RMS composite metrics - exploratory data analysis: Module 11

(update 2024-11-10)

Note: All analyses are done by round, using all respondents.

1. Correlation among select composite metrics across modules

Note:
* Varying colors show direction of coefficients (also printed). See legend.
* Blank color means the correlation coefficient is not significant with p-value >=0.1.
* Indices are in alphabetical order for comparison purposes across rounds.

Metrics for all women/households

Round 1

Round 2

Round 3

Metrics only for women/households that experienced shock**

Round 1

Round 2

Round 3

2. Assessment individual composite metrics by module

For each index metrics, we present the following:
1. Mean values of individual items by round
2. Correlation matrix
3. PCA results
* Percent variation explained by component/dimension
* Bi-plot of individual items with respect to the first and second components

Analysis by round allows us to think if there are seasonal/temporal differences in how the individual items are correlated. Of note, even if each round data are similar, interpretation is limited to the study setting. But, still a good contribution….

Module 11: Shocks

Metric: shocks_total

Number of shock types experienced (0-39: m11q1_xx

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shocks_total simple sum of items count 39 0 39
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: shocks_incidence

Frequency of shocks: sum of 39 types X 5 frequency categories: m11q2_xx

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shocks_incidence simple sum of items 5 categories (1-5), 0 if not experienced 39 0 195
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: shocks_impact

Impact of shocks: sum of 39 types X 5 impact categories: m11q3_xx

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shocks_impact simple sum of items 5 categories (1-5), 0 if not experienced 39 0 195
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: shocks_impact_select

Impact of shocks, abbreviated: sum of select 33 types X 5 impact categories: m11q3_xx

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shocks_impact_select simple sum of items 5 categories (1-5), 0 if not experienced 33 0 165
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: shocks_total_impacthealth

Number of shock types that impacted health: sum of 39 item, binary m11q4_xx

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shocks_total_impacthealth simple sum of items count 39 0 39
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Items: shock_*

Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Items: numshock_*

Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: shockimpact_env

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shockimpact_env simple sum of items binary (0/1) 8 0 8
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Metric: shockimpact_bio

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shockimpact_bio simple sum of items binary (0/1) 4 0 4
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Metric: shockimpact_conf

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shockimpact_conf simple sum of items binary (0/1) 12 0 12
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Metric: shockimpact_eco

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shockimpact_eco simple sum of items binary (0/1) 10 0 10
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Metric: shockimpact_dem

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
shockimpact_dem simple sum of items binary (0/1) 6 0 6
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

NOTE: No variation in several variables in R2. Thus, no significance test for those pairs.
##### PCA by round

Module 11: Coping, when having experienced shocks

Metric: coping_total

Number of coping strategies used

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
coping_total simple sum of items count 30 0 30
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Metric: coping_total_pos

Number of positive/neutral coping strategies used

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
coping_total_pos simple sum of items binary (0/1) 25 0 25
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round

Module 11: Recovery after shock - ATR, when having experienced shocks

Metric: atr

Self-reported recovery from shocks (ATR: ability to recover), Note: High scores = high recovery

List of composite metrics
variable_name construction item_type number_of_items possible_minimum_score possible_maximum_score
atr simple average of items 4 categories (1-4), only if experienced 33 1 4
Summary by round
Correlation matrix by round

Round 1

Round 2

Round 3

PCA by round