SESSION III: SCIENTIFIC METHODS AND STEPS IN CONDUCTING RESEARCH Intended Learning Outcomes By the end of this session, students should be able to:
Demonstrate the steps in conducting scientific research
Identify a research problem
Critically examine the problem
Generate research objectives
www.knust.edu.gh
2 Intended Learning Outcomes By the end of this session, students will be able to:
Design research in alignment with the objectives
Conduct research study either by survey or experiment
Collect, manage, analyze and interpret data
www.knust.edu.gh
3 Steps in Conducting Research Overview
• Research process is cyclical, but more exactly like a chain
o Begins with a question and ends with another question www.knust.edu.gh Steps in Conducting Research • Generating Research Idea Systematic Observation
Library research
Being adventurous
Interactions with others
Being inquisitive
www.knust.edu.gh
5 Formulation of Research Problem • Start by having the ideal situation in mind Where are we? Where should we be? Why aren’t we where we should be?
• Techniques involved in defining the problem
Statement of the problem in a general way Understanding the nature of the problem Surveying the available literature Developing the ideas through discussions Rephrasing the research problem into a working proposition
www.knust.edu.gh
3/18/2019 6 Formulation of Research Problem
www.knust.edu.gh
3/18/2019 7 Reviewing Literature
• Define the purpose of the literature review
• Provide an outline for the review including key words
• Search for relevant material (information)
• Synthesize ideas
• Provide references and sources of information
www.knust.edu.gh
3/18/2019 8 Literature Review • Sources of information includes; Technical reports Internet Journal articles Indigenous knowledge Books Videos Monographs Pictures Patent Conference proceedings Newspapers
www.knust.edu.gh
3/18/2019 9 Formulation of Hypothesis
• Develop idea into a testable hypothesis
• Research hypothesis = Scientific hypothesis
Statement of an expected or predicted relationship between variables What the experimenter believes will happen in the research study Can be directional or non directional
• Statistical hypothesis = Null hypothesis
States that there is no relationship between the variables
www.knust.edu.gh
3/18/2019 10 Research Design • It is the plan or blue print • Depends on: What is the study about? Why is the study being made? Where will the study be carried out What type of data is required Where can the data be found? What period of time will the study include? What will be the sample design? What techniques of data collection will be used How will the data be analysed In what style will the report be prepared www.knust.edu.gh
3/18/2019 11 Data Collection
• Variables being measured
• Instruments
• Level of measurement
• Precision and Accuracy
• Ethics
www.knust.edu.gh
3/18/2019 12 “In every success story, you will find someone who has made a Courageous decision” -unknown www.knust.edu.gh
13 Kwame Nkrumah University of Science & Technology, Kumasi, Ghana
SESSION V: DATA ANALYSIS & INTERPRETATIONS
14 Data Analysis and Interpretations
• Data analysis – An attempt by the researcher to summarize collected data.
• Data Interpretation – Attempt to find meaning
• How do these differ by research tradition?
– Quantitative – Qualitative www.knust.edu.gh Types of Data Data
No logical order Logical/Intrinsic order Counted items Measured characteristics
e.g e.g e.g. # of children e.g. Male/Female Rank # of packaging material Weight Colours Size of shoes # of ladies and gentleman Voltage Phone Types Hedonic scale in the class Temperature Likert scale Exercise No. Nominal Ordinal Discrete Continuous
1 The distance was 32.62 km
2 Team C were 1st while Team A and B took the 3rd and 2nd position.
3 Capital Cities in Ghana
4 The % fat was 94.5 5 Number of weeks in a month 6 Names of days in the week 7 I went to the gym at 5.00am 8 Brands of phone 9 Official Class Register/List
www.knust.edu.gh Key components of a data analysis plan • Purpose of the evaluation
• Questions
• What you hope to learn from the question
• Analysis technique
• How data will be presented
What should be the approach? • Think about analysis EARLY • Start with a plan • Code, enter, clean • Analyze • Interpret • Reflect What did we learn? What conclusions can we draw? What are our recommendations? What are the limitations of our analysis? Coding
• “Hypothesis is perhaps the most powerful tool, man has
invented to achieve dependable knowledge” – Fred Kerlinger
• Hypothesis is the testable answer to a scientific question
• is a test of a claim or an assumption
• The general idea of hypothesis testing involves:
1. Making an initial assumption
2. Collecting evidence (data) 3. Hypothesis Testing • Deciding whether to reject or not reject the initial assumption Hypothesis 1. Making an initial assumption a. Based on two competing hypotheses – Null hypothesis (Ho) – Alternative hypothesis (H1 or HA)
b. In statistics, we always assume the null hypothesis
is true until proven otherwise empirically.
That is, the null hypothesis is always our initial
assumption Type Null Alternative
Right-tailed Ho: 1 = 2 Ha: 1 > 2
Left-tailed Ho: 1 = 2 Ha: 1 < 2
Two-tailed Ho: 1 = 2 Ha: 1 2
OR Type Null Alternative
Right-tailed Ho: 1 2 Ha: 1 > 2
Left-tailed Ho: 1 2 Ha: 1 < 2
Two-tailed Ho: 1 = 2 Ha: 1 2
Exercise (Write the hypothesis for these claims/assumptions)
Q1. Based on the recent National Math and Science Quiz,
an educationist is investigating if the IQ of SHS students in the Ashanti Region are different from the other 9 regions in Ghana.
Q2. After a testing over 10 brands of yoghurt, an investor is
of the view that IcyCup is taste best as compared to the brands.
Q3. Samsung Note 7 is the worst phone produced and
marketed by Samsung Hypothesis Testing (p-value approach) – In statistics, we always make one of two decisions. We either "reject the null hypothesis" or we "fail to reject the null hypothesis."
– Testing is done at a level of significance, which is based on a
probability.
• The P-value approach involves determining "likely" or "unlikely" by
determining the probability — assuming the null hypothesis were true
• If the P-value is less than (or equal to) α, then the null hypothesis is rejected in favor of the alternative hypothesis. And, if the P-value is greater than α, then the null hypothesis is not rejected. Exercise (Hypothesis testing Write the hypothesis for these claims/assumptions)
Q1. Based on the recent National Math and Science Quiz, an educationist is investigating if the IQ of SHS students in the Ashanti Region are different from the other 9 regions in Ghana. a. P value = 0.002, α = 0.01 b. P value = 0.05, α = 0.05 c. P value = 0.03, α = 0.002
Q2. After a testing over 10 brands of yoghurt, an investor is of the view that IcyCup is taste best as compared to the brands. a. P value = 0.04, α = 0.05 b. P value = 0.19, α = 0.13 c. P value = 0.09, α = 0.08
Q3. Samsung Note 7 is the worst phone produced and marketed by Samsung a. P value = 0.15, α = 0.04 b. P value = 0.003, α = 0.03 c. P value = 0.06, α = 0.002
