Confidence interval
Confidence intervals are indications of the natural variation that would be expected around a rate and they should be considered when assessing or interpreting a rate. The size of the confidence interval is dependent on the number of events occurring and the size of the population from which the events came. In general, rates based on small numbers of events and small populations are likely to have wider confidence intervals. Conversely, rates based on large populations are likely to have narrower confidence intervals. A 95% confidence interval means that we are 95% confident that the true value of the estimate lies within the range.
Count
The count is the number of deaths by suspected suicide that occurred over a particular period of time.
Crude rate
A crude rate is the number of deaths by suspected suicide occurring in a population over a specific time period, expressed as the number of deaths per 100,000 of the population. These rates were used as they are most suitable to inform action, which is one of the aims of the RTSSS.
Mean
The average number of deaths.
Rate
The rates in this report are crude rates (see above).
Regions
The three regions of North Wales, Mid and West Wales and South-East Wales are defined below and are consistent with the regional suicide prevention fora in Wales.
North Wales – Health board: Betsi Cadwaladr University Health Board. Local authorities: Isle of Anglesey, Gwynedd, Conwy, Denbighshire, Flintshire, Wrexham.
Mid and West Wales – Health boards: Hywel Dda University Health Board, Swansea Bay University Health Board, Powys Teaching Health Board. Local authorities: Carmarthenshire, Ceredigion, Pembrokeshire, Swansea, Neath Port Talbot, Powys.
South-East Wales – Health Boards: Aneurin Bevan University Health Board, Cwm Taf Morgannwg University Health Board, Cardiff & Vale University Health Board. Local authorities: Blaenau Gwent, Caerphilly, Monmouthshire, Newport, Torfaen, Bridgend, Merthyr Tydfil, Rhondda Cynon Taf, Cardiff, Vale of Glamorgan.
Standard deviation
A measure of the amount of variation of a set of values in relation to the mean.
Statistical significance
Statistical significance when comparing local area estimates to the all-Wales value was determined using 95% confidence intervals. The local area estimate is statistically significantly different if its confidence interval lies outside the Wales value. If the confidence interval overlaps with the Wales value then the difference is not statistically significant.
When comparing local area estimates with another local area estimate, age groups by sex, and deprivation fifths, non-overlapping confidence intervals between values indicate that the difference is unlikely to have arisen from random fluctuation (i.e. statistically significant). However, when the confidence intervals overlap, we cannot determine if there is a statistically significant difference or not by comparing confidence intervals alone, so a more exact test is required. The pairwise comparison looked at the difference between the rates and the 95% confidence intervals of the difference. When the confidence interval of the rate difference is above zero, the two rates are considered significantly different with 95% confidence.
Suspected suicide
A death by suspected suicide as reported here has been determined by the Police. The College of Policing have outlined the classification of suspected suicide and state that:
“..There is often a requirement for an initial judgment to be made on whether a case is potentially suicide. … Officers should use their professional judgment – based on all the known facts – and supported by the national decision model (NDM), to record whether a fatality is a suspected suicide. Witness accounts, CCTV material, the presence of a suicide note and other available evidence will help in this determination. The ‘Ovenstone criteria’ (Ovenstone, 1973) may be used as a tool to support decision making on whether a death was more likely to have been suicide than not. Any judgement made in the first instance must be reviewed as further information becomes available.”