version 0.1.3

DESCRIPTION

@@ -1,12 +1,13 @@
 Package: MoNAn
 Type: Package
 Title: Mobility Network Analysis
-Version: 0.1.2
-Date: 2023-08-15
+Version: 0.1.3
+Date: 2024-02-04
 Authors@R: c(person("Per", "Block", role = c("cre", "aut", "cph"), email = "block@soziologie.uzh.ch", 
         comment = c(ORCID = "0000-0002-7583-2392")), 
     person("Christoph", "Stadtfeld", role = "aut", comment = c(ORCID = "0000-0002-2704-2134")),
-    person("Nico", "Keiser", role = "aut"))
+    person("Nico", "Keiser", role = "aut"),
+    person("Marion", "Hoffman", role = "aut"))
 Description: Implements the method to analyse weighted mobility networks or distribution networks as outlined in: 
     Block, P., Stadtfeld, C., & Robins, G. (2022) <doi:10.1016/j.socnet.2021.08.003>. 
     The purpose of the model is to analyse the structure of mobility, 
@@ -21,10 +22,11 @@ Imports: snowfall (>= 1.84-6.2), methods
 RoxygenNote: 7.2.3
 Suggests: knitr, rmarkdown
 NeedsCompilation: no
-Packaged: 2023-08-29 13:50:32 UTC; per
+Packaged: 2024-02-05 12:19:42 UTC; per
 Author: Per Block [cre, aut, cph] (<https://orcid.org/0000-0002-7583-2392>),
   Christoph Stadtfeld [aut] (<https://orcid.org/0000-0002-2704-2134>),
-  Nico Keiser [aut]
+  Nico Keiser [aut],
+  Marion Hoffman [aut]
 Maintainer: Per Block <block@soziologie.uzh.ch>
 Repository: CRAN
-Date/Publication: 2023-08-29 17:00:08 UTC
+Date/Publication: 2024-02-05 12:40:12 UTC

MD5

@@ -1,19 +1,22 @@
-fc078fa4019abf074f3f5d77a1918e44 *DESCRIPTION
-e0f77c1cd8d2c6306d0677ff89feadf5 *NAMESPACE
-a21acc25ca4e47f9fc820f067b149768 *R/1_hiddenFunctions.R
-7a0ed1249bf2f93013de03eadc84d993 *R/2_effectFunctions.R
+896856b7e6c7053c5fe48bb2de816a81 *DESCRIPTION
+0e69fc2c485b85fcd508877e1b940cec *NAMESPACE
+b950660784725f27005ec74d3e56e2ac *NEWS.md
+68e8f76910e9b70cd6026c20dda15244 *R/1_hiddenFunctions.R
+5ab2511df4b86a54287715c40e8e7727 *R/2_effectFunctions.R
 a2e222be5db7297c706e674938bcca89 *R/2a_effectFunctions_exogenous.R
-84bbcacfa2e0eaab6bc71fde5f282951 *R/2b_effectFunctions_loops.R
-fc5efafac87b9f1e93ba64d65a945938 *R/2c_effectFunctions_concentration.R
-afa6bdaee40ce855b7c81e571ad65521 *R/2d_effectFunctions_reciprocity.R
-c518774df6cb70018cd8333464ce7af6 *R/2e_effectFunctions_transitivity.R
-1028dfdaf16404caa12e65883543eb00 *R/3_coreFunctions.R
+04bf437debe88e63c5dd9606e768d263 *R/2b_effectFunctions_loops.R
+350c0536d963b1b30dd55c936867c2c2 *R/2c_effectFunctions_concentration.R
+abf1640e2f7f20cabb87a7a03dc6ad3b *R/2d_effectFunctions_reciprocity.R
+7658e04ecb52a355ef522c65ef1a04dc *R/2e_effectFunctions_transitivity.R
+d01d45efebe6b5b573880d248f04b805 *R/2x_effects_test.R
+da76cafa4371887f6f7d9dff38394e80 *R/3_coreFunctions.R
 42ce187a6b6027774b4f180c6b77ee1a *R/4_auxiliaryFunctions.R
 318289e507330a4bacd3f5dc5123d7e7 *R/5_gofParamFunctions.R
 df6cc46bc7fae1a55b713f3d5065b35a *R/MoNAn-package.R
-0c76cf98c9d13a9e6a469d70cd7f0010 *R/mobilityData.R
+b4f2bcdbfc04b12a3bac3cd07a4847de *R/mobilityData.R
 91c8dfa9876f8f4247561ecb872911cd *R/myOutcomeObjects.R
-61ccbe3e6eab83b74cda42289218dc26 *README.md
+fc6e4e4b7be3187a56b64c5e09d31587 *R/sysdata.rda
+1f8ed71a4a25d55a9c0a19d817b50732 *README.md
 7080893e02c49cd296d4424b9be55069 *build/partial.rdb
 74e2806b571377c74369affeb0b4b149 *data/indSex.rda
 f379efcd7e512d40b027ccaadc5b1983 *data/mobilityEdgelist.rda
@@ -25,13 +28,16 @@ fc30b8ed48dcd66634d78479e8adf970 *data/myEffects.rda
 2bfc06a2c2bc24f3dfb19464115499c1 *data/myState.rda
 cc4c941ce67f5462b75b56e576622dfe *data/orgRegion.rda
 9998a893c2dbbf2b20d493d5d3e7a74a *data/orgSize.rda
-f5ba16545263b150575c5b060c3dc9ec *man/MoNAn-package.Rd
+24dbc7408aa89a472de89181b3fb62fa *man/MoNAn-package.Rd
 948a67ef03577108a0548250fe02e4f5 *man/alter_covariate.Rd
 17681a2df2c541a87b63a2bc9f60af4b *man/autoCorrelationTest.Rd
-7105fdd78873eec2cb4d877b3f565938 *man/concentration_GW.Rd
-64026dae76b04962a7b65aa3989aae07 *man/concentration_GW_dyad_covar_bin.Rd
+bdc34929ad931b9824f6409765576d96 *man/concentration_GW.Rd
+04651f93aad6ee892c6d9a413f4fe5c2 *man/concentration_GW_dyad_covar.Rd
 c5238d0d84ce7ae8757fa9b6bff671ec *man/concentration_basic.Rd
-e9f9810d2cdc1a9cb407e4aa8a028ae9 *man/createAlgorithm.Rd
+ec854ae92d1ebfa885e31f1c3e56bb13 *man/concentration_prop.Rd
+3c88a3fe15a9669030c77fa3ae60dde7 *man/concentration_prop_orig_cov.Rd
+7790bcc6c3a8c16c1597738d3a1c40b1 *man/concentration_rankGW.Rd
+00932f6d22b4793ad4e00f1cda0326ed *man/createAlgorithm.Rd
 47c8c502b16c67ce5fed6b75f01a470f *man/createEdgelist.Rd
 8eba45cedeffecc4eac432efd8d968e9 *man/createEffectsObject.Rd
 0275629e8b72cd30c34c6c09c91879ce *man/createNetwork.Rd
@@ -42,7 +48,7 @@ a18cf408cb2aa724aa523f7695915a08 *man/createNodeVariable.Rd
 51b10fc6e703fb35fafd5ad43696931b *man/crowding_out_prop_covar_bin.Rd
 bcafba8d085f97364cfd46c81aee7e06 *man/dyadic_covariate.Rd
 c7e5d98fbac6b1198e0b094c26c9729b *man/dyadic_covariate_resource_attribute.Rd
-9f7e76362fbaec48605a543a76ac06d7 *man/estimateMobilityNetwork.Rd
+fbe597727af8c8de158854e3aac0536f *man/estimateMobilityNetwork.Rd
 5f3dbb5e6c2f200c1dc005ab421b9cc7 *man/extractTraces.Rd
 0e3a0c5de1e1b9736e04f659dde1feda *man/figures/README-unnamed-chunk-15-1.png
 354b1982c7e6a0d53948930b339a52c1 *man/figures/README-unnamed-chunk-15-2.png
@@ -67,25 +73,37 @@ af5800f5e3cc905d65ebf777a707f59f *man/figures/README-unnamed-chunk-18-3.png
 d4ce37c9f4b8e5ae5754ad7b93d1be74 *man/getTieWeights.Rd
 8bdee67010eb4fc559ed2c55ccb22507 *man/gofMobilityNetwork.Rd
 d9f6d5e83092d8bfedbc62de1eab7195 *man/in_ties_loops.Rd
+96b99fd039be44e1a163c1b4c9e3773e *man/in_weights_GW.Rd
 eae7a0ef9e2683ee4dc8408ee74e3878 *man/in_weights_exponent.Rd
 3ba8523207b373ced583c7284986e8dc *man/loops.Rd
 35e5b2feca34845664f39e8676558271 *man/loops_GW.Rd
+51fc2912c75d5a1f0781e7e3a875af90 *man/loops_additional_origin.Rd
 6570e832b484404826d4a08797d807c5 *man/loops_node_covar.Rd
 64f1d507404fc4819fb6dae20e073f4a *man/loops_resource_covar.Rd
 79af17244b3b1935708d5fae1e0f071d *man/loops_resource_covar_node_covar.Rd
-05a1b254285d1fddcaa6c46c3d05c602 *man/mobilityData.Rd
+c2faf6ee2b138131bada61ffea8803d4 *man/loops_x_loops_additional_origin.Rd
+5fa07cd7c9404980524652fce343db09 *man/mobilityData.Rd
 6c9fb9d8b48e04f3e15844bd94e224f2 *man/myOutcomeObjects.Rd
 673bf084277e6655b7251e340aab089e *man/present_relations.Rd
-badabd77cf7bfbb058cb8bbfa2becb8d *man/reciprocity_GW.Rd
-859a0148163717d6a2f0468d9ce0290b *man/reciprocity_GW_dyad_covar_bin.Rd
+5320a60bd9667efccc900b7085d6241e *man/reciprocity_GW.Rd
+2d4793ae09c09261779ad4cb3874b7f2 *man/reciprocity_GW_dyad_covar.Rd
+af9b3703978315b0681398455cf93935 *man/reciprocity_GW_dyad_covar_bin.Rd
 d80c09233e44e50782145d19ff4bedec *man/reciprocity_basic.Rd
 bf6fb147777801c31f03d6750c1a05ab *man/reciprocity_min.Rd
+c2fb499b2fe8269fbe8a17cb77f029d0 *man/reciprocity_min_dyad_covar.Rd
 9d36a4752db8d79f468d760a6094d306 *man/reciprocity_min_resource_covar.Rd
 82aa8005716e5243047201be37872e5f *man/resource_covar_to_node_covar.Rd
 18a29720c9c0c4c9cc1fed6483f06287 *man/same_covariate.Rd
 f44c9d205621de2be0e28c13f7f78099 *man/scoreTest.Rd
 2c94679f25fd339dabb377e032465bf8 *man/sim_covariate.Rd
-d5d0c3633f840bd15d9e4f4c8b483402 *man/simulateMobilityNetworks.Rd
+0522da2f247c2b135be3ed7c8a27c8b3 *man/simulateMobilityNetworks.Rd
 e3fda95b9366212b682d2479af1ded62 *man/staying_by_prop_bin_inflow.Rd
+38c78c1991c8354722f814cfa1953bb1 *man/target_change_match.Rd
+c67407e0df2c1d4bc1d16539788f5e7a *man/test_effect.Rd
+fabd94e5e3be125b7bf4848f0c7b8181 *man/transitivity_GW.Rd
+fa68fd0196bc899db04b80b5050d9cdb *man/transitivity_basic.Rd
 651adf24f829b5d0313d7199c797f283 *man/transitivity_min.Rd
 ab9d6c92a364b82ef1de83930e01cb13 *man/transitivity_netflow.Rd
+ec415f029ef856edcaf9db8b125ff3ce *man/triad120C.Rd
+c3bfc3bc42c8c442cbf3c3b1dd1a1cd9 *man/triad120D.Rd
+8a8301e9a72153a68a11d5f72a4e64cb *man/triad120U.Rd

NAMESPACE

@@ -13,6 +13,10 @@ export(
   plot.gof.stats.monan, 
   plot.traces.monan, print.result.monan, print.scoretest.monan, scoreTest,
 
+  # test functions
+  target_change_match,
+  test_effect,
+
   # effect functions: exogenous
   alter_covariate, dyadic_covariate,
   dyadic_covariate_resource_attribute,
@@ -21,22 +25,27 @@ export(
 
   # effect functions: loops
   loops, loops_GW, loops_node_covar, 
-  loops_resource_covar_node_covar, loops_resource_covar, 
+  loops_resource_covar_node_covar, loops_resource_covar,
+  loops_additional_origin,
+  loops_x_loops_additional_origin,
 
   # effect functions: concentration
-  concentration_basic, concentration_GW, concentration_GW_dyad_covar_bin,
+  concentration_basic, concentration_GW, concentration_GW_dyad_covar,
+  concentration_prop, concentration_prop_orig_cov, concentration_rankGW,
 
   # effect functions: reciprocity
   reciprocity_basic,
-  reciprocity_min, reciprocity_min_resource_covar,
-  reciprocity_GW, reciprocity_GW_dyad_covar_bin,
+  reciprocity_min, reciprocity_min_resource_covar, reciprocity_min_dyad_covar,
+  reciprocity_GW, reciprocity_GW_dyad_covar_bin, reciprocity_GW_dyad_covar,
 
   # effect functions: transitivity
-  transitivity_min, transitivity_netflow,
+  transitivity_basic, transitivity_min, transitivity_netflow, transitivity_GW,
+  triad120D, triad120U, triad120C,
 
   # effect functions: other
   crowding_out_prop_covar_bin,  
   in_ties_loops, in_weights_exponent, 
+  in_weights_GW,
   present_relations,  staying_by_prop_bin_inflow, 
 
   # gof param functions

NEWS.md

@@ -0,0 +1,5 @@
+# MoNAn 0.1.3
+
+# MoNAn 0.1.2
+
+* Added a `NEWS.md` file to track changes to the package.

R/1_hiddenFunctions.R

@@ -8,6 +8,73 @@ binarizeNetwork <- function(network) {
 }
 
 
+# checkProcessState
+checkProcessState <- function(state) {
+
+  # extract dependent variable
+  dep.var <- state$dep.var
+
+  # make sure that dependent variable has corresponding edgelist
+  if (!(dep.var %in% names(state))) {
+    stop("Dependent variable has no corresponding edgelist in the state object.")
+  }
+
+  # is edgelist of class 'edgelist.monan'?
+  if (!(inherits(state[[dep.var]], "edgelist.monan"))) {
+    stop("Dependent variable is not of class 'edgelist.monan'.")
+  }
+
+
+  # extract nodeset names defined in edgelist
+  nodesets <- c()
+  nodesets[1] <- state[[dep.var]]$nodeSet[1]
+  nodesets[2] <- state[[dep.var]]$nodeSet[2]
+  nodesets[3] <- state[[dep.var]]$nodeSet[3]
+
+  # do nodeset names from edgelist have a corresponding nodeset and are they of class 'nodeset.monan'?
+  for (i in 1:length(nodesets)) {
+    if (!(nodesets[i] %in% names(state))) {
+      stop(paste(nodesets[i], "has no corresponding object.",
+                 "Nodesets specified in the edgelist must have a corresponding object with the same name."))
+    }
+    if (!(inherits(state[[nodesets[i]]], "nodeSet.monan"))) {
+      stop(paste(nodesets[i], "is not of class 'nodeSet.monan'."))
+    }
+  }
+
+  # do dependent variable and individual nodeset have the same number of observations?
+  if (!(dim(state[[dep.var]]$data)[1] == length(state[[nodesets[3]]]$ids))) {
+    stop("Dependent variable and individual nodeset do not have the same number of observations.")
+  }
+
+  # extract covar names
+  covars <- names(state)[!(names(state) %in% c(dep.var, nodesets, "dep.var"))]
+
+  # if there are covars, check them
+  if (length(covars) != 0) {
+
+    # are covars of class 'nodeVar.monan' or 'network.monan'? do they have correctly
+    # specified nodeset names and are these nodesets of the correct size?
+    for (i in 1:length(covars)) {
+      #class
+      if (!(inherits(state[[covars[i]]], "nodeVar.monan") || 
+            inherits(state[[covars[i]]], "network.monan"))) {
+        stop(paste(covars[i], "must either be of class 'nodeVar.monan' or 'network.monan'."))
+      }
+      # nodeset names
+      if (!(all(state[[covars[i]]]$nodeSet %in% names(state)))) {
+        stop(paste("The nodeset of covar '", covars[i], "' has no corresponding object.",
+                   "Nodesets assigned when creating covars must have a corresponding object with the same name."           ))
+      }
+      # nodeset sizes
+      if (!(state[[covars[i]]]$size[1] == length(state[[state[[covars[i]]]$nodeSet[1]]]$ids))) {
+        stop(paste("The covar '", covars[i], "' is not of the same size as its assigned nodeset."))
+      }
+    }
+  }
+}
+
+
 # getCovarianceMatrix
 getCovarianceMatrix <- function(statistics) {
   meanStatistics <- colMeans(statistics)

R/2_effectFunctions.R

@@ -199,6 +199,70 @@ in_weights_exponent <-
   }
 
 
+#' in_weights_GW
+#' 
+#' Is there a preferential attachment in the mobility network, i.e., do individuals 
+#' move particularly to popular destinations?
+#' The geometrically weighted version avoids degeneracy.
+#'
+#' @param dep.var 
+#' @param state 
+#' @param cache 
+#' @param i 
+#' @param j 
+#' @param edge 
+#' @param update 
+#' @param getTargetContribution 
+#' @param alpha 
+#'
+#' @return Returns the change statistic or target statistic of the effect for 
+#' internal use by the estimation algorithm.
+#' @keywords internal
+in_weights_GW <-
+  function(dep.var = 1,
+           state,
+           cache,
+           i,
+           j,
+           edge,
+           update,
+           getTargetContribution = FALSE,
+           alpha = 2) {
+    if (alpha <= 0) {
+      stop("Alpha parameter in in_weights_GW weights function must be positive")
+    }
+
+    in_weight <- (sum(cache[[dep.var]]$valuedNetwork[,j]))
+
+    # a target contribution is calculated even for unconnected i-j pairs
+    if (getTargetContribution) {
+      g_cum <- function(y, a){
+        contr <- 0
+        for(k in 0:y){
+          contr <- contr + (y-k) * exp(-log(a)*k)
+        }
+        contr - y
+      }
+
+      return(g_cum(y = in_weight, a = alpha) / (length(cache[[dep.var]]$valuedNetwork[, j])))
+    }
+
+    g_mar <- function(y, a){
+      contr <- 0
+      for(k in 0:y){
+        contr <- contr + exp(-log(a)*k)
+      }
+      contr - 1
+    }
+
+    if(update < 0){
+      return(update * g_mar(y = (in_weight + update), a = alpha))
+    }
+    if(update > 0){
+      return(update * g_mar(y = in_weight, a = alpha))
+    }
+  }
+
 #' present_relations
 #' 
 #' Do individuals move along many or few paths out of their origin? This models