Hi all! I’m doing a research on inter-racial marriages and mixed-race children. I am thinking of going for a qualitative analysis. Highly confused what will work the best? I am currently working with three supervisors. All of them have a different say – grounded theory, IPA, discourse analysis etc. I personally want to go for […]
Continue reading Qualitative Analysis
What is the difference between open, axial, and selective coding? Actually, I am currently working on axial coding for one of my research projects, so need more and more information to do it better.
Hi, I want to know about the validity of a qualitative research and what does it require. All I know is that it is necessary to involve during data collection and analysis. Thanks.
Validity and reliability is something that is used in quantitative research. Though some argue against it, I find it extremely important to check and ensure the research. It’s totally up to you, whether or not you want to run validity for your investigation. I am attaching the link to a blog post that has wonderfully explained the concept of validity in qualitative research and what process is used to achieve the same. You can refer it to grasp the whole concept.
http://www.thesishelpcenter.com/blog/establishing-the-validity-of-qualitative-research/
Okay so APA for everything in a thesis or dissertation is achievable, but SPSS? That is a road block for me. I have so many tables in my document and not one is appropriate. What’s more, I am unable to format it accurately as it is. I heard that you can automatically get SPSS tables […]
Continue reading APA format for SPSS tables
I was stuck at the same point. To format SPSS result tables is a one BIG task and tedious, to say the least. If you have a lot of tables then you can just automatically do it, without wasting any time. I am attaching a post which wonderfully explains all the steps for that. You can just follow the steps, it’s actually simple.
In my research, I did not generate automatic APA formatted SPSS table, but formatted the tables later. It wasn’t much time consuming, when you get the hang of it. I formatted the tables by referring to this post:
Hey I need to know which test would be best for my case. I have 50 respondents forming 2 groups of managers and employees. I need to compare them and find the association between them. What test would be the best? Chi-square, T-Test or ANOVA?
I know that chi-square test is used to find the relationship between categorical variables. So I think you can use that and t-test for the comparison.
There is this site on statistics which I am simply in love with, phdstatistics.com. Read its blog for information about such statistical problems.
http://www.phdstatistics.com/blog/
Also, take a look of this resource, its’ on inferential statistics and explains parametric and non-parametric tests.
http://www.resourcesvalley.com/learn-inferential-statistics/
I think ANOVA is the best option. I too need to make a comparison in my study, and my supervisor told me to us ANOVA. I didn’t read much about it, but I guess you can, to be sure. Also, tests are usually decided on the basis of hypothesis, so you need to refer them before settling on the tests.
Chi-square- a statistical method assessing the goodness of fit between a set of observed values and those expected theoretically.
T-Test- A T-test is a statistical examination of two population means. A two-sample t-test examines whether two samples are different and is commonly used when the variances of two normal distributions are unknown and when an experiment uses a small sample size.
ANOVA- Analysis of Variance (ANOVA) is a statistical method used to test differences between two or more means. It may seem odd that the technique is called “Analysis of Variance” rather than “Analysis of Means.” I hope with the above mentioned details you would be able to extract further clarity and use the same for your research.
I’ll suggest you to use T-test as your research methodology. Which will help you to compare whether two groups have different average value or not as you have 50 respondents forming 2 groups of managers and employees. You can try T-test to arrive at favourable results and avoid ANOVA because it is usually used to compare three or more variables and you have just two variables to compare.
I think ANOVA will do as it is one of the best approaches to test hypotheses when two populations are involved. It will tell you the variations between the two samples.
For determining the tests, you need to first identify the type of variable. Is it categorical, quantitative or nominal? On that basis you can use tests like Wilcoxon, paired t test, one sample t test and chi square test. I know that settling for a test is quite a work, so I would suggest you consult with your teachers on what would be the best option.
ANOVA test and chi square test, this is what I am settling for, on the basis of the variables. Thank you all for helping me out. I really do appreciate it!
Hi all. Hope you guys out there are doing great. 🙂 I need to prepare a mixed questionnaire (quantitative and qualitative) to assess the factors and measures for attracting FDI in a country. As this is my data collection method, my analysis and results are completely relying on it. I am simply looking for guidance […]
Continue reading Developing questionnaire
I developed my questionnaire from my conceptual framework; I think that’s how you can do it. I had four independent and one dependent variable. It was really not that difficult. If you don’t understand, how about you check on with the related studies?
You can definitely find developed-questionnaires online pertaining to your topic. On typing a query on how to develop a questionnaire in Google, you will get ample amount of information. You can find the basics of questionnaire on wiki how article:
http://www.wikihow.com/Develop-a-Questionnaire-for-Research
Also, this PDF is quite elaborative on how to get on with a questionnaire:
I came across this blog on how to design a questionnaire, found it useful and maybe you’ll too!
http://www.fivevidya.com/blog/how-to-proceed-while-designing-a-questionnaire/
Hey all, thank you so much for your replies. I have started making my questionnaires on the basis of my variables. The resources were useful. But I still have doubts. How long should I make it? I know that there shouldn’t be any redundancy, but my topic is vast and to cover it all, I need to gather more information.
There is no straight answer to that. I developed my questionnaire on the basis of my variables (5 independent and 1 dependent). I formulated 8 to 10 questions each for all the variables, which was a lot I guess, as now I am finding it quite difficult to analyse the data. So, what I mean to say that the exact length can’t be told but it should be as precise as it can be while keeping a check on the relevancy.
Pilot testing. That’s the way to ensure that your questionnaire is appropriate. Take only few people from your sample and distribute your developed questionnaire among them. Check for their responses and if it’s giving you the relevant information, then it’s correct. If it’s not, then you gotta make revisions.
Deciding on the length of questionnaire is a fundamental question; the number of questions that are sufficient in a questionnaire method to good Ph.D. Research work depends on the study, the field, and the budget of the study. It should also be compared to similar studies in the field and trying to surpass previous and existing studies. So, you can check out the thesis or papers pertaining to your filed and refer their questionnaires.
As your questionnaire will be developed on the basis of social marketing research, you can check out the following article http://www.social-marketing.com/research.html . This article will give you an insight on how to develop a questionnaire which will articulate both qualitative and quantitative questions which will help you to develop an in depth questionnaire.
Who knew that developing a questionnaire can be so tedious. I made a tentative questionnaire that seems to be ‘less’ (as per my professor). I have developed 4 questions each for each variable, which are 6. So that makes 24 questions apart from the questions related to demographics. Won’t the addition of more questions backfire on me?
Length of the questionnaire may be okay but its analysis will be too much. You can go with it though, if you have enough time.
How much time can your respondents give to you? That is the question you should ask before determining the length of your questionnaire. Analysis can be tedious, true, but it can be done with careful evaluation. The length however, should be appropriate as per the respondents.
Okay, thanks for the advice, I think that nobody really has that much time to give to a questionnaire. Moreover they can get bored and not answer the questions seriously. What I am thinking is to conduct pilot testing of the questionnaire that I have already built and then I’ll make the necessary changes.
Hi I need some advice regarding what type of analysis I should do, maybe mixed method, using thematic analysis with quantitative analysis. I am a bit lost as it is quite confusing. In my study I have to investigate the marketing strategies adopted by the international fast food entrants in India and what difficulties they […]
Continue reading Feeling confused with mixed methods and survey analysis
Have you thought about other strategies like case studies and observations? If you are thinking about interviews and generating themes, are you allowed to video or record participants and generate transcripts? And what are you aiming at, I mean what all do you want to investigate in the marketing strategies? Have you identified your research questions?
@Danielle: You almost scared me with so many questions. No, I haven’t thought about case studies and observation method, I strongly believe that interviews and survey are the best options. I am planning to generate transcripts and conduct interviews with the managers of McDonalds, Dominos and KFC. I want to investigate the most popular and effective marketing strategy that they use (the reason behind their popularity). Also I want to find their shortcomings and how they can improve. My research questions are:
For what reasons do Indian consumers prefer foreign fast foods entrants over Indian restaurants?
What are the marketing strategies adopted by foreign fast food entrants?
How do the marketing strategies adopted by foreign fast food entrants differ from the marketing strategies adopted by the Indian marketers?
What are the challenges encountered by the international fast food companies learn about Indian belief and different cultural values?
Hey, sorry for scaring you. Questionnaires are best useful when you have to collect large amount of information. The data collected from then is easily quantified and analyzed more scientifically. However, they are not that could for validity and reliability as you don’t know what the respondents have interpreted from your questions and if they are honest about their answers or not. On the other hand, interviews are useful for in-depth research. You can get more detailed information about your respondent’s perceptions and then you can generate themes from them. Both the methods will be good for your research but time-consuming. The data will be large so its analysis will also require more time and efforts. Also, you have to decide on the type of interviews and questionnaires.
Thanks for that. I am settling for conducting structured interviews with the employees and quantitative questionnaire with the customers. I can then generate themes from the interview transcripts and do descriptive statistics on the data collected from the questionnaires. At least that is what I am planning. My next doubt is what sample should I choose?
What is your population? Determine that first. Then using a sample size formula, calculate your sample on the basis of population and confidence interval. There a lot of calculators available online, you can refer them or look for a formula.
How to you settle for the population? I mean, there are so many people who visit the restaurant, how am I supposed to calculate that? Also, how to estimate the confidence interval?
Population is simply the people who you need to survey or target. For example, you want to find out the perception of people regarding the safety in airliners. For that, your population would be those who travel in airplanes. You can get the statistics from the report of airline industry in a particular region. Say the population is 1000 people who travel via planes. Now as far as confidence interval is concerned, I don’t know what that is, but I took it as 95% as that’s the general way. So, I can’t help in that respect. However, once you understand your confidence interval, you can use this formula for calculating the sample size:
n=(Z^2*p*q)/e^2
Where, n is the sample size, Z is the value for confidence level (1.96 for 95% confidence interval), p is percentage for picking a choice (usually 0.5), q is p-1, e is the desired level of precision (I took it as 0.4).
Begun by Sheila Mclaren and Lavonne Sisk, researchdiscussions.com is an assistance and interaction website. This website helps United States doctoral students in writing their thesis reports. Writing them is a daunting task and takes a toll on most of the students. Only few students are able to complete these reports accurately on their own. The […]
Continue reading www.researchdiscussions.com and Its Importance for Doctoral Students
Doctorate is just something where more and more of assistance is also less.
Right Roger. While someone is pursuing a research he really needs to go deeper and deeper and collect as much info he could
Collecting more information is always good it helps in the process of dissertation writing.
This is a very helpful and insightful portal.
yes it always helps in clearing doubts and making our thesis much better and professional manner
Henry Lush 3:43 am on December 12, 2016 Permalink | Log in to Reply
It’s a three tier process; in open coding, tentative labeling of chunks of data that summarize what you see is needed. Axial coding is done to identify relationships among the open codes. And in selective coding, figure out the core variable that includes all of the data. Then reread the transcripts and selectively code any data that relates to the core variable you identified.
abbiehrv20215 10:48 am on December 14, 2016 Permalink | Log in to Reply
Okay so they are inter-related?
Henry Lush 2:46 am on December 15, 2016 Permalink | Log in to Reply
One can say that. These are more stages/phases involved in qualitative research.
Henry Lush 1:56 am on December 16, 2016 Permalink | Log in to Reply
Also, while preparing an axial coding, we must put subsidiaries categories around a main category like conditions, strategies, context, and consequences.
Robert Taylor 10:54 am on December 16, 2016 Permalink | Log in to Reply
Got it. Thanks for reverting back.