SHE Consulting

Logo of Services in Health Economics (SHE)

Statistical Analysis

Providing Insight into Data

The analysis of data is perhaps the most important process of a study; it reveals the real value of the collected data, and translates raw data into meaningful tables and figures. However, to fully exploit the potential of a data set, statistical know-how is required.

SHE employee presenting performed statistical analysis
SHE employees in a meeting


Analyzing data is our core business. Simply put, it is what we do best. We specialize in analyzing clinical data from randomized controlled trials (phase 2 or phase 3 RCT data, STDN ADAM datasets for FDA), as well as observational data and real-world evidence (RWE). 

HEOR data from clinical trials are often under-analyzed, leaving their full potential untapped. SHE’s experienced statisticians provide dedicated support to biotech companies and other data holders to dive deep into the dataset and maximize its value. Our efforts to gain insights from data are often combined with economic modelling.

We use a systematic approach when it comes to handling large amounts of data to prevent the loss of time due to inefficiency. Throughout the process, we value close communication with our clients.

Interested in working with us? Get in touch!

News & Events

No Content Available

Our Statistical Analysis Process

Define Objectives and Scope

During this step, we define the aim of the analysis in close collaboration with our clients, combining specific requests with our own insights.

Statistical Analysis Plan (SAP)

A formal Statistical Analysis Plan (SAP) is frequently the preferred, or mandatory option for large data sets. In addition, we will agree on planned analysis with our clients by discussing table thells, which we draft based on previous steps.

Data Acquisition and Reception
Raw data may originate from various sources, including clinical data from clinical trials (Phase 2 or Phase 3 data, STDN ADAM datasets for FDA) and observational studies (Real World Evidence).
Data Cleaning and Preprocessing

We clean the raw data set to ensure accuracy, handle missing data, and transform variables and standardize formats where necessary.

Exploratory Data Analysis (EDA)

Unless only a set of specific analyses are requested, we will perform exploratory data analysis to understand the basic characteristics of the data and identify patterns and potential issues.

Statistical Analysis

We use SAS/STATA, R, Matlab, Python, or VBA to carry out the agreed upon analysis, which may include a variety of analysis techniques including, but not limited to:

  • Survival analysis
  • Analysis of repeated measurements of PROMs
  • Longitudinal analysis with appropriate missing data methods
  • Resource utilization and cost analysis
  • Time-series analysis
  • Multilevel analysis
  • Analysis of discrete choice experiments
  • Factor analysis
  • Clustering analysis
  • Missing data and multiple imputation techniques
  • Propensity scores adjustment for non-randomization
Quality Assurance
We perform internal checks on our code and results to make sure no mistakes were made and the analyses provide a clear answer to the research questions.

During this phase, we communicate the results of our analysis in a report, contextualizing charts and graphs with descriptions of overall trends or notable findings. The entire process, from data cleaning to analyzing, may also be documented if the client wishes to gain more clarity or transparency about this. 

Post-analysis Support

We remain stand-by to provide support in case our clients wish to request further analyses or have additional questions.

Other Services

Study Design
Employ our guidance in designing your study down to the finest details, including clinical endpoints, PROMs and resource utilization
Empower your staff with a course on health economics, on statistics or on the importance of including PROMs from one of our senior health economists or statisticians
Curious about our past endeavors? Dive into some of our academic writing