Distribution of word counts in response fields
We will focus on word count of response field because the data we are interested in lies there.
There’s a lot of variation in response word count. The response word count has a distribution with a tail is on the left side meaning that most of the values are accumulated on the left. So this distribution has a negative skew.
Figure 11: Distribution of word count of responses. A zoom to response word counts between 0 and 100.
If we look at the distribution of word count of responses by specific sectors which have relatively higher sample size:
Figure 12: Distribution of word count of responses in “VBG”, “Poblacion” and “Tecnico” sectors
Logistic regression
We use a logistic regression model to estimate the probability which average word counts belong to what sectors.
| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 12.534884 | 10.18453 | 1.23077715 | 2.186480e-01 |
| Acceso_a_educación | 64.848678 | 12.83833 | 5.05117806 | 5.073289e-07 |
| Agua, saneamiento e higiene | 24.361668 | 16.04753 | 1.51809478 | 1.292546e-01 |
| Alojamiento Temporal | 33.840116 | 19.55721 | 1.73031411 | 8.383191e-02 |
| Apoyo Educacional a Comunidades Receptoras | 6.465116 | 48.30946 | 0.13382714 | 8.935618e-01 |
| Asistencia técnica para educación | 6.465116 | 67.55651 | 0.09569938 | 9.237754e-01 |
| Asistencia técnica para el sector laboral | 30.083298 | 13.59479 | 2.21285456 | 2.709580e-02 |
| Asistencia técnica para gestion de la informacion y coordinacion | 101.255240 | 12.60112 | 8.03541460 | 2.218784e-15 |
| Asistencia técnica para protección | 20.504332 | 13.82674 | 1.48294793 | 1.383515e-01 |
| Asistencia técnica para protección de la infancia | 31.265116 | 31.55560 | 0.99079441 | 3.219862e-01 |
| Asistencia técnica para protección social | 1.465116 | 67.55651 | 0.02168727 | 9.827010e-01 |
| Asistencia técnica para protección/gestión de fronteras | 46.768147 | 15.45577 | 3.02593399 | 2.531581e-03 |
| Asistencia técnica para VBG-SSR | 56.374207 | 22.56532 | 2.49826801 | 1.261348e-02 |
| Cohesión_social | 42.384035 | 12.80613 | 3.30966736 | 9.618860e-04 |
| Manejo de la información para socios y análisis de las necesidades | 127.798450 | 14.48858 | 8.82063567 | 3.946044e-18 |
| Manejo de la información y entrega directa de la información a la población | 22.072959 | 11.20661 | 1.96963743 | 4.911023e-02 |
| Medios de vida y formación técnico-profesional | 40.275243 | 10.85537 | 3.71016822 | 2.166249e-04 |
| Necesidades básicas/Otro | 5.545116 | 16.79675 | 0.33013025 | 7.413593e-01 |
| Protección_LGBTI | 73.965116 | 20.55012 | 3.59925528 | 3.321721e-04 |
| Protección_VBG | 42.465116 | 11.72662 | 3.62125723 | 3.054375e-04 |
| Salud | 198.631783 | 29.10471 | 6.82472950 | 1.396240e-11 |
| Trata_y_tráfico | 20.865116 | 31.55560 | 0.66121745 | 5.086001e-01 |