Scribd
Upload
29 views

Topic 4 - Research Methodology and Statistical Tools - 2023

This chapter discusses research methodology and statistical tools. It aims to help students determine the appropriate research design, sampling method, sample size, research instruments, and statistical analysis for their study. Some key points covered include determining the right design such as descriptive, correlational or causal; sampling techniques like simple random, stratified, or Poisson; validating survey questionnaires; developing cover letters and question types; and addressing ethical concerns. Statistical tools covered include t-tests, ANOVA, factor analysis, multiple regression, and structural equation modeling.

Uploaded by

echo fate
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
29 views

Topic 4 - Research Methodology and Statistical Tools - 2023

This chapter discusses research methodology and statistical tools. It aims to help students determine the appropriate research design, sampling method, sample size, research instruments, and statistical analysis for their study. Some key points covered include determining the right design such as descriptive, correlational or causal; sampling techniques like simple random, stratified, or Poisson; validating survey questionnaires; developing cover letters and question types; and addressing ethical concerns. Statistical tools covered include t-tests, ANOVA, factor analysis, multiple regression, and structural equation modeling.

Uploaded by

echo fate
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Research Methodology

and Statistical Tools


Topic 4
Learning outcomes
After studying this chapter, the student should be able to:
a. determine what is the right research design for the study;
b. learn how to sample the respondents;
c. know what is the appropriate sample size;
d. identify what is the appropriate research instrument;
e. learn how to validate the survey questionnaire;
f. develop a cover letter,
g. develop close-ended questions, scales, rating, and ranking questions.
h. determine the ethical issues in business research; and
i. learn how to report the statistical treatment.
Research Methodology
• detailed outline of how an investigation will take place
• typically include
• how data are to be collected,
• what instruments will be employed,
• how the instruments will be used, and
• the intended means for analyzing data collected
What is the right research design for the
study?
• Conclusive
• Descriptive
• Correlational
• Causal
Guidelines for using correlational research tools
• If the problem involves hypothesis testing, decide on:
• hypothesis of relationships (between variables), use:
• for parametric data = Pearson R
• for nonparametric = Kendall’s tau B, Spearman’s rho, or chi-square
• hypothesis of difference, use:
• paired t-test (comparing pair of variables; interval or ordinal)
• independent samples t-test (comparing a variable [interval or ratio scaled] with a
nominal variable with two categories only
• one-way ANOVA (for comparing a variable with a nominal variable [interval or ratio
scaled] with at least three or more categories)
Guidelines for using correlational research tools
• If the problem is to know which factors/variables are valued by the
respondents, then the right technique is a multivariate technique
called factor analysis.
• to know which variables are important
• the unimportant variables will be eliminated (data reduction)
Guidelines for using correlational research tools
• If the problem is to know which of the variables (called independent
variables) would explain or predict a particular variable (called
dependent variable), then the right technique is a multivariate
technique called multiple regression analysis.
Guidelines for using correlational research tools
• Other techniques
• to know how to group (segment) the respondents based on their preferences
and profile them by cross-tabulating their demographic data
• cluster analysis
• to know how to measure the perception of the respondents and show the
results visually through a two- or three-dimensional perceptual map
• multidimensional scaling (MDS) – paired comparisons (interval or ratio scaled)
• multidimensional unfolding (MDU) – ranking (ordinal)
• correspondence analysis – multiple options (nominal)
• to determine which in the list of valued factors would result into the best
combinations for the respondents to choose from
• conjoint analysis
Guidelines for using causal research tools
• If the problem is to test the existing theoretical framework and
validate its measurement variables for research application
• Confirmatory factor analysis (CFA)
• If the problem is complex and characterized by complex relationships
(which cannot be solved by either of the ff: MRA, FA, Cluster analysis,
and conjoint analysis)
• either covariance-based structural equation modeling (CB-SEM) or partial
least squares structural equation modeling (PLS-SEM)
Sampling plan
How should the respondents be properly sampled?
• Sample sizes
• based on the margin of error and confidence level
• Slovin’s formula/Taro Yamane’s formula (known population)
• Cochran’s formula (unknown population)
• Raosoft - online sample size calculator (for reference)
Sampling plan
Which is preferred – random or purposive sampling?
• random – to generalize the results across the population
• purposive
• to determine the target market for a particular organization
• starts by qualifying the respondent first, then selecting them once qualified
by the quota method
Sampling plan
Types of random sampling
• Simple random sampling – if the population is known
• Stratified random sampling – if the population is known
• Random sampling based on Poisson distribution - if the population is
unknown
Sampling plan
Simple random sampling – if the population is known
• researcher has to have a sampling frame (the list of the the target population)
• research randomizers are available online
Sampling plan
Stratified random sampling – if the population is known
• if the target population has a natural grouping and some groups may have
more respondents than the other groups
• example: MSMEs, generational age
• once the stratified distribution and the sample size are computed, each
stratum should have the respondents randomly selected
Sampling plan
Poisson distribution – if the population is unknown
• example: mall intercept
Research instrument
What is the appropriate research instrument for gathering quantitative
research data?
• survey questionnaire
• + depth interview to complement (with caution; results may contradict with survey)
• instrument must address all the questions in the problem statement
• if there is a need to translate, separate version must be crafted
• instrument must be answerable in not more than 15 minutes
• if possible, supervised to minimize missing data or erroneous entries
Research instrument
What is the appropriate research instrument for gathering quantitative
research data?
• standardized survey questionnaire
• questions are adopted from an existing study
• no need to be validated by experts
• might not fully address the research problems; context is different; some variables in
your study are not included
• otherwise, subject the questionnaire to scales reliability test called the Cronbach’s alpha
Research instrument
What is the appropriate research instrument for gathering quantitative
research data?
• self-developed survey questionnaire
• questions are developed by the researcher
• needs to be validated by experts
• has to go through reliability and validity tests
• reliability (how well a test measures what it should)
• pretesting
• 30 or more respondents; outside of your sample size
• Cronbach’s alpha (coefficient alpha) measures reliability or internal consistency
Survey questionnaire design
• Choosing the right response anchors (levels: acceptability, importance,
agreement, frequency, desirability, priority, probability, knowledge of
action)
• Sample cover letter (pg. 53)
• Sample questions (pg. 54-56)
• Recoding a negatively stated item
• reverse coding should be applied; if not, interpretation might be affected as the
meaning is altered
• Ethical issues
• Informed consent
• Confidentiality
• Plagiarism

You might also like