FOI reference: FOI-2026-3565
You asked
Can you explain the full weighting process in 2023, 2024 and 2025 applied to unweighted figures in the following tables in Crime in England and Wales, Annual Supplementary tables - year ending March 2025, in such detail as I myself could try to replicate the process:
Table A11c: Prevalence of sexual assault and stalking in the last year among all people aged 16 to 59 years, by type [note 1, 2, 10]
Table A11b: Prevalence of sexual assault and stalking in the last year among women aged 16 to 59 years, by type [note 1, 2, 10]
Table A10b: Prevalence of sexual assault and stalking in the last year among people aged 16 years and over, by type and sex [note 1, 2, 3, 4]
Worksheet Table A8: Combined prevalence measure and estimated number of victims of combined measure of domestic abuse, sexual assault and stalking in the last year among people aged 16 years and over, by sex
Table A9b: Prevalence of domestic abuse in the last year among people aged 16 years and over, by abuse type and sex [note 1, 2, 3, 4]
Table A12: Prevalence of harassment experienced in the last year among people aged 16 and over, by type and sex [notes 1, 2]
And in brief terms, explain why the weighted figures reflect a decrease when the unweighted figures reflect an increase, in these tables in particular, between 2024 and 2025, for women. Police data and charity data show increases along with your raw data.
We said
Thank you for your request.
We are responsible for publishing crime statistics for England and Wales from two data sources: the Crime Survey for England and Wales (CSEW) and police recorded crime (PRC). The CSEW is a victimisation survey and asks sampled respondents about their experiences of crime.
As the CSEW is not asked to the whole population it is weighted to adjust for possible non-response bias to ensure the sample reflects the profile of the general population. The data presented in the tables listed, for example Table A8, show both the survey estimates and the unweighted bases. The unweighted base represents the number of people interviewed in the specified group. Changes in the unweighted bases reflect changes in the sample size each year. Data analysis should be conducted using the survey estimates, for example prevalence measures, and not the unweighted bases.
For further information on the Crime Survey please refer to our User Guide to Crime Statistics for England and Wales.