1. My replication project

The paper identifies that a lack of utilising local level deprivation data may be a driving cause of the lack of evidence in social sciences that deprivation can cause an increase in right-wing hate crime. The argument of the researchers is that ignoring these local level characteristics excludes important factors such as feelings of community abandonment and the perception political institutions do nothing for individuals within a community setting; this in turn leads individuals into far-right thinking. Two main analyses are conducted by the researchers, the first is a comparison of the distribution of far-right hate crimes across the UK between 2015 and 2018 using deprivation as the primary variable , the second uses data between 2019-21 to show that local level deprivation is a better predictor of right-wing hate attacks than other relevant indicators.

This is a preregistration of an extension project for the following study:

Belgioioso, M., Dworschak, C., & Gleditsch, K. S. (2023). Local deprivation predicts right-wing hate crime in England. PLOS ONE, 18(9), e0289423.

In my replication project I am focusing on the following argument made in the study:

Table 1.
Table 1.

2. Planned project extention

2.1. Rationale for a new hypothesis

Research performed by King & Sutton explores the relationship between singular events and their importance on hate crime events in the US and found evidence that massive, public events can lead to increases in hate crimes(King D. & Sutton, 2013). Brexit was a widely publicised and highly contentious discussion in the UK both before and after the referendum and work by Devine has confirmed that Brexit ‘led to an increase in hate crimes of 19-23%’ (Devine, 2018, p. 1). I am going to test whether Brexit, as a major political event, had an impact on hate crime rates across the UK, and whether this impact was as significant as local deprivation indicators.

2.2. Prediction

Research by Carr, et al. found that ‘hate crimes increased more in Leave areas’ (Carr, et al., 2022), which indicates local political leanings have an impact on whether people commit hate crimes, so I predict that there may be a higher proportion of hate crimes occurring in areas with a higher proportion of Brexit voters.

Hypothesis:

Hypothesis: The proportion of individuals in a Local Authority District which voted to Leave the European Union will have have a significant impact on the hate crime rates in that area

Null hypothesis: Proportion of Leave voters has no impact on the hate crime rates

3. Data

I will use the same dataset used by the original researchers: Deprivation_2023_BDG_Replication.RData (Dworschak, 2023) https://doi.org/10.7910/DVN/GSRPQY

Which includes: Hate Crime Statistics – ‘recorded by the UK Police for 2015–2021, and provided by the Crime Analysis Unit of the Home Office following a Freedom of Information request by the authors (FOI 69240).’ (Belgioioso, et al., 2023, p. 4)

Living Environment Deprivation, Education Deprivation and Income Deprivation data from the English Indices of Deprivation 2015 File 5: scores for indices of deprivation (Ministry of Housing, Communities and Local Government, 2015) Accessible here as of 16/05/2024: https://www.gov.uk/government/statistics/english-indices-of-deprivation-2015 Other demographic and socio-economic covariates data from the 2011 UK Census Data (Office for National Statistics, 2012)

I will then add additional data of the EU Referendum results (The Electoral Commission, 2021) Accessible here as of 16/05/2024: https://www.data.gov.uk/dataset/be2f2aec-11d8-4bfe-9800-649e5b8ec044/eu-referendum-results

Datasets will be merged using Local Authority District (LAD) identifiers that are in all datasets.

4. Data analysis plan

4.1. Model specification

I will test the hypothesis using a random intercept multi-level model. This method will be best as my data is captured at 2 levels. Local Level Super Output Area (LSOA) for hate crime statistics, IoD and demographic data, and at Local Authority District (LAD) level for Brexit referendum results. The LSOA and LAD data are not independent of one another, as LSOA’s and nested within LAD’s. A multi-level model allows for regression analysis to be performed on both the individual (LSOA) and group (LAD) level, taking into account that the Brexit referendum data will not change between LSOA’s in a single LAD, but does change between LAD’s (Gorard, 2003). This model differs from the one used in Table 1 as that is a linear regression model, which will not treat LSOA’s as nested within LAD’s but as independent.

I will test the hypothesis using a different regression model applied in the ‘Local deprivation predicts right-wing hate crime in England.’ study.

The data analysis will be performed in steps: 1 - Presenting my replication of original model 2 - Creating a new model utilising hate crime and Brexit referendum data 3 - Combining both models

4.2. Variables

Dependent variable(s): • Logged number of hate crimes per 100k inhabitants – hcrimes.cleaned.p100k.ln

Independent variables (IVs):

• Income deprivation - Income.Score

• Living environment deprivation - Living.Environment.Score

• Education deprivation - Education.Score

• Neighbouring Income deprivation - Income.Score.splag1.mean

• Neighbouring Living environment deprivation - Living.Environment.Score.splag1.mean

• Neighbouring Education deprivation - Education.Score.splag1.mean

• Population size (logged) - ln_pop

• Population age - age_mean

• Unemployment Percentage - uneployment_longterm_perct

• Christian Religion Percentage - reli_christian

• Urban Population – urban

• Arab ethnicity percentage - ethn_arab_perct

• BAME percentage - ethn_bame_perct

For information on how original researchers obtained scores for the above variables, please refer to: Supplementary Appendix for “Local deprivation predicts right-wing hate crime in England https://doi.org/10.1371/journal.pone.0289423.s001 (Belgioioso, et al., 2023)

• Percentage of Leave Votes in the EU referendum - Pct_leave

Measured as a percentage of ballots cast to Leave the European Union out of all ballots cast in each Local Authority District in the 2016 European Union Referendum

4.3. Interference criteria

We will use the standard p<0.05 criteria for determining if the statistical tests suggest that the results are significantly different from those expected in the null hypothesis.

4.4. Data exclusion

EU referendum data for Scotland and Wales will be omitted from the dataset used for analysis as the original data used by the researchers does not inlcude data for Scotland and Wales. Outliers will be included in final analysis.

4.5. Missing data

Not applicable, dataset contains no missing data.

4.6. Exploratory data anlysis

I expect that deprivation score and the proportion of Brexit voters may be correlated. Therefore I will look for a relationship between the Income, Education and Living Environment deprivation and the proportion of Brexit voters in a LAD.

I expect that LSOA’s within a LAD will have similar hate crime rates, therefore I will explore random intercepts by visualsing them and calculating the intra-class correlation

5. Session info

This preregistration form was completed in the following R environment:

## R version 4.3.1 (2023-06-16 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 19045)
## 
## Matrix products: default
## 
## 
## locale:
## [1] LC_COLLATE=English_United Kingdom.utf8 
## [2] LC_CTYPE=English_United Kingdom.utf8   
## [3] LC_MONETARY=English_United Kingdom.utf8
## [4] LC_NUMERIC=C                           
## [5] LC_TIME=English_United Kingdom.utf8    
## 
## time zone: Europe/London
## tzcode source: internal
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## loaded via a namespace (and not attached):
##  [1] digest_0.6.33     R6_2.5.1          fastmap_1.1.1     xfun_0.43        
##  [5] cachem_1.0.8      knitr_1.46        htmltools_0.5.6   rmarkdown_2.26   
##  [9] cli_3.6.1         sass_0.4.7        jquerylib_0.1.4   compiler_4.3.1   
## [13] rstudioapi_0.16.0 tools_4.3.1       evaluate_0.22     bslib_0.5.1      
## [17] yaml_2.3.7        rlang_1.1.1       jsonlite_1.8.7

6. References

Bartlett J. (2021). OSF preregistration template.Rmd. GitHub (accessed 03/05/2023)

Bowman, S. D., DeHaven, A. C., Errington, T. M., Hardwicke, T. E., Mellor, D. T., Nosek, B. A., & Soderberg, C. K. (2020). OSF Prereg Template. https://doi.org/10.31222/osf.io/epgjd. OSF (accessed 03/05/2023)

Belgioioso, M., Dworschak, C. & GleditschI, K. S., 2023. Local deprivation predicts right-wing hate crime. PLOS ONE, 6 September.18(9). https://doi.org/10.1371/journal.pone.0289423

Belgioioso, M., Dworschak, C. & GleditschI, K. S., 2023. Local deprivation predicts right-wing hate crime PLOS ONE, 6 September.18(9). Supplementary Appendix for “Local deprivation predicts right-wing hate crime in England https://doi.org/10.1371/journal.pone.0289423.s001

Carr, J., Clifton-Sprigg, J., James, J. & Vujic, S., 2022. Love Thy Neighbour? Brexit and Hate Crime, Bonn: Institute of Labour Economics (IZA).

Devine, D., 2018. The UK Referendum on Membership of the European Union as a Trigger Event for Hate Crimes, Southhampton: SSRN.

Dworschak, C., 2023. Replication Data for: Local deprivation predicts right-wing hate crime in England, s.l.: Harvard Dataverse.

Gorard, S., 2003. What is Multi–level Modelling For?. British Journal of Educational Studies, 51(1), pp. 46-63.

King D., R. & Sutton, G. M., 2013. High Times for Hate Crimes: Explaining the Temporal Clustering of Hate-Motivated Offending. Criminology, 51(4), pp. 871-894.

Ministry of Housing, Communities and Local Government, 2015. English indices of deprivation 2015, London: Ministry of Housing, Communities and Local Government.

Office for National Statistics, 2012. Census in England and Wales, London: Office for National Statstics.

The Electoral Commission, 2021. EU Referendum Results, London: Greater London Authority.