Research Skills Essay
johnathan1993
lecture_7_quantitative_research_analysis.pptxLECTURE 7: ANALYZING QUANTITATIVE By: Dr. Tao Zhang Email: [email protected]
RESEARCH SKILLS (SINGAPORE PROGRAMME)
Learning Outcomes
By the end of the session you should understand:
The importance of data preparation
How to code questions
Examples of descriptive Statistics
Testing Statistical Significance
Examples of inferential statistics
Data Preparation
Data Analysis
Presentation and
Reporting
Data Preparation
To ensure that
data are accurate
consistent with intent of the research
complete
arranged to simplify the data analysis
Blumberg et al 2005
Questionnaire Checking
Have all the questionnaires been completed?
Have they completed all the questions required of them?
Has the person you wanted completed the questionnaire?
What do the individual items say?
Coding Questions
Code each question.
Remember to reverse score.
E.g. Fish is a healthy food
Strongly Disagree (2)
Strongly Agree (6)
Neither agree or disagree (4)
Disagree (3)
Agree (5)
Very Strongly Agree (7)
Very Strongly Disagree (1)
E.g. Fish is difficult to prepare
Strongly Disagree (2) (6)
Strongly Agree
(6) (2)
Neither agree or disagree (4) (4)
Disagree (3) (5)
Agree (5) (3)
Very Strongly Agree
(7) (1)
Very Strongly Disagree
(1) (7)
Open Ended Questions
| Quote (Purchase of Fish) | Code |
| “It’s better for you and a healthier diet for the family.” | (01) Positive health reasons |
| “Because it helps prevent arthritis and I think anything you can eat that helps that is good.” | (02) Disease Prevention |
| “If it does what it says it will do, I would buy it for health reasons. It’s healthier than fish with saturated fats.” | (03) Fat content |
| “I would buy it to try it, if it was something new that was particularly good for you but the taste of it and whether the family enjoyed it would be more important than the fact it was healthy.” | (04) Family |
| “I don’t know, I just buy it if I fancy it. Can’t understand all this about polyunsaturated fat and things.” “It’s a lot of rubbish, a fad and I don’t really understand it. We all managed before this polyunsaturated food thing.” | (05)? |
| “I might try it but it would depend on what it was exactly. I try not to eat things which have been greatly processed. I prefer natural to artificial.” | (06)? |
| Well it would depend upon other factors whether it was attractively presented, if it was the sort of fish I liked anyway and if it was time consuming to prepare.”“If it looks ok and it’s got batter on it and it’s from Findus I’ll buy it.” | (07) ? |
| “I’m not into healthy eating. I eat fats for energy.” | (08) ? |
Data Analysis
Data analysis is the application of reasoning to understand the data that have been gathered
Information requirements
Characteristics of the research design
Nature of data gathered
Zikmund et al 2013
Quantitative Data Analysis
Zikmund et al 2013
-Univariate Statistical Analysis
- Bivariate Statistical Analysis
- Multivariate Statistical Analysis
Univariate analysis
Univariate analysis is analysis of one variable at a time. Common methods used:
Frequency Distribution
Diagrams
bar chart or pie chart (nominal or ordinal variables)
histogram (interval/ratio variables)
Measures of central tendency
Measures of dispersion/variablility
Frequency Distribution
number of people or cases in each category
often expressed as percentages of sample
interval/ratio data need to be grouped, e.g. ages:
18-25
25-32
33-40
A mathematical distribution whose objective is to obtain a count of the number of responses associated with different values of one variable and to express these counts in percentage terms.
(Malhotra and Birks 2003)
Frequency Distribution – How to present your results
E.g. How often do you buy any type of fish or shell fish for your family.
| Frequency of fish purchasing | Frequency (n = 311) | % |
| Never | 30 | 9.6 |
| Less than once a month | 29 | 9.3 |
| Once a month | 103 | 33.1 |
| Once a fortnight | 15 | 4.8 |
| Once a week | 103 | 33.11 |
| More than once a week | 31 | 10.0 |
Table 1: The Respondents’ Frequency of Purchasing Fish.
| Frequency of fish purchasing | % and frequency (n = 311) |
| Never | 9.6% (30) |
| Less than once a month | 9.3% (29) |
| Once a month | 33.15 (103) |
| Once a fortnight | 4.8% (15) |
| Once a week | 33.1% (103) |
| More than once a week | 10.0% (31) |
Table 1: The Respondents’ Frequency of Purchasing Fish.
CHECKLIST: Essential Table Presentation Points
Give the table a number and a full, clear title.
Give it clear column headings.
Make sure the columns and rows are in a logical sequence.
Make sure the units of measurement are clearly stated.
Make sure the sample size(s) are clearly stated.
If the table is secondary data include your source as reference underneath.
If any abbreviations are used ensure explanatory notes are included.
Refer to any table in the text.
Do not leave any table without commentary.
Use of Diagrams Bar Chart – Nominal data
What factors do you consider when making a purchase?
Base: All respondents
Quality of their products Pr ice of their products How much the company helps the community How well known the company is Good advertisements of products It is the company my friends buy from 0.7 0.16 0.09 0.03 0.01 0 AB
Quality of their products Price of their products How much the company helps the community How well known the company is Good advertisements of products It is the company my friends buy from 0.74 0.14000000000000001 0.08 0.03 0.01 0 C1
Quality of their products Price of their products How much the company helps the community How well known the company is Good advertisements of products It is the company my friends buy from 0.67 0.18 0.11 0.02 0.01 0
Pie Chart
Histogram – Interval data
Measures of central tendency
Measures of central tendency encapsulate in
one figure a value that is typical for a distribution of values:
Mean
sum all values in distribution, then divide by total number of values
Median
middle point within entire range of values
Mode
most frequently occurring value
Measures of dispersion
Dispersion means the amount of variation in a sample.
Measures of dispersion compare levels of variation in different samples to see if there is more variability in a variable in one sample than in another.
The range is the difference between the minimum and maximum values in a sample.
Range - the maximum value – minimum value
Distribution 1: 1, 8, 9, 9, 10, 10
Measures of Variability
Standard deviation (SD)
is the average distance from the mean
Is the average amount of variation around the mean
Measures of Variability
Mean = 20
Standard deviation = 2
Normal Distribution
SD=15
SD=15
Zikmund et al 2013
http://homepage.stat.uiowa.edu/~mbognar/applets/normal.html
22
Z-score
“A z-score measures the number of standard deviations an observation is away from the mean”
A positive z-score shows that observation is greater than the mean
A negative z-score shows that observation is lower than the mean
The z-score will be zero if the observation equals the mean
https:// www.youtube.com/watch?v=nKQU7lVce20#t=54
Foster et al 2014
Inferential Statistics
The previous statistics can be considered ‘Descriptive statistics’ as they do not enable the researcher to make conclusions beyond the data analysed or test any hypotheses previously developed. They simply describe data.
Inferential statistics allow the researcher to use samples to make generalizations about the populations from which the samples were drawn. Also allow for hypotheses to be tested
This makes it important to test the statistical significance – estimates of how confident one is that the results from the sample are generalizable to the population (Bryman and Bell, 2015)
https://statistics.laerd.com/statistical-guides/descriptive-inferential-statistics-faqs.php
24
Statistical Significance - Confidence Intervals
Statistical Significance Cont’d
How confident can we be that the findings from a sample can be generalized to the population as a whole?
How risky is it to make this inference?
Confidence intervals are often set at different levels 99% or 95%; 95% is the most commonly used
Correlation and significance
How confident can we be about a relationship between two variables?
Whether a correlation coefficient is statistically significant depends on:
the size of the coefficient (the higher the better)
the size of the sample (the larger the better)
Correlation Coefficient
Correlation coefficient is a numerical index that reflects the relationship between two variables
Ranges between -1 and +1
| +1 | a perfect positive correction |
| 0 < r < +1 | positive but not perfect correction |
| 0 | No association between the two variables |
| -1 < r < 0 | negative but not perfect correction |
| -1 | a perfect negative correction |
Sources: Developed from earlier editions; Hair et al. (2006)
28
Pearson’s r
Most commonly used correlation coefficient to A measure of the relationship between two interval/ratio variables
The coefficient shows the strength and direction of the relationship
https://www.youtube.com/watch?v= IIlyI7bsvIQ
Cronbach’s Alpha
Cronbach's alpha is a measure of internal consistency, that is, how closely related a set of items are as a group.
It is considered to be a measure of scale reliability.
Technically speaking, Cronbach's alpha is not a statistical test - it is a coefficient of reliability (or consistency).
Note that a reliability coefficient of .70 or higher is considered "acceptable" in most social science research situations.)
Mandhachitara, R., & Poolthong, Y. (2011). A model of customer loyalty and corporate social responsibility. Journal of Services Marketing, 25(2), 122-133.
31
Which statistical technique to use?
Salkind 2011
Bivariate analysis
Analysis of two variables at a time
Explores relationships between variables
Searches for co-variance and correlations
Can sometimes infer the direction of a causal relationship
if one variable is obviously independent of the other
T-test
T-test Key Points
Look at the column labelled Sig. If the value is less than .05 then the means of the two groups are significantly different.
ALWAYS report the t-statistic and the significance. Also report the means, their standard deviations and the sample size.
Interpretation - Look at the values of the means to tell you how the groups differ.
Implications - How does the finding impact on theory? How can managers use the finding?
Multivariate analysis
Three or more variables
The relationship between two variables might be spurious
each variable could be related to a separate, third variable
There might be an intervening variable that might be moderating the relationship
e.g. correlation between age and exercise could be moderated by gender
Regression
Multiple/Multivariate
Use of two or more ‘predictors’ (independent) variables to predict something about the dependent variable
Use of one predictor is simple regression
Exercise
Using the Lecture 7 ‘Case Exercise’ uploaded under ‘Lecture 7’ on Canvas work in groups of 5 and address the questions listed.
In addition, consider some questions that you may include to test correlations or co-variances
Essential Points for Writing Up Quantitative Data Analysis
Consider the nature of the data being analysed when using a particular technique
Meet your research objectives
Present only analyses that are relevant to your research questions
Ensure you include the appropriate figures e.g. for a t-test the t value and significance
Make sure tables and graphs are clearly presented
Comment on all the analyses presented
Bryman and Bell 2009
Common Problems with Results Sections
Lack of data interpretation
Lack of relevance
Placing too much emphasis on too few statistics
Lack of structure
Emphasis on the packaging rather than the quality
Reading
Ch 14 Quantitative Data Analysis, Ch 15 Using SPSS fpr Windows, Bryman and Bell,(2011), Business Research Methods, Second Edition, Oxford
Ch 12 Analysing Quantitative Data, Saunders, Lewis, Thornhill, (2009), Research Methods for Business Students, Fifth Edition, FT Prentice Hall
Ch 9, Analyzing Quantitative Data, Wilson, (2010) Essentials of Business Research: A Guide to Doing Your Research Project. Sage.
Ch. 17 Data Preparation, Ch 18 Frequency distribution, cross-tabulation and hypothesis testing,
CH 19 Analysis of Variance and Covariance, Malhotra N.K. and Birks D.F., (2007), Marketing Research An Applied Approach, Third Edition, Prentice Hall
Field A., (2009), Discovering Statistics Using SPSS, Third Edition, Sage
Kinnear P.R. & Gray C.D., (2009),SPSS 16 Made Simple, Hove and New York: Psychology Press
QUESTIONS?
Reading
Ch 14 Quantitative Data Analysis, Ch 15 Using SPSS fpr Windows, Bryman and Bell,(2011), Business Research Methods, Second Edition, Oxford
Ch 12 Analysing Quantitative Data, Saunders, Lewis, Thornhill, (2009), Research Methods for Business Students, Fifth Edition, FT Prentice Hall
Ch 9, Analyzing Quantitative Data, Wilson, (2010) Essentials of Business Research: A Guide to Doing Your Research Project. Sage.
Ch. 17 Data Preparation, Ch 18 Frequency distribution, cross-tabulation and hypothesis testing,
CH 19 Analysis of Variance and Covariance, Malhotra N.K. and Birks D.F., (2007), Marketing Research An Applied Approach, Third Edition, Prentice Hall
Field A., (2009), Discovering Statistics Using SPSS, Third Edition, Sage
Kinnear P.R. & Gray C.D., (2009),SPSS 16 Made Simple, Hove and New York: Psychology Press
0
1
2
3
4
5
No. of people
81012141618202224262830
Score
