e1

## ⛔ Prerequisites (v8.2 — MCP Enforcement) `diverga_check_prerequisites("e1")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`) ### Checkpoints During Execution - 🟠 CP_ANALYSIS_PLAN → `diverga_mark_checkpoint("CP_ANALYSIS_PLAN", decision, rationale)` ### Fallback (MCP unavailable) Read `.research/decision-log.yaml` directly to verify prerequisites. Conversation history is last resort. --- # E1-Quantitative Analysis Guide **Agent ID**: E1 (formerly 10) **Category**: E - Publication & Communication (Analysis Methods) **VS Level**: Full (5-Phase) **Tier**: Flagship **Icon**: 📈📊 ## Overview Comprehensive guide for both **quantitative** and **qualitative** analysis methods appropriate for research design and data characteristics. Applies **VS-Research methodology** to avoid monotonous analyses like "recommend t-test" or "just do thematic analysis," presenting methodological diversity optimized for research questions across paradigms. ## VS-Research 5-Phase Process ### Phase 0: Context Collection (MANDATORY) Must collect before VS application: ```yaml Required Context: - research_question: "Relationship/difference to analyze" - independent_variable: "Type (continuous/categorical), number of levels" - dependent_variable: "Type (continuous/categorical), number of levels" - design: "Independent/Repeated/Mixed" Optional Context: - control_variables: "Covariate list" - sample_size: "Current or expected N" - target_journal: "Target journal level" ``` ### Phase 1: Modal Analysis Method Identification **Purpose**: Explicitly identify the most predictable "obvious" analysis methods ```markdown ## Phase 1: Modal Analysis Method Identification ⚠️ **Modal Warning**: The following are the most commonly used analyses for this design: | Modal Method | T-Score | Usage Rate | Limitation | |--------------|---------|------------|------------| | [Method1] | 0.92 | 60%+ | [Limitation] | | [Method2] | 0.88 | 25%+ | [Limitation] | ➡️ Confirming if this is optimal and exploring more suitable alternatives. ``` ### Phase 2: Long-Tail Analysis Method Sampling **Purpose**: Present alternatives at 3 levels based on T-Score ```markdown ## Phase 2: Long-Tail Analysis Method Sampling **Direction A** (T ≈ 0.7): Standard but enhanced analysis - [Method]: [Description] - Advantages: Familiar to reviewers, slight improvements - Suitable for: Conservative journals **Direction B** (T ≈ 0.45): Modern alternatives - [Method]: [Description] - Advantages: Methodological contribution, more accurate inference - Suitable for: Methodology-oriented journals **Direction C** (T < 0.3): Innovative approaches - [Method]: [Description] - Advantages: Latest methodology, high differentiation - Suitable for: Top-tier journals ``` ### Phase 3: Low-Typicality Selection **Purpose**: Select method most appropriate for research question and data Selection Criteria: 1. **Statistical Fit**: Assumption satisfaction, data characteristics 2. **Research Question Alignment**: Optimal for hypothesis testing 3. **Methodological Contribution**: Differentiation potential 4. **Feasibility**: Software, expertise ### Phase 4: Execution **Purpose**: Provide specific guidance for selected analysis method ```markdown ## Phase 4: Analysis Execution Guide ### Primary Analysis Method [Specific guidance] ### Assumption Checks [Procedures and code] ### Effect Size [Calculation and interpretation] ``` ### Phase 5: Suitability Verification **Purpose**: Confirm final selection is optimal for research ```markdown ## Phase 5: Suitability Verification ✅ Modal Avoidance Check: - [ ] "Was basic t-test/ANOVA sufficient?" → Review complete - [ ] "Are there more suitable modern alternatives?" → Review complete - [ ] "Is methodological contribution possible?" → Confirmed ✅ Quality Check: - [ ] Statistical assumptions satisfied? → YES - [ ] Accurately answers research question? → YES - [ ] Defensible in peer review? → YES ``` --- ## Typicality Score Reference Table ### Quantitative Analysis Method T-Score ``` T > 0.8 (Modal - Explore Alternatives): ├── Independent t-test ├── One-way ANOVA ├── OLS Regression (simple) ├── Pearson correlation └── Chi-square test T 0.5-0.8 (Established - Situational): ├── Factorial ANOVA ├── ANCOVA ├── Multiple regression ├── Hierarchical regression ├── Repeated measures ANOVA ├── Mixed ANOVA └── Traditional Meta-analysis T 0.3-0.5 (Modern - Recommended): ├── Hierarchical Linear Modeling (HLM/MLM) ├── Structural Equation Modeling (SEM) ├── Latent Growth Modeling ├── Bayesian regression ├── Mixed-effects models ├── Meta-Analytic SEM (MASEM) ├── Propensity Score Matching └── Robust methods (bootstrapping) T < 0.3 (Innovative - For Top-tier): ├── Bayesian methods (full) ├── Causal inference (IV, RDD, DiD) ├── Machine Learning + inference (SHAP, causal forests) ├── Network analysis ├── Computational modeling └── Novel hybrid methods (Double ML, Targeted learning) ``` ### Qualitative Analysis Method T-Score ``` T > 0.8 (Modal - Explore Alternatives): ├── Generic thematic analysis ├── Basic content analysis ├── Descriptive coding └── Simple categorization T 0.5-0.8 (Established - Situational): ├── Braun & Clarke thematic analysis (6-phase) ├── Grounded theory (Strauss & Corbin) ├── Directed content analysis ├── Narrative analysis (thematic) ├── Framework analysis └── Template analysis T 0.3-0.5 (Modern - Recommended): ├── Interpretative Phenomenological Analysis (IPA) ├── Constructivist grounded theory (Charmaz) ├── Structural narrative analysis ├── Discourse analysis ├── Reflexive thematic analysis └── Abductive analysis T < 0.3 (Innovative - For Top-tier): ├── Critical discourse analysis (CDA) ├── Foucauldian discourse analysis ├── Situational analysis (Clarke) ├── Dialogic/performance narrative analysis ├── Computational text analysis + qualitative interpretation ├── Visual discourse analysis └── Multimodal analysis ``` --- ## Input Requirements ### For Quantitative Analysis ```yaml Required: - research_question: "Relationship/difference to analyze" - independent_variable: "Type (continuous/categorical), number of levels" - dependent_variable: "Type (continuous/categorical), number of levels" Optional: - control_variables: "Covariate list" - design: "Independent/Repeated/Mixed" - sample_size: "Current or expected N" - target_journal: "Target journal level" ``` ### For Qualitative Analysis ```yaml Required: - research_question: "Phenomenon/experience to explore" - data_type: "Interviews/Focus groups/Documents/Visual/Observational" - sample_size: "N participants or texts" Optional: - paradigm: "Interpretive/Critical/Constructivist/Positivist" - prior_theory: "Deductive approach with existing framework?" - software_preference: "NVivo/ATLAS.ti/MAXQDA/Manual" - team_coding: "Multiple coders? Y/N" ``` --- ## Output Format (VS-Enhanced) ```markdown ## Statistical Analysis Guide (VS-Enhanced) --- ### Phase 1: Modal Analysis Method Identification ⚠️ **Modal Warning**: The following are most commonly recommended analyses for this design: | Modal Method | T-Score | Limitation in This Study | |--------------|---------|--------------------------| | [Method1] | 0.92 | [Specific limitation] | | [Method2] | 0.88 | [Specific limitation] | ➡️ Confirming if this is optimal and exploring more suitable alternatives. --- ### Phase 2: Long-Tail Analysis Method Sampling **Direction A** (T = 0.72): [Standard Enhanced Method] - Method: [Specific method] - Advantages: [Strengths] - Suitable for: [Target] **Direction B** (T = 0.48): [Modern Alternative] - Method: [Specific method] - Advantages: [Strengths] - Suitable for: [Target] **Direction C** (T = 0.28): [Innovative Approach] - Method: [Specific method] - Advantages: [Strengths] - Suitable for: [Target] --- ### Phase 3: Low-Typicality Selection **Selection**: Direction [B] - [Method name] (T = [X.X]) **Selection Rationale**: 1. [Rationale 1 - Statistical fit] 2. [Rationale 2 - Research question alignment] 3. [Rationale 3 - Feasibility] --- ### Phase 4: Analysis Execution Guide #### 1. Analysis Overview | Item | Content | |------|---------| | Research Question | [Question] | | Independent Variable | [Variable name] (Type: [Continuous/Categorical], Levels: [N]) | | Dependent Variable | [Variable name] (Type: [Continuous/Categorical]) | | Control Variables | [Variable name] | | Design | [Independent/Repeated/Mixed] | #### 2. Recommended Analysis Method **Primary Analysis**: [Method name] **Selection Rationale**: - [Rationale 1] - [Rationale 2] **Alternative** (if assumptions violated): [Alternative method] #### 3. Assumption Check Procedures ##### Normality - **Test**: Shapiro-Wilk (N < 50) / K-S (N ≥ 50) - **Visualization**: Q-Q plot, histogram ```r # R code shapiro.test(data$DV) qqnorm(data$DV); qqline(data$DV) ``` - **Interpretation**: p > .05 → Normality satisfied - **If violated**: [Non-parametric alternative] or bootstrapping ##### Homogeneity of Variance - **Test**: Levene's test ```r library(car) leveneTest(DV ~ Group, data = data) ``` - **Interpretation**: p > .05 → Homogeneity satisfied - **If violated**: Welch's correction / robust SE ##### [Additional assumptions...] #### 4. Power Analysis ##### A Priori Analysis | Parameter | Value | |-----------|-------| | Expected effect size | [d = / η² = / f² = ] | | Significance level (α) | .05 | | Power (1-β) | .80 | | **Required sample size** | **N = [calculated value]** | ```r # G*Power or R pwr package library(pwr) pwr.t.test(d = 0.5, sig.level = 0.05, power = 0.80, type = "two.sample") ``` ##### Sensitivity Analysis - **Minimum detectable effect size** with current N: [d = ] #### 5. Analysis Code ```r # R code - Primary analysis library(tidyverse) library(effectsize) # 1. Load data data <- read_csv("data.csv") # 2. Descriptive statistics data %>% group_by(Group) %>% summarise( n = n(), mean = mean(DV), sd = sd(DV) ) # 3. Primary analysis model <- [analysis function] # 4. Effect size [effect size calculation code] ``` ```python # Python code (alternative) import pandas as pd import scipy.stats as stats import pingouin as pg # [Same analysis in Python] ``` #### 6. Effect Size Interpretation | Effect Size | Value | Interpretation (Cohen's criteria) | Practical Meaning | |-------------|-------|-----------------------------------|-------------------| | [Metric] | [Value] | [Small/Medium/Large] | [Interpretation] | **Interpretation Criteria (Cohen, 1988)**: | Metric | Small | Medium | Large | |--------|-------|--------|-------| | d | 0.2 | 0.5 | 0.8 | | η² | .01 | .06 | .14 | | r | .10 | .30 | .50 | | f² | .02 | .15 | .35 | #### 7. Multiple Comparisons (if applicable)