generate_CSU_site

Produces the **lossless**, pattern-level sufficient statistics for a single site:
pattern counts `Ck`, outcome sums `Sk = \(\sum y\)`, squared sums `S2k = \(\sum y^2\)`, and the
corresponding pattern matrix `X0`. Works for both binomial and Poisson outcomes
(for Bernoulli, `S2k == Sk`).

internal

A collection of privacy-preserving distributed algorithms (PDAs) for conducting federated statistical learning across multiple data sites. The PDA framework includes models for various tasks such as regression, trial emulation, causal inference, design-specific analysis, and clustering. The PDA algorithms run on a lead site and only require summary statistics from collaborating sites, with one or few iterations. The package can be used together with the online data transfer system (<https://pda-ota.pdamethods.org/>) for safe and convenient collaboration. For more information, please visit our software websites: <https://github.com/Penncil/pda>, and <https://pdamethods.org/>.

Chongliang Luo

Privacy-Preserving Distributed Algorithms

Rui Duan

Mackenzie Edmondson

Jiayi Tong

Xiaokang Liu

Kenneth Locke

Jie Hu

Bingyu Zhang

Yicheng Shen

Yudong Wang

Yiwen Lu

Lu Li

Yong Chen

Penn Computing Inference Learning (PennCIL) lab 

generate_CSU_site function

<dl><dt>df_site</dt>
<dd>Data frame for one site. Must include outcome column named `y`
and the fixed-effect covariates in `x_names`. If `intercept = TRUE`, the
function will add an `Intercept` column when missing.</dd>
<dt>x_names</dt>
<dd>Character vector of fixed-effect names (binary covariates; may
include `"Intercept"` if `intercept = TRUE`).</dd>
<dt>intercept</dt>
<dd>Logical; include a fixed intercept in the pattern matrix.</dd></dl>

Arguments

One-shot site summaries for COLA-GLMM — generate_CSU_site

<dl>

<dt>df_site</dt>
<dd>Data frame for one site. Must include outcome column named `y`
and the fixed-effect covariates in `x_names`. If `intercept = TRUE`, the
function will add an `Intercept` column when missing.</dd>


<dt>x_names</dt>
<dd>Character vector of fixed-effect names (binary covariates; may
include `"Intercept"` if `intercept = TRUE`).</dd>


<dt>intercept</dt>
<dd>Logical; include a fixed intercept in the pattern matrix.</dd>

</dl>

One-shot site summaries for COLA-GLMM

generate_CSU_site: One-shot site summaries for COLA-GLMM

Description

Usage

Value

Arguments

Examples