Former Exam Q
How do we ensure research quality in qualitative research?
Research quality in qualitative research is ensured through systematic and transparent analytical procedures, grounding claims in clear and demonstrable empirical patterns, considering contradictory evidence, and acknowledging the researcher’s active role in interpretation. These practices support credibility, transferability, dependability, and confirmability, which together establish the trustworthiness of qualitative findings.
What are the validity criteria in quantitative research?
Validity criteria in quantitative research include internal validity, which concerns whether causal conclusions are justified; external and ecological validity, which address the generalizability of findings to other contexts and real-world settings; construct validity, which assesses whether variables accurately measure theoretical concepts; and content validity, which evaluates whether a measure fully captures the domain of the construct.
What is the purpose of Confirmatory Factor Analysis (CFA)?
The purpose of Confirmatory Factor Analysis is to test whether empirical data fit a hypothesized measurement model derived from theory. CFA allows researchers to assess whether observed indicators load onto latent constructs as expected, thereby evaluating the validity of measurement instruments.
What is the difference between qualitative methods & quantitative methods?
The difference between quantitative and qualitative methods lies in what they aim to understand, how data are generated, and how knowledge is produced.
Quantitative methods are primarily used to measure, compare, and test relationships between variables. They rely on structured data, numerical measurement, and statistical analysis, and they are typically grounded in a deductive logic, where theory is tested against empirical data. In quantitative research, concepts are operationalized into variables, hypotheses are specified in advance, and methods such as experiments, surveys, or archival data are used to identify patterns, differences, or causal effects. The strength of quantitative methods lies in their ability to support generalization, precision, and causal inference, but they often abstract away from context and meaning.
Qualitative methods, in contrast, are used to understand meanings, processes, and interpretations in context. They rely on rich, non-numerical data such as interviews, observations, and documents, and they often follow an inductive or abductive logic, where theory is developed or refined through engagement with empirical material. Rather than testing predefined hypotheses, qualitative research explores how people make sense of situations, how practices unfold, and why certain behaviors occur. Qualitative methods offer depth, nuance, and contextual understanding, but they do not aim for statistical generalization.
In short, quantitative methods answer questions such as “what is the effect?” or “how much?”, while qualitative methods address “how?” and “why?”. In your project, combining the two allowed you to test patterns in accountability perceptions while also understanding how students reason about responsibility when AI is involved.
What is the purpose of experiments compared to, for instance, observation studies?
The purpose of experiments is to establish causal relationships by actively manipulating the independent variable and observing its effect on the dependent variable. Unlike observational studies, which can only identify associations, experiments allow researchers to infer whether changes in the independent variable actually cause changes in the outcome, because alternative explanations can be controlled more effectively.
What is the basic process of clustering?
The basic process of clustering involves first measuring similarity or distance between observations based on selected variables, then grouping similar observations into clusters, and finally evaluating the quality of the clustering solution to assess whether the clusters are meaningful, distinct, and interpretable in relation to the research purpose.
What is the main difference between EFA and CFA?
The main difference between Exploratory Factor Analysis and Confirmatory Factor Analysis lies in their purpose. EFA is used to explore the underlying factor structure when relationships between variables are unknown, whereas CFA is used to confirm a predefined factor structure based on theoretical expectations.
What is a confounding variable?
A confounding variable is a variable that influences both the independent and the dependent variable, creating a statistical relationship that does not reflect a true causal effect. Confounders are problematic because they can produce correlations that appear meaningful but are actually driven by an unobserved third factor.
How does K-means clustering work intuitively?
K-means clustering works intuitively by assigning each observation to the nearest cluster center, recalculating the centers based on the assigned observations, and repeating this process iteratively until the cluster assignments no longer change. The algorithm aims to minimize within-cluster variation while maximizing differences between clusters.
What are the key model fit (GOF) indices in CFA?
Key goodness-of-fit indices in CFA include the Comparative Fit Index (CFI) and Tucker–Lewis Index (TLI), which assess relative model fit, as well as the Root Mean Square Error of Approximation (RMSEA) and the Standardized Root Mean Square Residual (SRMR), which evaluate absolute model fit.
How does an experiment remove the influence of confounding variables?
Experiments remove the influence of confounding variables primarily through random assignment of participants to different levels of the independent variable. Randomization ensures that confounding variables are distributed evenly across conditions, preventing them from systematically influencing the independent variable and thereby strengthening causal inference.
What questions can t-tests answer, and what are the main types of t-tests?
t-tests are used to compare mean values between groups in order to assess whether observed differences are statistically significant. The main types are independent-samples t-tests, which compare two separate groups; paired-samples t-tests, which compare the same group measured twice; and one-sample t-tests, which compare a sample mean to a known or hypothesized value.
What is convergent validity in CFA?
Convergent validity in CFA refers to the extent to which indicators of the same construct are strongly related to one another. It is typically assessed through high factor loadings and an Average Variance Extracted (AVE) value of at least 0.50, indicating that the construct explains more than half of the variance in its indicators.
What is a full factorial experimental design?
A full factorial experimental design is an experiment that includes two or more independent variables, called factors, and tests all possible combinations of their levels. This design allows researchers to examine not only the main effects of each factor but also interaction effects between factors.
What is the purpose of ANOVA, and can you outline at least two types of ANOVA?
The purpose of ANOVA is to test whether there are statistically significant mean differences across three or more groups. Common types include one-way ANOVA, which examines the effect of a single factor, two-way ANOVA, which examines the effects of two factors and their interaction, and repeated-measures ANOVA, which is used when the same participants are measured under multiple conditions.
What is discriminant validity in CFA?
Discriminant validity in CFA refers to the extent to which constructs are empirically distinct from one another. It is commonly demonstrated when a construct’s AVE exceeds the squared correlations between that construct and other constructs, indicating that it shares more variance with its own indicators than with other constructs.