Critically reading scientific papers is critical for Data Scientists working some areas - especially those working in health. With that in mind, here are some key considerations in reading scientific (peer-review, grey literature) papers:

Theory: Is the theory sound? Are there theoretical issues in the design that cause…

An emerging trend in the private equity space is an enhanced focus on data science.

This focus has historically been more on the operations side (post-acquisition) where data scientists have been leveraged to help companies improve performance in many key areas including marketing, business intelligence, financial analysis, and human resources. The advantage of focusing data scientists on the operations side is rather obvious: after an acquisition has occurred, the data challenges and…

Continuing my thoughts on random experiments and what can go wrong:

Another common problem is Attrition, especially situations where the attrition rate is not randomly distributed (if the attrition rate is randomly distributed then you have lost power in your study).

After random…

Continuing my thoughts on random experiments and what can go wrong:

One common problem is Contamination of the Control Group

The only difference between the treatment and control groups should be the treatment.  That said, this isn't always true.  How the treatment is administered can affect the control group.  Think about health examples where, for example, deworming…

Randomization, including A/B testing, often fails...for a variety of reasons.  When that happens you will likely find yourself in a situation where the treatment and control groups differ significantly.

First thing to remember is that some differences can occur in studies that are unavoidable.  Are the differences practically significant?  Are they statistically…

Before implementing a program, I like to first develop a logic model.  

This can be a fast exercise that can lead to insights into the strengths and weaknesses of the program design.  There are many different models used and I prefer a simple one with 4 basic parts:

1. Inputs—resources that go into a program including staff, materials, money, equipment, facilities,…

In business, we often implement programs and then try to determine if the program had an impact. This is an example of program evaluation where, more generally, program evaluation is a study conducted with the intent of determining how effective a given intervention (program) is at achieving a specific outcome.

What types of programs? That could be a cross-sell program, customer retention program, new advertising method etc.

Is this just A/ B testing? A/B testing is a great…

Data science had broad applications across many different industries. 

If we focus on industries that are in the business of buying (some or all) of a company, then trying to improve the operations before selling then we can identify at least three critical stages for data science to play a significant role.

1. Early Exploration: Mining databases for trend and customer insights
2. Enhanced Pre-acquisition Analysis: Linking early exploration…

Background: Business intelligence software casts a wide net. Software for site selection, customer segmentation, marketing tests, employee productivity, operational metrics, sentiment analysis, profitability sectors and mapping tools all fall in this category. 

Businesses are constantly challenged with business intelligence software questions such as:

·      Should we “Build or Buy”?

·      Should we “Retain, Upgrade, or Replace”…

We tried to do XYZ. Did it make a difference?”

Whether you are in the for-profit world or the not-for profit world, this is a very basic question that many people try to answer.  

You could be working at a bank trying to figure out which offer is most appealing to customers, at an online retailer figuring out which ad display gets the most clicks, at the Department of Education trying to test the effect of smaller class sizes, at the city government office trying to see if the…