graph TD
    A[Research Question] --> B[Literature Review]
    B --> C[Identify Knowledge Gap]
    C --> D[Formulate Hypothesis]
    D --> E[Design Experiment]
    E --> F[Power Analysis: Sample Size]
    F --> G[Define Controls + Variables]
    G --> H[Ethical Review Preparation]
    H --> I[Data Collection Protocol]
    I --> J[Analysis Plan: Pre-registered]
    J --> K[Execute + Collect Data]
    K --> L[Analyze per Pre-registered Plan]
    L --> M[Write Manuscript]
    M --> N[Peer Review Preparation]

class ResearchProtocol:
    def formulate_hypothesis(self, observation: str, literature: list[str]) -> dict:
        return {
            "null_hypothesis": "There is no significant difference between...",
            "alternative_hypothesis": "Treatment X increases Y by at least Z...",
            "falsifiability": "This hypothesis is falsifiable because...",
            "variables": {
                "independent": ["Treatment type (A vs B vs control)"],
                "dependent": ["Measured outcome Y"],
                "controlled": ["Age, sex, baseline Z"],
                "confounding": ["Prior exposure to X"],
            },
        }

    def power_analysis(self, effect_size: float, alpha: float = 0.05, power: float = 0.80) -> dict:
        from statsmodels.stats.power import TTestIndPower
        analysis = TTestIndPower()
        n = analysis.solve_power(effect_size=effect_size, alpha=alpha, power=power)
        return {
            "required_n_per_group": int(np.ceil(n)),
            "total_n": int(np.ceil(n)) * 2,
            "effect_size": effect_size,
            "alpha": alpha,
            "power": power,
            "recommendation": f"Recruit {int(np.ceil(n * 1.2))} per group to account for 20% attrition",
        }

    def literature_search(self, topic: str) -> dict:
        return {
            "databases": ["PubMed", "Scopus", "Web of Science"],
            "query": f'("{topic}") AND (randomized OR controlled) AND ("2020"[Date] : "2026"[Date])',
            "inclusion_criteria": [
                "Peer-reviewed original research",
                "English language",
                "Human subjects",
                "Published 2020-2026",
            ],
            "exclusion_criteria": [
                "Review articles (captured separately)",
                "Case reports (n < 10)",
                "Non-peer-reviewed preprints",
            ],
            "prisma_flow": "Record screening, eligibility, and inclusion counts per PRISMA 2020",
        }

    def experimental_design(self, hypothesis: dict) -> dict:
        return {
            "design": "Randomized controlled trial, double-blind, parallel group",
            "randomization": "Block randomization with variable block sizes (4, 6, 8)",
            "blinding": "Participants and assessors blinded; unblinded statistician",
            "primary_outcome": hypothesis["variables"]["dependent"][0],
            "secondary_outcomes": [],
            "timeline": "Baseline → 4 weeks intervention → 8 weeks follow-up",
            "analysis_plan": "Pre-registered at OSF.io before data collection",
        }