Abbreviations and glossary

A guide to words used in the Social Housing Test Case and Technical Report.

Abbreviations

Quick link to Glossary

ACC

Accident Compensation Corporation

AMSTAR standard

Tool to assess the methodological quality of systematic reviews

AS

Accommodation Supplement

ATT

Average Treatment Effect on the Treated (group)

AUC

Area Under Curve

CART

Classification and Regression Tree-based

CBA

Cost Benefit Analysis

CHP

Community Housing Provider

COR

Department of Corrections

CYF

Child, Youth and Family

DHB

District Health Board

DIA

Department of Internal Affairs

ERP

Estimated Resident Population

ESOL

English for Speakers of Other Languages

F&C

Forecasting and Costing

GAM

Generalised Additive Model

GBT

Gradient Boosted Tree

GCV

Generalised Cross Validation

GLM

Generalised Linear Model

GMS

General Medical Subsidy

HNZ

Housing New Zealand Corporation

IDI

Integrated Data Infrastructure

iMSD

Insights MSD

IPTW

Inverse Probability of Treatment Weighting

IR

Inland Revenue

IRC costs

International Rescue Committee – a cost analysis methodology

IRR

Income-Related Rent

IRRS

Income-Related Rent Subsidy

MoE

Ministry of Education

MoH

Ministry of Health

MoJ

Ministry of Justice

MSD

Ministry of Social Development

MVCOT

Ministry for Vulnerable Children, Oranga Tamariki

NGO

Non-Governmental Organisation

NNPAC

National Non-admitted Patient Collection

PFD

Publicly funded hospital discharges

POL

New Zealand Police

PRIMHD

Pronounced ‘primed’ - MoH mental health activity and outcomes data

PSM

Propensity Score Matching

PTCE

Person Time Cost Event

RCT

Randomised Control Trial

ROI

Return on Investment

S&R

Sentencing & Remands

SAS

Social Allocation System

SIAL

Social Investment Analytical Layer

SIU

Social Investment Unit

SME

Subject Matter Expert

SMS

Maryland Scientific Methods Scale

TA

Territorial Authority

TAS

Temporary Additional Support

UID

(Statistics NZ) Unique Identifier

W&S

Wages and Salaries

WIES

Weighted Inlier Equivalent Separations

YU

Youth Justice

Glossary

Area Under Curve (AUC)

Used in classification analysis to determine which of the used models predicts the classes best

Average Treatment Effect on the Treated group (ATT)

Measuring the Average Treatment Effect on the Treated, that is, the   difference in outcomes due to receiving treatment, corrected for all other confounding factors

Classification and   Regression Tree (CART)

Umbrella term for Classification and Regression Tree-based methods provide a more efficient way to search and discover variable interaction of interest. Classification tree analysis is when the predicted outcome is the class to which the data belongs

Cohort

A group of subjects who share a defining characteristic, typically subjects who experienced a common event within a selected time period

Collinearity (and   multi-collinearity)

A phenomenon in which two or more predictor variables in a multiple regression model are highly correlated, meaning one can be linearly predicted from the others with a substantial degree of accuracy

Counterfactual (group)

A second group for observing and comparing results to those expected if an intervention had not taken place

Covariates

Any of two or more random variables that are possibly predictive of the outcome under study

Decile

Any one of nine numbers that divide a frequency distribution into 10 classes, each containing the same number of individuals

Estimated Resident Population

An estimate of all people who usually live in New Zealand at a given date

Fiscal

Relating to the public treasury or revenues, or financial matters in general

Generalised Additive Model (GAM)

A flexible generalisation of ordinary linear regression allowing for response   variables that have error distribution models other than a normal distribution

Integrated   Data Infrastructure (IDI)

Large (Statistics NZ) research database containing microdata about people and households. Data is from a range of government agencies, Stats NZ surveys and non-governmental organisations

Liability

Monies owed; debts or pecuniary obligations as opposed to assets; liabilities as  detailed on a balance sheet, especially in relation to assets and capital

Logistic regression models

Used to build propensity scores; their wide use is due to the ease with which   models are trained and their high interpretability

Propensity score matching

Statistical matching technique estimating the probability of an individual receiving a treatment based on a set of identified characteristics

Randomised   Control Trial (RCT)

A study in which subjects are allocated by chance to receive one of several   clinical interventions. One of these interventions is the standard of comparison or control

Return   on Investment (ROI)

A ratio of net benefit to cost; the amount of return on an investment relative to the cost of the investment, expressed as a percentage

Segment

Group of people who share a common set of characteristics

Spine

Term given to IDI data once it has been linked at the individual level

WIES

Weighted Inlier Equivalent Separation (WIES) is a cost weight adjustment used by MoH for time spent in hospital.

Export PDF