• Simple random sample
–Systematic random sample
–Stratified random sample
–Multistage sample
–Multiphase sample
–Cluster sample
• Non-Probability Samples
–Convenience sample
–Purposive sample
–Quota 59
Sampling techniques
Sampling methods
• Selective or random (the best)
Sampling size
• There is no fixed size of sample.
• The formulas used to calculate sample size vary from study to study and from problem to problem.
• In cross sectional study, sample size is determined by: I. Prevalence of disease or problem under study.
II. Required confidence limit and α error
III. Required Precision (δ)
Random error
60
Study variables
Definition of the study variables: 1. Independent variables (exposure variables)
2. Confounding variables
3. Dependent variable (outcome).
• Methods of measurement of the study variables
• Methods of categorization if any (Tertiles, Quartiles, etc)
Information bias (Misclassification)
Confounding bias 61
Types of Data: Primary and Secondary data
• Primary data: Data collected by the investigator himself/ herself for a specific purpose.
Examples: Data collected by a student for his/her thesis or research project.
• Secondary data: Data collected by someone else
for some other purpose (but being utilized by the investigator for another purpose).
Examples: Census data being used to analyze the impact of education on career choice and earning.
Data collection
• Methods of data collection
- Observation
- Questionnaire
- Interview
- Record analysis
• Quality of data
- who collect data
- measurement tools
- data recording (aberrant and missing data).
Information bias (Misclassification) 64
Strengths and limitations of the study
• All the studies have limitations.
• Study limitations are known to affect study results and generalization.
• The aim is to reduce the limitations and increasing study strength points as much as possible, thereby not affecting the obtained study results.
• In discussion, reporting limitations are as important as reporting study strengths
65
Accuracy of the study (Precision and validity)
• The precision is determined by the degree to which random error
may contribute to the study results. In sampling contexts, the
random error is called sampling error.
• Sampling error is the degree to which a sample might differ from
the population.
• Mathematically, random error is calculated by dividing the
standard deviation of the sample by the square root of the
sample size (n).
SE = s / √n [formula when mean is estimated]
SE = √pq / n [formula when proportion is estimated]
By using SE, CI can be also calculated.
66
Validity of the study
General population
Target population
Sample
Internal validity
External validity Internal validity - Selection bias
- Information bias
- Confounding bias
External validity - Generalization (extrapolation)
the extent to which the study is actually estimating what it is intended to estimate.
67
Internal validity
• It is determined by the extent of systematic error that is
avoided or minimized.
• Systematic error (bias) can thus be distinguished from
random error.
Selection bias
-Non response bias
-Prevalence-incidence bias
-Hospital-based cases bias
-Publicity bias
-Healthy Worker Effect
Confounding bias
Characters of Confounder?
How to control?
Information bias
1. Non-differential
misclassification
2. Differential
misclassification
-Recall bias
-Diagnostic suspicious bias
-The clever Hans effect
68
Elements of Testing hypothesis
• Null Hypothesis "الفرضية الصفرية"
• Alternative hypothesis "الفرضية البحثية"
• Identify level of significance
• Test statistic
• Identify p-value / confidence interval
• Conclusion
69
Statistical analysis
• The used program of statistics (SAS, SPSS, etc).
• Hypothesis testing
i. Type I or α error
By convention it is 0.05 and indicates that the detected
difference is true and not due to chance.
ii. Type II or β error
By convention it is 0.20, and (1- β) is termed the
statistical power which means that the obtained
measure or difference between the studied groups
actually exists.
• Statistical tests (chi square test, test, ANOVA, etc).
70
Data types
Variables
Scale
Continuous
Measurements
takes any value
Discrete:
Counts/ integers
Categorical
Ordinal:
obvious order
Nominal:
no meaningful order
Choosing summary statistics
Which average and measure of spread?
Scale
Normally distributed
Mean (Standard deviation)
Skewed data Median
(Interquartile range)
Categorical
Ordinal: Median
(Interquartile range)
Nominal: Mode (None)
Which Test to Use?
Scale of Data
Nominal Chi-square test
Ordinal Mann-Whitney U test
Interval (continuous)
- 2 groups T-test
Interval (continuous)
- 3 or more groups ANOVA
73
Types of inferential statistics
1. Bivariate Parametric Tests
2. Nonparametric statistical tests: Nominal Data (1 group or more)
3. Nonparametric statistical tests: Ordinal Data (2 groups or more)
For continuous data
Tests for correlations between variables
Types of inferential statistics
1. Bivariate Parametric Tests:
• (a) One Sample t test (t)
• (b) Two Sample t test (t)
• (c) Analysis of Variance/ANOVA (F)
• (d) Pearson’s Product Moment Correlations(r) >> we use it if the two variables are continuous (intervals and ratios).
Types of inferential statistics
2. Nonparametric statistical tests: Nominal Data (1 group or more): (a) Chi-Square Goodness-of-Fit Test (b) Chi-Square Test of Independence
We choose between (a) or (b) according to the groups;
being dependent or independent: • If it's 1 group we use pre and post test. • If there are 2 or more groups we have 2 options: -for dependent groups >> (a) -for independent groups >> (b)
Types of inferential statistics
3. Nonparametric statistical tests: Ordinal Data (2 groups or more):
(a) Mann Whitney U Test (U) >> for 2 groups
(b) Kruskal Wallis Test (H) >> for more than 2 groups
Types of inferential statistics
→For continuous data: a) For 1 group: Z-score T-test 2 means (pre & post) >> dependent t-test b) For 2 groups 2 means >> independent t-test c) 2 or more groups: One way ANOVA
→Tests for correlations between variables: Both variables are continuous >> Pearson’s correlations (as explained earlier) Both variables are ordinal data >> Spearman test If the dependent variable was continuous and the independent was
categorical/nominal >> t-test or z-test If the dependent variable was continuous and the independent was ordinal >>
point biserial correlation
Comparing means
Comparing means
Comparing BETWEEN groups
Comparing measurements WITHIN
the same subject
3+
2
Independent t-test
One way ANOVA
2 Paired t-test
Repeated measures
ANOVA
3+
ANOVA = Analysis of variance
Ethical consideration
The aim is to:
i. Respect for human dignity.
ii. Respect for free and informed consent.
iii. Respect for vulnerable persons (Aging,
handicapping, etc).
iv. Respect for privacy and confidentiality.
v. Respect for justice and inclusiveness.
vi. Maximizing benefit and minimizing harm.
80
Timeline • Describe how long it will take to do your study • Provide timeline benchmarks • Example:
– Months 1 – 3 Prepare study tools – Months 4-10 Collect data – Months 11-12 Analyze data
81
82
83
84
Plagiarism – Just Don’t Do IT!
• Plagiarism involves: – Intentionally copying someone else’s ideas or
words and not attributing them
– Colluding with other students on work when prohibited from doing so
– Cutting and pasting text from the Internet and passing it off as your own
– Purchasing someone else’s work and describing it as your own
85
Research
Problem Literature
Review
Research
Design
Research
Findings
1. Informs
4. Contributes to
3. Reforms
2. Informs
86
The Hallmarks of Good Research
• Serves a purpose and is relevant
• Clearly focussed and scoped
• Scientific (depends on context)
• Uses appropriate techniques & methods of data collection
• Findings are presented as objectively as possible
• Conclusions are based on the findings
• Sources of information and ideas are clearly attributed
87
88