Predictive HR Analytics: Mastering the HR Metric

Predictive HR Analytics: Mastering the HR Metric

by Martin R. Edwards, Kirsten Edwards

Paperback(New Edition)



While other departments in an organization deal with profits, sales growth, and strategic planning, Human Resources (HR) is responsible for employee well-being, engagement, and staff motivation.  Even though it may not be immediately obvious, the management of these duties often requires a great deal of measurement and technical skill. Predictive HR Analytics provides a clear and accessible framework to understanding and learning to work with HR analytics at an advanced level, using examples of particular predictive models, such as diversity analysis, predicting turnover, evaluating interventions, and predicting performance.

When dealing with metrics, management information, and analytics, HR practitioners rarely use any advanced statistical techniques or go beyond describing the characteristics of the workforce.  Authors Martin Edwards and Kirsten Edwards explain the business applications of HR predictive models; the ethics and limitations of HR analytics; how to carry out an analysis; predict turnover, performance, recruiting, and selection outcomes; and monitor the impact of interventions.

Product Details

ISBN-13: 9780749473914
Publisher: Kogan Page, Ltd
Publication date: 03/28/2016
Edition description: New Edition
Pages: 472
Product dimensions: 6.00(w) x 9.10(h) x 1.20(d)

About the Author

Martin R. Edwards teaches HRM and Organizational Psychology at King's College London. He has run many HR analytic workshops with companies including AstraZeneca, advised on employee engagement surveys, and run multiple employee attitude surveys.

Kirsten Edwards is a Diversity Specialist at Pearn Kandola, a business psychology consulting company specializing in diversity, assessment, and development.  She has taught diversity and inclusion at Kings College London and the University of Kent.

Table of Contents


01 Understanding HR analytics
Predictive HR analytics defined
Understanding the need (and business case) for mastering and utilizing predictive HR analytic techniques Human capital data storage and 'big (HR) data' manipulation
Predictors, prediction and predictive modelling
Current state of HR analytic professional and academic training
Business applications of modelling
HR analytics and HR people strategy
Becoming a persuasive HR function
Further reading

02 HR information systems and data
Information sources
Analysis software options
Using SPSS
Preparing the data
Big data

03 Analysis strategies
From descriptive reports to predictive analytics
Statistical significance
Data integrity
Types of data
Categorical variable types
Continuous variable types
Using group/team-level or individual-level data
Dependent variables and independent variables
Your toolkit: types of statistical tests
Statistical tests for categorical data (binary, nominal, ordinal)
Statistical tests for continuous/interval-level data
Factor analysis and reliability analysis
What you will need

04 Case study 1: diversity analysis
Equality, diversity and inclusion
Approaches to measuring and managing D&I
Example 1: gender and job grade analysis using frequency tables and chi square
Example 2a: exploring ethnic diversity across teams using descriptive statistics
Example 2b: comparing ethnicity and gender across two functions in an organization using the independent samples t-test
Example 3: using multiple linear regression to model and predict ethnic diversity variation across teams
Testing the impact of diversity: interacting diversity categories in predictive modelling
A final note

05 Case study 2: employee attitude surveys-engagement and workforce perceptions
What is employee engagement?
How do we measure employee engagement?
Interrogating the measures
Conceptual explanation of factor analysis
Example 1: two constructs-exploratory factor analysis
Reliability analysis
Example 2: reliability analysis on a four-item engagement scale
Example 3: reliability and factor testing with group-level engagement data
Analysis and outcomes
Example 4: using the independent samples t-test to determine differences in engagement levels
Example 5: using multiple regression to predict team-level engagement
Actions and business context

06 Case study 3: predicting employee turnover
Employee turnover and why it is such an important part of HR management information
Descriptive turnover analysis as a day-to-day activity
Measuring turnover at individual or team level
Exploring differences in both individual and team-level turnover
Example 1a: using frequency tables to explore regional differences in staff turnover
Example 1b: using chi-square analysis to explore regional differences in individual staff turnover
Example 2: using one-way ANOVA to analyse team-level turnover by country
Example 3: predicting individual turnover
Example 4: predicting team turnover
Modelling the costs of turnover and the business case for action

07 Case study 4: predicting employee performance
What can we measure to indicate performance?
What methods might we use?
Practical examples using multiple linear regression to predict performance
Ethical considerations caveat in performance data analysis
Considering the possible range of performance analytics models

08 Case study 5: recruitment and selection analytics
Reliability and validity of selection methods
Human bias in recruitment selection
Example 1: consistency of gender and BAME proportions in the applicant pool
Example 2: investigating the influence of gender and BAME on shortlisting and offers made
Validating selection techniques as predictors of performance
Example 3: predicting performance from selection data using multiple linear regression
Example 4: predicting turnover from selection data-validating selection techniques by predicting turnover
Further considerations

09 Case study 6: Monitoring the impact of interventions
Tracking the impact of interventions
Example 1: stress before and after intervention
Example 2: stress before and after intervention by gender
Example 3: value change initiative
Example 4: value-change initiative by department
Example 5: supermarket checkout training intervention
Example 6: supermarket checkout training course-Redux
Evidence-based practice and responsible investment

10 Business applications: Scenario modelling and business cases
Predictive modelling scenarios
Example 1: customer reinvestment
Example 2: modelling the potential impact of a training programme
Obtaining individual values for the outcomes of our predictive models
Example 3: predicting the likelihood of leaving
Making graduate selection decisions with evidence obtained from previous performance data
Example 4: constructing the business case for investment in an induction day
Example 5: using predictive models to help make a selection decision in graduate recruitment
Example 6: which candidate might be a 'flight risk'?
Further consideration on the use of evidence-based recommendations in selection

11 More advanced HR analytic techniques
Mediation processes
Moderation and interaction analysis
Multi-level linear modelling
Curvilinear relationships
Structural equation models
Growth models
Latent class analysis
Response surface methodology and polynomial regression analysis
The SPSS syntax interface

12 Reflection on HR analytics: Usage, ethics and limitations
HR analytics as a scientific discipline
The metric becomes the behaviour driver: Institutionalized Metric-Oriented Behaviour (IMOB)
Balanced scorecard of metrics
What is the analytic sample?
The missing group
The missing factor
Carving time and space to be rigorous and thorough
Be sceptical and interrogate the results
The importance of quality data and measures
Taking ethical considerations seriously
Ethical standards for the HR analytics team
The metric and the data is linked to human beings


Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews