ecosystem.rmzuha.com

Category: Research Methodology

  • Writing Problem Statement

    Using Problem Framing as a guide, students can now construct Problem Statement & Justification in the Research Background section of the Research Proposal Template.

    1. Problem Statement & Justification

    The research problem is the foundation of your entire proposal. It clearly defines the issue or gap in knowledge that your study aims to address. Use your Problem Framing as reference to write a strong problem statement and justification:

    Paragraph 1 – Provide Context: Start by pinpointing a specific real-world issue, challenge, or question within your chosen field. 

    Paragraph 2 – Highlight the Gap:   Show where current understanding falls short or where there are conflicting viewpoints. Provide limitations of current methods with proofs.

    Paragraph 3 – The Justification: Demonstrate why this issue is important and why existing knowledge is insufficient. Justify the current approach, including why the application Machine Learning is needed.

    2. Research Questions

      Research questions are the cornerstone of your research project. They act as a roadmap, guiding your investigation and focusing your analysis. Here’s how to craft effective research questions for your proposal:

      a. Main Research Question

        Your main research question should stem directly from the problem statement you identified and derived from your problem framing. It should be specific and directly address the gaps in knowledge you highlighted.

        b. Sub-questions 

          Provide 2-3 smaller questions that help you answer the main question. Frame your questions in a concise and clear way. Avoid ambiguity and ensure they can be answered through your chosen research methods and data you plan to collect.

          Make sure your questions are measurable and feasible within the scope of your project.

          By following these guidelines, you can develop strong research questions that will guide your research and ensure a well-focused proposal. Remember, your research questions should spark curiosity, provide direction, and ultimately lead to valuable insights!

          3. Research Objective and Hypothesis

          a. Main Objective

            The main objective is the goal of your research project. It’s a broad statement that captures the general direction of your investigation and answerable to the Main Research Question.

            b. Specific Objectives

              Specific objectives break down the main objective into smaller, more manageable steps and answerable to Sub-questions. They outline the concrete actions you’ll take to achieve your overall goal. Specific objectives should be SMART (Specific, Measurable, Achievable, Relevant, and Time-bound).

              c. Hypothesis 

                A hypothesis is a specific prediction about the outcome of your research. It’s an educated guess based on existing knowledge or theories. Not all research projects require a hypothesis, particularly exploratory studies.

              1. Problem Framing

                Problem framing is a critical thinking process before starting an ML project (and any other research projects). Basically, researchers spend about 70-80% of entire research time to define and fine tune the direction of their researches. Imagine like preparing a blueprint of a building that requires information and modification until the foundation is solid. The design of the building can be expanded and customized based on new inputs later.

                But the main point of doing problem framing in ML is to decide whether you even need ML in your project.

                Follow the step-by-step guide for conducting problem framing.

                1. Context
                  Provide context from the real-world situation.
                  Explain what is actually happening and why this problem matter.
                2. Question
                  Convert context in a simple single answerable question.
                  e.g. Can fabric appearance estimate exposure time to local microclimate?

                ML Justification Check – Determine whether ML is necessary or if a simpler method can solve the problem.

                1. Define input-output mapping.
                  Specify what data goes in (input) and what the model should predict (output).
                  X(Features): Image of larval head capsules.
                  Y(Label): Larval age/instar
                2. Select ML task type
                  Determine the appropriate ML (classification, regression, clustering).
                3. Identify data representation
                  Decide how data is structured and encoded.
                  e.g. image of larval cephalopharyngeal skeleton labelled according to species.
                4. Define success metrics
                  Establish how model performance will be measured and its meaning in biology.

                  Classification > accuracy, F1
                  Regression > RMSE, MAE
                  Clustering > Silhouette

                  For undergraduate project proposal, indicate success criteria based on input and output e.g. The model successfully classify cephalopharyngeal skeleton according to species.
                5. Identify assumptions, limitations and biases
                  Explicitly state any underlying assumptions, limitations and biases in the study.
                  E.g. Sampling bias, unknown environmental data.
                6. Check feasibility
                  Assess if the project solvable within time and provided resources.
                7. Iterate
                  Based on 7 and 8, revisit 3, 4, 5 and 6.


                Practice Problem Framing using this template.