Questions

1.a How many strata does the Harmonia survey will have?

1.b List and briefly describe at least two advantages and disadvantages of having these many strata compared to having more, for example 100 (one for each district)? (MANDATORY)

Answer:-

1a. Harmonia has 10 province which is equal to 10 Strata I.e. one province = 1 stratum

1b. Advantages of having many strata over small number of strata.

Advantage

Many strata means wider sample size with better Precision and effective sample sized. In other word many eligible children and house hold could be reach with some minimum bias (selection bias).
Many strata may give room for wider coverage or wide selection chances of the participants with different features in a given population.

 

Disadvantages

Many strata may lead to high cost in term of human and material logistics
Number of sample selected will concentrated with in a given number of clusters instead of strata. This may lead to problem of selection bias.

 

3.a What kind of data do you need to collect to complete a table like the one below? (MANDATORY)

3.b How does this table relate to potential selection bias and what cautions should you have when interpreting the vaccination indicators if response rate is not 100% and/or several households could not be interviewed? (MANDATORY)

Answer:

a. You need three different data or information to collect viz

Bio data of the respondents which include: Age, sex,
Demographic information: - Nationality, Province, District and settlement (Strata, cluster and unit).
Vaccination status: Number of doses receive per schedule per age and the various antigen per schedule.

b. Any aspect of the way subjects are assembled in the study that creates a systematic difference between the compared populations that is not due to the association under study is called selection bias.( MAUUN ,2015).

Therefore, some of the possible potential selection bias related to the table above could be associated to error either type 1 or type 2 error. These errors include:-

Sampling error or systemic error as describe in WHO 2018 reference manual.
Poor sampling method at certain stage
Selection of the sample by uncertain interviewer in the field and poor field procedure may lead to increase in coverage (upward bias in coverage result).
Issues related to residency requirement.
Selection of inappropriate sample size for the survey goal.
Inappropriate weighted analysis for effective selection.

Caution to avoid potential selection bias:

As recommended by WHO, using probability – based sampling method at each stage is paramount. Choosing optimum sample design (appropriate number and size of cluster) and adjustment of sample size will assist in achieving desired precision. WHO, 2018 reference manual.
To avoid selection bias, household (HH) to be selected by a central group of planners rather than interviewers in the field. This may minimized or avoid selection bias and the desired precision can be achieved. However, pre selection of HHs and ensure strict supervision is also required.
Residency requirement should be logically eliminated in the since that, both residents and all other persons who slept in the HH the previous night should be consider and provision of questionnaire to capture how long surveyed individual has lived in that HH. This was recommended in 2018 reference material.
Accurate verbal history to be obtain from the caregiver. This can be achieved only when neutral attitude is maintain.
Visit facilities to find vaccination records when HBR not available.
Work with community to enhance survey participation rate.
Conduct revisit as necessary to locate care givers and HBRs
Don’t substitute HHs while revisited absent.

4.a What variables do you need to collect or define in the analysis to estimate a [weighted] vaccination coverage with the first dose of diphtheria-tetanus-pertussis containing vaccine (DTP1) and with the third dose of diphtheria-tetanus-pertussis containing vaccine (DTP3) among children aged 12-23 months in each stratum

Answer: -

The variables need to be collect are by

a) ‘Documented evidence of vaccination (home-based record – HBR OR facility-based record – FBR)’ and

c) ‘by documented evidence of vaccination + recall’

4.b How does this table relate to potential information bias and what cautions should you have when interpreting the vaccination indicators in surveys with “low” percentage of documented evidence? (MANDATORY)

Answer:-

According to 2018 reference manual two different information bias was identified;

Information bias due to lack of HBR or poorly filled HBR and information bias as a result of inaccurate verbal history. This could be related by the information provided in the table, as follows

Information bias due to HBR it may likely be under or over - estimate the coverage depending on how missing data are handled and how HBRs are read or interpreted.
Inaccurate verbal history as a result of caregiver may forget or cannot recall how many doses child have been received or may over report if feel pressure to say they have been vaccinated.

 

Some of the identified caution indicated in the reference manual 2018 are stated as follows;

Consider publicizing remainders about the HBRs prior to survey.
Allow time for mothers to look for the HBR
Create time for revisit as necessary to locate caretakers and HBRs
Do not substitute HHs
Ensure neutral attitude is maintain.
Give time to mothers to respond
Design short questioner to avoid interviewee fatigue
Standardize questions, use visual aids,
Ask caregiver questions about all doses received according to schedule and frequency.

 

References:

Pearl, J., (2009). Simpson's Paradox, Confounding, and Collapsibility in Causality: Models, Reasoning and Inference (2nd ed.). New York: Cambridge University Press. In MAAUN 2016.
World Health Organization Vaccination Coverage Cluster Survey: Reference Manual (June, 2018).

 

Questions

1.a How many strata does the Harmonia survey will have?

1.b List and briefly describe at least two advantages and disadvantages of having these many strata compared to having more, for example 100 (one for each district)? (MANDATORY)

Answer:-

1a. Harmonia has 10 province which is equal to 10 Strata I.e. one province = 1 stratum

1b. Advantages of having many strata over small number of strata.

Advantage

Many strata means wider sample size with better Precision and effective sample sized. In other word many eligible children and house hold could be reach with some minimum bias (selection bias).
Many strata may give room for wider coverage or wide selection chances of the participants with different features in a given population.

 

Disadvantages

Many strata may lead to high cost in term of human and material logistics
Number of sample selected will concentrated with in a given number of clusters instead of strata. This may lead to problem of selection bias.

 

3.a What kind of data do you need to collect to complete a table like the one below? (MANDATORY)

3.b How does this table relate to potential selection bias and what cautions should you have when interpreting the vaccination indicators if response rate is not 100% and/or several households could not be interviewed? (MANDATORY)

Answer:

a. You need three different data or information to collect viz

Bio data of the respondents which include: Age, sex,
Demographic information: - Nationality, Province, District and settlement (Strata, cluster and unit).
Vaccination status: Number of doses receive per schedule per age and the various antigen per schedule.

b. Any aspect of the way subjects are assembled in the study that creates a systematic difference between the compared populations that is not due to the association under study is called selection bias.( MAUUN ,2015).

Therefore, some of the possible potential selection bias related to the table above could be associated to error either type 1 or type 2 error. These errors include:-

Sampling error or systemic error as describe in WHO 2018 reference manual.
Poor sampling method at certain stage
Selection of the sample by uncertain interviewer in the field and poor field procedure may lead to increase in coverage (upward bias in coverage result).
Issues related to residency requirement.
Selection of inappropriate sample size for the survey goal.
Inappropriate weighted analysis for effective selection.

Caution to avoid potential selection bias:

As recommended by WHO, using probability – based sampling method at each stage is paramount. Choosing optimum sample design (appropriate number and size of cluster) and adjustment of sample size will assist in achieving desired precision. WHO, 2018 reference manual.
To avoid selection bias, household (HH) to be selected by a central group of planners rather than interviewers in the field. This may minimized or avoid selection bias and the desired precision can be achieved. However, pre selection of HHs and ensure strict supervision is also required.
Residency requirement should be logically eliminated in the since that, both residents and all other persons who slept in the HH the previous night should be consider and provision of questionnaire to capture how long surveyed individual has lived in that HH. This was recommended in 2018 reference material.
Accurate verbal history to be obtain from the caregiver. This can be achieved only when neutral attitude is maintain.
Visit facilities to find vaccination records when HBR not available.
Work with community to enhance survey participation rate.
Conduct revisit as necessary to locate care givers and HBRs
Don’t substitute HHs while revisited absent.

4.a What variables do you need to collect or define in the analysis to estimate a [weighted] vaccination coverage with the first dose of diphtheria-tetanus-pertussis containing vaccine (DTP1) and with the third dose of diphtheria-tetanus-pertussis containing vaccine (DTP3) among children aged 12-23 months in each stratum

Answer: -

The variables need to be collect are by

a) ‘Documented evidence of vaccination (home-based record – HBR OR facility-based record – FBR)’ and

c) ‘by documented evidence of vaccination + recall’

4.b How does this table relate to potential information bias and what cautions should you have when interpreting the vaccination indicators in surveys with “low” percentage of documented evidence? (MANDATORY)

Answer:-

According to 2018 reference manual two different information bias was identified;

Information bias due to lack of HBR or poorly filled HBR and information bias as a result of inaccurate verbal history. This could be related by the information provided in the table, as follows

Information bias due to HBR it may likely be under or over - estimate the coverage depending on how missing data are handled and how HBRs are read or interpreted.
Inaccurate verbal history as a result of caregiver may forget or cannot recall how many doses child have been received or may over report if feel pressure to say they have been vaccinated.

 

Some of the identified caution indicated in the reference manual 2018 are stated as follows;

Consider publicizing remainders about the HBRs prior to survey.
Allow time for mothers to look for the HBR
Create time for revisit as necessary to locate caretakers and HBRs
Do not substitute HHs
Ensure neutral attitude is maintain.
Give time to mothers to respond
Design short questioner to avoid interviewee fatigue
Standardize questions, use visual aids,
Ask caregiver questions about all doses received according to schedule and frequency.

 

References:

Pearl, J., (2009). Simpson's Paradox, Confounding, and Collapsibility in Causality: Models, Reasoning and Inference (2nd ed.). New York: Cambridge University Press. In MAAUN 2016.
World Health Organization Vaccination Coverage Cluster Survey: Reference Manual (June, 2018).