Doc and vignette updates

Author: ngreifer

README.Rmd

@@ -13,7 +13,7 @@ knitr::opts_chunk$set(
 )
 ```
 
-# `apm`: Averaged Prediction Models
+## `apm`: Averaged Prediction Models
 
 <!-- badges: start -->
 <!-- badges: end -->
@@ -23,7 +23,7 @@ library(apm)
 data("ptpdata")
 ```
 
-## Supplying models
+### Supplying models
 
 We can specify the models to test using `apm_mod()`. This create a full cross of all supplied arguments, which include model formula, families, whether the outcome is logged or not, whether fixed effects are included or not, whether the outcome should be a difference, and whether outcome lags should appear as predictors. Below, we create a cross of 9 models.
 
@@ -50,7 +50,7 @@ models
 
 This leaves us with 10 models.
 
-## Fitting the models
+### Fitting the models
 
 Next we fit all 10 models to the data. We do so once for each validation time to compute the average prediction error that will be used to select the optimal model. All models are fit simultaneously so the simulation can use the full joint distribution of model parameter estimates. For each validation time, each model is fit using a dataset that contains data points prior to that time.
 
@@ -67,15 +67,14 @@ fits <- apm_pre(models,
 fits
 ```
 
-## Computing the ATT
+### Computing the ATT
 
 We compute the ATT using `apm_est()`, which uses bootstrapping to compute model uncertainty due to sampling along with uncertainty due to model selection.
 
 ```{r}
 est <- apm_est(fits,
                post_time = 2008,
-               M = 1,
-               R = 50)
+               M = 1)
 
 est
 

README.md

@@ -260,8 +260,7 @@ model selection.
 ``` r
 est <- apm_est(fits,
                post_time = 2008,
-               M = 1,
-               R = 50)
+               M = 1)
 
 est
 #> An `apm_est` object
@@ -272,12 +271,12 @@ est
 #>    - validation times: 
 #>    - post-treatment time: 2008
 #>  - sensitivity parameter (M): 1
-#>  - bootstrap replications: 50
+#>  - bootstrap replications: 1000
 #> 
 #> Use `summary()` or `plot()` to examine estimates and uncertainty bounds.
 
 summary(est)
 #>       Estimate Std. Error  CI low CI high z_value Pr(>|z|)
-#> ATT      60.12      40.13  -18.54  138.78   1.498    0.134
-#> M = 1        .          . -115.24  179.47       .        .
+#> ATT      61.65      39.80  -16.36  139.66   1.549    0.121
+#> M = 1        .          . -113.19  180.71       .        .
 ```

vignettes/demo.Rmd _dev/demo.Rmd

@@ -0,0 +1,83 @@
+@book{gelmanhill2006,
+	address = {New York, NY},
+	author = {Gelman, Andrew and Hill, Jennifer},
+	date-added = {2019-11-19 13:50:34 -0500},
+	date-modified = {2019-11-19 13:51:33 -0500},
+	publisher = {Cambridge University Press},
+	title = {Data Analysis Using Regression and Multilevel/Hierarchical Models},
+	year = {2006}}
+
+@article{manskipepper2018,
+	author = {Manski, Charles F and Pepper, John V},
+	date-added = {2020-01-17 21:32:17 -0400},
+	date-modified = {2020-04-07 11:34:02 -0400},
+	journal = {The Review of Economics and Statistics},
+	number = {2},
+	pages = {232-244},
+	title = {How Do Right-to-Carry Laws Affect Crime Rates? {C}oping with Ambiguity Using Bounded-Variation Assumptions},
+	volume = {100},
+	year = {2018}}
+
+@article{rambachanroth2023,
+	author = {Rambachan, Ashesh and Roth, Jonathan},
+	date-added = {2020-01-17 19:44:15 -0400},
+	date-modified = {2024-06-30 21:17:36 -0400},
+	journal = {Review of Economic Studies},
+	number = {5},
+	pages = {2555-2591},
+	title = {A More Credible Approach to Parallel Trends},
+	volume = {90},
+	year = {2023}}
+
+@book{gelmanhill2006,
+	address = {New York, NY},
+	author = {Gelman, Andrew and Hill, Jennifer},
+	date-added = {2019-11-19 13:50:34 -0500},
+	date-modified = {2019-11-19 13:51:33 -0500},
+	publisher = {Cambridge University Press},
+	title = {Data Analysis Using Regression and Multilevel/Hierarchical Models},
+	year = {2006}}
+
+@article{antonellietal2022,
+	author = {Antonelli, Joseph and Papadogeorgou, Georgia and Dominici, Francesca},
+	date-added = {2024-04-14 22:09:15 -0400},
+	date-modified = {2024-04-14 22:10:21 -0400},
+	journal = {Biometrics},
+	number = {1},
+	pages = {100-114},
+	title = {Causal inference in high dimensions: A marriage between {B}ayesian modeling and good frequentist properties},
+	volume = {78},
+	year = {2022}}
+
+@article{websteretal2014,
+	author = {Webster, Daniel and Crifasi, Cassandra Kercher and Vernick, Jon S},
+	date-added = {2022-07-16 17:07:41 -0400},
+	date-modified = {2022-07-16 17:08:58 -0400},
+	journal = {Journal of Urban Health: Bulletin of the {N}ew {Y}ork {A}cademy of {M}edicine},
+	number = {2},
+	pages = {293-302},
+	title = {Effects of the Repeal of {M}issouri's Handgun Purchaser Licensing Law on Homicides},
+	volume = {91},
+	year = {2014}}
+
+@article{hasegawaetal2019,
+	author = {Hasegawa, Raiden B and Webster, Daniel W and Small, Dylan S},
+	date-added = {2020-07-14 18:53:21 -0400},
+	date-modified = {2020-09-02 00:03:23 -0400},
+	journal = {Epidemiology},
+	number = {3},
+	pages = {371-379},
+	title = {Evaluating {M}issouri's Handgun Purchaser Law: A Bracketing Method for Addressing Concerns About History Interacting with Group},
+	volume = {30},
+	year = {2019}}
+
+@article{xuetal2020,
+	author = {Xu, Li and Gotwalt, Chris and Hong, Yili and King, Caleb B and Meeker, William Q},
+	date-added = {2023-12-08 23:38:35 -0500},
+	date-modified = {2023-12-08 23:39:46 -0500},
+	journal = {The American Statistician},
+	number = {4},
+	pages = {345-358},
+	title = {Applications of the Fractional-Random-Weight Bootstrap},
+	volume = {74},
+	year = {2020}}