| Title: | Exemplar Data Sets for Student Growth Percentiles (SGP) Analyses |
|---|---|
| Description: | Data sets utilized by the 'SGP' package as exemplars for users to conduct their own student growth percentiles (SGP) analyses. |
| Authors: | Damian W. Betebenner [aut, cre], Adam R. Van Iwaarden [aut], Ben Domingue [aut] |
| Maintainer: | Damian W. Betebenner <[email protected]> |
| License: | GPL-3 |
| Version: | 28.0-0.0 |
| Built: | 2024-11-13 06:00:59 UTC |
| Source: | https://github.com/centerforassessment/sgpdata |
The 'SGPdata' package contains five exemplar data sets utilized by the 'SGP' package for testing and examples.
| Package: | SGPdata |
| Type: | Package |
| Version: | 28.0-0.0 |
| Date: | 2024-7-14 |
| License: | GPL-3 |
| LazyLoad: | Yes |
| LazyData: | Yes |
A dataset comprising a subset of five years of state assessment reading data suitable for student growth percentile
and percentile growth projection/trajectory analyses. The dataset is used in examples provided in the documentation
for the studentGrowthPercentiles and studentGrowthProjections functions, and serves as an exemplar for user construction
of their own datasets for growth percentile analyses.
A data frame of student level observations for five years on the following variables.
IDStudent ID
GRADE_2020Student Grade Tested 2020, possibly missing
GRADE_2021Student Grade Tested 2021, possibly missing
GRADE_2022Student Grade Tested 2022, possibly missing
GRADE_2023Student Grade Tested 2023, possibly missing
GRADE_2024Student Grade Tested 2024, possibly missing
SS_2020Student Scale Score 2020, possibly missing
SS_2021Student Scale Score 2021, possibly missing
SS_2022Student Scale Score 2022, possibly missing
SS_2023Student Scale Score 2023, possibly missing
SS_2024Student Scale Score 2024, possibly missing
All datasets used with studentGrowthPercentiles and studentGrowthProjections must be specifically formatted as wide format files. The first
variable/column is the student ID variable. The next set of columns provide the grade of the student across all the years provided in the dataset (possibly missing).
The last set of columns provide the scales scores of the student in the respective grades. Multi-year operational analyses benefit from putting data in long format.
See sgpData_LONG and associated documentation for a comprehensive account.
Anonymized student level state assessment data
A lookup table comprising student IDs associated with INSTRUCTOR_NUMBERa subset of five years of state assessment reading and mathematics data suitable for student growth percentile and percentile growth projection/trajectory analyses. The dataset is in LONG format with each record representing a unique teacher by student by year by content area combination.
A data frame of student level observations for five years and two content areas for the following variables.
IDUnique Student Identification Number
CONTENT_AREAContent area for student/teacher record (Reading or Mathematics)
YEARYear for student/teacher record
INSTRUCTOR_NUMBERUnique instructor number identifier
INSTRUCTOR_LAST_NAMEInstructor last name
INSTRUCTOR_FIRST_NAMEInstructor first name
INSTRUCTOR_WEIGHTProportional weight associated with student/teacher record
INSTRUCTOR_ENROLLMENT_STATUSIndicator of full enrollment status of student with teacher
Anonymized student/teacher lookup table in LONG format
A dataset comprising a subset of five years of state assessment reading and mathematics data suitable for student growth percentile (SGP) and percentile growth projection/trajectory analyses. The dataset is in LONG format with each record representing a unique student, by year by content area combination. The example data is used in examples and illustration in the enclosed documentation to show how SGPs can be operationalized across years with the results being used to produce a variety of high quality visualizations both at the aggregate (e.g., school) and individual level.
A data frame of student level observations for five years and two content areas for the following variables.
IDUnique Student Identification Number
LAST_NAMEStudent last name
FIRST_NAMEStudent first name
CONTENT_AREAContent area for student observation (Reading or Mathematics)
YEARYear for student observation
GRADEGrade level of student observation
SCALE_SCOREStudent Scale Score
ACHIEVEMENT_LEVELAchievement level associated with student scale score
GENDERStudent gender
ETHNICITYStudent ethnicity
FREE_REDUCED_LUNCH_STATUSStudent free/reduced lunch status
ELL_STATUSStudent English Language Learner status
IEP_STATUSStudent Individual Education Plan status
GIFTED_AND_TALENTED_PROGRAM_STATUSStudent Gifted and Talented Program status
SCHOOL_NUMBERSchool number associated with student record
SCHOOL_NAMESchool name associated with school number and student record
EMH_LEVELElementary, Middle, High school indicator for school attended
DISTRICT_NUMBERDistrict number associated with student record
DISTRICT_NAMEDistrict name associated with school number and student record
SCHOOL_ENROLLMENT_STATUSIndicator of full academic year student enrollment in school
DISTRICT_ENROLLMENT_STATUSIndicator of full academic year student enrollment in school
STATE_ENROLLMENT_STATUSIndicator of full academic year student enrollment in school
VALID_CASEIndicator of whether the case is valid or invalid
All datasets used with studentGrowthPercentiles and studentGrowthProjections must be specifically formatted as wide format files. The first
variable/column is the student ID variable. The next set of columns provide the grade of the student across all the years provided in the dataset (possibly missing).
The last set of columns provide the scales scores of the student in the respective grades. Operational users of this package are advised to use data formatted similar to the sgpData_LONG
with the higher level functions prepareSGP, analyzeSGP, combineSGP, summarizeSGP, visualizeSGP, and outputSGP
Anonymized student level state assessment data in LONG format
A dataset comprising a subset of seven years of state assessment ELA and mathematics data across an 8 year span suitable for student growth percentile (SGP) and percentile growth projection/trajectory analyses. The dataset is missing 2020 data to help users model COVID related interuptions to student growth. The dataset is in LONG format with each record representing a unique student, by year by content area combination. The example data is used in examples and illustration in the enclosed documentation to show how SGPs can be operationalized across years with the results being used to produce a variety of high quality visualizations both at the aggregate (e.g., school) and individual level.
A data frame of student level observations for seven years (across an 8 year span) and two content areas for the following variables.
VALID_CASEIndicator of whether the case is valid or invalid
CONTENT_AREAContent area for student observation (ELA or Mathematics)
YEARYear for student observation
IDUnique Student Identification Number
IEP_STATUSStudent Individual Education Plan status
GRADEGrade level of student observation
SCALE_SCOREStudent Scale Score
SCALE_SCORE_without_COVID_IMPACTStudent Scale Score without COVID impact. Original scale score
ACHIEVEMENT_LEVELAchievement level associated with student scale score
ETHNICITYStudent ethnicity
FREE_REDUCED_LUNCH_STATUSStudent free/reduced lunch status
ELL_STATUSStudent English Language Learner status
GENDERStudent gender
SCHOOL_NUMBERSchool number associated with student record
SCHOOL_NAMESchool name associated with school number and student record
DISTRICT_NUMBERDistrict number associated with student record
DISTRICT_NAMEDistrict name associated with school number and student record
All datasets used with studentGrowthPercentiles and studentGrowthProjections must be specifically formatted as wide format files. The first
variable/column is the student ID variable. The next set of columns provide the grade of the student across all the years provided in the dataset (possibly missing).
The last set of columns provide the scales scores of the student in the respective grades. Operational users of this package are advised to use data formatted similar to
the sgpData_LONG_COVID with the higher level functions prepareSGP, analyzeSGP, combineSGP, summarizeSGP, visualizeSGP, and outputSGP
Anonymized and altered student level state assessment data in LONG format
A dataset comprising a subset of 3 years (and time periods) of interim assessment early literacy, reading and mathematics data suitable for time dependent student growth percentile (SGPt) and percentile growth projection/trajectory analyses. The dataset is in LONG format with each record representing a unique student, by year/time period by content area combination. The example data is used in examples and illustrations in the enclosed documentation to show how SGPts can be operationalized across years with the results being used to produce a variety of high quality visualizations both at the aggregate (e.g., school) and individual level.
A data frame of student level observations for five years and two content areas for the following variables.
COUNTRYVariable indicating the COUNTRY associated with test record.
STATEState associated with the test record.
VALID_CASEVALID_CASE variable.
CONTENT_AREAVariable indicating content area associated with test record.
YEARVariable indicating the year associated with the test record.
DATEVariable indicating the year associated with the test record: Must be in YYYY-MM-DD format.
IDUnique student identifier associated with test record.
GRADEVariable indicating the grade associated with the test record.
SCALE_SCOREVariable providing the scale score associated with the test record.
SCALE_SCORE_RASCHVariable providing the Rasch score associated with the test record.
SEMVariable indicating the standard error of measurement associated with the scale score.
ACHIEVEMENT_LEVELVariable indicating the achievement level associated with the scale score.
Anonymized student level interim assessment data in LONG format