Residents-class indicators describe different aspects of the long-term (weekly, monthly or seasonal) variation in the number of people whose home location is within an area of interest.
You can read more about our methods for assigning home locations here.
Arrived residents
The arrived residents indicator estimates the number of people who relocated (i.e changed their home location) into an area during a given period of time. The units of this indicator are numbers of people.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to understand the variation in the number of residents in an area over time and what drives these changes (i.e. is a change in the number of residents due to a change in the numbers of people relocating into an area). This indicator does not however capture international migration.
- Calculation
-
We calculate the arrived indicator using the home relocations aggregate.
For a given area, we estimate the number of subscribers relocating into the area as the sum of the unredacted counts of the number of subscribers whose home location changed from another area to the area of interest.
- Adjustment
-
We adjust the estimated number of subscribers relocating into an area with respect to the changes in the number of active subscribers in the area of interest. The adjustment factor is calculated as the median number of subscribers who continue to be observed residing in the area between time steps during the reference period divided by the number of subscribers who are observed to continue to reside in the area during the period of interest.
We can also convert the indicator from the number of subscribers to the number of people arriving into an area using a static population figure, such as that produced by a census. We may also adjust the indicator for representation biases based on mobility errors estimated from survey data.
Departed residents
The departed residents indicator estimates the number of people who relocated (moved home) out of an area during a given period of time. The units of this indicator are numbers of people.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to understand the variation in the number of residents in an area over time and what drives these changes (i.e. is a change in the number of residents due to a change in the numbers of people relocating out of an area). This indicator does not however capture international migration.
- Calculation
-
We calculate the departed indicator using the home relocations aggregate.
For a given area, we estimate the number of people relocating out of the area as the sum of the unredacted counts of subscribers whose home location changes from the area of interest to another area.
- Adjustment
-
We adjust the estimated number of subscribers relocating out of an area with respect to the changes in the number of active subscribers in the area of interest. The adjustment factor is calculated as the median number of subscribers who continue to be observed residing in the area between time steps during the reference period divided by the number of subscribers who continued to be observed residing in the area during the period of interest.
We can also convert the indicator from the number of subscribers to the number of people departing from an area using a static population figure, such as that produced by a census. We may also adjust the indicator for representation biases based on mobility errors estimated from survey data.
Net inflow
The net inflow residents indicator estimates the difference between number of people relocating into (arrived residents) and out of (departed residents) an area during a given period of time. The units of this indicator are numbers of people.
If more people relocate into the area than out, the indicator will have a positive value; if more people relocate out of the area, the value will be negative.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to describe the net change in the number of people residing in an area during a given time period, due to internal migration. This indicator does not however capture international migration.
- Calculation
-
We calculate the net inflow indicator from the arrived and departed indicators which are derived from the home relocations aggregate as described above.
We estimate the difference between the number of people relocating into and out of the area by subtracting the departed indicator from the arrived indicator.
- Adjustment
-
We adjust the arrived and departed residents indicators with respect to the number of active subscribers in the area of interest as described above. These adjusted values are used to calculate the net inflow indicator.
We can also convert the indicator for the net number of subscribers to the net number of people arriving into an area using a static population figure, such as that produced by a census. We may also adjust the indicator for representation biases based on mobility errors estimated from survey data.
Residents
The residents indicator estimates the number of people residing in an area during a given period of time. The units of this indicator are numbers of people.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to monitor the variation in the number of people residing in an area over time.
- Calculation
-
We calculate the residents indicator using the home relocations aggregate and the baseline number of residents in the area during a reference period. The baseline can be calculated using the residents aggregate, for example by calculating the median number of residents during the reference period. We advise against directly estimating the number of residents outside of the reference period from the residents aggregate as this may be more influenced by variation in the number of active subscribers than by subscriber mobility.
We use the unredacted home relocations aggregate to derive the net change in the number of subscribers residing in the area, as described for the net inflow indicator, for each timestep between the baseline period and the period of interest.
The cumulative sum of the change in the number of subscribers between the baseline period and period of interest gives us the total change in the number of subscribers residing in an area. By adding the cumulative net change in the baseline number of residents during the reference period we can estimate the number of people residing in the given area in the given time period.
- Adjustment
-
As described above, when estimating the change in the number of resident subscribers in a given area, we adjust the number of relocations into and out of the area with respect to change in the number of active subscribers in the area of interest.
We can also convert the indicator from the number of resident subscribers to the number of resident people in an area using a static population figure, such as that produced by a census. We may also adjust the indicator for representation biases based on mobility errors estimated from survey data.
Residents per square kilometre
The residents per square kilometre indicator estimates the average number of people residing in an area per square kilometre during a given period of time. The units of this indicator are numbers of people per square kilometre.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to monitor the variation in the resident population density of an area over time.
- Calculation
-
We estimate the number of residents in a given area using the home relocations aggregate and the baseline number of residents in the area as described above.
We then divide this by the size of the given area, in square kilometres, to derive the number of residents per square kilometre.
- Adjustments
-
As described above, when estimating the change in the number of residents in a given area, we adjust the number of relocations into and out of the area with respect to change in the number of active subscribers in the area of interest.
We can also convert the indicator for the density of resident subscribers per square km to the density of residents in an area using a static population figure, such as that produced by a census.
Similarly, we may adjust the residents per square kilometre indicator for representation biases based on mobility errors estimated from survey data.
Residents difference
The residents difference indicator estimates the difference in number of residents between a given time period and a reference period. This difference is expressed in terms of numbers of people. If the number of residents has increased, the indicator will have a positive value; if the number has decreased, the value will be negative.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to determine the change in the number of residents in a given area over time.
- Calculation
-
We calculate the residents difference indicator using the home relocations aggregate. We advise against directly estimating the change in the number of residents from the residents aggregate as this may be more influenced by variation in the number of active subscribers than by subscriber mobility.
We use the (unredacted) home relocations aggregate to derive the number of subscribers residing in the area (as described above). We subtract the baseline number of residents for the reference period to calculate the change in the number of residents.
- Adjustment
-
As described above, when estimating the change in the number of resident subscribers in a given area, we adjust the number of relocations into and out of the area with respect to change in the number of active subscribers in the area of interest.
We can also convert the indicator for the change in the number of resident subscribers to the change in the number of residents in an area using a static population figure, such as that produced by a census. Similarly, we may adjust the residents per square kilometre indicator for representation biases based on mobility errors estimated from survey data.
Percent change in residents difference:
The percentage change in residents indicator estimates the change in number of residents between this month and a reference period, relative to the number of residents in the reference period. This difference is expressed as a percentage of a baseline value calculated for the reference period. If the number of residents have increased, the indicator will have a positive value; if the number has decreased, the value will be negative.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator can be used to determine the change in the number of residents in a given area relative to the number of residents during a reference period.
- Calculation
-
We calculate the percentage change in residents indicator using the home relocations aggregate and the baseline number of residents in the area during a reference period. The baseline can be calculated using the residents aggregate, for example by calculating the median number of residents during the reference period. We advise against directly estimating the number of residents outside of the reference period from the residents aggregate as this may be more influenced by variation in the number of active subscribers than by subscriber mobility.
We estimate the difference in the number of residents relative to the baseline as described above. We divide this difference by the baseline number of residents in the reference period and multiply by 100 to derive the percentage change.
- Adjustment
-
As described above, when estimating the change in the number of residents in a given area, we adjust the number of relocations into and out of the area with respect to change in the number of active subscribers in the area of interest.
We can also convert the indicator for the percentage change in the number of resident subscribers to the percentage change in the number of residents in an area. Similarly, we may adjust the indicator for representation biases based on mobility errors estimated from survey data.
Abnormality
The residents abnormality indicator measures the deviation of the number of people residing in a given area during a period of time relative to a reference period, expressed as a z-score. A positive value for this indicator greater than 3 indicates a statistically significant increase in the number of residents in a given area; a value less than -3 indicates a statistically significant decrease in residents.
The usual resolution for this indicator is:
- Temporal: monthly
- Spatial: admin3
This indicator describes how unusual the number of residents in an area is, given the amount of variation observed during the reference period. Higher absolute values indicate greater deviation from the normal variation in population density, and therefore greater probability that the change is meaningful. Such changes may be associated with specific events or may be caused by technical issues. Very large abnormalities (absolute values greater than 6), however, may also be indicative of a technical issue.
- Calculation
-
We calculate the residents abnormality indicator using the home relocations aggregate and the baseline number of residents in the area during a reference period. The baseline can be calculated using the residents aggregate, for example by calculating the median number of residents during the reference period. We advise against directly estimating the change in the number of residents from the residents aggregate as this may be more influenced by variation in the number of active subscribers than by subscriber mobility.
The residents abnormality is the z-score, or the number of standard deviations the number of residents in a given period is above or below the median number of residents in the reference period.
To calculate the z-score, we calculate the difference in the number of residents relative to the baseline as described above. We then divide this difference by the median absolute deviation (MAD) in the number of residents during the reference period.
- Adjustment
-
As described above, when estimating the change in the number of residents in a given area, we adjust the number of relocations into and out of the area with respect to change in the number of active subscribers in the area of interest.
As this indicator is expressed as a z-score (i.e. a number of standard deviations) this indicator does not need to be scaled to the size of the population.