Duflo, Dupas, and Kremer (2011) Peer Effects and Teacher Incentives Dataset

Randomized evaluation in Kenyan primary schools, focusing on student test scores, demographic information, and class characteristics. The dataset includes 5,795 observations with information on endline and follow-up test scores.

Usage

ddk2011

Format

A data frame with 5,795 observations and 62 variables.

pupilid: ID of student
schoolid: ID of primary school
district: District
bungoma: Indicator if school is located in Bungoma District
bungoma_num: Bungoma indicator as numeric variable
division: Division
zone: Zone
tracking: Indicator if school is sampled for tracking
tracking_num: Tracking indicator as numeric variable
sbm: Indicator if school is sampled for School-Based Management
sbm_num: SBM indicator as numeric variable
girl: Sex of student (1 if female, 0 otherwise)
girl_num: Girl indicator as numeric variable
agetest: Age of student at time of test
etpteacher: Indicator if student is assigned to a contract teacher
etpteacher_num: ETP teacher indicator as numeric variable
lowstream: Indicator if student is assigned to lower-ability section (in tracking schools)
lowstream_num: Lowstream indicator as numeric variable
stream_meanpercentile: Mean standardized percentile of classmates at baseline
sdstream_std_mark: Standard deviation of baseline scores within stream (including own score)
meanstream_std_mark: Mean of baseline scores within stream (including own score)
bottomhalf: Indicator if student is in the bottom half of initial distribution
bottomhalf_num: Bottomhalf indicator as numeric variable
tophalf: Indicator if student is in the top half of initial distribution
tophalf_num: Tophalf indicator as numeric variable
bottomquarter: Indicator if student is in the bottom quarter of initial distribution
bottomquarter_num: Bottomquarter indicator as numeric variable
secondquarter: Indicator if student is in the second quarter of initial distribution
secondquarter_num: Secondquarter indicator as numeric variable
thirdquarter: Indicator if student is in the third quarter of initial distribution
thirdquarter_num: Thirdquarter indicator as numeric variable
topquarter: Indicator if student is in the top quarter of initial distribution
topquarter_num: Topquarter indicator as numeric variable
std_mark: Student's standardized mark in baseline exam
percentile: Student’s percentile in initial distribution
realpercentile: Student’s percentile in initial distribution (integer values)
quantile5p: Student's 20-quantile at baseline
attrition: Indicator if student was absent for endline test (Fall 2006)
attrition_num: Attrition indicator as numeric variable
wordscore: Endline score on word recognition (max: 24)
sentscore: Endline score on sentence recognition (max: 40)
letterscore: Endline score on letter recognition (max: 70)
spellscore: Endline score on spelling (max: 10)
sentscore24: Rescaled endline score on sentence recognition (0-24 scale)
letterscore24: Rescaled endline score on letter recognition (0-24 scale)
spellscore24: Rescaled endline score on spelling (0-24 scale)
litscore: Total endline score on literacy test
additions_score: Endline score on additions section
substractions_score: Endline score on subtractions section
multiplications_score: Endline score on multiplications section
mathscoreraw: Total endline score on math test
totalscore: Total endline score
rmeanstream_std_baselinemark: Peers' mean score at baseline, excluding own score
rsdstream_std_baselinemark: Peers' standard deviation in baseline score, excluding own score
rmeanstream_std_total: Peers' mean total score at endline (Fall 2006)
rsdstream_std_total: Peers' standard deviation in total score at endline
rmeanstream_std_math: Peers' mean math score at endline
rsdstream_std_math: Peers' standard deviation in math score at endline
rmeanstream_std_lit: Peers' mean literacy score at endline
rsdstream_std_lit: Peers' standard deviation in literacy score at endline
r2_attrition: Indicator if student was absent at long-term follow-up test (Fall 2007)
r2_attrition_num: R2 attrition indicator as numeric variable
r2_age: Age of student at long-term follow-up test
r2_wordscore: Score on word recognition at long-term follow-up
r2_sentscore: Score on sentence recognition at long-term follow-up
r2_letterscore: Score on letter recognition at long-term follow-up
r2_spellscore: Score on spelling at long-term follow-up
r2_sentscore24: Rescaled score on sentence recognition at long-term follow-up
r2_letterscore24: Rescaled score on letter recognition at long-term follow-up
r2_spellscore24: Rescaled score on spelling at long-term follow-up
r2_litscore: Total literacy score at long-term follow-up
r2_mathscoreraw: Total math score at long-term follow-up
r2_additions_score: Score on additions section at long-term follow-up
r2_substractions_score: Score on subtractions section at long-term follow-up
r2_multiplications_score: Score on multiplications section at long-term follow-up
r2_totalscore: Total score at long-term follow-up

Source

Duflo, E., Dupas, P., & Kremer, M. (2011). "Peer Effects, Teacher Incentives, and the Impact of Tracking: Evidence from a Randomized Evaluation in Kenya." American Economic Review, 101(5), 1739-1774. Data available at https://dataverse.harvard.edu/dataset.xhtml?persistentId=hdl:1902.1/16787