Start networking and exchanging professional insights

Register now or log in to join your professional community.

Follow

Is there any correlation between Research Type and Method type used in data analysis? If so, how?

Does the type of data collected for such research work restrict your choices in such particular of data analysis method, rather than others? Whatever your job role, I can accept any opinion you suggests in this issue. thanks

user-image
Question added by Lubna Al-Sharif , Medical Laboratory Technician , Nablus Specailized Hospital
Date Posted: 2013/05/19
حازم عبد الحميد محمد دياب
by حازم عبد الحميد محمد دياب , technical office manager , Kased Khair

method type used in data analysis derive your research to go in a certain form but the famous types are such: 1-Exploratory research, which helps to identify and define a problem or question.
2-Constructive research, which tests theories and proposes solutions to a problem or question.
3-Empirical research, which tests the feasibility of a solution using empirical evidence.
There are two major types of research design: qualitative research and quantitative research.
Researchers choose qualitative or quantitative methods according to the nature of the research topic they want to investigate and the research questions they aim to answer *Qualitative research Understanding of human behavior and the reasons that govern such behavior.
Asking a broad question and collecting data in the form of words, images, video etc that is analyzed searching for themes *Quantitative research Systematic empirical investigation of quantitative properties and phenomena and their relationships.
Asking a narrow question and collecting numerical data to analyze utilizing statistical methods.
The quantitative research designs are experimental, correlational, and survey (or descriptive).
Statistics derived from quantitative research can be used to establish the existence of associative or causal relationships between variables.
that's what i have in your question.

Ashwin Pires
by Ashwin Pires , Team Lead , ZENITHR

Two basic research types

Practical : consists of the empirical study of the topic under research and hands on approach.

Theoretical : researching through archives of public libraries, court rooms and published academic journals.

 

In Practical Research the methods used will be more pratical and based on observations and hands on approach such as interviews, questionnaires, surveys, etc.

 

In theoretical approach it is mostly based on past data. like archives, journals as i have already mentioned

 

So i feel that there is a correlation between the type of Research you undertake and the method that will be used.

DrRenji Issac
by DrRenji Issac , Author - Researcher , FREELANCE

Of course. The research type;ie....quantitative or qualitative the research design is important and connected to complete study 

abdenacer garidi
by abdenacer garidi , Ingénieur de Projet , SETIRAIL

no there  is no  correlation between Research Type and Method type used in data analysis.

Pratap David
by Pratap David , Instructor

The basic steps of any quantitative research are as follows:

1. Define your research question

2. Design appropriate study

3. Collect the data 

4. Analyze the data 

5. Draw conclusions from the data 

Step4, which is what we are talking about , does not really depend on Steps1 &2 but actually relies heavily on Step3- the Nature of variables involved and the type of data collected. Let me illustrate the point.

Suppose you are interested to know whether there is any relationship between exercise and energy level among healthy adults, your research question could be as follows:

Is exercising correlated with higher energy levels among healthy adults?

                                           OR

Does exercising cause higher energy levels among healthy adults?

To answer the  first research question you have to design an Observational or correlational study. To do this you would typically do a cross-sectional study in which you would randomly select healthy adults from your population of interest and classify them into two or more groups based on their exercise status. Then you would measure the energy level of each participant and compare the mean energy levels of the groups using a t-test or ANOVA to check for significant differences.

However if your research question is the second one then you would design an experimental or causal study in which you would enroll participants and randomly assign them to two or more groups and give them different instructions regarding exercise.  Then after some time you would measure the energy level of each participant and compare the mean energy levels of the groups using a t-test or ANOVA to check for significant differences.

Please note that whether your research is observational or  experimental , the method of data analysis is still the same, i.e, you use a t-test or ANOVA in both cases. The reason for this is that in both the above studies the outcome variable is Energy level ( which is quantitative) 

So , basically data analysis methods depend on the following3 aspects:

1. Is the outcome variable quantitative ( eg. age, cognitive function) or binary/ categorical( eg. pregnant yes/no)? 

2. Are the observations independent or correlated?

3. Are the assumptions of normality and homoscedasticity violated? 

You could use the following guidelines:

1. If outcome variable is continuous and

     a. the observations are independent- t-test, ANOVA,Linear correlation/regression

     b. the observations are correlated- Paired t-test, Repeated Measures ANOVA

     c. the assuptions are violated- Wilcoxon sign -rank test, Wilcoxon rank-sum test, Kruskal-Wallis test, Spearman rank correlation 

2. If outcome variable is Binary/categorical and 

     a. observations are independent- Risk difference/ relative risks, Chi-square test, Logistic regression

     b. observations are correlated- McNemar's test, Conditional logistic regression.

     c. assumptions are violated- Fisher's exact test, McNemar's exact test.

Adnan Ameen Bakather
by Adnan Ameen Bakather , Founder & Managing Director , Consult & Perform

Yes, there is a correlation between the research type and the methodology and methods of data analysis. For example, quantitative research vs qualitative, each has different methods and data analysis technique. In addition, if you are conducting empirical study, you have to make choice between the parametric and parametric techniques of data analysis. We have to use the parametric techniques if the dependent variable is dichotomous (0,1; Yes, No) 

More Questions Like This