README.Rmd

---
output: github_document
---

<!-- README.md is generated from README.Rmd. Please edit that file -->

```{r setup, include = F}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
# devtools::install_github("Hemken/Statamarkdown")
library(Statamarkdown)
```

# summclust

Stata module for cluster level measures of leverage, influence,  and a cluster jackknife variance estimator.

For a very detailed description see:

MacKinnon, J.G., Nielsen, M.Ø., Webb, M.D., 2022. [Leverage, influence,
and the Jackknife in Clustered Regression Models: Reliable Inference
Using Summclust](https://arxiv.org/abs/2205.03288). Stata Journal (accepted).    

### nlswork example - using regress

```{stata}
webuse nlswork, clear
keep if inrange(age,20,40)
reg ln_wage i.grade i.age i.birth_yr union race msp, cluster(ind)
```

### nlswork - using summclust

```{stata, echo=-1}
webuse nlswork, clear
keep if inrange(age,20,40)
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind)
```

### adding industry fixed effects using absorb

```{stata, echo=-1}
webuse nlswork, clear
keep if inrange(age,20,40)
summclust ln_wage msp union race, fevar(grade age birth_yr)     absorb(ind) cluster(ind) nog 
```
  
            
### Effective Number of Clusters using gstar or rho.

```{stata, echo=-1}
webuse nlswork, clear
keep if inrange(age,20,40)
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind) nog gstar

summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind) nog rho(0.5)
```
  
### All Output

```{stata, echo=-1}
webuse nlswork, clear
keep if inrange(age,20,40)
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind)  regtable rho(0.5) addmeans table 
```