Title page
Contents
Chapter 1. Introduction 10
1.1. Overview of Data File Documentation (DFD) Report 10
1.2. Historical Background: NCES Secondary Longitudinal Studies Program 11
1.3. High School Longitudinal Study of 2009 14
1.3.1. Base Year, First Follow-up, 2013 Update 15
1.3.2. Second Follow-up 16
1.3.3. Research and Policy Issues and Analytic Levels 18
Chapter 2. Sample Design 25
2.1. Base-year Sample Design 25
2.2. First Follow-up Sample Design 26
2.3. 2013 Update and High School Transcript Study Sample Design 27
2.4. Second Follow-up Sample Design 28
Chapter 3. Instrumentation 30
3.1. Base-year, First Follow-up, and 2013 Update Instruments 30
3.2. Instrument Development in the Second Follow-up: Goals, Processes, Procedures 31
3.3. Survey Instrument Content in the Second Follow-up 32
3.4. Survey Instrument Design and Features in the Second Follow-up 36
3.5. Criteria for Defining Completed Interviews in the Second Follow-up 39
Chapter 4. Data Collection Methodology and Results 40
4.1. Data Collection Methodology 40
4.1.1. Website 40
4.1.2. Help Desk 42
4.1.3. Data Collection Staff Training 42
4.1.4. Tracing, Locating, and Interviewing Procedures 44
4.1.5. Data Collection Quality Control Procedures 54
4.2. Responsive Design Methodology 55
4.2.1. Data Collection Design Details 57
4.3. Data Collection Results 67
4.3.1. Tracing and Locating Outcomes 70
4.3.2. Interview Participation Rates 73
4.3.3. Survey Timing 78
Chapter 5. Data Preparation and Processing 83
5.1. Overview of Systems 83
5.2. Data Cleaning and Editing 85
5.3. Coding 87
5.3.1. Major or Field of Study Coding 87
5.3.2. Occupation Coding 89
5.3.3. Respondent Job at Age 30 Coding 92
5.3.4. High School Coding 93
5.3.5. Postsecondary Institution Coding 94
Chapter 6. Response Rates, Analytic Weights, Variance and Design Effects Estimation, Nonresponse Bias Analysis, Imputation, and Disclosure Avoidance 97
6.1. Unit Response Rates 97
6.2. Overview of Weighting in the Base Year, First Follow-up, and 2013 Update 100
6.3. Second Follow-up and Supplemental 2013 Update Weights 101
6.3.1. Second Follow-up Weights 102
6.3.2. Supplemental 2013 Update Weights 107
6.3.3. Weighting Quality Control 109
6.4. Choosing an Analytic Weight 111
6.4.1. Base-year School-level Analysis 120
6.4.2. Base-year Student-level Analysis 120
6.4.3. First Follow-up Student-level Analysis 122
6.4.4. 2013 Update and High School Transcript Student-level Analysis 124
6.4.5. Second Follow-up Student-level Analysis 129
6.5. Measures of Precision: Standard Errors and Design Effects 131
6.5.1. Standard Errors 131
6.5.2. Design Effects 135
6.6. Item-level Declined Response 139
6.7. Unit and Item Nonresponse Bias Analysis 142
6.7.1. Unit Nonresponse Bias Analysis 142
6.7.2. Item Nonresponse Bias Analysis 147
6.8. Single-value Item Imputation 157
6.8.1. Imputed Survey Questionnaire Items 158
6.8.2. Evaluation of the Imputed Values 160
6.9. Disclosure Risk Analysis and Protections 161
Chapter 7. Data File Contents 163
7.1. Base-year to Second Follow-up Data File 163
7.1.1. Restricted-use Data 163
7.1.2. Public-use Data 164
7.1.3. Mixed-use Data Products 165
7.2. Contents of the Second Follow-up Data Products 165
7.3. Variable Naming Schema 168
7.4. Reserve Codes 169
7.5. Composite Variables 169
7.5.1. Revised SES indices 170
References 172
Table 1. Data collection staff trainings: 2016 43
Table 2. Hardcopy mailings: 2016 52
Table 3. Data collection schedule: 2016 57
Table 4. Calibration sample and main sample sizes, by subgroup: 2016 64
Table 5. Participation rates, by prior response status and student type: 2016 69
Table 6. Located status, by prior response status and student type: 2016 71
Table 7. Batch processing case match rates, by tracing source: 2016 72
Table 8. Intensive tracing rates and rates located though intensive tracing, by prior response status and student type: 2016 73
Table 9. Distribution of interview participation, by interview mode: 2016 74
Table 10. Participation status of field cases, by interview mode: 2016 75
Table 11. Distribution of interview respondents, by data collection phase: 2016 76
Table 12. Interview completeness among respondents: 2016 76
Table 13. Refusal and refusal conversion rates, by prior response status and student type: 2016 77
Table 14. Incentive selection among web and centralized telephone respondents who were offered an incentive: 2016 78
Table 15. Average time in minutes to complete the full interview, by interview section and mode: 2016 80
Table 16. Average time in minutes to complete the abbreviated interview, by interview section and mode: 2016 82
Table 17. Logically inferred variables: 2016 86
Table 18. Survey-uncoded majors, by coding method: 2016 88
Table 19. Results of quality control recoding and upcoding of major: 2016 89
Table 20. Results of quality control recoding and upcoding of occupation: 2016 91
Table 21. Job at age 30 results, by coding method: 2016 92
Table 22. Results of quality control of job at age 30 upcoding: 2016 93
Table 23. Final disposition of survey-uncoded high schools, after coding: 2016 94
Table 24. Survey-uncoded postsecondary institutions, by coding method: 2016 95
Table 25. Final disposition of survey-uncoded postsecondary institutions, after coding: 2016 96
Table 26. HSLS:09 Base-weighted Unit Response Rates 99
Table 27. Descriptive characteristics of second follow-up survey weights 107
Table 28. Descriptive characteristics of supplemental 2013 Update survey weights 109
Table 29. HSLS:09 analytic weights 113
Table 30. Number and percentage of completed surveys, High School Transcript responses, or their combinations for the student sample, and associated recommended weights: Second follow-up 116
Table 31. Average design effects (deff) and root design effects (deft) for second follow-up student variables 138
Table 32. Item-level declined response over 5 percent, by variable and mode: 2016 140
Table 33. Summary statistics for unit nonresponse bias analyses before and after weight adjustments for nonresponse, by HSLS:09 second follow-up and supplemental 2013 Update analytic weights 144
Table 34. Student-level questionnaire items with a weighted item response rate below 85 percent using W4STUDENT weight 150
Table 35. Frequency distribution of the estimated bias ratios 156
Table 36. Summary statistics for student-level item nonresponse bias analyses 157
Table 37. Student questionnaire and composite variables included in single value imputation by number and weighted percent of values missing 159
Table 38. Reserve code values: 2016 169
Figure 1. Longitudinal design for the NCES Secondary Longitudinal Studies program: 1972-2025 13
Figure 2. Longitudinal design for the HSLS:09 9th-grade cohort: 2009-2025 15
Figure 3. HSLS:09 base-year student survey conceptual map 19
Figure 4. Student eligibility and fielding disposition from base year to the second follow-up: 2016 29
Figure 5. HSLS:09 second follow-up website: 2016 41
Figure 6. Tracing and locating procedures: 2016 46
Figure 7. Timeline of data collection phases and activities: 2016 47
Figure 8. Overall locating and interviewing results: 2016 70
Figure 9. Second follow-up weight construction process for the four weights with sequential adjustments for nonresponse 103
Figure 10. Example SAS-callable SUDAAN code to calculate an estimated mean and linearization standard error for a second follow-up student-level analysis 134
Figure 11. Example SUDAAN code to calculate an estimated mean and replicate (BRR) standard error for a second follow-up student-level longitudinal analysis 134
Figure 12. Example Stata code to calculate an estimated mean and linearization standard error for a second follow-up student-level analysis 134
Figure 13. Example Stata code to calculate an estimated mean and replicate (BRR) standard error for second follow-up student-level analysis 134
Figure 14. Example SAS code to calculate an estimated mean and linearization standard error for a second follow-up student-level analysis 135
Figure 15. Example SAS code to calculate an estimated mean and replicate (BRR) standard error for a second follow-up student-level longitudinal analysis 135