geocausal0.3.4 package

Causal Inference with Spatio-Temporal Data

conv_owin_into_sf

Convert windows into sf objects

get_base_dens

Get the baseline density

get_cate

Generate a Hajek estimator for heterogeneity analysis

get_cf_dens

Get counterfactual densities

get_cf_sum_log_intens

Calculate the log counterfactual densities

get_dist_focus

Get distance maps

get_dist_line

Get distance maps from lines and polygons

get_distexp

Get the expectation of treatment events with arbitrary distances

get_elev

Get elevation data

get_em_vec

convert a list of im objects to a vector

get_est

Get causal estimates comparing two scenarios

get_estimates

Generate a Hajek estimator

get_hfr

Create a hyperframe

get_hist

Obtain histories of treatment or outcome events

get_obs_dens

Generate observed densities

get_power_dens

Get power densities

get_var_bound

Calculate variance upper bounds

get_weighted_surf

Generate average weighted surfaces

get_window

Generate a window

imls_to_arr

convert a list of im objects to a three-dimensional array

pixel_count_ppp

Get number of events in a pixel

plot.cate

Plot estimated CATE

plot.cflist

Plot simulated counterfactual densities

plot.distlist

Plot distance-based expectations

plot.est

Plot estimates

plot.hyperframe

Plot estimates

plot.im

Plot im

plot.imlist

Plot im objects (list)

plot.list

Plot lists

plot.obs

Plot observed densities

plot.powerlist

Plot simulated power densities

plot.ppplist

Plot point pattern (list)

plot.weights

Plot weights

predict_obs_dens

Perform out-of-sample prediction

print.cate

Print results

print.est

Print results

sim_cf_dens

Simulate counterfactual densities

sim_power_dens

Simulate power densities

smooth_ppp

Smooth outcome events

summary.cate

Summarize results

summary.est

Summarize results

summary.obs

Summarize results

Spatio-temporal causal inference based on point process data. You provide the raw data of locations and timings of treatment and outcome events, specify counterfactual scenarios, and the package estimates causal effects over specified spatial and temporal windows. See Papadogeorgou, et al. (2022) <doi:10.1111/rssb.12548> and Mukaigawara, et al. (2024) <doi:10.31219/osf.io/5kc6f>.