Business research proposal
SJ/-
tutorial7.pptxResearch Methodology Deep Dive
Business Research Methods (C19RH)
The Essential Components
Framing the study
Short Introduction (remind the reader of your topic)
Research Philosophy
Data Collection Methods
Data Analysis Techniques
Ethical Considerations
Positivism vs. Interpretivism
Data Collection Method (ii)
What is the method?
Why this method?
Advantages and disadvantages of this method.
What issues do you need to consider if you are embracing this method?
Awareness that other approaches are available.
Methodology
Look back generally: Qualitative & quantitative methodologies
Types of qualitative research
Types of qualitative methods
Activities/handouts etc.
EDU610
5
General Tendencies & Comparisons (Sarantakos, 1998, p. 55)
| Quantitative Research | Qualitative Research |
| Aims to test theory | Aims to build theory |
| Uses a deductive approach | Uses an inductive approach |
| Researcher is distant | Research is close to respondent(s) |
| Uses high levels of measurement | Uses low levels of measurement |
| ? | ? |
EDU610
6
Qualitative Methodologies
Inquiry (characteristics)
Context & meaning
Natural settings
Researcher as instrument
Data: descriptive (words, pictures, etc.)
Design: emergent
Data analysis: inductive
EDU610
7
Some Types of Qualitative Research
Ethnographic
Case studies
Narrative
Action Research
EDU610
8
Types: Ethnographic Approach
Theoretical foundations
History (anthropology)
Holism
Culture
In-depth (long-term)
Insider’s view
EDU610
9
Types: Case Studies
Focus
Individual instances
Unit of study
Multiple research strategies
EDU610
10
Narrative Research
Focus on stories
Questions to ask:
Who is telling the story?
In which order is the story being told?
How is it being told?
Are there multiple truths?
How is language being used?
EDU610
11
Which methods are employed to gather qualitative data?
Interviews
Focus groups
Open-ended questionnaires
Researcher observation
Researcher participation
Document analysis
Researcher reflections
Conversations/discussions
EDU610
12
Qualitative Methods: Collecting data
Interviews & Questionnaires
*unstructured (open-ended)
*semi-structured
*electronic interview or questionnaire
EDU610
http://cf.ltkcdn.net/autism/images/feat-lg/124438-280x190r1-BestToysForAutisticChildren.jpg 2/10/11
13
Quantitative Methods
Quantitative Methods are generally related to an empirical methodology
The benefits of quantitative methods are:
‘big picture research’ or the ability to collect and analyse a lot of data
The ability to generalise results using statistical tools
Allows you to answer the question of scale - ‘how many?’
Presentation of results in graphic form for impact
Can examine correlations (cause and effect)
Outline
Introduction
Frequency Distribution
Tests of association/correlation
Standard Distribution
Z test
T test
Two-sample t test
Paired t test
ANOVA
Quantitative methods arise are derived from the scientific method – the use of empirical tests to prove or disprove a hypothesis.
Benefits:
-generalizability
-can establish validity through scientific method
-can manage great amounts of data and look at very broad trends
How does quantitative research deal with data to achieve results that are valid and generalizable?
Statistics!
In this seminar we will review some of the important tools that are used to prove the validity, reliability and significance of quantitative data.
Applying quantitative methods: Frequency
Frequency distribution involves a process of recording the number of times a particular value of a variable occurs.
Survey results
Attitudinal surveys
Think of a research question examining frequency, and how you would collect, record and analyse the data.
18
Frequency distributions
| Marks (%) | No: of Students |
| < 40 | 5 |
| 41-50 | 12 |
| 51-60 | 30 |
| 61-70 | 6 |
| > 70 | 2 |
| Total | 55 |
| Marks (%) | Distribution of Students (%) |
| < 40 | 9 |
| 41-50 | 22 |
| 51-60 | 54 |
| 61-70 | 11 |
| > 70 | 4 |
| Total | 100 |
Distribution of Students (%)
Marks (%)< 40 41-50 51-60 61-70 > 70 9 22 54 11 4 Column3
< 40 41-50 51-60 61-70 > 70 Column4
< 40 41-50 51-60 61-70 > 70
Applying quantitative methods: Association
Correlation measures whether two variables are associated
Regression measures correlation. If we want to measure cause and effect relationship, correlation does not help. Correlation does not mean causation. A relationship does not guarantee or even imply a causality between the variables
When would you use this in educational research?
Relationship between factor(s) and results
Think of a research question examining association, and how you would collect, record and analyse the data.
Regression analysis
Analysis used to predict the relationship between variables.
Used for making predictive models
An “average causal effect”
http://news.mit.edu/2010/explained-reg-analysis-0316
20
Applying quantitative methods: Standard Distribution
Standard deviation is the effect whereby with a large population, the distribution of a characteristic falls into a regular curve.
Comparing results against the usual curve to make conclusions about generalizability of results.
Think of a research question using standard distribution, and how you would collect, record and analyse the data.
Distribution
For any large population, the distribution of a characteristic would be similar to the one given below. Fewer people on the extremes, maximum around the average tapering off symmetrically on both the sides of the average.
| Students Marks in a Maths Class | ||
| Range of Marks | Tally Marks | Frequency |
| 85-89 | I | 1 |
| 80-84 | II | 2 |
| 75-79 | IIII | 4 |
| 70-74 | IIIIIII | 7 |
| 65-69 | IIIIIIIIII | 10 |
| 60-64 | IIIIIIIIIIIIIIII | 16 |
| 55-59 | IIIIIIIIIIIIIIIIIIII | 20 |
| 50-54 | IIIIIIIIIIIIIIIIIIIIIIIIIIIIII | 30 |
| 45-49 | IIIIIIIIIIIIIIIIIIII | 20 |
| 40-44 | IIIIIIIIIIIIIIII | 16 |
| 35-39 | IIIIIIIIII | 10 |
| 30-34 | IIIIIII | 7 |
| 25-29 | IIII | 4 |
| 20-24 | II | 2 |
| 15-19 | I | 1 |
Applying quantitative methods: Z test
A z-test is used to determine where a small sample group falls as against a standard deviation (where known).
Comparing results from a small sample against general averages
Think of a research question examining correlation, and how you would collect, record and analyse the data.
Applying quantitative methods: T test
A t-test to compare the results of two different groups, and whether they have different averages.
Is the difference between the results and the average statistically significant
Think of a research question using a t-test, and how you would collect, record and analyse the data.
Applying quantitative methods: two-sample - T test
A two sample t-test compare means between two distinct/independent groups
Comparing the results of one group with another to determine whether the difference is significant.
Think of a research question using a two sample t-test, and how you would collect, record and analyse the data.
Applying quantitative methods: paired t test
A two sample t-test compares two quantitative measurements taken from the same individual.
Comparing the results of one test subject or group when exposed to different independent variable over time.
Think of a research question using a paired t-test, and how you would collect, record and analyse the data.
Applying quantitative methods: ANOVA
A t-test to compare the results of two different groups, and whether they have different averages.
Is the difference between the results and the average statistically significant
Think of a research question using a t-test, and how you would collect, record and analyse the data.
What about your research question?
What is your dependent and independent variable?
What kind of quantitative method are you going to use?
How will you gather your data?
How will you analyse your data?
What will your analysis prove?
Identify potential issues with validity?
| Analysis Type | Example | Parametric Procedure |
| Compare means between two distinct/independent groups | Is the mean systolic blood pressure (at baseline) for patients assigned to placebo different from the mean for patients assigned to the treatment group? | Two-sample t-test |
| Compare two quantitative measurements taken from the same individual | Was there a significant change in systolic blood pressure between baseline and the six-month follow up measurement in the treatment group? | Paired t-test |
| Compare means between three or more distinct/independent groups | If our experiment had three groups (e.g., placebo, new drug #1, new drug #2), we might want to know whether the mean systolic blood pressure at baseline differed among the three groups? | Analysis of variance (ANOVA) |
| Estimate the degree of association between two quantitative variables | Is systolic blood pressure associated with the patient’s age? | Pearson coefficient of correlation |
| In case of ordinal variable | Is the ranking given to choice criteria for schools by the sample respondents generalizable? | Chi square test |
| Analysis Type | Example | Parametric Procedure |
| Hypothesis testing when n>30 and standard deviation is known | Is the performance of one group on the same lines as that of the a larger sample without a standard deviation? | Z test |
| 1) Hypothesis testing When sample size is greater than 30 but standard deviation is NOT known 2) When sample size is less than 30 | Is the performance of one group on the same lines as one with a standard deviation? | T test for single population |
| Compare means between two distinct/independent groups | Is there a significant difference in the scores of one sample group from another? | Two-sample t-test |
| Compare two quantitative measurements taken from the same individual | Was there a significant change in attitudes before or after an event? | Paired t-test |
| Compare means between three or more distinct/independent groups | Is there a significant difference between 3 or more groups? | Analysis of variance (ANOVA) |
| Estimate the degree of association between two ordinal variables? | Relationship between curriculum (categorical variable) and international mindedness (ordinal variable measured on a scale) | Chi square test |
