Methodological note · Official statistics · 23 September 2026

The consumption survey came back with two headline numbers

India went eleven years without a published consumption expenditure survey. The series that returned publishes every figure twice, with and without the imputed value of items received free through welfare programmes, and the choice between them moves the growth rate.

Consumption Official Statistics Imputation

Methodological note · Data quality · 23 September 2026

The total row

Published statistical tables carry their own total. Summing the column instead double-counts exactly, every internal consistency check still passes, and the error survives every review that does not know the table.

Data Quality Official Statistics Validation

Methodological note · Indicators · 23 September 2026

When a scale stops discriminating

An evidence tier that returns the same value for every case reports nothing about the evidence. Look at how a derived variable is distributed before trusting how it is defined: the cases that did vary were often reporting a bug in the code that computed them.

Indicators Measurement Evidence

Methodological note · RCT design · 29 May 2026

Power calculations in cluster RCTs with realistic ICCs

Power calculations in cluster RCTs are only as good as the intra-cluster correlation coefficients they assume. Plugging in 0.02 because the paper you copied it from did is the most common way trials come back underpowered.

RCT Power Calculation ICC

Methodological note · Survey design · 29 May 2026

Non-response as data

Non-response codes on survey instruments are usually treated as noise to be minimised. They are also structured information about who refuses, on which items and at which points in the questionnaire, and the pattern is often the finding.

Non-Response Survey Design Missing Data

Methodological note · Labour economics · 29 May 2026

The wage-gap decomposition that didn't decompose cleanly

Blinder-Oaxaca decompositions treat the unexplained residual as discrimination. When the residual is 60-80% of the gap, it mostly measures what the model leaves out.

Wage Gap Blinder-Oaxaca Labour Economics

Methodological note · Administrative data · 29 May 2026

When admin data is the only data

Administrative data such as NREGA muster rolls, PMAY-G records and PDS records is often the only large-N source for remote districts. It is collected to administer schemes, and the gap between administration and measurement is where the most consequential errors live.

Administrative Data NREGA PMAY-G

Field note · Caste & access · 29 May 2026

The interview that ended at the doorway

Caste-based access constraints in Indian fieldwork are invisible in most methods sections, but they shape every sample we collect. Who refuses, who is sent away, and who is sent away on someone else's behalf are all structured by hierarchy, and they bias data systematically.

Caste Fieldwork Access

Methodological note · Programme design · 9 May 2026

Theory of change isn't a flowchart

Most theories of change are decorative diagrams. A useful TOC names assumptions specifically enough that evidence could prove them wrong.

Theory of Change Programme Design Contribution Analysis

Methodological note · Indicators · 9 May 2026

The composite index that hid the policy choice

Composite indices in development policy look technical but bury policy decisions in weight selection. The rank order is more sensitive to weights than most users realise.

Indicators Composite Index Policy

Methodological note · Survey design · 9 May 2026

What translation does to a survey instrument

Forward-back translation is treated as the standard for adapting survey instruments across languages. It catches a small fraction of the failures that matter.

Survey Design Translation Multilingual

Methodological note · Panel data · 9 May 2026

Attrition isn't random: the households panel surveys lose

Panel surveys are biased in ways cross-sectional designs aren't, because the households most affected by shocks are the most likely to drop out. Standard corrections understate this.

Panel Data Selection Bias Methodology

Methodological note · Beneficiary feedback · 9 May 2026

Why we stopped trusting satisfaction scores

Beneficiary satisfaction scores in development contexts are systematically inflated. What they record is the respondent's relationship with the survey team. Behavioural data, comparative questions and a change of survey mode give better measures.

Beneficiary Feedback Courtesy Bias Survey Design

Methodological note · IHCRF

Why quantitative surveys in India need Human-Centred Design

Methodological note from the IHCRF district learning programme: why HCD belongs in survey instrument development.

HCD Survey Design IHCRF

Field note · IHCRF District Research

What district base papers revealed about climate-health interdependence

Field note from writing district base papers for the India Health and Climate Resilience Fund.

Climate-Health District Research IHCRF

Methodological note · DIU / Transform Rural India

Listening for aspiration in rural and peri-urban India

Methodological note from the DIU / Transform Rural India study on women's aspirations, on getting past the scripted answers that decades of programme intake forms have trained respondents to give.

Gender Aspirations Rural India

Field note · Alliance for Responsible Aquaculture

Evidence standards in a sector without a research tradition

Field note from leading India operations for the Alliance for Responsible Aquaculture.

Animal Welfare Policy Aquaculture

Field note · Railway Children India

Reunification research along the Delhi–Bengal corridor

Field note from family reunification research with Railway Children India.

Child Protection Qualitative Railway Corridor

Methodological note · India Institute

Advising a critical thinking RCT in government schools

Methodological note on the India Institute critical thinking RCT in Tamil Nadu government schools.

RCT Education Tamil Nadu

Methodological note · Bihar & Odisha

Co-designing MEL frameworks with women's collectives

Methodological reflection on co-designing MEL frameworks with women's collectives across Bihar and Odisha, and on how the measurement process became part of the intervention.

Gender MEL Bihar & Odisha

Methodological note · Bangladesh

What photovoice revealed about climate displacement

Methodological reflection on using photovoice with climate-displaced families in Bangladesh.

Climate Participatory Bangladesh

Methodological note · Bangladesh

When RCT results complicated the narrative

Methodological reflection on a mobile money RCT with garment workers in Bangladesh.

RCT Financial Inclusion Bangladesh

Methodological note · Sri Lanka

Facility assessments don't tell the full story

Methodological note on multi-perspective primary health care evaluation in Sri Lanka.

Health Evaluation Sri Lanka

Methodological note · Rajasthan

The gap between stated and revealed preferences

Methodological note on community-level norm effects in rural Rajasthan secondary education.

Education Social Norms Rajasthan

Policy note · Odisha

When programmes interact: PDS meets ICDS

Policy note on PDS and ICDS interaction effects in tribal districts of Odisha.

Social Protection Policy Odisha

Want to discuss a research challenge?

We enjoy conversations about methods, evidence, and development practice.

Get in touch