Knowledge base

Writing the methodology for your research can be difficult because each element must follow from the previous one. Learn how to organise the aim, research questions, hypotheses, variables, indicators, method, technique and research instrument in a bachelor’s or master’s thesis. Have you already collected responses? See step-by-step survey result analysis, including how to calculate percentages and a sample description. It is worth preparing the analysis plan in advance so that each research question has its place in the write-up. If your quantitative study will compare groups or test associations, also plan how you will assess the hypotheses. As part of test selection and statistical analysis I will help link the research questions to the variable types and calculations needed. Qualitative research or a theoretical thesis will require a different approach to analysis. When investigating associations, specify which characteristic you want to explain and which one you will examine alongside it. The dependent variable is the characteristic whose variation you are analysing. The independent variable is the characteristic assumed as the explanatory factor or the basis for comparison (Apanowicz, 2005). For example, when studying the relationship between social media use and peer relationships, you might treat time spent using social media as the independent variable and the reported frequency of meetings with peers as the dependent variable. Specify how you will measure both. An association in questionnaire data alone does not show that one characteristic causes a change in the other. Once the research design is established and you need only the instrument itself, see . Questionnaire items and response options should follow from the research questions and analysis plan, rather than take the place of developing them. Example of linking a research question, questionnaire item and analysis This illustrates one link between the question and the planned analysis, not a validated scale of peer relationships. Before collecting data, check that the item is understandable and fits the aim. After collecting responses, describe the instrument actually used; do not rewrite the description as though a revised version had been used in the study. The same considerations are needed for an independent…

Do you have survey or interview results and do not know how to prepare the research chapter? Find out how to organise the data, calculate percentages, choose charts and write comments on the results. See concrete examples, principles for analysing open-ended responses and a checklist before sending the thesis to your supervisor. The workbook contains 30 fictional responses: 18 'Yes’, 7 'No’ and 5 'Hard to say’. Change the responses in the Data tab, then check the recalculated counts, percentages and chart in the Results tab. Missing data are shown separately. Percentages refer to valid responses to this question. After changing the data, adjust the comment on the results as well. You can find a sample description below. The following steps use the same fictitious frequencies as the previous example: 18 “yes” responses, 7 “no”, and 5 “hard to say”. Perform your own calculations on a copy of the data. The cell layout is an example to be reproduced independently, not a description of all form exports. Place data for one person in one row and the answer to one question in one column. Assume that responses to the question about difficulties with the bibliography are in cells B2:B31. Standardise the notation of the same answer, e.g. remove unnecessary spaces, while preserving the original export. Add a separate note about changes and the meaning of codes. A category number, e.g. 1 for “yes”, is a label, not a measure of the difficulty level. In C2, C3 and C4, enter the Polish example categories in order: tak (yes), nie (no), trudno powiedzieć (hard to say). In D2, enter =LICZ.JEŻELI($B$2:$B$31;C2) and copy the formula to D4. You will get 18, 7, and 5. This is the syntax for the Polish version of Excel; in the English version, the function is called COUNTIF, and the argument separator depends on settings. Check that every non-empty response belongs to one of these categories. Unknown entries must be explained rather than omitted without comment. For this question, the number of valid responses is the sum of the counts in three mutually exclusive categories. In D5, enter…

A research questionnaire should not be a collection of random questions. A good research instrument must follow from the thesis aim, research questions, hypotheses and variables. Learn how to prepare a questionnaire step by step so that it is easier to report the results in your research chapter later. For each question, note provisionally how you will present the answers. For single-choice questions, this may be the number of people and the percentage; for multiple-choice questions, the number of selections for each option; and for open questions, thematic categories along with a description of how they were created. Practise this on a small set of fictitious answers, clearly marked as a test. If a question about difficulties allows selecting several options, the sum of percentages of people may exceed 100%. If a question applies only to participants of consultations, percentages must be calculated for that group, not for everyone who fills in the questionnaire. Also record how missing data will be handled. No answer to the question “How many times did you use consultations?” does not mean zero consultations. Meanwhile, “I do not remember” is a provided answer with a different meaning than an empty field. If you plan to compare groups, ensure that you have a variable allowing you to identify them. If you want to calculate a composite score from several items, establish the justification for such a combination and the scoring rules in advance. Do not sum random questions just because each has answers marked with numbers from 1 to 5. We described the next stage in the guide on processing research results, percentages and comments on the questionnaire. It is worth looking at it before the study to check whether the designed questions will provide the data needed in the empirical chapter. Are you planning group comparisons or tests of associations and unsure what data you will need? Before distributing the questionnaire, you can discuss with me selecting statistical analyses for research questions. I will help determine whether the answers will allow the planned calculations to be performed, before you collect material that cannot be used…