add spglm citation to joss

inst/joss/paper.Rmd

@@ -147,7 +147,7 @@ ggplot() +
     theme_bw()
 ```
 
-Generalized spatial linear models for binary, count, proportion, and skewed data are available via the `ssn_glm()` function. `ssn_lm()` and `ssn_glm()` also accommodate several advanced features, which include nonspatial random effects as in `lme4` [@bates2015lme4] and `nlme` [@pinheiro2006mixed] Euclidean anisotropy [@zimmerman2024spatial], and more. In addition to modeling, simulating data on a stream network is performed via `ssn_simulate()`. 
+Spatial generalized linear models for binary, count, proportion, and skewed data [@ver2024marginal] are applied to stream networks via the `ssn_glm()` function. `ssn_lm()` and `ssn_glm()` also accommodate several advanced features, which include nonspatial random effects as in `lme4` [@bates2015lme4] and `nlme` [@pinheiro2006mixed] Euclidean anisotropy [@zimmerman2024spatial], and more. In addition to modeling, simulating data on a stream network is performed via `ssn_simulate()`. 
 
 # Discussion
 

inst/joss/paper.bib

@@ -431,6 +431,14 @@ @article{ver2014ssn
   doi={10.18637/jss.v056.i03}
 }
 
+@article{ver2024marginal,
+  title={Marginal inference for hierarchical generalized linear mixed models with patterned covariance matrices using the Laplace approximation},
+  author={{Ver Hoef}, Jay M and Blagg, Eryn and Dumelle, Michael and Dixon, Phillip M and Zimmerman, Dale L and Conn, Paul B},
+  journal={Environmetrics},
+  year={2024},
+  doi={10.1002/env.2872}
+}
+
 @Book{wickham2016ggplot2,
   author = {Hadley Wickham},
   title = {{ggplot2}: Elegant Graphics for Data Analysis},

inst/joss/paper.log

@@ -1,4 +1,4 @@
-This is XeTeX, Version 3.141592653-2.6-0.999995 (TeX Live 2023) (preloaded format=xelatex 2024.3.4)  17 JUL 2024 17:09
+This is XeTeX, Version 3.141592653-2.6-0.999995 (TeX Live 2023) (preloaded format=xelatex 2024.3.4)  23 JUL 2024 08:56
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.
@@ -1077,12 +1077,12 @@ Package fancyhdr Warning: \headheight is too small (62.59596pt):
 (fancyhdr)                \addtolength{\topmargin}{-0.95425pt}.
 
 [7]
-Overfull \hbox (56.36137pt too wide) in paragraph at lines 878--883
+Overfull \hbox (56.36137pt too wide) in paragraph at lines 879--884
 [][][][][][][][] [] [][] [] [][][][] [] [][][] [] [][][][][] [] [][][][][][][] [] [][][][][] [] [][][][][][][][] [] [][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][][] []
  []
 
 
-Underfull \hbox (badness 1231) in paragraph at lines 890--894
+Underfull \hbox (badness 1231) in paragraph at lines 891--895
 \TU/lmr/m/n/10 data. Boulder, CO, USA: University Corporation for Atmospheric Research.
  []
 
@@ -1117,10 +1117,10 @@ Package logreq Info: Writing requests to 'paper.run.xml'.
 
  ) 
 Here is how much of TeX's memory you used:
- 36774 strings out of 476752
- 757639 string characters out of 5799757
+ 36775 strings out of 476752
+ 757660 string characters out of 5799757
  1948842 words of memory out of 5000000
- 58257 multiletter control sequences out of 15000+600000
+ 58258 multiletter control sequences out of 15000+600000
  564933 words of font info for 83 fonts, out of 8000000 for 9000
  14 hyphenation exceptions out of 8191
  84i,12n,87p,1194b,850s stack positions out of 10000i,1000n,20000p,200000b,200000s

inst/joss/paper.md

@@ -295,7 +295,7 @@ ggplot() +
 \caption{Predicted Middle Fork 2004 mean summer temperatures (Celsius) spaced one kilometer apart. As expected, temperature is predicted to be lower in areas of higher elevation.}\label{fig:steam-preds}
 \end{figure}
 
-Generalized spatial linear models for binary, count, proportion, and skewed data are available via the `ssn_glm()` function. `ssn_lm()` and `ssn_glm()` also accommodate several advanced features, which include nonspatial random effects as in `lme4` [@bates2015lme4] and `nlme` [@pinheiro2006mixed] Euclidean anisotropy [@zimmerman2024spatial], and more. In addition to modeling, simulating data on a stream network is performed via `ssn_simulate()`. 
+Spatial generalized linear models for binary, count, proportion, and skewed data [@ver2024marginal] are applied to stream networks via the `ssn_glm()` function. `ssn_lm()` and `ssn_glm()` also accommodate several advanced features, which include nonspatial random effects as in `lme4` [@bates2015lme4] and `nlme` [@pinheiro2006mixed] Euclidean anisotropy [@zimmerman2024spatial], and more. In addition to modeling, simulating data on a stream network is performed via `ssn_simulate()`. 
 
 # Discussion