Variance of response word count per sector
If we look at the standard deviation, which is a statistics to show the measure of spread in data, of word count of responses in each sector, we can clearly see that some of the sectors have high variability.
That’s important metric to consider which sectors do have responses that are worth to conduct analyses.
| SD and Sample size of response word counts per sector name | ||
|---|---|---|
| Measure the spread with standard deviation | ||
| Sector name | SD | Sample size |
| Tecnico | 46.71 | 316 |
| Poblacion | 55.40 | 204 |
| VBG | 48.35 | 132 |
| Coordinacion | 97.08 | 81 |
| SocialCohesion | 35.55 | 74 |
| Educacion | 53.00 | 73 |
| SectorLaboral | 24.51 | 55 |
| Proteccion | 22.46 | 51 |
| Habitat | 7.78 | 43 |
| Socios | 233.79 | 42 |
| Fronteras | 46.51 | 33 |
| Agua | 27.32 | 29 |
| Necesidades | 15.76 | 25 |
| Alojamiento | 61.47 | 16 |
| LGBTI | 90.37 | 14 |
| VBG_SSR | 34.22 | 11 |
| Salud | 141.10 | 6 |
| ProteccionInfancia | 16.35 | 5 |
| Trafico | 17.01 | 5 |
| Educacional | 16.97 | 2 |
| Asistencia técnica para protección social | NA | 1 |
| AsistenciaEducacion | NA | 1 |
The table above clearly shows that some of the sectors are quite different in terms of the word count in responses.
Tecnico has 316 sample size with a standard deviation of 46.71
Poblacion has 204 sample size with a standard deviation of 55.4
VBG has 132 sample size with a standard deviation of 48.35
On the other hand, some sectors have very low sample size and high deviation.
- Salud has only 6 records with diverse word counts, which are 13, 46, 302, 302, 302, 302.