Skip to main content

Table 5 Estimates of stealing counts-Google Trends search interest elasticities allowing for disposability dynamics and the influence of other market forces

From: Explaining offenders’ longitudinal product-specific target selection through changes in disposability, availability, and value: an open-source intelligence web-scraping approach

 

Log (Stealing counts) β

(1)

(2)

(3)

(4)

(5)

(6)

(7)

Log (Google trends)

0.886**

0.626**

0.575**

0.578**

0.591**

 − 0.080

 − 0.005

 

(0.279)

(0.212)

(0.215)

(0.215)

(0.187)

(0.067)

(0.039)

Log (Google trends) lag1

 

0.447***

0.327***

0.351**

0.348**

0.097

0.179*

  

(0.089)

(0.093)

(0.112)

(0.109)

(0.093)

(0.090)

Log (Google trends) lag2

  

0.221***

0.258***

0.284***

0.199*

0.314***

   

(0.059)

(0.062)

(0.067)

(0.096)

(0.058)

Log (Google trends) lag3

   

 − 0.072

 − 0.074

 − 0.105

 − 0.172

    

(0.016)

(0.169)

(0.132)

(0.184)

Log (Mean price)

    

 − 0.669**

 − 0.178

 − 0.138

     

(0.233)

(0.149)

(0.120)

Log (FA sales)

     

1.096***

0.291

      

(0.133)

(0.204)

Console fixed effects

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Time fixed effects

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Number of consoles

8

8

8

8

8

8

6

Number of observations

576

576

576

576

576

576

432

  1. *** p < 0.001 ** p < 0.01 * p < 0.05. Standard errors clustered by console code in parentheses. FA = faulty adjusted cumulative lifetime sales. Variables with the term ‘lagx’ indicate a time series variable where the values are lagged by x months. Β coefficients can be interpreted as a 1% change in the independent variable being associated with a Β% change in stealing counts. For example, in specification (1), a 1% change in Google trends values was associated with a 0.89% change in stealing counts
Back to article page

Crime Science

ISSN: 2193-7680

Contact us