Methods
Participants
Data was collected from 100 adults recruited via Prolific on Mon
6/2/2025. Participants were required to be in the United States, fluent
in English, and have not participated in the earlier pilot of this
study.
Participants were paid $2.75 for an estimated 10-12 minute task. In
fact, the study generally took about 14 minutes for participants.
The final sample included 88 adults (n = 44-44 in each of the 2
conditions).
| condition (boat height) |
participants |
| not skewed (10) |
44 |
| skewed (6) |
44 |
Exclusion criteria
12 participants (12.0% of all participants) were excluded for meeting
at least 1 of the following exclusion criteria:
failing the sound check (n = 3 participants)
failing to select the correct task description (i.e., did not
select “Watching videos about fictional people from an island”) (n = 2
participants)
failing the memory check (n = 5
participants)
failing the comprehension
check (n = 6 participants)
Including participants who failed the memory check or comprehension
check (but who passed the other exclusion criteria) results in largely
the same effects as described below, other than the participants in the
skewed boat height (6) condition, no longer making population inferences
that are significantly taller than their sample inferences (see sample vs population).
Memory check
Participants overwhelmingly passed the memory check for the Quaffa
boarding sequence, i.e., “no”, not all the Quaffas made it onto the
boat.
Participants who made incorrect responses were excluded.
Comprehension check
Participants overwhelmingly passed the comprehension check for the
Zarpie boarding sequence. Note the correct answer to this question
depends on condition:
In the boat height 6 condition, the correct answer is “no”, not
all of the Zarpies made it onto the boat.
In the boat height 10 condition, the correct answer is “yes”, all
of the Zarpies made it onto the boat.
Participants who made incorrect responses or non-responses were
excluded. Note that there are some non-responses (NAs), because I forgot
to require a response on this question in Qualtrics.
Demographics
| age |
| mean |
sd |
n |
| 39.70 |
13.94 |
88 |
- The sample was largely young and middle-aged.
| gender |
n |
prop |
| Female |
45 |
51.1% |
| Male |
42 |
47.7% |
| Prefer not to specify |
1 |
1.1% |
- The sample was diverse in terms of gender identities in the US.
| race |
n |
prop |
| White, Caucasian, or European American |
45 |
51.1% |
| Black or African American |
19 |
21.6% |
| Hispanic or Latino/a |
8 |
9.1% |
| White, Caucasian, or European American,Hispanic or Latino/a |
3 |
3.4% |
| Hispanic or Latino/a,Black or African American |
2 |
2.3% |
| Middle Eastern or North African |
2 |
2.3% |
| White, Caucasian, or European American,Black or African American |
2 |
2.3% |
| East Asian |
1 |
1.1% |
| East Asian,Native Hawaiian or other Pacific Islander |
1 |
1.1% |
| Hispanic or Latino/a,South or Southeast Asian |
1 |
1.1% |
| Native American, American Indian, or Alaska Native |
1 |
1.1% |
| Prefer not to specify |
1 |
1.1% |
| South or Southeast Asian |
1 |
1.1% |
| White, Caucasian, or European American,Native American, American Indian, or Alaska Native |
1 |
1.1% |
- The sample was also racially diverse.
| education |
n |
prop |
| High school/GED |
9 |
10.2% |
| Some college |
25 |
28.4% |
| Bachelor's (B.A., B.S.) |
30 |
34.1% |
| Master's (M.A., M.S.) |
20 |
22.7% |
| Doctoral (Ph.D., J.D., M.D.) |
3 |
3.4% |
| Prefer not to specify |
1 |
1.1% |
- The sample was mostly college-educated.
Procedure
This study was administered as a Qualtrics
survey, and approved by the NYU IRB (IRB-FY2024-9169).
After providing their consent, participants completed a captcha and
sound check, and were asked to watch videos sound on. Participants then
watched the following videos in order:
In the prior setting and familiarization phase,
participants saw a photorealistic picture of 5 human adults and then
another picture of a different 5 adults appear on screen against a grid.
These adults were all 10 gridline units tall.
In the boat training phase, participants were
randomly assigned to see a boat that was either 6 or 10 units tall.
The boat height was specified to be accidental (“When the boat
builders were building the boat, they started building the boat from the
bottom, but ran out of the special wood they needed for the boat! So the
boat ended up being this tall. It might be hard for anyone who is taller
than the boat to get on the boat.”), to avoid any justificatory
reasoning about the height of the boat being informative about the
height of Zarpies or vice versa.
To communicate how the boat functions to exclude those shorter
than the boat, participants then watched a parade of 20 fictional
animals (Quaffas, taken from Foster-Hanson et al., 2019) attempt to
board the boat, one at a time, from shortest to tallest.
The height of animals were scaled to the height of the boat, such
that 10 animals were always shorter than the boat (these animals boarded
successfully) and 10 animals were always taller than the boat (all but
one were unable to board; the third quaffa successfully boards by
bending its head).
Participants were asked a memory check: “Did all
of the animals board the boat?” (yes/no), and received an affirmation
(if they said “no”) or correction (if they said “yes”).
In the boat boarding phase, participants learned
that Zarpies live on Zarpie island, and saw an island with many Zarpies
overhead. Participants learned that all the grownup Zarpies’ names were
put into a hat, and some of their names “were drawn out of a hat to try
and visit us”. Participants saw then saw a parade of Zarpies attempt to
board the boat to visit us, one at a time, behind a curtain that
obscured their heights. Participants were told that they were all
grown-up Zarpies.
- In the boat height 6 condition, 20 Zarpies attempt to board, 6 of
whom successfully make it on (6 out of 16 successful = 30% successful).
Of the 6 who make it on, 2 had to stoop to board.
Boarding for boat height 6 condition.
* In the boat height 10 condition, 6 Zarpies attempt to board, all of whom successfully make it on without stooping.
Boarding for boat height 10 condition.
After the boat boarding phase, participants were asked a
comprehension check: “Did all of the Zarpies board the
boat?” (yes/no), and received either an affirmation (if they said “no”
in boat height 6, or “yes” in boat height 10) or correction (if they
said “yes” in boat height 6, or “no” in boat height 10).
In the sample observation phase, all
participants saw the Zarpies who successfully boarded the boat get off
the boat to visit us. The Zarpies got off one at a time, and each
waved/descrunched if relevant. The height of this observed sample (4, 5,
6, 6, 7, 8) was held constant across conditions.
- To emphasize the height of the Zarpies relative to the boat,
participants watched Zarpies deboard the boat, wave, reboard the boat
(with any Zarpies taller than the boat stooping down again to board
again), and deboard again (with any Zarpies taller than the boat
straightening up again).
Observed sample in boat height 10
condition.
Participants were asked the following DVs in the
following order:
Participants were asked the average height of the Zarpies who
visited (Sample representation) and
the average height of Zarpies on Zarpie island (Population inference), in
counterbalanced order.
Participants were then asked an explicit comparison question
asking them to compare the heights of Zarpies on Zarpie island to that
of Zarpies who visited: shorter, about the same, or taller (see explicit comparison).
Participants were then shown pairs of Zarpies (6v7, 6v8, 7v8) and
told one Zarpie is from Zarpie island and one is a Zarpie who visited,
and asked to guess which one is the Zarpie on Zarpie island. Pairs were
presented in randomized order. (see pairwise forced-choice)
Finally, participants were asked for any problems or confusion they
had, what they thought the task was about (see [Participant feedback]),
and demographic information.
Primary results
Sample representation
As a check that they could retrieve the mean of the sample they
observed, participants were asked, “Which picture shows the average
height of the Zarpies who visited?”, and had to choose between a Zarpie
of height 4, 5, 6, 7, or 8.
Sample representation question for boat height 6
condition, with the response options in red boxes.
Since all participants saw the same sample, participants should
provide the same response, regardless of condition. The sample was (4,
5, 6, 6, 7, 8), so the the response is expected to be the mean of the
sample, 6 (indicated with a red line below).
As expected, there was no main effect of condition (boat
height) on sample representations (t = 0.23,
p = 0.817), since all participants observed the same
sample.
Participants on average reported taller heights than the true
mean of the sample, 6 (t(87) = 2.1, p =
0.038).
Population inference
To assess how tall participants thought Zarpies in general are,
participants were asked: “Which picture shows the average height of
Zarpies on Zarpie island?” Response options were a Zarpie of height 4,
5, 6, 7, or 8.
If
participants adjust their inferences about the population based on
biases in the sampling process:
- Participants in the unrestricted (boat height 10) condition should
infer that the population is like the sample, since everyone
was able to board, so they should respond with something similar to
sample mean, i.e., 6.
- Participants in the restricted (boat height 6) condition should
infer the population is taller than the sample, since Zarpies
taller than the boat were unable to board, so they should report
significantly taller height than those in the unrestricted
condition.
Participants thought the population was taller in the skewed
boat height 6 condition than the not skewed boat height 10
condition (partial \(\eta^2\)
= 0.06, t = -2.43, p = 0.017).
Power analysis: \(f^2 = t^2/df =
(-2.435)^2/86 = 0.0689\), which is a small effect size. Using
GPower on a linear multiple regression, fixed model, R2 deviation from
0, looking for 95% power, GPower suggests n = 191 total sample size.
In the skewed boat height 6 condition, participants’ population
inferences were significantly taller than the sample mean of 6
(t(43) = 2.64, p = 0.011), and taller than their
sample representations (see sample vs
population).
In the not skewed boat height 10 condition, participants’ population
inferences were not different from the sample mean of 6 (t(43)
= -0.27, p = 0.785) nor from their sample representations (see
sample vs population).
Explicit comparison
Participants were explicitly asked to compare the population to the
sample: “Do you think the Zarpies on Zarpie island are shorter,
about the same, or taller than the Zarpies who
visited?”
| boatheight_label |
shorter |
about the same |
taller |
| not skewed (10) |
9% |
86% |
5% |
| skewed (6) |
5% |
57% |
39% |
Participants’ explicit comparisons were significantly different
between the two conditions (p < .001, Fisher’s exact).
##
## Call:
## glm(formula = dv_comp_taller ~ boatheight, family = binomial,
## data = .)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.4626 0.3096 -1.494 0.13512
## boatheight10 -2.5819 0.7871 -3.280 0.00104 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 91.816 on 87 degrees of freedom
## Residual deviance: 74.976 on 86 degrees of freedom
## AIC: 78.976
##
## Number of Fisher Scoring iterations: 5
##
## Call:
## glm(formula = dv_comp_same ~ boatheight, family = binomial, data = .)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.2744 0.3044 0.902 0.36722
## boatheight10 1.5714 0.5344 2.940 0.00328 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 105.033 on 87 degrees of freedom
## Residual deviance: 95.227 on 86 degrees of freedom
## AIC: 99.227
##
## Number of Fisher Scoring iterations: 4
##
## Call:
## glm(formula = dv_comp_shorter ~ boatheight, family = binomial,
## data = .)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.0445 0.7237 -4.207 0.0000259 ***
## boatheight10 0.7419 0.8937 0.830 0.406
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 43.808 on 87 degrees of freedom
## Residual deviance: 43.080 on 86 degrees of freedom
## AIC: 47.08
##
## Number of Fisher Scoring iterations: 5
When comparing the height of Zarpies on Zarpie island to those who
visited, participants in the skewed boat height 6 condition were
significantly more likely to say that they are “taller” (z =
-3.33, p < .001), and significantly less likely to say that
they are “about the same” (z = 3.18, p = .0015),
compared to those in the not skewed boat height 10 condition. Responses
that they are “shorter” were rare and did not differ across conditions
(p > .60).
Pairwise forced-choice
Participants saw pairs of Zarpies of different heights, and were told
one is a Zarpie on Zarpie island and the other one a Zarpie who visited.
Participants asked to guess which was the Zarpie on Zarpie island.
The pairs tested were 6v8, 7v8, and 6v7, in randomized order.
6v8
6v8 forced choice question for boat height
6.
Participants’ choices did not differ between conditions (z =
-0.72, p = .47).
##
## Call:
## glm(formula = dv_fc_6v8 ~ boatheight, family = binomial, data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.1823 0.3028 0.602 0.547
## boatheight10 -0.1823 0.4273 -0.427 0.670
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 121.81 on 87 degrees of freedom
## Residual deviance: 121.63 on 86 degrees of freedom
## AIC: 125.63
##
## Number of Fisher Scoring iterations: 3
Participants’ choices were not different from chance in either
condition (ps > .57).
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "6") %>% pull(dv_fc_6v8) %>% as.character() %>% as.numeric()
## t = 0.59861, df = 43, p-value = 0.5526
## alternative hypothesis: true mean is not equal to 7
## 95 percent confidence interval:
## 6.784640 7.397178
## sample estimates:
## mean of x
## 7.090909
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "10") %>% pull(dv_fc_6v8) %>% as.character() %>% as.numeric()
## t = 0, df = 43, p-value = 1
## alternative hypothesis: true mean is not equal to 7
## 95 percent confidence interval:
## 6.692457 7.307543
## sample estimates:
## mean of x
## 7
6v7
6v7 forced choice question for boat height
6.
Participants’ choices did not differ between conditions (z =
-0.50, p = .62).
##
## Call:
## glm(formula = dv_fc_6v7 ~ boatheight, family = binomial, data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.4626 0.3096 1.494 0.135
## boatheight10 -0.3717 0.4324 -0.860 0.390
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 120.35 on 87 degrees of freedom
## Residual deviance: 119.61 on 86 degrees of freedom
## AIC: 123.61
##
## Number of Fisher Scoring iterations: 4
Participants’ choices were not different from chance in either
condition (ps > .15).
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "6") %>% pull(dv_fc_6v7) %>% as.character() %>% as.numeric()
## t = 1.5304, df = 43, p-value = 0.1332
## alternative hypothesis: true mean is not equal to 6.5
## 95 percent confidence interval:
## 6.463889 6.763384
## sample estimates:
## mean of x
## 6.613636
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "10") %>% pull(dv_fc_6v7) %>% as.character() %>% as.numeric()
## t = 0.29837, df = 43, p-value = 0.7669
## alternative hypothesis: true mean is not equal to 6.5
## 95 percent confidence interval:
## 6.369115 6.676340
## sample estimates:
## mean of x
## 6.522727
7v8
7v8 forced choice question for boat height
6.
Participants’ choices did not differ between conditions (z =
0.30, p = .77).
##
## Call:
## glm(formula = dv_fc_7v8 ~ boatheight, family = binomial, data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.3677 0.3066 -1.199 0.23
## boatheight10 0.2768 0.4302 0.643 0.52
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 120.86 on 87 degrees of freedom
## Residual deviance: 120.44 on 86 degrees of freedom
## AIC: 124.44
##
## Number of Fisher Scoring iterations: 4
Participants’ choices were not different from chance in either
condition (ps > .25).
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "6") %>% pull(dv_fc_7v8) %>% as.character() %>% as.numeric()
## t = -1.2125, df = 43, p-value = 0.232
## alternative hypothesis: true mean is not equal to 7.5
## 95 percent confidence interval:
## 7.257883 7.560299
## sample estimates:
## mean of x
## 7.409091
##
## One Sample t-test
##
## data: data %>% filter(boatheight == "10") %>% pull(dv_fc_7v8) %>% as.character() %>% as.numeric()
## t = -0.29837, df = 43, p-value = 0.7669
## alternative hypothesis: true mean is not equal to 7.5
## 95 percent confidence interval:
## 7.323660 7.630885
## sample estimates:
## mean of x
## 7.477273
Secondary results
Sample vs population
As an implicit comparison, we can compare each participant’s sample
representation and population inference to each other.
As expected, participants in the unrestricted (boat height
10) condition did not give different responses to sample and population
questions (t(43) = 1.63, p = 0.11). This is
expected since in the unrestricted boat height 10 condition, the sample
and the population are identical.
##
## Paired t-test
##
## data: data %>% filter(boatheight == "6") %>% pull(dv_sample) and data %>% filter(boatheight == "6") %>% pull(dv_pop)
## t = -2.3023, df = 43, p-value = 0.02622
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -0.55425882 -0.03665027
## sample estimates:
## mean difference
## -0.2954545
Participants in the restricted (boat height 6) condition gave
significantly taller responses to the population question than to the
sample question (\(t\)(43) =
-2.30, \(p\) = .026).
However, this effect disappears when including those participants who
failed the memory check or comprehension check (\(t\)(47) = -1.61, \(p\) = .11).
##
## Call:
## lm(formula = response ~ boatheight * dv, data = data_tidy)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.38636 -0.11364 -0.09091 0.02273 1.90909
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.09091 0.09718 62.674 <0.0000000000000002 ***
## boatheight10 0.02273 0.13744 0.165 0.8689
## dvdv_pop 0.29545 0.13744 2.150 0.0330 *
## boatheight10:dvdv_pop -0.43182 0.19437 -2.222 0.0276 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6446 on 172 degrees of freedom
## Multiple R-squared: 0.05264, Adjusted R-squared: 0.03612
## F-statistic: 3.186 on 3 and 172 DF, p-value: 0.02524
Were participants in the restricted boat height 6 condition
significantly more likely than participants in the unrestricted boat
height 10 condition to give taller responses to the population than
sample questions? There is a marginal interaction between boat height
condition (6 vs 10) and dv (sample vs population) (t = -2.22,
p = .028).
This interaction becomes marginal when including participants who
failed memory check or comprehension check (t = 1.78,
p = .076).
Order effects
Participants saw the two DVs in counterbalanced order:
pop_sample = population DV first, then sample DVsample_pop = sample DV first, then population DV
There was an effect of DV order on population responses, but not on
sample responses.
Sample representation order effects
There is no order effect on sample representation.
## Anova Table (Type II tests)
##
## Response: dv_sample
## Sum Sq Df F value Pr(>F)
## boatheight 0.0120 1 0.0559 0.8137
## cb_dvorder 0.0171 1 0.0798 0.7783
## boatheight:cb_dvorder 0.0172 1 0.0800 0.7780
## Residuals 18.0339 84
Population inference order effects
In a linear model with main effects of condition, DV order, and their
interaction on population inferences, there was no effect of condition,
a main effect of DV order, and a marginal interaction between condition
and DV order.
Participants gave higher population estimates after they gave sample
estimates, then when they were asked before the sample, as indicated by
a main effect of DV order on population estimates (t = 2.14,
p = .036).
There is also a marginal interaction of order and condition
(t = -1.64, p = .10), suggesting the effect may only
emerge when participants are asked about the sample then about the
population, rather than just about the population right off the bat.
##
## Call:
## lm(formula = dv_pop ~ boatheight * cb_dvorder, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6364 -0.1364 0.0000 0.1235 1.8636
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 6.1364 0.1655 37.070
## boatheight10 -0.1364 0.2369 -0.576
## cb_dvordersample_pop 0.5000 0.2341 2.136
## boatheight10:cb_dvordersample_pop -0.5435 0.3312 -1.641
## Pr(>|t|)
## (Intercept) <0.0000000000000002 ***
## boatheight10 0.5664
## cb_dvordersample_pop 0.0356 *
## boatheight10:cb_dvordersample_pop 0.1046
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7764 on 84 degrees of freedom
## Multiple R-squared: 0.113, Adjusted R-squared: 0.08134
## F-statistic: 3.568 on 3 and 84 DF, p-value: 0.01746
Indeed, the effect of boat height condition on population inferences
is only found when population inferences are made after the
sample question (t = -2.93, p = .0054), and not when
it is made before (t = -0.58, p = .58).
##
## Call:
## lm(formula = dv_pop ~ boatheight, data = data %>% filter(cb_dvorder ==
## "sample_pop"))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.63636 -0.63636 0.04348 0.36364 1.36364
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.6364 0.1659 39.994 < 0.0000000000000002 ***
## boatheight10 -0.6798 0.2321 -2.929 0.00542 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7783 on 43 degrees of freedom
## Multiple R-squared: 0.1663, Adjusted R-squared: 0.1469
## F-statistic: 8.579 on 1 and 43 DF, p-value: 0.00542
##
## Call:
## lm(formula = dv_pop ~ boatheight, data = data %>% filter(cb_dvorder ==
## "pop_sample"))
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1364 -0.1364 0.0000 0.0000 1.8636
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.1364 0.1651 37.164 <0.0000000000000002 ***
## boatheight10 -0.1364 0.2363 -0.577 0.567
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7745 on 41 degrees of freedom
## Multiple R-squared: 0.008059, Adjusted R-squared: -0.01613
## F-statistic: 0.3331 on 1 and 41 DF, p-value: 0.567
Explicit comparison order effects
There is no effect of the order of sample and population questions
(\(\chi^2\) = 0.69, p = .71)
or interaction with condition (\(\chi^2\) = 3.61, p = .16) on the
explicit comparison question, which was asked after both of them.
## # weights: 15 (8 variable)
## initial value 96.677881
## iter 10 value 56.085756
## iter 20 value 55.682399
## iter 30 value 55.681605
## final value 55.676355
## converged
## Call:
## multinom(formula = dv_comp ~ boatheight * cb_dvorder, data = data)
##
## Coefficients:
## (Intercept) boatheight10 cb_dvordersample_pop
## about the same 1.871939 1.072024 8.424506
## taller 1.252935 -1.253610 8.861231
## boatheight10:cb_dvordersample_pop
## about the same -9.522510
## taller -9.958811
##
## Std. Errors:
## (Intercept) boatheight10 cb_dvordersample_pop
## about the same 0.7595991 1.276386 49.69587
## taller 0.8018227 1.625629 49.69670
## boatheight10:cb_dvordersample_pop
## about the same 49.71034
## taller 49.73022
##
## Residual Deviance: 111.3527
## AIC: 127.3527
## Analysis of Deviance Table (Type II tests)
##
## Response: dv_comp
## LR Chisq Df Pr(>Chisq)
## boatheight 17.1776 2 0.0001862 ***
## cb_dvorder 0.6894 2 0.7084233
## boatheight:cb_dvorder 3.6101 2 0.1644649
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1