1 1. Business context and research objectives

The Portland Trail Blazers use multigame ticket packages to balance consumer appeal, ticket revenue, seating restrictions, and the cost of promotional benefits. In the case setting, falling attendance and pressure on ticket sales make it important to understand not only which features fans prefer, but also how much additional ticket price a feature can support. A high-utility attribute may be expensive to supply; conversely, a relatively inexpensive benefit may deliver substantial perceived value.

The project evaluates four attributes—number of games, ticket price per seat per game, seat location, and promotional item—using the part-worth utility inputs in Portland Trail Blazers_Keman_Xiang.xlsx. The underlying case reports 204 valid survey responses from 960 contacted former ticket buyers and 20 conjoint tasks per respondent. The available project inputs are the reported attribute-level utility estimates. Consequently, this module evaluates monetary trade-offs implied by those estimates rather than fitting new choice coefficients or estimating confidence intervals.

This module answers three questions:

  1. Price sensitivity: Is the marginal disutility of price approximately constant across the observed ticket-price levels?
  2. Willingness-to-pay (WTP): What monetary equivalents can be assigned to changes in games, seats, and promotional features, and how do those equivalents depend on the reference price?
  3. Promotional economics and trade-offs: Which benefits provide positive incremental utility relative to no promotion, and how do their monetary equivalents compare with reported direct costs?

The analysis proceeds from the price-utility curve to local and piecewise WTP, then to promotional valuation and concrete seat-price comparisons. The following module will combine these consumer-side results with the full feasible package set and clearly defined financial assumptions.

2 2. Data inputs, definitions, and validation

2.1 2.1 Analytical inputs and unit of observation

The project reads data/processed/partworth_levels.csv, written by Module 1 — Data Input, Validation & Exploratory Analysis directly from the workbook. The dataset contains one row per attribute level, with its estimated part-worth utility and, where applicable, a reported cost. Module 2 uses the same inputs to calculate utility ranges and package-level systematic utility.

Ticket price is USD per seat per game. A price-equivalent WTP in this module is therefore initially expressed in USD per seat per game, not automatically per six-game package or per customer relationship. Reported promotion costs are compared separately and should not be multiplied by game count unless the benefit’s delivery frequency is established.

partworth <- utils::read.csv(input_path, stringsAsFactors = FALSE, check.names = FALSE,
                             na.strings = c("", "NA"))
required_cols <- c("attribute", "level_id", "product_level", "utility", "cost_usd")
assert(all(required_cols %in% names(partworth)),
       paste("Missing columns:", paste(setdiff(required_cols, names(partworth)), collapse = ", ")))
partworth$level_id <- as.integer(partworth$level_id)
partworth$utility <- as.numeric(partworth$utility)
partworth$cost_usd <- as.numeric(partworth$cost_usd)
attribute_order <- c("Number of Games", "Ticket Price", "Ticket Location", "Promotional Item")
partworth <- partworth |>
  arrange(match(attribute, attribute_order), level_id)
assert(nrow(partworth) == 16L && !anyNA(partworth$utility), "Invalid 16-level utility input")
assert(identical(as.integer(table(factor(partworth$attribute, levels = attribute_order))),
                 c(3L, 4L, 4L, 5L)), "Unexpected attribute-level counts")
assert(!anyDuplicated(partworth[c("attribute", "level_id")]), "Duplicate attribute-level keys")

price <- partworth |> filter(attribute == "Ticket Price") |>
  mutate(price_usd = suppressWarnings(as.numeric(product_level))) |>
  arrange(price_usd)
assert(identical(price$price_usd, c(15, 25, 35, 60)), "Unexpected ticket-price levels")
assert(all(diff(price$utility) < 0), "Price utility must decrease across the observed levels")
assert(all(is.finite(partworth$cost_usd[partworth$attribute %in%
                  c("Ticket Location", "Promotional Item")])),
       "Seat and promotion costs must be present and numeric")

knitr::kable(partworth[, c("attribute", "level_id", "product_level", "utility", "cost_usd")],
             digits = 5, caption = "Validated conjoint part-worths and reported costs")
Validated conjoint part-worths and reported costs
attribute level_id product_level utility cost_usd
Number of Games 1 3 0.03257 NA
Number of Games 2 6 0.24383 NA
Number of Games 3 10 -0.27640 NA
Ticket Price 1 15 0.65646 NA
Ticket Price 2 25 0.22011 NA
Ticket Price 3 35 0.12600 NA
Ticket Price 4 60 -1.00257 NA
Ticket Location 1 300 level, behind the baskets -0.73169 10.00
Ticket Location 2 300 level, on the corners -0.43716 12.00
Ticket Location 3 300 level, midcourt 0.15736 18.00
Ticket Location 4 200 level, midcourt 1.01148 40.00
Promotional Item 1 Priority for home playoff tickets 0.12511 0.00
Promotional Item 2 Hot dog and soda with each ticket 0.17428 3.25
Promotional Item 3 Trail Blazer apparel (hat, jersey, etc.) 0.00158 12.00
Promotional Item 4 $20 gift certificate for popular local restaurant 0.01689 10.00
Promotional Item 5 No promotional item -0.31786 0.00

Interpretation. The table contains 16 attribute-level estimates across four attributes. The part-worths measure relative systematic utility; they are neither direct monetary values nor observed purchase probabilities. The price levels provide the conversion scale for the WTP calculations below. Costs are included to distinguish consumers’ implied valuations from the provider’s expenses.

2.2 2.2 Define a transparent lookup and valuation convention

An additive utility model implies that changing one nonprice attribute from level \(a\) to level \(b\) produces

\[\Delta U=u_b-u_a.\]

A positive \(\Delta U\) indicates a preferred improvement, holding all other attributes constant. If ticket price rises from \(p_0\) to \(p_1\), the monetary compensation condition is

\[u_P(p_1)-u_P(p_0)=-\Delta U.\]

This module reports two different monetary concepts:

  • Local-slope WTP: divide \(\Delta U\) by the absolute price-utility slope in a specified interval. This is a linear approximation that can exceed the interval used to calculate it.
  • Piecewise compensating price increment: linearly interpolate between observed price points, then solve \(u_P(p_1)=u_P(p_0)-\Delta U\) when that target lies within the observed $15–$60 domain. If the required price lies outside that domain, the estimate is not identified without extrapolation and is reported as unavailable.

Neither approach provides sampling uncertainty because individual choice observations and coefficient covariance estimates are unavailable.

lookup_level <- function(attribute_name, id) {
  z <- partworth |> filter(attribute == attribute_name, level_id == id)
  assert(nrow(z) == 1L, paste("Missing level:", attribute_name, id))
  z
}
lookup_u <- function(attribute_name, id) lookup_level(attribute_name, id)$utility[[1]]
lookup_label <- function(attribute_name, id) as.character(lookup_level(attribute_name, id)$product_level[[1]])

3 3. Price sensitivity and nonlinearity

3.1 3.1 Price part-worths and observed marginal slopes

The ticket-price attribute has four levels: $15, $25, $35, and $60 per seat per game. The project treats the supplied price part-worths as categorical estimates. Therefore, the marginal utility of one dollar is not assumed constant. For two adjacent levels \(p_a<p_b\):

\[s_{a,b}=\frac{u_P(p_b)-u_P(p_a)}{p_b-p_a},\qquad s_{a,b}<0.\]

The magnitude \(|s_{a,b}|\) gives the utility loss per additional dollar within that observed interval under a linear interpolation assumption.

price_steps <- data.frame(
  price_from = head(price$price_usd, -1),
  price_to = tail(price$price_usd, -1),
  utility_from = head(price$utility, -1),
  utility_to = tail(price$utility, -1)) |>
  mutate(price_change_usd = price_to - price_from,
         utility_change = utility_to - utility_from,
         slope_utility_per_usd = utility_change / price_change_usd,
         usd_per_utility = 1 / abs(slope_utility_per_usd),
         interval = paste0("$", price_from, "–$", price_to))

full_range_slope <- (tail(price$utility, 1) - head(price$utility, 1)) /
                    (tail(price$price_usd, 1) - head(price$price_usd, 1))
assert(all(price_steps$slope_utility_per_usd < 0), "Non-monotone price slopes")
knitr::kable(price_steps, digits = 6,
             caption = "Observed price intervals and utility-per-dollar conversion rates")
Observed price intervals and utility-per-dollar conversion rates
price_from price_to utility_from utility_to price_change_usd utility_change slope_utility_per_usd usd_per_utility interval
15 25 0.65646 0.22011 10 -0.43635 -0.043635 22.91738 $15–$25
25 35 0.22011 0.12600 10 -0.09411 -0.009411 106.25863 $25–$35
35 60 0.12600 -1.00257 25 -1.12857 -0.045143 22.15193 $35–$60

Results and interpretation. The absolute price slopes are 0.04364, 0.00941, and 0.04514 utility units per dollar. The $25–$35 segment is markedly flatter than the neighboring intervals. In this range, the same utility improvement produces a much larger local monetary equivalent. This variation makes a single global price coefficient potentially misleading.

p_price <- ggplot(price, aes(price_usd, utility)) +
  geom_hline(yintercept = 0, linewidth = 0.3, color = "grey65") +
  geom_line(linewidth = 0.9, color = "#236C86") +
  geom_point(size = 3, color = "#236C86") +
  geom_text(aes(label = sprintf("%.5f", utility)), vjust = -0.8, size = 3.5) +
  scale_x_continuous(breaks = price$price_usd) +
  labs(x = "Price (USD per seat per game)", y = "Price part-worth utility") +
  theme_minimal(base_size = 12)
print(p_price)
Price part-worths and observed segment slopes

Price part-worths and observed segment slopes

save_figure(p_price, "03_price_partworth_nonlinearity.png")

Figure interpretation. The line joins four observed utility estimates; the connecting segments are a transparent interpolation convention, not an independently estimated continuous demand curve. Utility declines with price, but the rate of decline varies. The $25–$35 segment should not be used to extrapolate WTP beyond its interval without explicitly labeling the result as an approximation.

3.2 3.2 Quantify the consequence of a single price coefficient

A useful diagnostic compares the observed categorical price part-worths with a simple linear approximation. This regression uses four aggregated attribute-level estimates; its residuals are a measure of approximation error.

linear_price_fit <- stats::lm(utility ~ price_usd, data = price)
price$linear_approximation <- as.numeric(stats::predict(linear_price_fit, newdata = price))
price$approximation_error <- price$utility - price$linear_approximation
price_fit_summary <- data.frame(
  metric = c("Linear slope (utility per USD)", "Maximum absolute approximation error",
             "Root mean squared approximation error", "Full-range secant slope"),
  value = c(unname(coef(linear_price_fit)[[2]]),
            max(abs(price$approximation_error)),
            sqrt(mean(price$approximation_error^2)), full_range_slope))
knitr::kable(price_fit_summary, digits = 6,
             caption = "Descriptive diagnostics of a single linear price approximation")
Descriptive diagnostics of a single linear price approximation
metric value
Linear slope (utility per USD) -0.036107
Maximum absolute approximation error 0.171134
Root mean squared approximation error 0.102336
Full-range secant slope -0.036867

Interpretation. The fitted straight line summarizes the overall downward trend, but its approximation errors show how much it departs from the four observed levels. The full-range secant slope, -0.036867 utility units per dollar, is a separate endpoint-based conversion; it should not be confused with the fitted regression slope or the local slopes.

4 4. Attribute improvements and willingness-to-pay

4.1 4.1 Construct meaningful within-attribute improvements

WTP is calculated for improvements within the number-of-games, seating, and promotion attributes. Every comparison is explicitly identified by its starting and ending level. For promotions, no promotion is the reference, so the measured benefit is the incremental utility of providing an item rather than the item’s absolute part-worth.

make_change <- function(attribute_name, from_id, to_id, group) {
  data.frame(group = group, attribute = attribute_name,
             from_id = from_id, to_id = to_id,
             from_level = lookup_label(attribute_name, from_id),
             to_level = lookup_label(attribute_name, to_id),
             delta_utility = lookup_u(attribute_name, to_id) - lookup_u(attribute_name, from_id),
             stringsAsFactors = FALSE)
}
changes <- dplyr::bind_rows(
  make_change("Number of Games", 1, 2, "Games"),
  make_change("Number of Games", 3, 1, "Games"),
  make_change("Number of Games", 3, 2, "Games"),
  make_change("Ticket Location", 1, 2, "Seating"),
  make_change("Ticket Location", 1, 3, "Seating"),
  make_change("Ticket Location", 1, 4, "Seating"),
  make_change("Ticket Location", 2, 3, "Seating"),
  make_change("Ticket Location", 3, 4, "Seating"),
  make_change("Promotional Item", 5, 1, "Promotions"),
  make_change("Promotional Item", 5, 2, "Promotions"),
  make_change("Promotional Item", 5, 3, "Promotions"),
  make_change("Promotional Item", 5, 4, "Promotions"))
assert(all(changes$delta_utility > 0), "Each specified comparison must be a utility improvement")
knitr::kable(changes[, c("group", "from_level", "to_level", "delta_utility")],
             digits = 5, caption = "Positive utility gains for selected attribute changes")
Positive utility gains for selected attribute changes
group from_level to_level delta_utility
Games 3 6 0.21126
Games 10 3 0.30897
Games 10 6 0.52023
Seating 300 level, behind the baskets 300 level, on the corners 0.29453
Seating 300 level, behind the baskets 300 level, midcourt 0.88905
Seating 300 level, behind the baskets 200 level, midcourt 1.74317
Seating 300 level, on the corners 300 level, midcourt 0.59452
Seating 300 level, midcourt 200 level, midcourt 0.85412
Promotions No promotional item Priority for home playoff tickets 0.44297
Promotions No promotional item Hot dog and soda with each ticket 0.49214
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) 0.31944
Promotions No promotional item $20 gift certificate for popular local restaurant 0.33475

Results and interpretation. Increasing package size from three to six games yields 0.21126 additional utility units, while changing from ten to six games yields 0.52023. This reinforces that the six-game option is preferred to both alternatives in the supplied estimates. Replacing no promotion with hot dog and soda adds 0.49214 utility units, which can now be compared with ticket-price disutility and reported costs.

4.2 4.2 Local-slope WTP across the three price intervals

For a positive improvement \(\Delta U\), the local-slope monetary equivalent in interval \(k\) is

\[\widehat{WTP}_{k}^{\mathrm{local}}=\frac{\Delta U}{|s_k|}.\]

This calculation is informative as a slope sensitivity analysis. It does not imply that a consumer would necessarily pay the resulting amount, especially if the result extends beyond the price interval used for conversion.

local_wtp <- tidyr::crossing(changes, price_steps[, c("interval", "price_from", "price_to",
                                                   "slope_utility_per_usd")]) |>
  mutate(wtp_local_usd = delta_utility / abs(slope_utility_per_usd),
         within_interval_width = wtp_local_usd <= (price_to - price_from) + 1e-10)
knitr::kable(local_wtp |>
               select(group, from_level, to_level, interval, delta_utility,
                      wtp_local_usd, within_interval_width),
             digits = 3, caption = "Local-slope WTP and interval-width diagnostic")
Local-slope WTP and interval-width diagnostic
group from_level to_level interval delta_utility wtp_local_usd within_interval_width
Games 3 6 $15–$25 0.211 4.842 TRUE
Games 3 6 $25–$35 0.211 22.448 FALSE
Games 3 6 $35–$60 0.211 4.680 TRUE
Games 10 3 $15–$25 0.309 7.081 TRUE
Games 10 3 $25–$35 0.309 32.831 FALSE
Games 10 3 $35–$60 0.309 6.844 TRUE
Games 10 6 $15–$25 0.520 11.922 FALSE
Games 10 6 $25–$35 0.520 55.279 FALSE
Games 10 6 $35–$60 0.520 11.524 TRUE
Promotions No promotional item Priority for home playoff tickets $15–$25 0.443 10.152 FALSE
Promotions No promotional item Priority for home playoff tickets $25–$35 0.443 47.069 FALSE
Promotions No promotional item Priority for home playoff tickets $35–$60 0.443 9.813 TRUE
Promotions No promotional item Hot dog and soda with each ticket $15–$25 0.492 11.279 FALSE
Promotions No promotional item Hot dog and soda with each ticket $25–$35 0.492 52.294 FALSE
Promotions No promotional item Hot dog and soda with each ticket $35–$60 0.492 10.902 TRUE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $15–$25 0.319 7.321 TRUE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $25–$35 0.319 33.943 FALSE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $35–$60 0.319 7.076 TRUE
Promotions No promotional item $20 gift certificate for popular local restaurant $15–$25 0.335 7.672 TRUE
Promotions No promotional item $20 gift certificate for popular local restaurant $25–$35 0.335 35.570 FALSE
Promotions No promotional item $20 gift certificate for popular local restaurant $35–$60 0.335 7.415 TRUE
Seating 300 level, behind the baskets 300 level, on the corners $15–$25 0.295 6.750 TRUE
Seating 300 level, behind the baskets 300 level, on the corners $25–$35 0.295 31.296 FALSE
Seating 300 level, behind the baskets 300 level, on the corners $35–$60 0.295 6.524 TRUE
Seating 300 level, behind the baskets 300 level, midcourt $15–$25 0.889 20.375 FALSE
Seating 300 level, behind the baskets 300 level, midcourt $25–$35 0.889 94.469 FALSE
Seating 300 level, behind the baskets 300 level, midcourt $35–$60 0.889 19.694 TRUE
Seating 300 level, behind the baskets 200 level, midcourt $15–$25 1.743 39.949 FALSE
Seating 300 level, behind the baskets 200 level, midcourt $25–$35 1.743 185.227 FALSE
Seating 300 level, behind the baskets 200 level, midcourt $35–$60 1.743 38.615 FALSE
Seating 300 level, on the corners 300 level, midcourt $15–$25 0.595 13.625 FALSE
Seating 300 level, on the corners 300 level, midcourt $25–$35 0.595 63.173 FALSE
Seating 300 level, on the corners 300 level, midcourt $35–$60 0.595 13.170 TRUE
Seating 300 level, midcourt 200 level, midcourt $15–$25 0.854 19.574 FALSE
Seating 300 level, midcourt 200 level, midcourt $25–$35 0.854 90.758 FALSE
Seating 300 level, midcourt 200 level, midcourt $35–$60 0.854 18.920 TRUE

Interpretation. The same utility gain produces different monetary equivalents depending on the interval. For the three-to-six-game improvement, local-slope WTP is $4.84 in the $15–$25 segment and $22.45 in the $25–$35 segment. The within_interval_width flag identifies when the estimated price change exceeds the interval width; even when it does not, the result is a local approximation and depends on where the change begins.

p_local <- local_wtp |>
  ggplot(aes(x = interval, y = wtp_local_usd, fill = interval)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~group, scales = "free_y") +
  labs(x = "Observed price interval", y = "Local WTP (USD per seat per game)") +
  theme_minimal(base_size = 11) +
  theme(axis.text.x = element_text(angle = 30, hjust = 1))
print(p_local)
Local monetary equivalents vary with the reference price interval

Local monetary equivalents vary with the reference price interval

save_figure(p_local, "03_local_wtp_by_price_interval.png", 11, 8)

Figure interpretation. The large variation across price intervals reflects the shape of the supplied price part-worth function. These are alternative valuation assumptions applied to the same attribute improvements, not separate estimates from different respondent groups. The plot should therefore be read as a model-sensitivity comparison.

4.3 4.3 Piecewise-linear compensating price changes

Local-slope division can be misleading when an improvement is large enough to cross a price breakpoint. The project therefore constructs a continuous piecewise-linear interpolation through the four observed price utilities and solves the compensating price condition exactly within the observed domain:

\[u_P(p_0+WTP)-u_P(p_0)=-\Delta U.\]

Because the price-utility curve is strictly decreasing, a unique solution exists if and only if the target utility remains between the observed endpoint utilities. No extrapolation outside $15–$60 is performed. WTP may be unavailable at a high starting price even when the attribute improvement is valuable: the price ceiling simply prevents identification of the full compensation.

price_utility <- function(p) {
  stats::approx(x = price$price_usd, y = price$utility,
                xout = p, method = "linear", rule = 1, ties = "ordered")$y
}
compensating_wtp <- function(delta_u, reference_price) {
  assert(length(delta_u) == 1L && is.finite(delta_u) && delta_u >= 0,
         "A nonnegative utility improvement is required")
  assert(reference_price >= min(price$price_usd) &&
           reference_price <= max(price$price_usd), "Reference price is outside the observed range")
  target_u <- price_utility(reference_price) - delta_u
  if (target_u < min(price$utility) - 1e-10) return(NA_real_)
  # Invert the strictly monotone interpolated price-utility curve.
  target_price <- stats::approx(x = rev(price$utility), y = rev(price$price_usd),
                                xout = target_u, method = "linear", rule = 1,
                                ties = "ordered")$y
  if (length(target_price) != 1L || is.na(target_price)) return(NA_real_)
  max(0, target_price - reference_price)
}
reference_prices <- price$price_usd[1:3]  # $15, $25, $35; $60 leaves no upward room.
piecewise_wtp <- tidyr::crossing(changes, reference_price = reference_prices) |>
  rowwise() |>
  mutate(wtp_piecewise_usd = compensating_wtp(delta_utility, reference_price),
         target_price_usd = ifelse(is.na(wtp_piecewise_usd), NA_real_,
                                  reference_price + wtp_piecewise_usd),
         identifiable_in_observed_range = !is.na(wtp_piecewise_usd)) |>
  ungroup()
knitr::kable(piecewise_wtp |>
               select(group, from_level, to_level, reference_price,
                      delta_utility, wtp_piecewise_usd, target_price_usd,
                      identifiable_in_observed_range),
             digits = 3,
             caption = "Compensating WTP using piecewise price utility within $15–$60")
Compensating WTP using piecewise price utility within $15–$60
group from_level to_level reference_price delta_utility wtp_piecewise_usd target_price_usd identifiable_in_observed_range
Games 3 6 15 0.211 4.842 19.842 TRUE
Games 3 6 25 0.211 12.595 37.595 TRUE
Games 3 6 35 0.211 4.680 39.680 TRUE
Games 10 3 15 0.309 7.081 22.081 TRUE
Games 10 3 25 0.309 14.760 39.760 TRUE
Games 10 3 35 0.309 6.844 41.844 TRUE
Games 10 6 15 0.520 18.913 33.913 TRUE
Games 10 6 25 0.520 19.439 44.439 TRUE
Games 10 6 35 0.520 11.524 46.524 TRUE
Promotions No promotional item Priority for home playoff tickets 15 0.443 10.703 25.703 TRUE
Promotions No promotional item Priority for home playoff tickets 25 0.443 17.728 42.728 TRUE
Promotions No promotional item Priority for home playoff tickets 35 0.443 9.813 44.813 TRUE
Promotions No promotional item Hot dog and soda with each ticket 15 0.492 15.928 30.928 TRUE
Promotions No promotional item Hot dog and soda with each ticket 25 0.492 18.817 43.817 TRUE
Promotions No promotional item Hot dog and soda with each ticket 35 0.492 10.902 45.902 TRUE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) 15 0.319 7.321 22.321 TRUE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) 25 0.319 14.991 39.991 TRUE
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) 35 0.319 7.076 42.076 TRUE
Promotions No promotional item $20 gift certificate for popular local restaurant 15 0.335 7.672 22.672 TRUE
Promotions No promotional item $20 gift certificate for popular local restaurant 25 0.335 15.331 40.331 TRUE
Promotions No promotional item $20 gift certificate for popular local restaurant 35 0.335 7.415 42.415 TRUE
Seating 300 level, behind the baskets 300 level, on the corners 15 0.295 6.750 21.750 TRUE
Seating 300 level, behind the baskets 300 level, on the corners 25 0.295 14.440 39.440 TRUE
Seating 300 level, behind the baskets 300 level, on the corners 35 0.295 6.524 41.524 TRUE
Seating 300 level, behind the baskets 300 level, midcourt 15 0.889 27.943 42.943 TRUE
Seating 300 level, behind the baskets 300 level, midcourt 25 0.889 27.609 52.609 TRUE
Seating 300 level, behind the baskets 300 level, midcourt 35 0.889 19.694 54.694 TRUE
Seating 300 level, behind the baskets 200 level, midcourt 15 1.743 NA NA FALSE
Seating 300 level, behind the baskets 200 level, midcourt 25 1.743 NA NA FALSE
Seating 300 level, behind the baskets 200 level, midcourt 35 1.743 NA NA FALSE
Seating 300 level, on the corners 300 level, midcourt 15 0.595 21.419 36.419 TRUE
Seating 300 level, on the corners 300 level, midcourt 25 0.595 21.085 46.085 TRUE
Seating 300 level, on the corners 300 level, midcourt 35 0.595 13.170 48.170 TRUE
Seating 300 level, midcourt 200 level, midcourt 15 0.854 27.170 42.170 TRUE
Seating 300 level, midcourt 200 level, midcourt 25 0.854 26.836 51.836 TRUE
Seating 300 level, midcourt 200 level, midcourt 35 0.854 18.920 53.920 TRUE

Results and interpretation. The piecewise method follows the actual observed changes in the price utility estimates. An unavailable (NA) result means that the specified utility improvement cannot be fully offset by raising the ticket price within the observed price range; it does not mean zero WTP. Starting at $25, the three-to-six-game improvement has a piecewise monetary equivalent of $12.60, incorporating the flatter $25–$35 segment and, when necessary, the steeper $35–$60 segment.

p_piecewise <- piecewise_wtp |>
  mutate(change_label = paste(from_level, "→", to_level)) |>
  ggplot(aes(x = factor(reference_price), y = wtp_piecewise_usd,
             group = change_label, color = change_label)) +
  geom_point(size = 2, na.rm = TRUE) +
  geom_line(linewidth = 0.7, na.rm = TRUE) +
  facet_wrap(~group, scales = "free_y") +
  labs(x = "Starting ticket price (USD)", y = "Piecewise WTP (USD per seat per game)",
       color = "Attribute improvement") +
  theme_minimal(base_size = 10) +
  theme(legend.position = "bottom")
print(p_piecewise)
Piecewise compensating WTP by starting ticket price

Piecewise compensating WTP by starting ticket price

save_figure(p_piecewise, "03_piecewise_wtp_reference_prices.png", 12, 9)

Figure interpretation. Starting price matters even when the attribute improvement is unchanged. The plotted estimates are restricted to cases where the compensating price lies in the observed domain; missing points should not be interpreted as unattractive features. The method is more internally consistent than extending a local slope beyond its segment, but the interpolation itself remains a modeling assumption rather than a directly observed continuous preference function.

5 5. Promotional benefits: consumer value versus provider cost

5.1 5.1 Incremental utility relative to no promotion

A promotion should be evaluated against a meaningful alternative. The appropriate consumer-side comparison is the same package without a promotional item:

\[\Delta U_m=u_{M,m}-u_{M,\mathrm{none}}.\]

This is distinct from dividing the absolute promotional part-worth by cost, which is sensitive to utility normalization and does not isolate the benefit of providing the item. The project pairs each incremental utility with its reported direct cost, preserving the distinction between monetary equivalents and actual cash flows.

promos <- partworth |> filter(attribute == "Promotional Item") |> arrange(level_id)
none <- promos |> filter(level_id == 5L)
assert(nrow(none) == 1L, "The fifth promotion level must be 'none'")
assert(abs(none$cost_usd[[1]]) < 1e-9, "No-promotion direct cost is expected to be zero")
promotion_values <- promos |>
  mutate(delta_u_vs_none = utility - none$utility[[1]],
         incremental_cost_usd = cost_usd - none$cost_usd[[1]],
         wtp_full_range_usd = delta_u_vs_none / abs(full_range_slope),
         value_minus_cost_full_range = wtp_full_range_usd - incremental_cost_usd,
         cost_per_utility_gain = ifelse(delta_u_vs_none > 0,
                                       incremental_cost_usd / delta_u_vs_none, NA_real_)) |>
  select(level_id, product_level, utility, delta_u_vs_none, incremental_cost_usd,
         wtp_full_range_usd, value_minus_cost_full_range, cost_per_utility_gain)
knitr::kable(promotion_values, digits = 4,
             caption = "Promotion utility gains, full-range monetary equivalents, and reported costs")
Promotion utility gains, full-range monetary equivalents, and reported costs
level_id product_level utility delta_u_vs_none incremental_cost_usd wtp_full_range_usd value_minus_cost_full_range cost_per_utility_gain
1 Priority for home playoff tickets 0.1251 0.4430 0.00 12.0152 12.0152 0.0000
2 Hot dog and soda with each ticket 0.1743 0.4921 3.25 13.3489 10.0989 6.6038
3 Trail Blazer apparel (hat, jersey, etc.) 0.0016 0.3194 12.00 8.6646 -3.3354 37.5657
4 $20 gift certificate for popular local restaurant 0.0169 0.3348 10.00 9.0799 -0.9201 29.8730
5 No promotional item -0.3179 0.0000 0.00 0.0000 0.0000 NA

Results and interpretation. Relative to no promotion, hot dog and soda adds 0.49214 utility units at a reported cost of $3.25. Using the full $15–$60 endpoint slope, its price-equivalent value is $13.35. Apparel adds 0.31944 utility units, with an endpoint-slope equivalent of $8.66 against a reported cost of $12.00.

The endpoint conversion is useful as a descriptive benchmark, not a universal WTP estimate. In particular, value_minus_cost_full_range is a difference between a modeled consumer valuation and a reported direct cost. It is not accounting profit, and it is not automatically comparable across promotions if the benefit and cost apply at different delivery frequencies. Priority access to playoff tickets has zero reported direct cost, but may still entail capacity or opportunity costs.

5.2 5.2 Promotion value under alternative price assumptions

To test whether the promotion conclusion depends on a single price conversion, the project evaluates each benefit using all three local slopes, the full-range secant, and piecewise compensation at $15, $25, and $35. The result is a valuation sensitivity table, not an estimate of a consumer WTP distribution.

promo_changes <- changes |> filter(group == "Promotions")
promo_local <- local_wtp |> filter(group == "Promotions") |>
  transmute(to_level, valuation_method = paste0("Local slope ", interval),
            wtp_usd = wtp_local_usd)
promo_full <- promotion_values |> filter(level_id != 5L) |>
  transmute(to_level = product_level, valuation_method = "Full-range endpoint slope",
            wtp_usd = wtp_full_range_usd)
promo_piecewise <- piecewise_wtp |> filter(group == "Promotions") |>
  transmute(to_level, valuation_method = paste0("Piecewise from $", reference_price),
            wtp_usd = wtp_piecewise_usd)
promotion_sensitivity <- bind_rows(promo_local, promo_full, promo_piecewise) |>
  left_join(promotion_values |> select(product_level, incremental_cost_usd),
            by = c("to_level" = "product_level")) |>
  mutate(value_less_reported_cost = wtp_usd - incremental_cost_usd,
         identifiable = !is.na(wtp_usd))
knitr::kable(promotion_sensitivity, digits = 3,
             caption = "Promotion monetary equivalents under alternative price specifications")
Promotion monetary equivalents under alternative price specifications
to_level valuation_method wtp_usd incremental_cost_usd value_less_reported_cost identifiable
Priority for home playoff tickets Local slope $15–$25 10.152 0.00 10.152 TRUE
Priority for home playoff tickets Local slope $25–$35 47.069 0.00 47.069 TRUE
Priority for home playoff tickets Local slope $35–$60 9.813 0.00 9.813 TRUE
Hot dog and soda with each ticket Local slope $15–$25 11.279 3.25 8.029 TRUE
Hot dog and soda with each ticket Local slope $25–$35 52.294 3.25 49.044 TRUE
Hot dog and soda with each ticket Local slope $35–$60 10.902 3.25 7.652 TRUE
Trail Blazer apparel (hat, jersey, etc.) Local slope $15–$25 7.321 12.00 -4.679 TRUE
Trail Blazer apparel (hat, jersey, etc.) Local slope $25–$35 33.943 12.00 21.943 TRUE
Trail Blazer apparel (hat, jersey, etc.) Local slope $35–$60 7.076 12.00 -4.924 TRUE
$20 gift certificate for popular local restaurant Local slope $15–$25 7.672 10.00 -2.328 TRUE
$20 gift certificate for popular local restaurant Local slope $25–$35 35.570 10.00 25.570 TRUE
$20 gift certificate for popular local restaurant Local slope $35–$60 7.415 10.00 -2.585 TRUE
Priority for home playoff tickets Full-range endpoint slope 12.015 0.00 12.015 TRUE
Hot dog and soda with each ticket Full-range endpoint slope 13.349 3.25 10.099 TRUE
Trail Blazer apparel (hat, jersey, etc.) Full-range endpoint slope 8.665 12.00 -3.335 TRUE
$20 gift certificate for popular local restaurant Full-range endpoint slope 9.080 10.00 -0.920 TRUE
Priority for home playoff tickets Piecewise from $15 10.703 0.00 10.703 TRUE
Priority for home playoff tickets Piecewise from $25 17.728 0.00 17.728 TRUE
Priority for home playoff tickets Piecewise from $35 9.813 0.00 9.813 TRUE
Hot dog and soda with each ticket Piecewise from $15 15.928 3.25 12.678 TRUE
Hot dog and soda with each ticket Piecewise from $25 18.817 3.25 15.567 TRUE
Hot dog and soda with each ticket Piecewise from $35 10.902 3.25 7.652 TRUE
Trail Blazer apparel (hat, jersey, etc.) Piecewise from $15 7.321 12.00 -4.679 TRUE
Trail Blazer apparel (hat, jersey, etc.) Piecewise from $25 14.991 12.00 2.991 TRUE
Trail Blazer apparel (hat, jersey, etc.) Piecewise from $35 7.076 12.00 -4.924 TRUE
$20 gift certificate for popular local restaurant Piecewise from $15 7.672 10.00 -2.328 TRUE
$20 gift certificate for popular local restaurant Piecewise from $25 15.331 10.00 5.331 TRUE
$20 gift certificate for popular local restaurant Piecewise from $35 7.415 10.00 -2.585 TRUE

Interpretation. A positive difference between modeled value and reported cost is suggestive of a potentially attractive benefit under the stated valuation convention. It is not sufficient to conclude that a giveaway increases revenue or profit: the analysis does not identify the change in purchase probability, the number of purchases, or the cost frequency. Some piecewise estimates may be unavailable because the required compensating price exceeds $60; these are boundary limitations, not negative valuations.

p_promo <- promotion_sensitivity |>
  filter(identifiable) |>
  ggplot(aes(x = valuation_method, y = wtp_usd)) +
  geom_col(fill = "#287C92", alpha = 0.82) +
  geom_hline(aes(yintercept = incremental_cost_usd), linetype = "dashed",
             color = "#B64A36", linewidth = 0.7) +
  facet_wrap(~to_level, scales = "free_y") +
  labs(x = NULL, y = "Price-equivalent value (USD per seat per game)",
       caption = "Dashed line: reported direct promotion cost; units and delivery frequency must be checked before financial comparison.") +
  theme_minimal(base_size = 10) +
  theme(axis.text.x = element_text(angle = 65, hjust = 1))
print(p_promo)
Promotional valuation benchmarks versus reported direct costs

Promotional valuation benchmarks versus reported direct costs

save_figure(p_promo, "03_promotion_wtp_cost_sensitivity.png", 13, 9)

Figure interpretation. The same promotional benefit can appear more or less attractive depending on the price-utility assumption. The dashed cost reference is deliberately shown alongside—not subtracted from—a demand or profit forecast. The strongest conclusion supported by these inputs is that hot dog and soda generates the largest incremental promotional utility, while the economic ranking of giveaways depends on the price valuation rule, delivery frequency, and commercial response.

6 6. Attribute trade-offs and pricing decisions

6.1 6.1 Compare attribute improvements with specified price reductions

For a price reduction from \(p_{\mathrm{high}}\) to \(p_{\mathrm{low}}\), the consumer’s utility gain is

\[\Delta U_{\mathrm{price}}=u_P(p_{\mathrm{low}})-u_P(p_{\mathrm{high}}).\]

The project compares that gain with each positive attribute improvement. This comparison establishes which change raises modeled consumer utility more, not which is economically preferable for the Trail Blazers. A price cut reduces revenue per ticket, while an attribute improvement may carry a direct cost.

price_cuts <- data.frame(from_price = c(25, 35, 60, 60),
                         to_price = c(15, 25, 35, 15)) |>
  mutate(price_cut_usd = from_price - to_price,
         utility_gain = price_utility(to_price) - price_utility(from_price),
         price_cut_label = paste0("$", from_price, " → $", to_price))
tradeoffs <- tidyr::crossing(changes, price_cuts) |>
  mutate(utility_advantage_of_attribute = delta_utility - utility_gain,
         larger_consumer_utility_gain = case_when(
           abs(utility_advantage_of_attribute) < 1e-10 ~ "Equal",
           utility_advantage_of_attribute > 0 ~ "Attribute improvement",
           TRUE ~ "Price reduction"))
knitr::kable(tradeoffs |>
               select(group, from_level, to_level, price_cut_label,
                      delta_utility, utility_gain, utility_advantage_of_attribute,
                      larger_consumer_utility_gain),
             digits = 5, caption = "Utility comparison of attribute changes and price reductions")
Utility comparison of attribute changes and price reductions
group from_level to_level price_cut_label delta_utility utility_gain utility_advantage_of_attribute larger_consumer_utility_gain
Games 3 6 $25 → $15 0.21126 0.43635 -0.22509 Price reduction
Games 3 6 $35 → $25 0.21126 0.09411 0.11715 Attribute improvement
Games 3 6 $60 → $15 0.21126 1.65903 -1.44777 Price reduction
Games 3 6 $60 → $35 0.21126 1.12857 -0.91731 Price reduction
Games 10 3 $25 → $15 0.30897 0.43635 -0.12738 Price reduction
Games 10 3 $35 → $25 0.30897 0.09411 0.21486 Attribute improvement
Games 10 3 $60 → $15 0.30897 1.65903 -1.35006 Price reduction
Games 10 3 $60 → $35 0.30897 1.12857 -0.81960 Price reduction
Games 10 6 $25 → $15 0.52023 0.43635 0.08388 Attribute improvement
Games 10 6 $35 → $25 0.52023 0.09411 0.42612 Attribute improvement
Games 10 6 $60 → $15 0.52023 1.65903 -1.13880 Price reduction
Games 10 6 $60 → $35 0.52023 1.12857 -0.60834 Price reduction
Promotions No promotional item Priority for home playoff tickets $25 → $15 0.44297 0.43635 0.00662 Attribute improvement
Promotions No promotional item Priority for home playoff tickets $35 → $25 0.44297 0.09411 0.34886 Attribute improvement
Promotions No promotional item Priority for home playoff tickets $60 → $15 0.44297 1.65903 -1.21606 Price reduction
Promotions No promotional item Priority for home playoff tickets $60 → $35 0.44297 1.12857 -0.68560 Price reduction
Promotions No promotional item Hot dog and soda with each ticket $25 → $15 0.49214 0.43635 0.05579 Attribute improvement
Promotions No promotional item Hot dog and soda with each ticket $35 → $25 0.49214 0.09411 0.39803 Attribute improvement
Promotions No promotional item Hot dog and soda with each ticket $60 → $15 0.49214 1.65903 -1.16689 Price reduction
Promotions No promotional item Hot dog and soda with each ticket $60 → $35 0.49214 1.12857 -0.63643 Price reduction
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $25 → $15 0.31944 0.43635 -0.11691 Price reduction
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $35 → $25 0.31944 0.09411 0.22533 Attribute improvement
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $60 → $15 0.31944 1.65903 -1.33959 Price reduction
Promotions No promotional item Trail Blazer apparel (hat, jersey, etc.) $60 → $35 0.31944 1.12857 -0.80913 Price reduction
Promotions No promotional item $20 gift certificate for popular local restaurant $25 → $15 0.33475 0.43635 -0.10160 Price reduction
Promotions No promotional item $20 gift certificate for popular local restaurant $35 → $25 0.33475 0.09411 0.24064 Attribute improvement
Promotions No promotional item $20 gift certificate for popular local restaurant $60 → $15 0.33475 1.65903 -1.32428 Price reduction
Promotions No promotional item $20 gift certificate for popular local restaurant $60 → $35 0.33475 1.12857 -0.79382 Price reduction
Seating 300 level, behind the baskets 300 level, on the corners $25 → $15 0.29453 0.43635 -0.14182 Price reduction
Seating 300 level, behind the baskets 300 level, on the corners $35 → $25 0.29453 0.09411 0.20042 Attribute improvement
Seating 300 level, behind the baskets 300 level, on the corners $60 → $15 0.29453 1.65903 -1.36450 Price reduction
Seating 300 level, behind the baskets 300 level, on the corners $60 → $35 0.29453 1.12857 -0.83404 Price reduction
Seating 300 level, behind the baskets 300 level, midcourt $25 → $15 0.88905 0.43635 0.45270 Attribute improvement
Seating 300 level, behind the baskets 300 level, midcourt $35 → $25 0.88905 0.09411 0.79494 Attribute improvement
Seating 300 level, behind the baskets 300 level, midcourt $60 → $15 0.88905 1.65903 -0.76998 Price reduction
Seating 300 level, behind the baskets 300 level, midcourt $60 → $35 0.88905 1.12857 -0.23952 Price reduction
Seating 300 level, behind the baskets 200 level, midcourt $25 → $15 1.74317 0.43635 1.30682 Attribute improvement
Seating 300 level, behind the baskets 200 level, midcourt $35 → $25 1.74317 0.09411 1.64906 Attribute improvement
Seating 300 level, behind the baskets 200 level, midcourt $60 → $15 1.74317 1.65903 0.08414 Attribute improvement
Seating 300 level, behind the baskets 200 level, midcourt $60 → $35 1.74317 1.12857 0.61460 Attribute improvement
Seating 300 level, on the corners 300 level, midcourt $25 → $15 0.59452 0.43635 0.15817 Attribute improvement
Seating 300 level, on the corners 300 level, midcourt $35 → $25 0.59452 0.09411 0.50041 Attribute improvement
Seating 300 level, on the corners 300 level, midcourt $60 → $15 0.59452 1.65903 -1.06451 Price reduction
Seating 300 level, on the corners 300 level, midcourt $60 → $35 0.59452 1.12857 -0.53405 Price reduction
Seating 300 level, midcourt 200 level, midcourt $25 → $15 0.85412 0.43635 0.41777 Attribute improvement
Seating 300 level, midcourt 200 level, midcourt $35 → $25 0.85412 0.09411 0.76001 Attribute improvement
Seating 300 level, midcourt 200 level, midcourt $60 → $15 0.85412 1.65903 -0.80491 Price reduction
Seating 300 level, midcourt 200 level, midcourt $60 → $35 0.85412 1.12857 -0.27445 Price reduction

Results and interpretation. A price reduction from $25 to $15 increases utility by 0.43635, compared with 0.21126 for increasing the package from three to six games. Thus the specified price cut generates the larger consumer utility gain, but the model alone cannot establish that it is the better financial decision. This distinction prevents utility rankings from being mistaken for profit rankings.

6.2 6.2 Existing seat-price configurations

The case also describes current seat-price pairings. Their combined utility isolates two central attributes—ticket location and price—while holding game count and promotion unspecified. The four combinations are:

  • 300-level behind baskets at $15;
  • 300-level corners at $25;
  • 300-level midcourt at $35;
  • 200-level midcourt at $60.

These combinations are used as case-defined management scenarios, not as observed purchases or estimates of actual demand.

seat_price_pairs <- data.frame(seat_id = 1:4, price_usd = c(15, 25, 35, 60))
seat_price_pairs$seat <- vapply(seat_price_pairs$seat_id,
                               function(id) lookup_label("Ticket Location", id), character(1))
seat_price_pairs$seat_utility <- vapply(seat_price_pairs$seat_id,
                                       function(id) lookup_u("Ticket Location", id), numeric(1))
seat_price_pairs$price_utility <- price_utility(seat_price_pairs$price_usd)
seat_price_pairs$combined_utility <- seat_price_pairs$seat_utility + seat_price_pairs$price_utility
seat_price_pairs <- seat_price_pairs |> arrange(desc(combined_utility))
knitr::kable(seat_price_pairs[, c("seat", "price_usd", "seat_utility",
                                "price_utility", "combined_utility")],
             digits = 5, caption = "Case seat-price combinations and combined systematic utility")
Case seat-price combinations and combined systematic utility
seat price_usd seat_utility price_utility combined_utility
300 level, midcourt 35 0.15736 0.12600 0.28336
200 level, midcourt 60 1.01148 -1.00257 0.00891
300 level, behind the baskets 15 -0.73169 0.65646 -0.07523
300 level, on the corners 25 -0.43716 0.22011 -0.21705

Results and interpretation. Among these four configurations, 300 level, midcourt at $35.00 yields the highest combined seat-and-price utility (0.28336). The comparison identifies an opportunity to examine pricing headroom, not an automatic recommendation to increase price in a weak attendance environment.

6.3 6.3 Illustrative price headroom for 300-level midcourt

Consider the $35 300-level midcourt configuration. The project calculates the additional price that would reduce its combined utility to that of the $60 200-level midcourt alternative. It holds seating fixed, assumes piecewise-linear price utility, and does not extrapolate beyond the observed price levels.

mid300 <- seat_price_pairs |> filter(seat_id == 3L)
mid200 <- seat_price_pairs |> filter(seat_id == 4L)
assert(nrow(mid300) == 1L && nrow(mid200) == 1L, "Missing reference seat-price scenarios")
headroom_delta_u <- mid300$combined_utility - mid200$combined_utility
assert(headroom_delta_u >= 0, "Reference configuration does not have positive utility headroom")
headroom_usd <- compensating_wtp(headroom_delta_u, mid300$price_usd)
headroom_summary <- data.frame(
  baseline_price_usd = mid300$price_usd,
  baseline_combined_utility = mid300$combined_utility,
  comparator_price_usd = mid200$price_usd,
  comparator_combined_utility = mid200$combined_utility,
  utility_gap = headroom_delta_u,
  estimated_price_headroom_usd = headroom_usd,
  indifference_price_usd = mid300$price_usd + headroom_usd)
knitr::kable(headroom_summary, digits = 4,
             caption = "Illustrative price headroom for 300-level midcourt seats")
Illustrative price headroom for 300-level midcourt seats
baseline_price_usd baseline_combined_utility comparator_price_usd comparator_combined_utility utility_gap estimated_price_headroom_usd indifference_price_usd
35 0.2834 60 0.0089 0.2745 6.0796 41.0796

Interpretation. The combined utility gap is 0.27445 units. Using the observed $35–$60 price segment, the illustrative price headroom is $6.08 per seat per game, implying an indifference price of approximately $41.08. This is a model-implied indifference calculation, not a demand forecast, a tested optimal price, or a recommendation to implement the full increase. Actual pricing would also require consideration of attendance, customer retention, inventory, competitive alternatives, and cannibalization.

7 7. Model checks and research interpretation

7.1 7.1 Numerical validation

The analysis performs checks on the monotonic price function, endpoint interpolation, WTP inversion, and promotion increments. These checks assess the internal consistency of the calculations. They do not substitute for external validation with respondent-level choices.

probe <- seq(min(price$price_usd), max(price$price_usd), by = 0.25)
valid_wtp <- piecewise_wtp |> filter(identifiable_in_observed_range)
inversion_error <- if (nrow(valid_wtp)) {
  max(abs(price_utility(valid_wtp$target_price_usd) -
          (price_utility(valid_wtp$reference_price) - valid_wtp$delta_utility)))
} else NA_real_
validation <- data.frame(
  check = c("Price utility matches all four source levels",
            "Interpolated price utility is monotonically decreasing",
            "Local price slopes are strictly negative",
            "Piecewise WTP satisfies compensating utility equation",
            "All promotion utility increments are nonnegative",
            "All reported promotional costs are nonnegative",
            "Seat-price reference comparisons remain feasible"),
  passed = c(max(abs(price_utility(price$price_usd) - price$utility)) < 1e-10,
             all(diff(price_utility(probe)) < 1e-10),
             all(price_steps$slope_utility_per_usd < 0),
             is.finite(inversion_error) && inversion_error < 1e-8,
             all(promotion_values$delta_u_vs_none >= -1e-10),
             all(promotion_values$incremental_cost_usd >= -1e-10),
             all(seat_price_pairs$price_usd >= c(0, 0, 25, 60)[seat_price_pairs$seat_id])))
assert(all(validation$passed), "Module 3 numerical validation failed")
knitr::kable(validation, caption = "Module 3 numerical validation checks")
Module 3 numerical validation checks
check passed
Price utility matches all four source levels TRUE
Interpolated price utility is monotonically decreasing TRUE
Local price slopes are strictly negative TRUE
Piecewise WTP satisfies compensating utility equation TRUE
All promotion utility increments are nonnegative TRUE
All reported promotional costs are nonnegative TRUE
Seat-price reference comparisons remain feasible TRUE

Validation result. 7 of 7 checks passed. The maximum absolute inversion error among identifiable piecewise WTP comparisons is 3.885781e-16. These checks verify arithmetic and model implementation, not the predictive accuracy of the underlying conjoint survey.

7.2 7.2 Substantive findings

The analysis yields four connected findings:

  1. Price sensitivity is nonlinear across the supplied levels. The observed price-utility slope changes substantially across the $15–$25, $25–$35, and $35–$60 intervals. Monetary valuations therefore depend on the conversion convention and starting price.
  2. WTP should be interpreted relative to a specified baseline. Local-slope WTP is useful for comparison but may exceed the interval that defines its slope. Piecewise compensation is internally consistent within the observed price domain, yet some improvements cannot be fully valued without extrapolation.
  3. Promotions have measurable incremental value. Hot dog and soda has the largest utility improvement relative to no promotion. Its modeled monetary equivalent can exceed its reported direct cost under several conversion conventions, but this does not by itself establish profitability.
  4. Consumer utility and management performance are distinct. Price cuts, seat upgrades, and promotions can be ranked by utility gain; selecting among them requires additional financial and demand assumptions.

7.3 7.3 Limitations and scope of inference

Data granularity. The project uses 16 supplied part-worth estimates, not the 204 respondents’ individual choice records. It cannot estimate individual-level WTP heterogeneity, statistical standard errors, or out-of-sample purchase accuracy from these inputs.

Price specification. Price is represented by four categorical part-worths. The local-slope, endpoint-slope, and piecewise-linear approaches are alternative valuation conventions; the data do not establish a uniquely correct continuous price-response function.

Price bounds and feasibility. WTP above $60 cannot be identified by the piecewise method without extrapolation. A monetary equivalent for a hypothetical attribute improvement is not necessarily a feasible price for a particular seat category or an observed market offer.

Units and costs. Price is per seat per game, while promotional costs require a documented delivery frequency before full package contribution can be calculated. A comparison between price-equivalent value and reported promotional cost is illustrative until these accounting units are aligned.

Decision relevance. The analysis does not model the outside option, total demand, seat capacity, substitution across packages, or competitive responses. Therefore, no estimate here is a calibrated profit-maximizing price or an empirically validated revenue forecast.

8 8. Export results for the remaining modules

The project saves all monetary valuations and diagnostic tables using a 03_ prefix. These outputs support the package design and cost analysis in Module 4 and the sensitivity analysis in Module 5. The input workbook and the processed utility table remain unchanged.

save_table(price_steps, "03_price_utility_intervals.csv")
save_table(price_fit_summary, "03_linear_price_diagnostics.csv")
save_table(changes, "03_attribute_utility_improvements.csv")
save_table(local_wtp, "03_local_slope_wtp.csv")
save_table(piecewise_wtp, "03_piecewise_wtp.csv")
save_table(promotion_values, "03_promotion_incremental_values.csv")
save_table(promotion_sensitivity, "03_promotion_valuation_sensitivity.csv")
save_table(price_cuts, "03_price_reductions.csv")
save_table(tradeoffs, "03_attribute_price_tradeoffs.csv")
save_table(seat_price_pairs, "03_seat_price_comparisons.csv")
save_table(headroom_summary, "03_seat_price_headroom.csv")
save_table(validation, "03_numerical_validation.csv")
export_manifest <- data.frame(
  category = c(rep("Table", 12), rep("Figure", 4)),
  file = c("03_price_utility_intervals.csv", "03_linear_price_diagnostics.csv",
           "03_attribute_utility_improvements.csv", "03_local_slope_wtp.csv",
           "03_piecewise_wtp.csv", "03_promotion_incremental_values.csv",
           "03_promotion_valuation_sensitivity.csv", "03_price_reductions.csv",
           "03_attribute_price_tradeoffs.csv", "03_seat_price_comparisons.csv",
           "03_seat_price_headroom.csv", "03_numerical_validation.csv",
           "03_price_partworth_nonlinearity.png", "03_local_wtp_by_price_interval.png",
           "03_piecewise_wtp_reference_prices.png", "03_promotion_wtp_cost_sensitivity.png"))
knitr::kable(export_manifest, caption = "Module 3 output manifest")
Module 3 output manifest
category file
Table 03_price_utility_intervals.csv
Table 03_linear_price_diagnostics.csv
Table 03_attribute_utility_improvements.csv
Table 03_local_slope_wtp.csv
Table 03_piecewise_wtp.csv
Table 03_promotion_incremental_values.csv
Table 03_promotion_valuation_sensitivity.csv
Table 03_price_reductions.csv
Table 03_attribute_price_tradeoffs.csv
Table 03_seat_price_comparisons.csv
Table 03_seat_price_headroom.csv
Table 03_numerical_validation.csv
Figure 03_price_partworth_nonlinearity.png
Figure 03_local_wtp_by_price_interval.png
Figure 03_piecewise_wtp_reference_prices.png
Figure 03_promotion_wtp_cost_sensitivity.png

9 9. Conclusion and transition to package design

Conjoint-based valuation reveals that a feature’s economic interpretation depends on both its incremental utility and the way price enters the utility model. The supplied price estimates are not linear across observed levels, so a single WTP figure can conceal important sensitivity. By reporting local approximations, bounded piecewise compensation, and explicit promotional cost benchmarks, the project provides a more transparent basis for evaluating ticket-package features.

The central managerial insight is that consumer value is necessary but not sufficient for a financial recommendation. Module 4 — Ticket Package Design & Constrained Decision Analysis — will evaluate the feasible combinations of games, price, seating, and promotions and distinguish systematic utility from clearly defined economic contribution measures.

10 References and data provenance

  • Wilcox, Ronald T. Portland Trail Blazers. Darden Business Publishing, case UV2971 (revised April 2017). Business context, survey description, ticket attributes, pricing constraints, and reported cost schedule.
  • Xiang, Keman. Portland Trail Blazers_Keman_Xiang.xlsx. Project input workbook, including Table 1. Utility score data., Product Analysis, Willingness to pay, and Attribute Tradeoff.
  • Xiang, Keman. Assignment 3. Project discussion of attribute importance, ticket-price comparisons, and promotional valuation.
  • Project Module 1: 01_data_input_validation_eda.Rmd; Module 2: 02_conjoint_utility_importance.Rmd.