Quantitative Analysis for Academic Health Research

Freelance Job: Cluster Analysis, Factor Analysis & Regression for Academic Research

Project Overview
I am looking for an experienced statistician or data analyst to conduct a series of statistical analyses on a pilot dataset (N=100) using SPSS or R. The analysis will focus on descriptive statistics, cluster analysis, factor analysis, and regression modeling. The dataset is in Danish, but only variable names are affected.

The results must be delivered in clear academic English, ready to be used in a research article. The freelancer should also provide well-documented SPSS syntax or R scripts, along with appropriate visualizations.

Key Analyses Required
1. Descriptive Analysis

Summary statistics for key variables (mean, SD, frequencies, distributions).
Graphical visualizations (histograms, box plots, etc.).

2.Cluster Analysis (Theory-Driven Approach)

Perform K-means and/or Hierarchical Clustering.
Determine the optimal number of clusters using:
Elbow Method
Silhouette Analysis
Gap Statistic

Test theoretical typologies based on predefined characteristics:

Double-Compensating Network Capital: High health literacy (HL), high education level, strong social network with highly competent members.

Moderately-Compensating Network Capital: Low to moderate HL, possibly one or few network members with professional competencies.

Negatively-Compensating Network Capital: Low HL, limited or no competent social network.

Key Variables for Clustering:
-Health literacy (HL) (self-assessed ability to understand and use health information).
-Education level (formal education).
-Social network competence (perceived skills of network members).
-Network strength (size, frequency of contact, perceived support).
-Comparison of Empirical Clusters vs. Theoretical Typologies:
-Use discriminant analysis or ANOVA to test cluster differentiation.
-Assess how well the empirical clusters align with the predefined categories.
Provide detailed interpretation & visualization (e.g., cluster profiles, heatmaps, dendrograms).

3.Factor Analysis

Exploratory Factor Analysis (EFA) to identify latent structures in the dataset.
Confirmatory Factor Analysis (CFA) (if applicable) to validate theoretical constructs.
Factor loadings, eigenvalues, and scree plots for interpretation.
4.Regression Analysis

Multiple regression models testing relationships between key variables.
Model fit assessment (R², adjusted R², p-values, confidence intervals).

Deliverables & Quality Requirements
-Detailed academic report in clear English, ready for use in a research article.
-Well-documented SPSS syntax or R scripts, ensuring reproducibility.
-Visualizations (heatmaps, dendrograms, scatter plots, scree plots, regression graphs).
-Comparison between empirical clusters and theoretical typologies, including statistical validation.
-Structured and well-explained results, ensuring clarity for non-statistical readers.

Project Timeline & Milestones
Milestone 1 (25%) – Descriptive statistics & data preparation (Deliverable within 2 days).
Milestone 2 (50%) – Cluster analysis, factor analysis, and preliminary results (Deliverable within 5 days).
Milestone 3 (25%) – Final report, regression analysis & review (Deliverable within 7 days).

Revisions & Feedback
One round of revisions included to ensure clarity and alignment with expectations.
Regular updates during the project are expected.

Requirements for Applicants
-Proven experience in statistical analysis using SPSS or R.
-Strong academic writing skills in English.
-Prior experience with cluster analysis, factor analysis, and regression modeling.
-Background in social sciences, public health, or related fields is a plus.


If you are interested, please include in your proposal:

-A short description of your relevant experience.
-An example of a previous statistical report or similar analysis.
-A brief explanation of how you would approach this project.
-Looking forward to collaborating!