ECM Regression Analysis

NEHA NEHRA | AYAPPARAJ SKS | ADITYA NATHIREDDY |
VIBEESH CS
API (Annual Performance Indicator)
: Elementary School
ECONOMETRICS PROJECT PRESENTATION

Agenda
 API – Introduction
 Key features of the API
 Business Objective
 Overall Data Sanity Check
 Regression Model
 Inferences
 Recommendations

API: An Introduction
• The API is a single number, ranging from a low of 200 to a high of 1000,
which reflects a school’s, an Local Educational Agencies (LEA) , or a student
group’s performance level, based on the results of statewide assessments. Its
purpose is to measure the academic performance and improvement of
schools.
• The API is calculated by converting a student’s performance on statewide
assessments across multiple content areas into points on the API scale. These
points are then averaged across all students and all tests. The result is the API.
An API is calculated for schools, LEAs, and for each student group with 11 or
more valid scores at a school or an LEA.

API: Key features
• The API is based on an improvement model. The assessment results from
one year are compared to assessment results from the prior year to measure
improvement.
• The API is used to rank schools. A school is compared to other schools
statewide and to 100 other schools that have similar opportunities and
challenges.
• The API is a cross-sectional look at student achievement. It does not track
individual student progress across years but rather compares snapshots of
school or LEA achievement results from one year to the next.
• The API is currently a school-based requirement only under state law.
However, API reports are provided for LEAs in order to meet federal
requirements under the federal Elementary and Secondary Education Act
(ESEA).

To find the factors that have most influence on the performance of
elementary schools in California, from 400 elementary schools from the
California Department of Education's API 2000 dataset.

Overall Data Sanity Check
: Missing Value Treatment
 Dataset consists of 400 school
and 21 Variables
 Imputing mobility,acs_k3 and
acs_46 with column wise mean
18.25 , 18.55 , 29.69 respectively
 Pct free meals impute by
category wise mean. Refer Notes
below
 Imputing 19 values of avg_ed as
0 since variables not_hsg, hsg,
some_col,col_grad and
grad_school are 0 parents are
neither high school graduates
neither went to some college or
school

Overall Data Sanity Check
: Outlier Treatment
 ACS-K3: 6 values are negative , this is only for district number 140. This
shows there is some manual input error as class size cannot be negative
 We would take absolute values for the same
 Variable Full Percentage of full time teachers : Values which are less than
1 as the percentage figures are between 1 -100. Multiply those with 100

Regression Model
API = (869.12*Intercept)+(2.27*grad_sch)-(3.67*meals)-(41.21*yr_rnd)
Model Significance:
1) Adjusted R2 is 81.35% where 81.35% of variability in API is being explained by
variables grad_sch , meals and yr_rnd
2) The variables are significant at 99% significant level and VIF less than 1.8
3) This model has MAPE of 8.15

Variable 1 Inferences : Parent Grad School
 1) This is a positive indicator on the API.
If grad_sch increases by 1 the API
increases by 2.77

 2) A graduate parent plays a strong and
a role of a contributor in the life of
his/her child

 3) They help in the academics arena as
well as creating an overall outlook
towards life

 4) They would be able to understand the
gap areas well and help their child in the
improvement areas

 5) They focus on inculcating the
discipline and right virtues that help in
development of the child thereby API

Variable 2 Inferences : Percentage of Free
Meals  1) This is a negative indicator on the
API .If meals increases by 1 the API
decreases by 3.67

 2) The access of free meals is a sign
of poor background of the students
who are deprived of basic
necessities.
 The main concern for these students
is to get food as they cannot afford
the same

 3) The academic performance
suffers as a result for the same

 4) A large expenditure would go in
arranging of these meals thereby
reducing budget on other key
parameters like hiring of teachers
etc

Variable 3 Inference : Year Round School
 1) This is a negative indicator on the API .If
meals increases by 1 the API decreases by
41.21
 2) Students in a year round schooling attend
school the same number of days as in
traditional school (180 Days) but former has
several short vacations instead of one long
vacation

 3) This is a huge burden for schools to
manage the maintenance of infrastructure
and teachers. This would reduce the budget
planned for other activities

 4) Students can’t plan for other activities
which they can learn during long holidays like
summer intern-ships, hobby classes thereby
impacting student's performance

Recommendations
 1) Year Round Schools have an add on
pressure for all the sides schools, teachers
and students. Proper incentives to school
focusing on teachers development and
curriculum planning.

 2) Focus on guiding schools on proper
budget planning and track the expenditure
spent on various aspects. This will ensure
proper utilization o the funds.

 3) Meals that are provided must be healthy
and good quality.

 4) Graduate Parents must be brought in
panel as part of guest lectures, workshop .
This would help in boosting the morale of
the students and guiding the poor students
in performing better.

ECM Regression Analysis

More Related Content

What's hot (6)

Viewers also liked (9)

Similar to ECM Regression Analysis (20)

Recently uploaded (20)

ECM Regression Analysis

Editor's Notes