Post on 03-Jan-2016
A Discrete-Time Hazard Duration Model of A Discrete-Time Hazard Duration Model of SME Business Establishment Survival in SME Business Establishment Survival in
the City of Hamilton, Ontariothe City of Hamilton, Ontario
By
Hanna MAOH and Pavlos KANAROGLOU
Association of American Geographers (AAG)
2005 Annual Meeting, Denver (April 5 – 9)
OutlineOutlineIntroduction
Research objectives
Study Area and Data
Exploring survival
Modeling business establishment failure
Conclusion & Acknowledgments
IntroductionIntroduction
Studying the evolution of Business establishments is important for the future of cities
Firm demography approach: concerned with studying processes that relate to: Establishment of new businesses Failure, migration, growth and decline of
existing businesses
Research ObjectivesResearch ObjectivesAdvance the current state of knowledge on firmographic processes in the urban context
Devise behavioral firmographic Decision Support System (DSS) to assess the inter-play between the local economy and Hamilton’s urban form
To compare and contrast the micro approach with the conventional macro-approach
The evolutionary process of business establishment population over time
Intra-urban mobile
establishments*
In-migrated establishments
Newly formedestablishments
Establishment population at
time t
Establishment population at
time t + 1
Out-migratedestablishments
Failed establishments
+ +
– –
* A growth/decline will be determined for stayer and intra-urban mobile establishments
Data: Business Register (BR)Data: Business Register (BR)BR retains information about all Canadian businesses at the business establishment level that goes back to 1990
Each business establishment has the following attributes: Establishment Number(EN), postal code address, paid workers, operating revenue, 4-digit 1980 Standard Industrial Classification (SIC) code, Standard Geographical Classification SGC code, and Street name and number
We make use of self-owned small and medium (SME) size establishments since the BR retains annual information about those businesses
Exploring SurvivalExploring Survival
We follow the life trajectory of 1990 and 1996 small and medium size establishments till 2002
We determine the duration of survival and time of failure
We explore variation in establishment survival by size, age, industry and geography
Non-parametric survival curves suggests that size, age, industry and geography has an influence on the survival rates
Survival and Hazard Rates, 1991 and 1996 SME cohorts Survival S(t) Hazard h(t)
Time t
1991 cohort
1996 cohort
1991 cohort
1996 cohort
[1-2) 0.84 0.85 0.17 0.17 [2-3) 0.73 0.74 0.14 0.14 [3-4) 0.65 0.67 0.11 0.10 [4-5) 0.59 0.62 0.09 0.07 [5-6) 0.54 0.58 0.09 0.07 [6-7) 0.49 0.54 0.10 0.07 [7-8) 0.45 0.09 [8-9) 0.42 0.06 [9-10) 0.40 0.05 [10-11) 0.38 0.06 [11-12) 0.36 0.05
Survival rates of the 1991 cohort by size class
Survival rates of the 1991 cohort by industrial class
Survival rates of the 1996 cohort by age class
Failure ModelFailure Model
We follow the life trajectory of 1996 SME cohort till 2002 to model the failure process via a discrete time hazard duration model:
Pit(f) = 1/(1 + exp(-t+ xit))
Firm specific variablesAge (+ve)Size (-ve) and Size-squaredGrowth (-ve)Relocation (-ve)
Macro economic variablesUnemployment rate (+ve)Average total income (-ve)
Geography specific variablesLocal Competition (+ve)Agglomeration economies (-ve)Location dummies
Industry specific variablesAverage size of industry (+ve)Industry dummies
Estimation ResultsEstimation ResultsFirm specific variables
– Young and small establishments are more susceptible to failure
– Growing establishments are more likely to remain in business– Relocation signals a superiority in performance either because
it is undertaken to expand or as a reaction to location stress
Geography specific variables– Market power (competition) has a positive influence on
failure– Market share (agglomeration) has a negative influence on
failure– Suburban establishments are less likely to fail compared to
those located in the core
Estimation ResultsEstimation ResultsMacro economic variables
– Economic downturn or low demand for services and goods lead to higher rates of failure
– High levels of demand for services and goods (purchase power) in the city decrease the propensity of failure
Industry specific variables
– Small establishments in large industries are more likely to fail
– Failure vary by industry (Health and Social Services have the lowest rates of failure; finance insurance services have the highest rates of failure)
ConclusionConclusionFirm, geography, macro-economy and industry specific factors can explain failure with firm and macro-economic being the most influential
The BR can be useful in developing agent-based firm demographic models
Extension of the modeling framework to study the failure by economic sector may have a value added
Firm specific model
Industry specific model
Geography Specific model
Macro-economy specific model
Full model
Pseudo R2 0.0710 0.0186 0.0154 0.0309 0.1003 % Explained Right 66.5 58.3 55.3 53.9 69.9
AcknowledgmentsAcknowledgmentsWe would like to thank Statistics Canada for supporting this research through their (2003 – 2004) Statistics Canada PhD Research Stipend program.
Thanks go to Dr. John Baldwin, Dr. Mark Brown and Mr. Desmond Beckstead from Statistics Canada for their useful discussions, input and assistance.
Thanks go to the Social Sciences and Humanities Research Council of Canada (SSHRC) for supporting this research through a Standard Research Grant and Postgraduate Scholarship