Consulting Services

I partner with academic researchers to utilize data and advanced analytic techniques to identify and evaluate risk and resiliency factors, longitudinal trends, intervention outcomes, and optimize measurement systems.

My main programming language is R. R is open source, which supports reproducibility a key principle of the open science movement. It allows me to create pipelines from data cleaning to analysis, enabling analyses to be re-run in an efficient, seamless, and reproducible manner.

I am also familiar with other statistical software, such as SPSS, SAS, and Mplus.

Advanced Statistical Analyses

I am familiar with a range of statistical techniques to answer empirical research questions, including:

  • Structural Equation Modeling (SEM): How do certain behavioral, psychological, or physiological factors influence each other? This approach includes mediation and moderation models. SEM also allows for latent variable modeling to increase the precision of our findings. Example 🖼️
  • Latent Variable Modeling: How do individual data sources represent or measure broader theoretical concepts (latent variables)? This includes Confirmatory Factor Analysis (CFA), which tests whether specific items represent subcategories or subscales of an overall measure. Example 🖼️
  • Latent Growth Modeling (Longitudinal Data): Are there changes in these variables over time? Do certain variables or interventions influence change?
  • Latent Profile Analysis: Are there distinct subgroups within this population based on specific characteristics (variables)?
  • Meta-Analysis: How does the relationship between two variables, such as an intervention and an outcome, vary across studies? How robust is this relationship?

Many of these approaches are based on regression modeling, which relies on certain types of data. I am also experienced with techniques for non-normally distributed or non-continuous data (e.g., logistic regression). I often consult with researchers to ensure their research questions align with the data, either before or after data collection.

Other specialties:

  • Reliability statistics (Kappa, ICC, Cronbach’s alpha)
  • Odds ratios, risk ratios
  • Specificity / sensitivity analyses (AUC/ROC)
  • Power analyses

Data Science

Let me build tools to help automate your data pipelines, clean data that has been collected, combine complex data-sets, or integrate online information into your data.

  • Data Visualization: Bringing data to life using graphics. R has many pre-existing packages that maximize visual insights tailored to the data type or analysis. I can also customize color schemes and fonts to match your institution or brand. Example 🖼️

  • Data Cleaning: Converting raw data into usable variables for analysis. This can also include converting data types (for example, using timestamps to categorize data into phases of a clinical trial, even with multiple cohorts with different start dates) into a more useable format.

  • Missing Data: There are many approaches to dealing with missing data, depending on your dataset and analytic plan. I am familiar with a range of imputation methods and analytic approaches that account for missingness (e.g., FIML).

  • Web Scraping: Extracting data from webpages into a spreadsheet for decision-making, visualization, or analysis. Example 🔗

  • Text-Based Data: Converting qualitative data into a quantitative format. This may include automated coding of free-text responses from surveys or short interview transcripts. Example 🔗

Clinical Trials

Due to my shared background in quantitative methods and clinical practice, I can provide support for implementing clinical trials, to help maximize data collection efforts and findings.

  • Support across all phases of clinical trial implementation
    • Grant writing and study design
    • Set-up and maintenance of data monitoring and quality assurance systems
    • Building data cleaning pipelines for real-time analysis
  • Experience with a range of clinical populations across the lifespan, including non-speaking individuals, individuals with cognitive disabilities, and families.
  • Familiarity with diverse data collection methods
    • Biometric Data: Structural MRI, Eye-gaze tracking (EGT), electroencephalography (EEG)
    • Ecological Momentary Assessment (EMA)
    • Observational coding
    • Standardized cognitive, academic, and social-emotional assessments
    • Self-report and parent-report measures
    • Qualitative interviews

Fees

  • Hourly rate: $75/hr
  • Discounted rate available for graduate students and early career researchers: $50/hr
  • Full data analysis projects that result in a manuscript typically take about 20 hours
  • Once a manuscript is submitted, I do not charge for minor edits during the revision process.
  • I currently have capacity for up to 10 hours / week for projects. Projects that require additional time will be considered with advanced notice.
  • Payment options: Check or online payment (3% processing fee)

Let’s Get Started

Have an idea or project you’d like to collaborate on? Email me 📧 to set up a free 30-minute consultation.