The Dazzle Farm Hypothesis: G*Power Analysis

Context & Methodology

Location: Ptuj, Slovenia (August 2020)

Observation periods:

Hypotheses:

Test parameters: One-tailed z-test for proportions, α = 0.05, Power = 90%

Using G*Power methodology with arcsine transformation for proportions

Analysis Parameters

Current settings: Power = 90%, No Cohen's h filter
Rule of 400: For ±5% margin of error at 95% confidence, n = 400 observations required

Analysis 1: Random Observations (All Sightings)

Sample size needed to detect abnormal lighting with 90% power:

Key finding for H₀ = 75% (normal behavior):

n = 144 random observations needed

Cohen's h = 0.647 (medium effect)

At 8.92 visible hours/day, this could theoretically be collected in 17 nights of observation (assuming ~1 observation per visible hour). However, true independence requires observations separated across multiple days/weeks.

Analysis 2: Consecutive "Light On" Observations

When ignoring "off" sightings, consecutive "on" observations needed:

Key finding for H₀ = 75%:

k = 13 consecutive "on" sightings needed

Cohen's h = 0.647 (medium effect)

This ignores any "off" observations and only counts consecutive instances where the light is on. Using geometric probability: P(k consecutive | H₀=75%) must be < α, and P(k consecutive | H₁=98%) must provide 90% power.

Detailed Results Table

Legal Interpretation:

If normal behavior involves lights on 75% of visible hours, an observer would need 144 random observations to distinguish this from cannabis growing behavior (98% on) with 90% confidence and α = 0.05.

Alternatively, 13 consecutive "light on" sightings (ignoring any "off" observations) would provide equivalent statistical power.

The Cohen's h effect size is 0.647, which is considered a medium effect per Cohen's benchmarks.

Ptuj Police made zero recorded observations. Their warrant was issued on literally nothing.

The Five Pollyannaisms of Ptuj Police:

  1. Blind Pollyannaism: Ignoring that the broken blind is 50% of the signal
  2. Null Pollyannaism: Not recording "light off" observations (no black swans at night)
  3. Dim Pollyannaism: "All A is B, therefore all B is A" - invalid syllogism
  4. Jealous Pollyannaism: 4.2× average floor area = convenience sampling bias
  5. Fuzzy Pollyannaism: Verbal descriptions instead of objective measurements

Generated: | Analysis performed using G*Power methodology with arcsine transformation