The names for question types have changed in Q4.  Since a few new question types were being added to Q4, we took this chance to simplify the old question types.  The new names are shorter, more distinct, and relate better to the terminology used in surveys.  We hope that the new names will remove the confusion that existed in Q3 about the nature of the questions.

For example, in Q3 there was some confusion about the difference between Multiple Response - Binary and Multiple Response - Categorical questions.  They are now named Pick Any and Pick One - Multi questions, respectively.  The new names better represent the structure of the questions as they are used in questionnaires - e.g. "Pick any of the following that interests you" and "Pick one attribute that best represents each brand".

You can see a complete listing of all the new question types in the Quick Start guide, either in hard copy (page 35) or online (page 39 in Adobe Acrobat).  To understand how these question types determine what statistics are available in tables, click Help > Online Training in Q and complete the Question Types and Statistics tutorial, under Fundamentals, Creating Tables.

If you are a Q3 user who is upgrading to Q4, a list of the changes from Q3 to Q4 may help ease the transition for the first few weeks:

Time series plots in Q4 allow you to customize line and column plots with a Date variable on the horizontal axis.  For a guided tour, click Help > Online Training and complete the Time Series Plots tutorial under Fundamentals, Dates and Time Series Plots.

Below is an example time series plot which has had its date aggregation, duration and time series analysis options customised.  It also has its legend block broken up into multiple labels (having one legend block is also available).

There is a nifty new feature in Q4 that people have been asking for since we introduced spans during Q3's lifetime.  For a bit of background: spans get created as a result of creating a Banner question (using Create > Banner), or by right-clicking on two or more rows/columns in any table and selecting Create Span.  Now in Q4, these spans are exported to Excel when you export the table.

Spans in a table

Spans in Excel, after exporting

If you want to see filters and weights in the title of your exported tables (so they appear as titles in PowerPoint, or headings in print-outs and PDFs), then you will want to read on about a new feature in Q4.  Simply rename your tables or groups to include <filter> and/or <weight>, and when you export the table the <filter> and <weight> will be replaced by the labels of the filter and weight variables set on the table.

Report tree in your project
Exported to PowerPoint	Exported to PDF, or as printed

Correspondence analysis creates plots showing the relationship between multiple variables.

Q automatically works out the right type of map based on the data you choose to analyse.  It can create maps showing the rows and columns of a table, between individual respondents in the raw data and between three or more sets variables (multiple correspondence analysis). 

The maps are exported to Microsoft Office applications as fully-editable charts.  You can export either the traditional scatterplot or a moon plot.

Create maps by clicking on the Create menu and selecting Map.  

A series of online tutorials explain how to create maps.  From the Help menu, select Online Training, login and go Multivariate Techniques and Maps.

Max-Diff, sometimes known as a best-worst scaling, presents people with short lists of attributes and asks which they like best and which they like worst.  This is done multiple times, with different sets of attributes each time.  The sets of attributes are determined from an experimental design.

You can analyse Max-Diff questions in Q just like any other type of question, such as by crosstabbing with other questions, trees, latent class analysis, smart tables, mixture models, individual-level parameters and mapping. 

Max-diff and anchored max-diff experiments are setup in Q as Ranking questions, unless they are best-worst conjoint, in which case they are setup as an Experiment.  

This feature is only available in Q4; contact support@q-researchsoftware.com for a free upgrade.

Trees show the relationship between two sets of questions as an  upside-down tree.

While most tree-based methods, such as CHAID and CART only predict a single categorical or numeric variable, Q’s approach can predict all the different types of data: numeric, categorical, rankings, multiple response, conjoint and other types of experiments.   

The figure below shows Q’s graphical representation of segmentation, with bars showing categorical data and histograms representing numeric data.  

In Q4, trees are created by clicking on the Create menu, selecting Segments, selecting Split by questions (tree) and choose the questions to split by.  Contact support@q-researchsoftware.com for a free upgrade to Q4.

An online tutorial explains how to create trees.  From the Help menu in Q, select Online Training, sign in, then go to Multivariate Techniques, Segments and Trees.

Latent class analysis finds groups in data.  It is most commonly used for market segmentation. 

Latent class analysis is a big improvement on cluster analysis.  It automatically deals with missing data; even if there are lots of “don’t know” responses, each person is still assigned to a segment.  It accommodates all the different types of data: numeric, categorical, rankings, multiple response, conjoint and other types of experiments.   

The figure below show’s Q’s graphical representation of segmentation, with bars showing categorical data and histograms representing numeric data. 

In Q4, latent class analysis is conducted by clicking on the Create menu and selecting Segments; contact support@q-researchsoftware.com for a free upgrade to Q4.

An online tutorial explains how to use latent class analysis.  From the Help menu in Q, select Online Training, sign in, then go Multivariate Techniques, Segments and Latent Class Analysis.

Every variable in Q can have a comment added to it by right-clicking on it and selecting New Comment for Variable…. This allows you to easily work out why you did something, e.g. implemented a particular recode, because you have typed in the details.

Once you have added a comment, a little red marker lets you know that a comment exists, and you can click on the marker to go straight to the comment (just like Excel).

Thanks go to Scott Maclean for this tip.

Have you ever needed to show multiple statistics on a table, such as n, Base n, Total %?

Instead of right-clicking each time to re-open the menu, just hold down Ctrl on your keyboard while you click on the name of the statistic, and the menu will remain open, allowing you to select another statistic quickly!

This feature was introduced in Q4.