Structural Time Series Modelling of Crime Rates: the Case of Addis Ababa, Ethiopia

TABLE OF CONTENTS

LIST OF TABLES

LIST OF FIGURES

ABSTRACT

1. INTRODUCTION
1.1 Background
1.2 Statement of the Problem
1.3 Objective of the Study
1.4 Significance of the Study

2.LITERATURE REVIEW.
2.1 Background
2.2 Crime Definitions and Classifications
2.2.1 Personal/Violent Crimes
2.2.2 Property Crimes
2.3 Trend of Crime in Ethiopia
2.4 Factors or Causes of Crimes

3.METHODOLOGY
3.1 Description of Study Area
3.2 Data…
3.3 Variables used in this Study
3.3.1 Dependent Variables:
3.3.2 Independent Variables
3.4 Statistical Models
3.4.1 Regression Analysis
3.4.2 Intervention Component Analysis
3.4.3 Structural Time Series Models
3.4.4 Parameters Estimation
3.5 Diagnostic and Goodness of Fit Tests for STS Model
3.5.1 Diagnostic Tests
3.5.2 Goodness of Fit Measures

4.RESULTS AND DISCUSSION
4.1 Descriptive Statistics
4.2 Intervention Analysis Using Regression Model
4.3 STS Intervention Analysis Result
4.4 Parameter Estimation of State Space Model
4.5 Checking Adequacy of the Fitted Model
4.6 Prediction of Crime Rates by Using State Space Model Using the Final Models
4.7 Forecasting of Crime Rates by State Space Models Using the Final Models
4.8 Discussion

5.CONCLUSIONS AND RECOMMENDATIONS
5.1 Conclusions.
5.2 Recommendations
5.3 Limitations of the Study

6. REFERENCES

7. APPENDICES

8. BIOGRAPHY

LIST OF ABBREVIATIONS

illustration not visible in this excerpt

LIST OF TABLES

Table 1: Summary Results for Monthly Crime Rates under Study (Addis Ababa, 2002-2012)

Table 2: Descriptive Statistics for Monthly Explanatory Variables (Addis Ababa, 2002-2012)

Table 3: ML Parameter Estimates of the State Space Models for Murder

Table 4: ML Parameter Estimates of the State Space Models for Aggravated Assault

Table 5: ML Parameter Estimates of the State Space Models for Rape

Table 7: ML Parameter Estimates of the State Space Models for Burglary

Table 8: ML Parameter Estimates of the State Space Models for Larceny

LIST OF FIGURES

Figure 1: Crime Rates for Property: Burglary and Larceny.

Figure 2: Crime Rates for Violent: Murder, Aggravated Assault, Rape and Robbery.

Figure 3: Mean Changes in the Property Crime Rates: Burglary and Larceny.

Figure 4: Mean Changes in the Violent Crime Rates: Murder, Aggravated Assault, Rape and Robbery.

Figure 5: Data and Estimated Trends for Property Crime Rates (Burglary and Larceny) using structural time series models.

Figure 6: Data and estimated trends for violent crime rates (Murder, Aggravated Assault, Rape and Robbery) using structural time series models.

Figure 8: Trend and Seasonal Components in Property Crime Rates for Burglary and Larceny

Figure 9: Trend and Seasonal Components in Violent Crime Rates for Aggravated Assault, Murder, Rape and Robbery

Figure 10: Prediction and Actual Series for both Property and Violent Crime

Figure 11: Forecast of Crime Rate for both property and violent crimes

LIST OF TABLES AND FIGURES IN APPENDICES

Appendix I: Results of Estimated Interventions

Table A₁: Estimated Interventions for a Regression Models

Table A₂: Estimated Interventions of LL and LLT Model for Property Crimes and Robbery

Table A₃: Estimated Interventions of Structural Time Series Models for Violent Crimes

Table A₄: Estimated Interventions of LL and LLT Model for Property Crimes and Robbery

Table A₅: Estimated Interventions of LL and LLT Model for Violent Crimes

Table A₆: Estimated Interventions of LL and LLT Model for Property Crimes and Robbery

Table A₇: Estimated Interventions of LL and LLT Model for Violent Crimes

Table A_8:Result of Seasonal Effect Using State Space for the Fitted Model

Appendix II: Results for Normality Test of Residuals for the Fitted Model

Figure A₁: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Murder

Figure A₂: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Murder

Figure A₃: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Aggravated Assault

Figure A₄: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Aggravated Assault

Figure A₅: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Rape

Figure A₆: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Rape

Figure A₇: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Robbery

Figure A₈: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Robbery

Figure A₉: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Burglary

Figure A₁₀: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Burglary

Figure A₁₁: Density Plot of Residuals and Diagnostic Test for Normality of Irregular Residuals from Fitted Model for Larceny

Figure A₁₂: Density Plot of Residuals and Diagnostic Test for Normality of Level Residuals from Fitted Model for Larceny

Figure A₁₃: Density Plot of Residuals and Diagnostic Test for Normality of Slope Residuals from Fitted Model for Larceny88

Table A₉: H-Statistics, Portmanteau Box-Ljung - Ttest and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Murder. 89

Table A₁₀: H-Statistics, Portmanteau Box-Ljung - Test and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Aggravated Assault.

Table A₁₁: H-Statistics, Portmanteau Box-Ljung - Test and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Rape.

Table A₁₂: H-Statistics, Portmanteau Box-Ljung - Test and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Robbery.

Table A₁₃: H-Statistics, Portmanteau Box-Ljung - Test and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Burglary.

Table A₁₄: H-Statistics, Portmanteau Box-Ljung - Test and DW Diagnostic Test Results for Standardized Residuals from State Space Model for Larceny.

Table A_15: - ,and - Goodness of Fit Test Result for the Fitted Model from State Space Model for all Crime Rates.

Appendix III: Results for Adequacy Checking of Fitted Model

Appendix IV: Forecasted of Crime Rates by State Space Models for the Fitted Model

Table A₁₆: Forecast of Crime Rate of Murder for Period 2011(12) Forwards.

Table A₁₇: Forecast of Crime Rate of Aggravated Assault for Period 2011(12) Forwards.

Table A₁₈: Forecast of Crime Rate of Rape for Period 2011(12) Forwards.

Table A₁₉: Forecast of Crime Rate of Robbery for Period 2011(12) Forwards.

Table A₂₀: Forecast of Crime Rate of Burglary for Period 2011(12) Forwards.

Table A₂₁: Forecast of Crime Rate of Larceny for Period 2011(12) Forwards.

ABSTRACT

The basic goal of this study was to model monthly crime rates and the impact of sentence reforms on reported crime in Addis Ababa, Ethiopia, over the study period of April 2002 to January 2012 GC by incorporating intervention effects. Monthly data obtained from Addis Ababa Police Commission for a total of 118 months were used. The impact of this legislation on reported crime rates was examined using OLS regression model and time series approaches. In particular, structural time series models were employed for the intervention analysis. The best fitted models were selected based on the model capturing the variations in the data accessed through - , AIC and BIC. Comparisons of the selected model were carried out based on ability of prediction via predictive error variance. Both the local level and local linear trend models with inclusion of seasonal and cyclical effects was found to be the best fitted model for modelling of both property and violent crimes, such as murder, aggravated assault, rape, robbery, burglary and larceny. The result of the analysis shows that the coefficient of intervention was negative to rate of murder, robbery, rape and larceny but it was significant only for larceny. The effect of macroeconomic variables such as food inflation, non-food inflation, general inflation and unemployment were statistically significant for aggravated assault. It is recommended that the government and the concerned body should take some measures to tackle inflation and unemployment issues in the city. The rates of crimereported in the violent and property crimes contained seasonality. Thus, prevention mechanisms based on seasonals need to designed.

Keywords: Policy Intervention, Sentence Reforms, Regression Models, Structural Time Series Models.

1. INTRODUCTION

1.1 Background

Human beings need to live and work in a place where they are safe. They want to ensure that there is a concerned body that protects their lives as well as their properties from potential hazards. In fact, one of the main functions of any government is to ensure that law and order for the security of its citizens are put in place (Wilson, 1963). In other words, far from formulation and enactment of laws for the prevention of crime, governments must establish agencies and organizations which enforce these laws.

But a criminal and violent behavior has become a major concern in recent years across the world. More and more researches are being conducted in various parts of the world; however these are hampered by unavailability and inconsistency of crime data. The relationship of crime with macroeconomic variables is very much of interest to policy makers. Crime is a global phenomenon, whereby, most nations and their citizens are griped with fear due to the rising statistics of criminal activities (UNODC, 2010).

Crimes result not only in the loss of property, lives and misery, but also cause severe mental anguish. In developed world, Imrohoroglu et al. (2006) mentioned that according to the United Nations Inter regional Crime and Justice and Justice Research Institute, people victimized by property crime (as a % of the total population) varied between 14.8% in New Zealand to 12.7% in Italy, 12.2% in U.K, 10.0% in U.S, and 3.4% in Japan.

The impact of crime on an economy can be segregated into, primarily the prevention cost, secondarily the correctional cost and the lost opportunity of labor being held in correctional facility. Costs acquainted with crime preventions are private investment for crime prevention, gadgets (i.e anti theft and anti burglary equipments), government expenditures (i.e campaigns and education on safe society) and police personnel expenditure. The correctional cost refers to cost such as correction facilities cost and prison personnel, while the lost opportunity refers to the loss of potential labor contribution due to being in correction facilities.

The possible explanations of crime for cross country differences are many, ranging from distinct definitions of crimes and different reporting rates (percentage of the total number of crimes actually reported to the police), to real differences in the incidence of crime and even to different cultural aspects. It can even be contributed to democracy as explained by Lin (2007), whereby, compared to non democratic governments, democratic government punish major (minor) crime more (less) and hence, this crime rate is lower (higher).

No matter how one looks at it, crime is still an utmost important subject due to its large impact on economical aspect as well as psychological aspect. Its pernicious effects on economic activities and more generally on the quality of life of people contribute to the emerging fact that crime is merging as a priority in policy agendas worldwide. Due to the complexity of the phenomenon and lack of consensus among policy makers or scholars, research on this issue continues to be conducted in many areas.

Accordingly, in many countries, if not all, there are organizations such as courts, prosecutions and police, which are responsible for the maintenance of law and order.

In Ethiopia, the police organization was established in 1942 under proclamation No. 6 as an autonomous institution with the responsibility of preventing and investigating crime incidents. In 1966, the police institution was put under the Ministry of Emperor. Since its establishment, the police organization structure has been extended to the lower administration level, at “woreda” and sometimes at “kebele” (Mesfin, 1999).

Due to the new constitution adopted in 1994, the Ethiopian government has been exercising federal political system and hence both the structure and authority of the police is changed accordingly. Based on the Proclamation No. 1 Article 50, federal and regional governments are duly responsible to establish all the necessary administrative levels in their respective areas. In light with this political sphere, federal states established their own police institutions at a level of commission. As a result, Addis Ababa Police Commission has become responsible to maintain law and order together with other concerned agencies (Mesfin, 1999).

It is nearly half a century since the 1957, Ethiopian Penal Code entered into operation. During this period, radical political, economic and social changes have taken place in Ethiopia. Among the major changes are the recognition by the constitution and international agreements ratified by Ethiopia of the equality between religions, nations, nationalities and peoples, the democratic rights and freedoms of citizens and residents, human rights, and most of all, the rights of social groups like women and children. After all, these phenomena have taken place, it would be inappropriate to allow the continuance of the enforcement of the 1949 Penal Code (Federal Police Commission, 1996).

Another discernible gap, in the Penal Code, is its failure to properly address crimes born of advances in technology and the complexities of modern life. The Penal Code does not incorporate crimes such as the hijacking of aircraft, computer crimes and money laundering. know a day’s crimes related to corruption and drugs attracting attention both in the legislation and follow-up, not only within national frontiers but also on the regional and international levels, due to the grave crises they are causing. Hence, these was the problems with the panel code not to adequately deal with such crimes on degree of seriousness they deserves (Federal Police Commission, 2003).

Another point that should not be overlooked is the Penal Code's failure to acknowledge the grave injuries and sufferings caused to women and children by reason of harmful traditional practices. Surely, the constitution guarantees respect for the cultures of peoples, but it does not buttress up those practices scientifically proven to be harmful. It is also futile to issue a law that does not have the trust and support of the people for it usually remains impracticable. But it is well recognized in the philosophy of criminal legislation that the legislature should, by adopting progressive laws at times, educate and guide the public to dissociate itself from harmful traditional practices (Federal Police Commission, 2003).

In order to eliminate the above-mentioned shortcomings the Criminal Code of the Federal Democratic Republic of Ethiopia adopts a comprehensive Criminal Code. This Criminal Code as published in a separate volume of the Federal Negarit Gazeta under Proclamation No. 414/2004 has come into force as of the - of May 2005. Substantial such activities have been undertaken throughout the entire country. It aims at the prevention of crimes by giving due notice of the crimes, penalties prescribed by law, should this be ineffective by providing for the punishment of criminals in order to deter them from committing another crime and make them a lesson to others, or by providing for their reform and measures to prevent the commission of further crimes. It is mainly on the basis of public opinion that punishments have increased in respect of crimes like rape and aggravated theft.

Moreover, the opinions of legal scholars and the laws and experiences of foreign countries have been consulted to enrich the content of the Criminal Code and concerning the determination of sentence, essentially to facilitate the method by which Courts can pass similar punishments on similar cases and some major changes have been made in the provisions of the code. A sentencing manual has been issued to ensure and control the correctness and uniformity of sentencing. In connection with the determination of sentence, the purpose of Criminal Law is to preserve the peace and security of society and protects society by preventing the commission of crimes, and a major means of preventing the commission of crime is punishment (Federal Police Commission, 2003).

Punishment can deter wrongdoers from committing other crimes; it can also serve as a warning to prospective wrongdoers. Although imprisonment and death are enforced in respect of certain crimes, the main objective is temporarily or permanently to prevent wrongdoers from committing further crimes against society. And in such cases, with the exception of the death sentence, even criminals sentenced to life imprisonment can be released on parole before serving the whole term; in certain crimes convicts can be released on probation without the pronouncement of sentence or without the enforcement of the sentence pronounced. This helps wrongdoers to lead a peaceful life and it indicates the major place which the criminal Law has allocated for their rehabilitation (Ehrlich, 1996).

The fact that wrongdoers, instead of being made to suffer while in prison, take vocational training and participate in academic education which would benefit them upon their release, reaffirms the great concern envisaged by the Criminal Code about the reform of criminals.

Crime reduction is high on the public policy agenda, not the least because of the large economic and social benefits it brings (Cook and Zarkin, 1985). Indeed, research on the determinants of crime points in several directions as to how crime reduction can be facilitated.

For example, a relatively large body of research undertaken by social scientists considers the potential for expenditures on crime fighting resources (like increased police presence, or new crime fighting technologies), or on particular policies, to combat crime. Other work focuses more on the characteristics of criminals and considers what characteristics are more connected to higher criminal participation. In this latter case, policies that affect these characteristics can, if implemented successfully, be used to counter crime.

This study has been directed to focus on characteristic that has received some attention in the quantitative literature on the determinants of crime namely, unemployment, food inflation, non-food inflation and general inflation have been included and discussed in more detail the crime situation in Addis Ababa and its recent changes and developments in the sentence systems. Advanced time series methodologies for intervention analysis will be considered. Additionally, this study would provide a plan and details of empirical intervention study, in particular, using descriptive approaches.

Empirical results of this investigation on the effect of sentence reform for the crime rates in Addis Ababa, using regression and structural time series methods have been presented comparison of different methodological approaches to intervention analysis have been used.

1.2 Statement of the Problem

Crime is a complex social phenomenon and its cost is increasing due to a number of societal changes and the like. To curb this social evil, there is always a need for prudent crime prevention strategies and policies. Policy changes that increase the expected punishment per crime can lead to both greater deterrence and greater incapacitation (Kessler and Levitt, 1999). It is desirable to adopt a comprehensive code by assembling the various criminal provisions and evaluate the sentence reforms so that police can take crime prevention measures accordingly.

Through understanding factors affecting crime rates and digesting criminal records, police can extract crime patterns that could be invaluable in the process of crime prevention. According to the Megaputer Intelligence (2002), law enforcement agencies, in this case police and other government organizations, can benefit from crime pattern analysis by obtaining improved crime resolution rate based on dynamically changing crime patterns, and better crime prediction as well as prevention of offences. Determining the major factors that may affect crime rates is important to design better strategy and policy improves the prevention of crimes. But has Structural time series model is a powerful statistical method in criminology, have been very scarcely used in this country.

Structural time series models are formulated directly in terms of components of interest which have a direct interpretation and allow for time-varying parameters. So, this study is intended to time series analysis of crime rates. Accordingly, the central research question of this study is whether policy intervention (sentence reforms) affects the tragedy of series of crimes and determines the major factors of crime rates in Addis Ababa.

1.3 Objective of the Study

- General Objective :

The general objective of this study was to assess crime rate pattern and identify its determinants in Addis Ababa using structural time series models.

- Specific Objectives:

- To develop models for intervention analysis of crime rates.
- To identify whether intervention had any impacts on the crime rates.
- To determine whether unemployment and inflation had effect on crime rates.
- To forecast crime rates in Addis Ababa based on unemployment and inflation rates.
- To provide scientific information for researchers and policy makers.

1.4 Significance of the Study

This study attempted to extract crime patterns as related to criminal attributes and hence police officials can make use of these results in their day to day battle against crimes. Police officials in the crime prevention and intervention authority can make use of the results of this study in providing information on variables correlated with crime prevention. Moreover, the output of the study can be used for evaluating the effect of sentence reforms on crimes. The output of the study can also be used as a benchmark for police officials and further researchers. Furthermore, the result of this study;

- Can be used as a source of information to other researchers for further investigations to identify the pattern of crime rates and its determinants.
- Can be used as source of methodological approach for studies dealing on the intervention analysis on crime rates as well as other similar areas.

2. LITERATURE REVIEW

2.1 Background

According to Andargachew (1988), a criminal is an individual person who has violated the legally forbidden act. In fact, there are some factors that have to be taken into account to convict whether a person should be considered as a criminal or not. Among these, an individual should be of competent age in light with the law of the land; and there must be a well-predefined punishment for the particular act committed.

Sutherland and Cressey, cited in (Andargachew, 1988), stated that an act would be considered as a crime when it is prohibited by the criminal law. Criminal law, on the other hand, refers to a body of specific rules regarding human conduct, which have been explicitly stated by political authority.

Crime has increasingly become as complex as human nature. Modern technological advancement and tremendous progress in communication have facilitated criminals of every corner of the world to commit a crime using sophisticated equipment in one place and then escape to another place (Thakur, 2003). These days the globe is facing the proliferation of problems such as illicit drug trafficking, smuggling, hijacking, kidnapping and terrorism. Crime has adversely affected the societies of both civilized as well as developing countries by declining the quality of life, endangering human right, fundamental freedom and posing a serious challenge to the community. Although the level and intensity of the problem might vary from nation to nation, no country has remained unaffected.

2.2 Crime Definitions and Classifications

Even if different criminologists define crime in different words, Thakur (2003) has defined crime as an act or omission of an act, which is punishable by law. However, an act that is considered as a crime in one place and time may not be true in another place or time. Crime is classified in to two broad categories as: personal/violent crime and property crime.

2.2.1 Personal/Violent Crimes

A violent crime is any criminal offense which involves the use of, or even the threat of force or violence and it has a broad legal category that encompasses a number of criminal offences:

- Murder: Killing a human in a willful and non-negligent manner.
- Aggravated Assault: Unlawfully attacking another person to inflict severe or aggravated bodily injury, usually accompanied by the use of a weapon or by other means likely to produce death or grave bodily harm. Attempted aggravated assault that involves the use or threat of use of a gun, knife or other weapon is included in this crime category because serious personal injury likely would result.
- Forcible rape: The carnal knowledge of a female forcibly and against her will. UCR includes assaults and attempts to commit rape by force or threat of force but excludes statutory rape (without force) and other sex offenses. UCR collects data only on the rape of women.
- Robbery: Taking or attempting to take anything of value from a person by force or threat of force or violence.

2.2.2 Property Crimes

Includes those offences involving the loss of property during which there is no use of violence by the perpetrators. There are seven types of crimes in this category such as;

- Arson: Willfully or maliciously burning or attempting to burn, with or without intent to defraud, a house, public building, motor vehicle, aircraft or personal property.
- Burglary: Unlawfully entering a structure to commit a felony or theft. Forcible entry need not have occurred.
- Larceny-theft: Unlawfully taking property from another (e.g., stealing, shoplifting, pick pocketing) without force, violence or fraud. Attempted larcenies are included.
- Motor vehicle theft: The theft or attempted theft of a motor vehicle.

2.3 Trend of Crime in Ethiopia

In Ethiopia, crime statistics has shown that the rate of crime is increasing steadily. A sample survey conducted in the year 1996 by a research team of the Federal Police has shown that in 1986 about 51,869 crimes were reported to the police (Federal Police Commission, 1996). Taking the total population of the country during this period, this figure indicated that one crime was committed among 800 people during this year. The research report has shown that in the year 1994 about 96,995 different crimes were reported. This reveals that during this period one crime is committed among 568 people. As compared to the year 1986, the total number of crimes committed in 1994 have shown an increment.

The national crime statistics report compiled by the Federal Police Commission in 2003 has shown that about 219,539 crimes were reported to police throughout the country in 2002 and out of this 51 percent have committed in urban areas while the remaining 49 percent were occurred in rural areas (CSA, 2005).

2.4 Factors or Causes of Crimes

Even if the cause of crime is more complex, much criminological research involves trying to determine whether a particular factor increases the risk of involvement in crime when other possible risk factors are controlled (i.e. held constant). Of course, the discovery of a statistical association between some factors and crime never provides any guarantee that the factor in question causes crime, even when attempts have been made to control for other relevant factors. However, there are some factors which may be responsible for the growing rate of crime such as unemployment, economic backwardness, over population, illiteracy and inadequate equipment of the police force (Thakur, 2003). The form, seriousness and size of a crime may rely on the form of a society and, thus, its nature changes with the growth and development of the social system (Ibid ).

Every generation, has its own most critical, new and special problems of crime, although the crime problem is as old as man himself. In addition to this, the techniques employed to commit crime are changing in the sense that they make use of modern knowledge and technique. The rise in crime both national and transnational is generally thought to be the result of interplay between socio-economic changes.

The circumstances surrounding the individual offender such as his personality, physical characteristics, intelligence, family background, environmental surrounding such as peer groups and neighbors have been subject of the study of crime (Andargachew, 1988). Hence, understanding the attributes of criminals will be helpful to design and implement prudent crime prevention strategies.

Agencies and other related organizations are responsible to curb the rate and occurrence of crimes. To do so, crime prevention agencies need to issue and implement crime prevention strategies. Theoretically, it is argued that crime prevention is better than cure for the following reasons (Thakur, 2003):

- Prevention safeguards the life and property of the society whom the police are in duty to protect.
- It avoids a good deal of trouble to the victim both physical and mental.
- Crime prevention rules out litigation, which follows in the process of detecting a crime.
- Prevention also saves the police from the trouble of recording crime at all odd hours of the day and night and of taking immediate action for the investigation.

Thakur (2003) suggested that intent and opportunity are two major factors that lead to the occurrence of a crime. An individual cannot commit a crime unless and otherwise s/he gets an opportunity even though s/he is intended to commit a crime. Therefore, the best strategy for crime prevention is to provide a system that denies any opportunity for a criminal to commit a crime.

According to Megaputer Intelligence (2002), the analysis of crime patterns and trends is very important for police officers and analysts can learn from historical crime patterns and enhance crime resolution rate. It also helps to prevent future incidents by putting in place preventive mechanisms based on observed patterns. Another possible advantage is, it can reduce the training time for officers assigned to a new location and having no prior knowledge of site-specific patterns to assist them in investigations. In light with the crime patterns extracted from previous records, police can deploy scarce resources to the right place at the right time.

Madden and Chiu (1998) mentioned that it seems reasonable to expect that the level of property crime will be influenced in some way by the distribution of income (and wealth) while Teles (2004) reiterated that monetary and fiscal policies have impacts on crime. There are a large number of studies linking income inequality to crime such as Fajnzylber et al. (2002a, 2002b), Chisholm and Choe (2005), Imrohoroglu et al. (2006), Choe (2008), Lorenzo and Sandra (2008), Magnus and Matz (2008), to name a few.

Lu Han (2009) tested broadly concerned unemployment and crime relationship using annual time series data in England and Wales over the period 1971-2000. Accordingly, cointegration analysis approach and error correction model (ECM) were used to cope with the non-stationary variables. He found that, in the long-run, the overall and individual property crimes are cointegrated with unemployment as well as law enforcement instruments. Particularly, unemployment rate has positive cointegration with overall crime, burglary and theft, indicating that, for such crimes, the motivation effect is stronger than the opportunity effect.

Increased unemployment rate would reduce the opportunity cost of committing crimes, as argued in Ehrlich (1996), and motivate potential offenders to engage in illegal activities. Such effect could offset the impact that higher unemployment would reduce the potential opportunities for property crimes.

Using the VAR modelling approach, Saridakis (2004) concludes that unemployment plays a marginal role in violent crime in the US, while income inequality has a significant positive effect on murder. Cappell and Sykes (1991) use US data from 1933 to 1985 to examine the relationship between crime, unemployment, and imprisonment using ARIMA time-series approach. They estimate a simultaneous-equation model, where crime and imprisonment are treated as endogenous variables, and conclude that both the contemporaneous and lagged values of unemployment exhibit modest positive effect on crime.

On the other hand, Arvanites and Defina concluded that there are no significant effects of unemployment rates on state crime rates (as cited in Rosentfeld and Fomango, 2007). Part of the reason why there is no significant effect of unemployment rates on crime rates is that there are also opportunity and motivation effects on crime. For example, opportunity reduces crime even when unemployment rates are high by reducing target attractiveness and by increasing guardianship (Cohen and Felson (1979) as cited in Rosentfeld and Fomango, 2007). Also, motivation effects are reflected in increasing crime when unemployment blocks access to legitimate income production opportunities (Cloward and Ohlin (1975) as cited in Rosentfeld and Fomango, 2007).

On the other hand, Britt (1997) only finds support for the criminal motivation effect. Controlling for the variation in the unemployment crime relationship by age group and over time, he concludes that unemployment has a greater motivational effect on property crime among young adults. A time-varying unemployment crime relationship is only weekly supported. Ralston (1999) investigates economic determinants of property crime rates in the United States from 1958 to 1995. He uses inflation and unemployment (structural, cyclical, and frictional) as economic factors that predict property crime rates. Controlling for police and race (black/white) confounders, he concludes that changes in inflation, as well as changes in rates of cyclical and frictional unemployment are important predictors of property crime rates.

[...]