## ----setup, include = FALSE--------------------------------------------------- knitr::opts_chunk$set( collapse = TRUE, comment = "#>" ) library(tidycreel) ## ----complete_example, eval=FALSE--------------------------------------------- # library(tidycreel) # # # Standard workflow using complete trips (default) # data(example_calendar) # data(example_counts) # data(example_interviews) # # design <- creel_design(example_calendar, date = date, strata = day_type) |> # add_counts(example_counts) |> # add_interviews(example_interviews, # catch = catch_total, # effort = hours_fished, # harvest = catch_kept, # trip_status = trip_status, # trip_duration = trip_duration # ) # # # Estimate CPUE using complete trips only (default) # cpue <- estimate_catch_rate(design) # print(cpue) # # # Estimate total catch # total_catch <- estimate_total_catch(design) # print(total_catch) ## ----low_complete_warning, eval=FALSE----------------------------------------- # # If complete trip percentage drops below 10%, you'll see: # # Warning: Only 8% of interviews (n=5) are complete trips # # Best practice: ≥10% of interviews should be complete trips # # Consider extending survey hours or sampling more trips to completion ## ----anti_pattern, eval=FALSE------------------------------------------------- # # WRONG: Do not manually pool trip types # all_interviews <- rbind(complete_data, incomplete_data) # estimate_catch_rate(design_with_all_data) # INVALID — always, even after validation passes # # # WRONG: Do not use custom weights to combine # weighted_mean(c(complete_cpue, incomplete_cpue)) # INVALID! ## ----roving-default----------------------------------------------------------- roving_design <- creel_design( example_calendar, date = date, strata = day_type, survey_type = "instantaneous", h_open = 14 ) |> add_counts(example_counts, count_col = effort_hours) |> add_interviews( example_interviews, catch = catch_total, effort = hours_fished, n_anglers = n_anglers, harvest = catch_kept, trip_status = trip_status, trip_duration = trip_duration, interview_type = "roving" ) # Unspecified: routed to all-trip mean-of-ratios estimate_catch_rate(roving_design)$method # Named explicitly: complete trips, ratio-of-means estimate_catch_rate(roving_design, use_trips = "complete")$method ## ----validation_setup, eval=FALSE--------------------------------------------- # library(tidycreel) # # # Your survey data should have trip_status field # # Check trip type distribution # table(your_interviews$trip_status) # # # Ensure you have: # # - At least 10% complete trips (Pollock et al. 1994) # # - At least 30 incomplete trips (for stable estimates) # # - At least 10 complete trips (for ratio estimation) ## ----validation_design, eval=FALSE-------------------------------------------- # design <- creel_design(your_calendar, date = date, strata = day_type) |> # add_counts(your_counts) |> # add_interviews(your_interviews, # catch = catch_total, # effort = hours_fished, # trip_status = trip_status, # trip_duration = trip_duration # ) ## ----run_validation, eval=FALSE----------------------------------------------- # # Validate incomplete trips using TOST # validation <- validate_incomplete_trips(design, # catch = catch_total, # effort = hours_fished # ) # # print(validation) ## ----validation_plot, eval=FALSE---------------------------------------------- # # Print method automatically shows plot # print(validation) # Plot appears after text output # # # Or explicitly plot # plot(validation) ## ----example_pass------------------------------------------------------------- library(tidycreel) # Simulate data where catch rates are similar for complete vs incomplete set.seed(42) # Create calendar calendar <- data.frame( date = seq.Date(as.Date("2024-06-01"), as.Date("2024-06-14"), by = "day"), day_type = rep(c("weekday", "weekend"), length.out = 14) ) # Create counts counts <- data.frame( date = calendar$date, day_type = calendar$day_type, effort_hours = round(runif(14, min = 50, max = 150)) ) # Simulate interviews with SIMILAR catch rates for both trip types # (stationary catch rate throughout day) n_complete <- 50 n_incomplete <- 120 # Base CPUE around 2.4 fish/hour for both groups (PASSING scenario) complete_interviews <- data.frame( date = sample(calendar$date, n_complete, replace = TRUE), hours_fished = runif(n_complete, min = 2, max = 8), trip_status = "complete", trip_duration = runif(n_complete, min = 2, max = 8) ) complete_interviews$catch_total <- rpois(n_complete, lambda = complete_interviews$hours_fished * 2.4 ) incomplete_interviews <- data.frame( date = sample(calendar$date, n_incomplete, replace = TRUE), hours_fished = runif(n_incomplete, min = 1, max = 6), trip_status = "incomplete" ) # For incomplete trips, trip_duration = hours_fished (time interviewed, not total trip) incomplete_interviews$trip_duration <- incomplete_interviews$hours_fished # Similar CPUE for incomplete trips (2.3-2.5 range) incomplete_interviews$catch_total <- rpois(n_incomplete, lambda = incomplete_interviews$hours_fished * 2.35 ) interviews <- rbind(complete_interviews, incomplete_interviews) # Create design design <- creel_design(calendar, date = date, strata = day_type) |> add_counts(counts) |> add_interviews(interviews, catch = catch_total, effort = hours_fished, trip_status = trip_status, trip_duration = trip_duration ) # Run validation validation_pass <- validate_incomplete_trips(design, catch = catch_total, effort = hours_fished ) print(validation_pass) ## ----after_pass, eval=FALSE--------------------------------------------------- # # Now safe to use incomplete trips # cpue_incomplete <- estimate_catch_rate(design, use_trips = "incomplete") # print(cpue_incomplete) # # # Or use diagnostic mode to compare # cpue_diagnostic <- estimate_catch_rate(design, use_trips = "diagnostic") # print(cpue_diagnostic) ## ----example_fail------------------------------------------------------------- library(tidycreel) set.seed(123) # Same calendar and counts as before calendar <- data.frame( date = seq.Date(as.Date("2024-06-01"), as.Date("2024-06-14"), by = "day"), day_type = rep(c("weekday", "weekend"), length.out = 14) ) counts <- data.frame( date = calendar$date, day_type = calendar$day_type, effort_hours = round(runif(14, min = 50, max = 150)) ) # Simulate interviews with DIFFERENT catch rates (FAILING scenario) # Complete trips average full day (includes productive morning hours) # Incomplete trips are mostly afternoon interviews (lower catch rates) n_complete <- 45 n_incomplete <- 110 # Complete trips: higher CPUE (includes morning fishing, ~3.0 fish/hour) complete_interviews <- data.frame( date = sample(calendar$date, n_complete, replace = TRUE), hours_fished = runif(n_complete, min = 3, max = 8), trip_status = "complete", trip_duration = runif(n_complete, min = 3, max = 8) ) complete_interviews$catch_total <- rpois(n_complete, lambda = complete_interviews$hours_fished * 3.0 ) # Incomplete trips: lower CPUE (afternoon interviews, ~2.0 fish/hour) incomplete_interviews <- data.frame( date = sample(calendar$date, n_incomplete, replace = TRUE), hours_fished = runif(n_incomplete, min = 1, max = 5), trip_status = "incomplete" ) # For incomplete trips, trip_duration = hours_fished (time interviewed, not total trip) incomplete_interviews$trip_duration <- incomplete_interviews$hours_fished incomplete_interviews$catch_total <- rpois(n_incomplete, lambda = incomplete_interviews$hours_fished * 2.0 ) interviews_biased <- rbind(complete_interviews, incomplete_interviews) # Create design design_biased <- creel_design(calendar, date = date, strata = day_type) |> add_counts(counts) |> add_interviews(interviews_biased, catch = catch_total, effort = hours_fished, trip_status = trip_status, trip_duration = trip_duration ) # Run validation validation_fail <- validate_incomplete_trips(design_biased, catch = catch_total, effort = hours_fished ) print(validation_fail) ## ----after_fail, eval=FALSE--------------------------------------------------- # # DO NOT use incomplete trips # # Stick with default complete trip estimation # # `design_biased` is an access-point design, so an unspecified `use_trips` # # resolves to complete trips. On a roving design it would not -- name it. # cpue_complete <- estimate_catch_rate(design_biased, use_trips = "complete") # print(cpue_complete) # # # Investigate why estimates differ # # Possible reasons: # # - Time-of-day effects (morning vs afternoon catch rates) # # - Trip length correlates with skill level # # - Fish behavior changes throughout day (feeding windows) # # - Different angler types (early vs late arrivals) ## ----diagnostic_mode, eval=FALSE---------------------------------------------- # # Compare complete vs incomplete estimates # cpue_diagnostic <- estimate_catch_rate(design, # catch = catch_total, # effort = hours_fished, # use_trips = "diagnostic" # ) # # print(cpue_diagnostic) ## ----grouped_validation, eval=FALSE------------------------------------------- # # Validate with grouping # validation_grouped <- validate_incomplete_trips(design, # catch = catch_total, # effort = hours_fished, # by = day_type # ) # # print(validation_grouped) ## ----custom_threshold, eval=FALSE--------------------------------------------- # # Use stricter threshold (±15%), keeping the previous setting to restore later # old_opts <- options(tidycreel.equivalence_threshold = 0.15) # validation_strict <- validate_incomplete_trips(design, # catch = catch_total, # effort = hours_fished # ) # # # Use more permissive threshold (±25%) # options(tidycreel.equivalence_threshold = 0.25) # validation_permissive <- validate_incomplete_trips(design, # catch = catch_total, # effort = hours_fished # ) # # # Restore the threshold that was in effect before # options(old_opts) ## ----truncation, eval=FALSE--------------------------------------------------- # # Default: truncate incomplete trips <0.5 hours (30 minutes) # cpue_incomplete <- estimate_catch_rate(design, # use_trips = "incomplete", # estimator = "mor", # truncate_at = 0.5 # Default # ) # # # Custom truncation threshold # cpue_truncated <- estimate_catch_rate(design, # use_trips = "incomplete", # estimator = "mor", # truncate_at = 1.0 # More conservative: only trips ≥1 hour # ) # # # Disable truncation (not recommended) # cpue_no_truncation <- estimate_catch_rate(design, # use_trips = "incomplete", # estimator = "mor", # truncate_at = 0 # Includes all incomplete trips # )