Household and labour force forecasts with POPGROUP

Date:

23/06/2017

Organised by:

CMIST, University of Manchester

Presenter:

Ludi Simpson

Level:

Intermediate (some prior knowledge)

Contact:

Mark Kelly
0161 275 0796

Map:

View in Google Maps  (M13 9PL)

Venue:

Humanities Bridgeford Street Building
University of Manchester

Description:

The course reviews and implements the standard methods of forecasting households and the labour force, through use of the Derived Forecasts module of POPGROUP software. The course uses Data Modules to explore UK government forecasts and participants will make their own alternative scenarios. 

The focus is on sub-national forecasts for districts of England, but the principles transfer directly to national forecasts, to sub-national forecasts of other areas, and to social or ethnic groups, each of which are discussed.

The emphasis is on hands-on learning through practical sessions that take the participants through the preparation of inputs, running forecasts, analysing results, and adjusting forecasts to implement a range of scenarios or assumptions.

The course is motivated by the issues in policy and planning that require population, household and labour force projections, and the impact of housing plans or jobs targets on population. 

The morning session will focus on understanding the capacity of the software through an extended hands-on exercise using data for districts in England chosen by the participant. These forecasts will be developed in the afternoon following guidance or exploring the participant’s own priorities.

Please note that a portfolio of demographic-related course is offered at CMIST over a three-day period. Participants on this course may be interested in taking the course Forecasting Population with POPGROUP.  This course on Household and Labour Force Forecasts with POPGROUP takes place on day 3.

This course is designed for those who wish to understand the construction of household and labour force forecasts and to use them in a practical planning context. Participants wishing to get skilled up in this software most often have local government or business planning backgrounds, but might be from national government or be postgraduate or other academics in this field.

Objectives

  • Review the standard methods of forecasting households and labour force used by national statistical agencies and in local government.
  • Introduce participants to the ways in which Derived Forecasts stores data for each of the components of a forecast in structured Excel spreadsheets: the forecast population, the institutional population, and a set of derived population rates: household representative rates, household membership rates, or economic activity rates.
  • Give participants experience of all stages of household forecasting with Derived Forecasts software: introducing past data for each component; making assumptions about future trends; running a forecast; extracting data from a forecast; adjusting assumptions to reflect new scenarios.
  • Give participants experience of measuring the impact on population of housing or jobs targets.
  • Consider how to develop alternative scenarios which may each be plausible, and to judge their plausibility from past experience. 

Prerequisites

Familiarity with POPGROUP software is essential, equivalent to the course Forecasting population with POPGROUP, or completion of the exercises in POPGROUP User Guide 1 (How to get started with population projections).

Experience of using multiple Microsoft Excel files is essential.

Integrated local demographic forecasts constrained by the supply of housing or jobs: practice in the UK - Ludi Simpson, CMIST Working Paper 2016-01

Cost:

£140 (those from educational, government and charitable institutions); £195 (others)

Website and registration:

Region:

North West

Keywords:

Data Collection, Quantitative Data Handling and Data Analysis, popgroup , labour force forecasts , data modules , microsoft excel

Related publications and presentations:

Data Collection
Quantitative Data Handling and Data Analysis

Back to archive...