Sentinel Routine Querying Tool Report Documentation

​

## L2 Comparison File Parameters

​

The L2 Comparison File file is optional. This file must be specified if creating an L2 (inferential analysis) report. This file defines the model parameters and the output to include in the report.

​

**Table 1. L2COMPARISONFILE specification**

​

| **Parameter** | **Field Name** | **Description** |

| --- | --- | --- |

|Group Display Order|ORDER|Unique number for each ANALYSISGRP. This is used to determine the order of ANALYSISGRPs in the report. All ANALYSISGRPs should receive a unique ORDER value. ORDER values should start at 1 and be contiguous. <br><br>  **Format:** Numeric <br> **Example:** 1|

|RunID Corresponding to ANALYSISGRP|RUNID|RunID assigned to the run that corresponds to the specified ANALYSISGRP. <br> <br>  **Format:** SAS character $5<br> **Example:** r01|

|Output PS Distribution Histograms|OUTPUTPSDISTRIBUTION| Indicator specifying whether to output histograms of PS distribution between exposure and control cohorts, before and after adjustment, when applicable. <br><br> Valid values are: <ul><li> **Y:** Output PS histograms </li><li> **N:** Do not output PS histograms </ul></li>  **Format:** SAS character $1<br> **Example:** Y|

|Output Conditional Analysis|OUTPUTCONDITIONAL| Indicator specifying whether to output conditional analysis <br><br> Valid values are: <ul><li> **Y:** Output conditional analysis in report </li><li> **N:** Do not output conditional analysis  </ul></li> **Note 1:** specification of OUTPUTCONDITIONAL is relevant only to Type 2 PS fixed ratio matching analyses (conditional analyis will be automatically output for a PS variable ratio matching, PS stratification, or covariate stratification report).<br><br>**Format:** SAS character $1<br> **Example:** Y|

|Output Unconditional Analysis|OUTPUTUNCONDITIONAL| Indicator specifying whether to output unconditional analysis in report. <br><br> Valid values are: <ul><li> **Y:** Output unconditional analysis </li><li> **N:** Do not output unconditional analysis </ul></li> **Note 1:** specification of OUTPUTUNCONDITIONAL is relevant only to Type 2 PS fixed ratio matching analyses (unconditional analyis will be automatically output for a Type 4 PS fixed ratio matching report)<br><br> **Format:** SAS character $1<br> **Example:** Y|

|Output Forest Plot|OUTPUTFORESTPLOT| Indicator specifying whether to output forest plots in report for corresponding ANALYSISGRP. <br><br> Valid values are: <ul><li> **Y:** Output forest plots </li><li> **N:** Do not output forest plots </ul></li> **Note 1:** if requesting forest plot(s), Figure F2 must be included in the Type 2 or Type 4 Figure File. <br><br> **Format:** SAS character $1<br> **Example:** Y|

| Categorical Variables to Add to Model for Additional Adjustment | CLASSVARS | List of categorical variables to include in the Cox model (if Type 2) or the logistic model (if Type 4) for adjustment. Applicable when utilizing patient level data only.<br><br> **Valid values** include classification variables included in input analytic file [RUNID]\_adjusted\_[periodid].sas7bdat <br><br> **Note 1:** additional adjustment is not possible when using the Cochran-Mantel-Haenszel method for percentile analysis. <br><br> **Format:** SAS character - length can vary <br>**Example:** sex |

| Continuous Variables to Add to Model for Additional Adjustment | NOCLASSVARS | Additional continuous variables, separated by a space, to add to Cox model (if Type 2) or to logistic model (if Type 4) for adjustment. Applicable when utilizing patient level data only. <br><br>**Valid values** include continuous variables included in input analytic file [runid]\_adjusted\_[periodid].sas7bdat <br><br> **Note 1:** additional adjustment is not possible when using the Cochran-Mantel-Haenszel method for percentile analysis.  <br><br> **Format:** SAS character - length can vary <br>**Example:** NUMIP |

| Convergence Status to Consider | CONVRULE | Enter the convergence status values for considering whether the model has converged.<br><br> **Valid values are:** <ul><li> **0:** Convergence satisfied  </li><li> **0:** Missing initial values for some parameters </li><li> **1:** Quasi-complete separation  </li><li> **1:** Complete separation  </li><li> 2: Ridging has failed to improve the likelihood  </li><li> **2:** Iteration limit reached without convergence  </li><li> **2 or 3:** Missing initial values for some of the parameters  </li><li> **2 or 3:** Line search has failed to improve the likelihood  </li><li> **2 or 3:** Improper initial values for the intercept estimates </li><li> **3:** Improper initial values for estimating the model parameters</ul></li> **Note 1:** Specify multiple values via a space-separated or comma-separated list <br><br>  **Note 2:** Valid values based on variable STATUS from dataset [runid]\_estimates\_[periodid].sas7bdat <br><br> **Note 3:** Only DPs meeting convergence status requirement will be considered for effect estimates. <br><br> **Format:** SAS character - length can vary <br> **Example:** 0,1 |

| Number of HDPS variables to select from each DP | TOPNHDPS | Enter the number of high-dimensional propensity score (HDPS) variables to select from each Data Partner.<br><br>**Format:** Numeric <br>**Example:** 10|