In my research, I collected not only a group discussion but also the data. I have conducted a quantitative survey on this. This serves the fast collection of data, which I was able to evaluate in the roundtables together with the participants. In this article, I’ll give you some tips. The following sections are taken from my doctorate and quoted.

Benefits and pilot test

The advantage is that a high mass can be achieved quickly. The links to the questionnaire can be distributed specifically to already known participants and recommendations in their networks. In contrast to direct methods such as telephone interviews, the layout and design of the questionnaire is very important, since the researcher cannot support explanations (Porst 2014). Among other things, a question can be misinterpreted. For this reason, my questionnaires were always tested with 5 pilot persons, who then sent direct feedback to the research team.

Defining a target group

Each survey has a specific audience that you should define. On the one hand, you should narrow down the occupational group and, on the other hand, justify in the thesis why you are questioning it. It also shows whether you should ask online or offline. For example, I wanted to interview disciplinary leaders because I wanted to investigate leadership behavior in virtual teams. This was perfectly possible online. In another study on the digital workplace, my target group was micro-enterprises. These were usually difficult to reach via mail or internet, which is why we asked offline. So, before the survey, define and justify exactly the target group.

Tip: Don’t forget to limit your methodology cleanly.

Formulation of questions

The exact content of the questions depends, of course, on your research question. However, you should design the type of question exactly. You derive one variable (measurement) per question. This can be e.g. respondents’ turnover, team size, preferred agile method, company type or much more. Importantly, each question generates a variable. You can then create confirmed hypotheses from the variables. If you already have hypotheses in the run-up to your work, the questions should of course be adapted to the hypotheses.

If not, you can derive theses from your survey, e.g. From a team size of 12 persons, the managers surveyed prefer Kanban or managers from SMEs prefer Kanban and corporations prefer scrum. The formulation depends on the selected evaluation methods. I’ll tell you something about that below. In a thesis, 5-10 questions are usually enough.

Reading tip: Putting up theses

Excursion: Online vs. Offline

There are two possible types of the survey: Online and Offline. You can print the survey and run it offline. This has the advantage that you reach participants that you otherwise can’t reach and track the distribution very closely. For example, a questionnaire can be distributed specifically to managers or project managers. For example, in a study I wanted to interview the exact same companies that were interviewed by my co-author back in 2016. Thus, we have distributed the printed questionnaires specifically to them. No one else should take part in the survey. Limitation: Of course, you can also protect the survey online with access codes, but this is never 100% secure.

In the online survey, you can reach a high mass very quickly, but can hardly control how the link to the survey is distributed. This allows participants to pass it on. You should therefore formulate an initial question. In my survey of executives, for example, I asked the initial question of the number of employees of the respondent. When asked: no guidance, the questionnaire immediately abated. This is how you avoid incorrect answers. Someone who doesn’t lead can hardly say what leaders think. Similarly, only project leaders should respond to a survey of project leaders.

Structure and process

My online questionnaires are divided into small thematically separate blocks and care is taken to ensure that in addition to common answer types such as dropmenus, lists, checkboxes, radio buttons, etc., there are not too many questions on one page, because with too many questions the concentration of the research participants can decrease (Kuckartz et al. 2009) or an information flood can occur with too many different topic blocks among the participants. The questionnaire was therefore designed to last 15 minutes, which also proved to be an acceptable time in the pilot tests.

The interviews are always set by me at 4 weeks and a minimum of 60 valid answers. The data is then exported from the questionnaire software and first evaluated for validity in a tool. After sorting out low-completed questionnaires, SPSS evaluates them so that the data could be visualized.

Reading tip: Book by Kuckhartz

How many people should I ask?

This is a good question and it is generally true that the more you question, the more meaningful the results are. My tip is that you look at the results and calculate: How significantly the results have changed since the last 5 participants surveyed. If there is no change, it can be assumed that the results are stable.

Add the following sentence to your work: 25 participants were interviewed. According to Wilde and Hess (2006), the saturation criterion of a research method is reached when no significant new findings have been obtained after a certain amount of participants after an iteration. After measuring the last 5 participants, no significant new change in the survey could be achieved.

In short, if I ask more, the result will hardly change, e.g. 80% prefer agile over classical methods in IT. Even if you interview 40 more participants, it should change under normal circumstances.

Overall, however, I can say as a guideline that in my bachelor’s theses often 15-30 people were interviewed.

quantitative survey – evaluation

After completion of the simple evaluation, the data is exported from the questionnaire software. I have always examined the difference between SMEs and corporations. For example, I wanted to find out whether specific findings arise for leadership in SMEs. The SPSS analysis tool separates the data into the data of SMEs and non-SMEs and examines the responses per group for a significant difference. In the test, for statistical deviations, the predetermined standard significance level of α=5 % is used (Kuckartz et al. 2013). It is deduced whether a survey variable applies uniformly to the totality of all enterprises or whether there is a specific deviation for SMEs.

Reading tip: Book for evaluation

Four ways to evaluate

Among many other possibilities, there are four known ways to evaluate large amounts of data. Of course, there are also many methods such as differential analysis, con-joint analysis, neural networks and discriminant analysis. However, I only describe these four procedures, as I see them most often in thesis at my university.

Method Declaration Example
Significance analysis Deviation of responses How to invest in SMEs and compared to corporations?
Regression analysis Determine the relationship of variables How much does the marketing budget influence the sales figures of a B2B SME?
Correlation analysis Determining deviation of variables What is the current relationship between employee satisfaction and home office?
Cluster analysis Derive groupings from the answers Which generations prefer to start startups?

Significance analysis

As explained earlier, it is thus described how a hypothesis deviates from the null hypothesis. As in my example: SMEs and NON_KMU. This is worth it as soon as you ask 2 or more groups. There are differences between SMEs and NON_KMU e.g. in the number of home office days, etc. This makes sense as soon as you want to compare something or highlight differences or how I specifically examine SMEs.

Regression analysis

Here you try to map the dependency to another from one independent variable. For example, a CEO wants to know how much money they need to invest in advertising in order for something to change in the company, such as sales figures or new customers. They form so-called scatter plots and see if there is a connection between the selected variable and the others. In contrast to the next method, the cause-effect is examined here. This allows you to forecast what is worthwhile when you are looking at research questions if you want to make predictions.

Correlation anaylsis

Here you can see the connection between 2 variables. So whether they are related. For example, you can tell if employee satisfaction and days in the Home Office can be related. Does it rise or decrease with increased Home Office days? This makes sense if research investigates an impact on something. In contrast to regression, no cause effect is determined here, but only determined how similar are 2 variables. So here you are more likely to examine the context in the here and now.

Cluster analysis

Cluster analysis can be used to determine similarities in large groups and to summarize them. A great example is the customer group analyses. This is how a marketing manager looks at which customer groups are shopping in his online shop. In a thesis, similar answers are therefore grouped together. The result is groupings such as who founds startups. It is possible to group the data into groups using cluster analysis.

Conclusion: Tips on the quantitative survey method

The method was very suitable for my research and focuses on data collection. I used the method offline as well as online. The preparation and evaluation takes a long time, which is why every survey has to be properly prepared and planned. It is also important to interview at least 50 people, as the significance tests from 30 persons in particular only make sense, i.e. a total of 60 participants. My tips should give an initial orientation to the methodology. In any case, take a look at my other book tips!

Gibt es noch Fragen?

Falls es noch Fragen gibt, habe ich zwei Tipps. Ich habe meine Erfahrung aus 5 Jahren in der Betreuung von Abschlussarbeiten im Buch: "Empfehlungen für die Bachelor- und Masterarbeit" zusammengefasst. Dieses gibt es bei Springer und Amazon seit August 2020. Das Buch ist ein offzielles Fachbuch in kann damit zitiert werden. Weiterhin können Sie mich gerne mal anrufen. Hierzu einfach im Buchungssystem nach einen freien Termin schauen. Ich nehme mir jeden Monat einige Stunden Zeit um Studenten zu helfen.

Mein Tipp vor der Abgabe Ihrer Abschlussarbeit

Es lohnt sich immer eine Abschlussarbeit professionell Korrekturlesen oder auf Plagiat prüfen zu lassen. Der Vorteil ist, dass Sie dabei auch Feedback erhalten und den akademischen Sprachstil verbessern. Anbieter wie bspw. Scribbr helfen mit guten Preisen bei der Abschlussarbeit.

Genderhinweis: Ich habe zur leichteren Lesbarkeit die männliche Form verwendet. Sofern keine explizite Unterscheidung getroffen wird, sind daher stets sowohl Frauen, Diverse als auch Männer sowie Menschen jeder Herkunft und Nation gemeint. Lesen Sie mehr dazu.

Verwendete Quellen anzeigen

Kuckartz, U., Rädiker, S., Ebert, T., & Schehl, J. (2013): Statistics: An Understandable Introduction, Wiesbaden: VS Verlag für Sozialwissenschaften.

Kuckartz, U., Ebert, T., Rädiker, S. and Stefer, C. (2009): Evaluation online: Internet-based survey in practice, 1st edition, Wiesbaden: VS Verlag für Sozialwissenschaften.

Porst, R. (2014): Questionnaire – A workbook, 1st edition, Wiesbaden: VS Verlag für Sozialwissenschaften.

Designed by Freepik

Avatar
Author

I blog about the impact of digitalization on our working environment. For this purpose, I present content from science in a practical way and show helpful tips from my everyday work. I am a manager in an SME myself and I wrote my doctoral thesis at the University of Erlangen-Nuremberg at the chair of IT Management.

Durch die weitere Nutzung der Seite stimmen Sie der Verwendung von Cookies zu. Weitere Informationen

Die Cookie-Einstellungen auf dieser Website sind auf "Cookies zulassen" eingestellt, um das beste Surferlebnis zu ermöglichen. Wenn du diese Website ohne Änderung der Cookie-Einstellungen verwendest oder auf "Akzeptieren" klickst, erklärst du sich damit einverstanden.

Schließen