Market Research.

Market research is used to figure out how things work. This is often by systematically gathering data about people or companies using surveys.

Here, we write about the main market research techniques. These techniques include correspondence analysis, MaxDiff, and choice modeling. We also share tips and tricks for significance testing. And how to best present market research findings using PowerPoint and online dashboards (often considered a better alternative to PowerPoint) are explored.

Checking Convergence When Using Hierarchical Bayes for MaxDiff
16 January 2018 | by Justin Yap

Hierarchical Bayes is an approach to modelling MaxDiff data which can provide better predictive accuracy than other approaches (like latent class analysis). However, it is…

Continue reading

Using Q
Using Hierarchical Bayes for MaxDiff in Q
16 January 2018 | by Justin Yap

In this blog post I describe how to run Hierarchical Bayes for MaxDiff in Q, and explain the options and outputs available. Getting started Your…

Continue reading

Using Displayr
Using Hierarchical Bayes for MaxDiff in Displayr
16 January 2018 | by Justin Yap

In this blog post I describe how to run Hierarchical Bayes for MaxDiff in Displayr, and explain the options and outputs available. Getting started Your…

Continue reading

Using Displayr
Case Study: Updating Reporting
04 December 2017 | by Tim Bock

This is the sixth in a series of blog posts designed as a DIY training course for using Displayr. It illustrates how to update analyses and reporting…

Continue reading

NPS column chart with sparklines
Using Sparklines to Show Trends in Bar and Column Charts
09 November 2017 | by Tim Bock

Using sparklines in charts with multiple series of data improves readability by showing where are we today, movement since last time and long-term trend.

Continue reading

Comparing Tricked Logit and Rank-Ordered Logit with Ties for MaxDiff
17 October 2017 | by Justin Yap

This article compares two ways to analyze Max Diff data - Tricked Logit and Rank-Ordered Logit with Ties - for latent class analysis or Hierarchical Bayes

Continue reading

Image of dirty laundry in a basket
Automatic Data Checking: Let Your Analytics Package Do Your Dirty Laundry for You
16 October 2017 | by Matt Steele

  Data checking is a bore (and a step we skip at our peril!). The laundry-list of data checking tasks can be seemingly endless: identifying bogus…

Continue reading

Great looking dashboard
Create and Update PowerPoint Reports using R
31 August 2017 | by Tim Bock

An introduction to three tools that make creating and updating PowerPoint reports using R much more efficient and less painful.

Continue reading

Choice Simulator
How to Create an Online Choice Simulator
22 August 2017 | by Tim Bock

A worked example is used to show how to create an online choice simulator (conjoint simulator). Calculations are done in R & it is hosted in Displayr.

Continue reading

Adding Supplementary Points to a Correspondence Analysis
17 August 2017 | by Jake Hoare

Supplementary points of data can be added to a "core" correspondence analysis to aid interpretation without influencing the placement of core data.

Continue reading

Moonplot to show brand mapping from a correspondence analysis
Moonplots: A Better Visualization for Brand Maps
15 August 2017 | by Tim Bock

Correspondence analysis outputs are difficult to read correctly. Moonplots are a better alternative to brand maps because they are much easier to interpret.

Continue reading

MaxDiff analysis example
MaxDiff: 11 Tips to Do Your Own Analysis
03 August 2017 | by Tim Bock

MaxDiff analysis is an advanced technique that can be run by any good quant researcher. Here are 11 tips to help people relatively new to the field DIY.

Continue reading

experimental design
How to Check an Experimental Design (MaxDiff, Choice Modeling)
25 July 2017 | by Tim Bock

Experimental designs can be scary. Small mistakes ruin everything. I explain the process I use when doing a rough-and-ready check of an experimental design.

Continue reading

Correspondence Analysis for brand switching
Correspondence Analysis of Square Tables
25 July 2017 | by Jake Hoare

In this post I discuss the special case of Correspondence Analysis with square tables. Such tables often arise in the context of brand switching.

Continue reading

Put PowerPoint into Cruise Control: How to Automatically Update Your Reports
14 July 2017 | by Matt Steele

An exploration of what processes can be automated in PowerPoint, and how different analysis software packages leverage this.

Continue reading

correspondence analysis
Using Bubble Charts to Show Significant Relationships and Residuals in Correspondence Analysis
08 July 2017 | by Tim Bock

While correspondence analysis does a great job at highlighting relationships in large tables, a practical problem is that correspondence analysis only shows

Continue reading

Traditional Crosstab
Old-School Crosstabs: Obsolete Since 1990, but Still a Great Way to Waste Time and Reduce Quality
27 June 2017 | by Tim Bock

The table above is what I call an old-school crosstab. If you squint, and have seen one of these before, then you can probably read it.

Continue reading

Keep updated with the latest in data science.