it to ac work it 4

Importance of Skills: Finding scientific sources and managing them are essential skills acquired during university studies, enabling the navigation of vast digital academic landscapes.
Support Provided: Students at Indiana University (IU) are supported by the Library and Information Services (LIS) team through workshops and individual consultations.
Evaluation of Sources:
- Sources must be carefully evaluated to determine their appropriateness for citation in academic work.
- Systematic management of sources, utilizing suitable software (e.g., Zotero, Mendeley, or Citavi), aids in creating references and bibliographies in correct formats (APA, MLA, etc.).
Effective Reading Techniques: Includes strategies like SQ3R (Survey, Question, Read, Recite, Review) to quickly extract important information.
Citation Guidelines: Citing scientific sources must adhere to IU’s General Citation Guidelines to avoid plagiarism, which is the act of presenting someone else's work as your own.
Literature Discussion: Discussing literature on a topic helps form the foundation for independent arguments by highlighting gaps in current research.

Completion Outcomes: Upon completion, students will be able to:
- Discuss differences between fundamental research designs such as cross-sectional, longitudinal, and experimental studies.
- Identify key properties of basic scientific formats like monographs vs. journal articles.
- Discuss advantages (generalizability) and disadvantages (lack of depth) of quantitative research, and vice versa for qualitative designs.
- Name specific methods for data collection (e.g., Likert scales, semi-structured interviews).

Role of Research Design: It serves as a blueprint or logical structure of the inquiry, ensuring the evidence obtained enables the researcher to answer the initial questions as unambiguously as possible.
Key Considerations:
- Identify relevant academic formats in IT, such as technical reports or conference papers.
- Determine approach: Qualitative (exploratory) vs. Quantitative (confirmatory).
Quantitative Research: Focuses on numerical measurements to either:
- Deductively test established theories (Theory -> Hypothesis -> Observation -> Confirmation).
- Inductively test falsifiability (e.g., recording sensor data from $100$ nodes to find patterns).
Qualitative Research: Aims for a deep, holistic understanding of social phenomena. In IT, this includes UX research and Human-Computer Interaction (HCI).
Research Method Selection factors:
- Research Goal: Whether to Explain (causal), Understand (meaning), Predict (forecasting), or Criticize (emancipatory).
- Pragmatic constraints: Time limits ( $3$ - $6$ months for a thesis) and budget constraints for data acquisition.

Empirical Research:
- Collects original primary data to answer a specific research question.
- Systematic cycle: Problem definition -> Research design -> Data collection -> Data analysis -> Interpretation.
Literature and Review Work:
- A secondary research format providing a meta-level summary.
- Systematic Reviews: Follow a strict protocol to find all relevant studies on a topic.
Design Science Research (DSR):
- Predominant in Information Systems; focuses on solving problems via artifacts (e.g., algorithms, interfaces).
- The 7 Principles of DSR:
1. Artifact Design: Must be a construct, model, method, or instantiation.
2. Problem Relevance: Must solve an identified business or technical problem.
3. Design Evaluation: Requires rigorous utility, quality, and efficacy tests.
4. Research Contributions: Must provide clear contributions to the knowledge base.
5. Research Rigor: Requires rigorous methods in both construction and evaluation.
6. Design Optimization: Iterative search process to reach a solution.
7. Communication: Results must be presented to technology-oriented and management-oriented audiences.

Definition: A statistical measure (expressed by a coefficient between $-1$ and $1$ ) that describes the size and direction of a relationship between two variables.
Caution: Correlation ( $X$ and $Y$ move together) does not imply causation ( $X$ causes $Y$ ).

Large samples (n > 100) prioritized for statistical power.
Big Data: Involves the $3$ Vs: Volume, Velocity, and Variety, requiring specialized processing beyond standard databases.

Purpose: To overcome the intrinsic biases and problems of a single method.
Types:
- Data Triangulation: Using different data sources (e.g., at different times or from different people).
- Investigator Triangulation: Using multiple observers or interviewers to reduce subjective bias.
- Theory Triangulation: Using multiple theoretical schemes to interpret the results.
- Methodological Triangulation: Using multiple methods, such as a survey followed by an interview.

Data Saturation: The point in data collection when no new information or themes are observed in the data.
Quality Criteria:
- Credibility: Internal consistency.
- Transferability: Contextual applicability.
- Dependability: Traceability of the process.

Experiments: Manipulate an independent variable ( $X$ ) to see the effect on a dependent variable ( $Y$ ) while controlling for extraneous variables.
Quality Criteria:
- Objectivity: Result is independent of the researcher ( $r_{obj} \rightarrow 1$ ).
- Reliability: Consistency of the measurement instrument ( $r_{rel} \rightarrow 1$ ).
- Validity: The instrument measures what it is intended to measure ( $r_{val} \rightarrow 1$ ).

Coding: Labeling and organizing data to identify themes. Software like MAXQDA or NVivo automates the organization of codes.

Data Cleansing: Identifying and correcting (or removing) corrupt or inaccurate records (e.g., outliers or missing values).
Analysis levels:
- Univariate: Analysis of $1$ variable (e.g., mean, median).
- Bivariate: Analysis of the relationship between $2$ variables (e.g., Scatter plots).
- Multivariate: Analysis of $3$ or more variables simultaneously (e.g., Multiple Regression).