NEC METHODS: MATCHING, DEDUPLICATION, ANALYSIS & RESPONSE RATES - PowerPoint PPT Presentation

1 NEC METHODS: MATCHING, DEDUPLICATION, ANALYSIS & RESPONSE RATES 28 October 2014

Matching & Deduplication 2

Purpose of the Merged Analytic Cross- Region Datasets 3  PIF-ER Merged Dataset  Analyses on types of trainees who attended particular events  PIF-ER-ACRE Merged Dataset  Analyses on outcomes of AETC training programs related to self-assessed changes in provider behavior and clinical practice.

Analytic Dataset Creation Overview 4 Collect regional process and evaluation data 1. Convert data in submitted format (Excel, CSV, SPSS) to SAS 2. Reformat regional datasets to match expected data file 3. specifications (e.g., character/numeric type) Process data: HRSA data manual  Evaluation data: ACRE implementation manual  Create all-region ER, PIF, ACRE IP , ACRE FUP , and FTCC PIF 4. datasets by concatenating/appending regional files of the same type Create analytic PIF-ER merged dataset 5. Create analytic PIF-ER-ACRE datasets 6.

Cross-Region Analytic Data 5 Steps 1, 2, 3, 4: Collect, convert, reformat data. Create all-region ER, PIF, ACRE IP and FUP datasets. Step 5: Create analytic ER-PIF dataset Step 6: Create analytic ER-PIF-ACRE dataset

Creating the Analytic PIF-ER Merged Dataset 6  Check to see which regions have repeats on PROG_ID by LPS  Merge PIF and ER  For 1-2 regions with repeated PROG_ID, sort and merge the PIF and ER by AETC – LPS – and PROG_ID  For all other regions that have distinct PROG_ID, sort and merge the PIF and ER by AETC and PROG_ID only Bottom of PIF: AETC LPS PROG_ID

Creating the Analytic PIF-ER-ACRE Merged Dataset (1) 7  Select eligible ACRE IP data  Check to see which regions have repeats on PROG_ID by LPS  Exclude records where all 4 IP questions are missing/blank  Exclude records where the PIF_ID is . [missing], 0, or 99999999  De-duplicate IP records by AETC, LPS (if applicable), PROG_ID, PIF_ID, AIP1, AIP2  Select eligible records from the previously created ER-PIF merged dataset  Include only records where there is at least 1 PIF record included (e.g., there are some ERs without any PIFs)  Exclude records where the PIF_ID is . [missing], 0, or 99999999 Cont .’d

Creating the Analytic PIF-ER-ACRE Merged Dataset (2) 8  Sort the ER-PIF and the ACRE IP data by AETC LPS (if applicable) PROG_ID PIF_ID. The ER-PIF dataset is further sorted by PIFDATE  Merge the ER-PIF-IP by AETC LPS PROG_ID PIF_ID  De-duplicate the data based on the key variables AETC, LPS (if applicable), PROG_ID, PIF_ID [*Note, this deletes <200 records]  Sort the all-region ACRE FUP by AETC LPS (if applicable) PROG_ID PIF_ID  Sort the previously created ER-PIF-IP dataset by AETC LPS (if applicable) PROG_ID, PIF_ID  Merge the ER-PIF-IP with the ACRE FUP by these key variable  Restrict the analytic dataset to records with a valid, non-missing PIF_ID with a PIF available [Note, approx 20K records removed]

PIF ID 9 month of birth + day of birth + last 4 digits of SSN PIF_ID  PIF ID is available on the PIF, ACRE IP , and ACRE FUP data  Though not on the ER form, the Program ID on the PIF and ER allows PIF IDs to be associated with events  PIF ID used for matching  Across training events (repeat trainees)  Across evaluation forms (ACRE IP and FUP)

NEC valid PIF ID algorithm 10  Valid PIF ID contains:  Valid month of birth (1-12)  Valid day of birth (1-31)  Valid last 4 digits of SSN (≥1 and not 9999)  Valid PIF ID is a numeric value <99999999  Examples of invalid PIF IDs:  99999999  0  . [missing]  12345678  04049999  1122420932  Records with invalid PIF IDs are excluded from regression analyses

De-Duplication Examples 11  For overall ACRE regression analyses:  ER-PIF-ACRE dataset restricted to records with a valid PIF ID and with a linked PIF  Restricted dataset sorted by combined AETC region, PIF ID, eligibility for ACRE IP , having associated IP record, and PIF date  Last record is outputted  For MAI ACRE regression analyses, similar:  ER-PIF-ACRE dataset restricted to records with a valid PIF ID and with a linked PIF  Restricted ER-PIF-ACRE dataset sorted by combined AETC region, PIF ID, having an MAI training record, eligibility for ACRE IP , having associated IP record, and PIF date  Last record is outputted

Recoding & Analysis 12

Eligible Records for ACRE Regression Analyses 13  Last eligible record among repeat trainees is used  “Eligible” means the PIF_ID is not an invalid code according to the NEC algorithm, there is truly an associated PIF in the linked dataset  Analytic population includes:  For IP: targeted IP trainee (i.e., attended Level 1, 2, or 3 training), who has an associated PIF and IP record, and is a direct HIV provider (PIF13=1)  For FUP: targeted FUP trainee (i.e., attended Level 2 training and topic included clinical management [ER4_1-16] or prevention and behavior change [ER4_29-31] topics), who has an associated PIF and FUP record, and is a direct HIV provider (PIF13=1)

ACRE IP Eligible Trainings 14 ACRE immediate post questions asked immediately after training event ER9_1>0 -OR- ER9_2>0 -OR- ER9_3>0 Event Record form

ACRE FUP Eligible Trainings 15 ACRE follow-up asked 6 weeks after training through a web-based survey ER4_1=1 or ER4_2=1 or etc. -AND- ER9_2>0 ANY …. or ER4_31=1 Event Record form

FY 11/12 AETC Cross-Region Trainees in IP Analyses 16 N = 108,687 excludes n = 2,459 N = 72,642 N = 108,687 event records without a PIF ACRE IP records received by FY 11-12 trainees (based on associated and n = 5,736 records NEC linked AETC PIF and ER) with an invalid PIF ID. This number includes repeat trainees. n = 45,452 linked ER-PIF-ACRE IP Though n = 93,756 records n = 42,465 n = 2,987 fulfilled the IP target criteria, linked records and a linked records and NOT a n = 42,465 (45.3%) ER-PIF- targeted IP training targeted IP training IP records that linked and fulfilled the target. n = 30,331 Of these, n = 15,979 linked records, IP targeted, (52.7%) indicated they were and trainee’s last record in direct HIV providers on the FY 11-12 PIF. Data source: cross-region ER-PIF and ACRE IP FY11-12.

FY 11/12 AETC Cross-Region Trainees in FUP Analyses 17 N = 108,687 excludes n = 2,459 N = 3,847 N = 108,687 event records without a PIF ACRE FUP records received FY 11-12 trainees (based on associated and n = 5,736 records by NEC linked AETC PIF and ER) with an invalid PIF ID. This number includes repeat trainees. n = 2,620 linked ER-PIF-ACRE FUP Though n = 61,647 records n = 2,018 n = 602 fulfilled the FUP target linked records and a linked records and NOT a criteria, n = 2,018 (3.3%) targeted FUP training targeted FUP training ER-PIF-FUP records that linked and fulfilled the target. Of these, n = 1,014 (59.4%) n = 1,707 indicated they were direct linked records, FUP targeted, HIV providers on the PIF and and trainee’s last record in FY 11-12 FUP survey. Data source: cross-region ER-PIF and ACRE FUP FY11-12.

Analytic Variables 18  Regression models have included the following predictors:  Big 6  Worked in Ryan White funded setting  Minority provider  Minority serving  Provider experience  HIV+ clients per month  Repeat trainee  All of the above predictors come directly from the PIF except for Repeat trainee status, which is based on the linked PIF-ER  Regression models are restricted to direct providers of HIV+  ACRE FUP web survey is targeted to direct providers

Analytic Variable: Clinical Providers “BIG 6” 19  Comes from PIF question 3 PIF3 Mutually exclusive Clinical providers encompass 7 professional categories, though we often refer to them as “big 6” All other non-missing responses are coded as non-clinical providers Participant Information Form

Analytic Variable: Ryan White-Funded 20  From the RWFUND administrative variable on the bottom of the PIF RWFUND =1 =0  Exceptions apply: some regions have advised the NEC to use PIF8A for this information PIF8A =1 =0 =9 Participant Information Form

Analytic Variable: Minority Provider 21  A minority provider is Hispanic, multiracial, AI/AN, Asian, Native Hawaiian or Mutually exclusive PIF9 =0 =1 Pacific Islander, or Black Not mutually exclusive  A non-minority provider is a PIF10_1 PIF10_2 PIF10_3 non-Hispanic White provider PIF10_4 PIF10_5 with only a single race indicated  Those without any race indicated are left as missing Participant Information Form

Analytic Variable: Minority Serving 22 Skip pattern: This question should only be answered if PIF12_2 PIF12_1=1 and PIF13=1 =0 =1 =2 =3 =4  Among providers with direct service experience to HIV-infected clients (PIF12_1=1 and PIF13=1):  “Minority serving” (i.e., serves greater than half minorities): PIF12B = 3 or 4  Not minority serving (i.e., serves fewer than half minorities): PIF12B = 0, 1, or 2 Participant Information Form

Analytic Variable: Provider Experience 23 Skip pattern: This question PIF14 should only be answered if PIF12_1=1 and PIF13=1 = continuous numeric variable  Among providers with direct service experience to HIV-infected clients (PIF12_1=1 and PIF13=1):  Novice: 0 to <2 years of experience  New: 2 to <3 years of experience  Experienced: 3 or more years of experience