Quantitative Dissertation Mistakes That Cost You Months

Today, I'd like to talk about quantitative research challenges. And I'm going to preface this, we're going to talk about a number of them, but almost all of them can go away if we think about things from the beginning. We think about our data, if we think about our analysis, if we think about how we're going to write things. If we think about that at the beginning of the process, then the middle of the process and the end of the process gets much easier and we end up with a lot fewer questions or dilemmas or even problems. One of the issues we hear about is, hey, I can't get data. Is there usable data? Well, again, let's think about it from the beginning. There's a lot of really interesting questions, gaps in literature, but there may not be data for it. So that's something you want to think about when you're moving forward with something. And quite frankly, it's something your committee should be asking you. This is a great question, but can you get data? Is it doable? Is a big criteria we use. Along with can you get data is the idea that, yeah, there's data, but it doesn't align with my research questions. I got data. It doesn't align with my research questions. Well, again, if we thought about it at the beginning, here are the research questions. Here's the type of data that's available. That's not going to answer my research questions. So maybe you change your topic. Maybe if possible, your research questions change. But again, thinking about the process ahead of time, and I know I sound like a broken record here, but you don't want to end up going out gathering data and then find out, wow, it doesn't answer my research questions. What do I do? Well, then you go gather data again or change everything around. There aren't really any good answers at this point, or let me rephrase that. There's some good answers, there just aren't fast answers. Because when you get to this point, typically you want a fast answer. Along that data gathering is challenges collecting data. Well, if you're going to be doing, for example, a survey of, of people, there are services that will provide data for you. SurveyMonkey and Qualtrics come to mind. In my experience, SurveyMonkey is less expensive and requires more work on your part. Also, SurveyMonkey tends to give you a lot of responses, and some of them may not actually apply to what you're doing. That's my experience of working with clients on this. Qualtrics is more expensive, less work on your part, and they tend to give you exactly what you need with the qualifier if they have what you need or access to what you need. They don't have access to every type of respondent. So you want to talk to them because look, if you're dealing with SurveyMonkey or Qualtrics and they say, yeah, you know, you can get it for this many dollars, you can get this number of responses and we'll have it for you in a week. It may be worth the money as opposed to you sending out surveys and sending them out again and sending them out again and sending them out again through different groups and different populations. I've seen too many people say, oh yeah, there's 2,000 people here. I'll be able to get 120. And then they get 9 and they do it again and get 14 more. And it takes a long time. So the investment may be worth it time-wise. So just think about that as an option. Otherwise you're trying to get access to people through organizations because then you get, you're somewhat endorsed by them because it went through their organization or your LinkedIn lists or your Facebook groups or wherever you can get large numbers of people who can, you know, potentially be part of your study. There are also questions that come about in quantitative research about statistics. I don't know about the statistic I'm using, or I don't know about the analysis I'm doing. I don't know if it's the right test. This you can determine pretty early because I got this research question and here's the data I'm going to get. Is it going to be Likert data? Is it going to be continuous data? Is it, you know, what type of data is it? And then you can use services like LAIRD, L-A-I-R-D, who basically say, oh, if you're using this type of data, here's the test to use and here's why, and here's support for using that test. So that can one, help you understand that you have the right test or help you find the right test. And give support for that test for your committee. Now, here's one thing I find with people both in qualitative and quantitative research. They're going to use a package, and let's just stick with quantitative. They're going to use SPSS, let's say. And SPSS is a program that helps you do the statistics, but it's not just magic. You say, hand it to SPSS and say, here, do this for me. There are steps you have And if you have not done it, or if you're not familiar with it, and you've got all your data collected, you got 700 respondents or whatever, and now you're trying to put it into SPSS and you're having problems figuring out SPSS, it can be frustrating at that point because there's pressure. I got all this data. Well, frequently I will tell people to make up data, and that's not for their study. It's when you're waiting to collect data or you have downtime at some point. Make up a set of data, make it 3 or 4 responses, and then enter it into SPSS and start playing with it. And it's a lot easier to play with something like software when the results don't mean anything. You can have all kinds of mistakes, and it's not going to be that frustrating because it's just made-up data. But this way, you understand what steps need to be done before you actually have to do it. And and can make your life a lot easier and your dissertation move forward a lot faster. Some people worry about, okay, I've got my data, how do I clean it? Which means get rid of outliers, things like that. Well, if you've chosen your test ahead of time and you've used something like Laird, you have a method of doing this, of understanding these things ahead of time. It is also, at most schools, okay to get assistance to do things like this. Now, here's the disclaimer: it's assistance. Some people even have statisticians do their statistics for them. That's okay, as long as you understand what they've done and are able to answer questions from your committee. Because if your committee member says, "Hey, Steve, why did you do this?" I can't say, "You know, I don't know. That was, you know, Dr. Jones that I hired." It's your work. You have to understand it so you can answer questions. So if you have hired Dr. Jones, to do this for you, part of the package better be Dr. Jones explains it to you so that you understand it and can answer questions as to what you did, why you did it, and why you didn't do other things. Because that's what committees are looking for—your well-roundedness as a researcher. Final question that comes up from time to time is, how do I report this stuff? You know, how do I say what I found? Well, You do all of your tests, you've got tables and charts and all kinds of things. Now we look back to Chapter 3. What did I say I was going to do? Oh, I was going to do this. Therefore, I report what I found in each way along the path, each area I looked at. I found this was significant, this wasn't significant, and just report it. It's in Chapter 5 where you get to talk more about what it means and how it all interrelates. But again, I'm going to go back to a lot of issues can be avoided if we think about them ahead of time. If we're ready to say, I'm doing this type of research, what type of data am I going to get? What am I going to do with it once I get it? If we just decide we want to do research and then we react to everything from there, it can be done. It may be a lot more difficult and might take a lot more time. But if I'm in your shoes, I want it to be easier and faster. So I recommend thinking of things ahead of time and asking questions of your committee and others. Hey, what issues might I face with this? What should I be prepared for? Because you might not know what questions to ask, so ask others. And as always, we're out here if you need help. And I look forward to hearing from you. And please finish your dissertation. Thanks a lot.