关于「东西方原典考辨:《墨子·小取》「以类取,以类予」与密尔的差异法」,《合成控制与单站改版》给出的定量结论是什么?
结论:字面意义上的孪生站,平均每个面板只有 0.325 个,有至少一个的面板只占 0.260。密尔要求的那种事例,在三十四个站的店里大约四次里有三次根本不存在。前后对比作为同一对象的两个时刻,偏差 +33.64,均方根误差 35.61。单个孪生站的前期误差 9.43,偏差只有 +1.86,均方根误差却有 8.63:它的偏差小,是因为平移去掉了水平差,可它带着自己全部的噪声,单个站的随机起伏原样进入了估计。合成站的前期误差 6.84,偏差 +3.90,均方根误差 5.42,三者最小。合成站用多个站的加权平均摊薄了单个站的噪声,代价是一点插值造成的偏差。
数据口径:在一个三十四站的示意面板上,真实提升设为每周十二单,前后对比报出 37.77,主要误差来自季节;用单纯形约束权重把三十三个未改版的捐赠站加权成合成对照站,估计为 8.83。 两百个面板上,前后对比的均方根误差为 35.61,合成对照为 5.42。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.260, 0.325, 1.86, 3.90, 33.64, 35.61
| literal twins within 10% on 3 traits: mean 0.325 per panel, | |||
| share of panels with at least one: 0.260 | |||
| method | preRMSPE | bias | lift RMSE |
| before-after | n/a | +33.64 | 35.61 |
| single twin | 9.43 | +1.86 | 8.63 |
| synthetic | 6.84 | +3.90 | 5.42 |
查看完整验算程序
# Chapter 7. p71: Mill's method of difference with one twin site.
# Mill asks for two instances with "every circumstance in common save
# one". Panel as in p11 (illustrative, true lift +12), 200 panels.
# (a) How often does any of the 33 donors match the redesigned site
# within 10 per cent on level, season loading and market loading
# at once (a literal twin)? (b) Three comparisons: the same site
# before and after (Mill's two instances in time), the single best
# pre-fitted donor shifted to the site's level (a twin in space),
# and the synthetic site (a twin assembled from many donors).
import math
import random
from operator import mul
# 示意面板:每站周订单 = 基准 + 季节载荷 * 季节 + 大盘载荷 * 大盘 + 噪声
T0, POST, NS = 52, 12, 34
def panel(rep=0, n=NS, t0=T0, post=POST, tau=12.0, start=10):
rng = random.Random(20261113 + 7919 * rep)
weeks = t0 + post
mk = [0.0]
for _ in range(weeks - 1):
mk.append(mk[-1] + rng.gauss(0.05, 0.25))
ss = [math.sin(2.0 * math.pi * (start + t) / 52.0)
for t in range(weeks)]
ys, cf, pars = [], [], []
for i in range(n):
if i == 0:
mu, ra, rb, sd = 240.0, 0.20, 1.30, 7.0
else:
mu = rng.uniform(120.0, 360.0)
ra = rng.uniform(0.04, 0.22)
rb = rng.uniform(0.5, 1.7)
sd = rng.uniform(5.0, 9.0)
a, b = mu * ra, mu * rb / 20.0
y = [mu + a * ss[t] + b * mk[t] + rng.gauss(0.0, sd)
for t in range(weeks)]
cf.append(y[:])
if i == 0:
for t in range(t0, weeks):
y[t] = y[t] + tau
ys.append(y)
pars.append((mu, a, b, sd))
return ys, cf, pars, ss, mk
def dot(a, b):
return math.fsum(map(mul, a, b))
def mean(xs):
return math.fsum(xs) / len(xs)
def rmspe(xs):
return math.sqrt(math.fsum([x * x for x in xs]) / len(xs))
def gram(ys, t0):
n = len(ys)
pre = [y[:t0] for y in ys]
g = [[0.0] * n for _ in range(n)]
for i in range(n):
for k in range(i, n):
v = dot(pre[i], pre[k]) / t0
g[i][k] = v
g[k][i] = v
return g
def solve(a, b):
m = len(b)
r = [row[:] + [b[i]] for i, row in enumerate(a)]
for c in range(m):
p = max(range(c, m), key=lambda i: abs(r[i][c]))
r[c], r[p] = r[p], r[c]
for i in range(c + 1, m):
f = r[i][c] / r[c][c]
if f:
r[i] = [x - f * y for x, y in zip(r[i], r[c])]
x = [0.0] * m
for i in range(m - 1, -1, -1):
s = math.fsum([r[i][k] * x[k] for k in range(i + 1, m)])
x[i] = (r[i][m] - s) / r[i][i]
return x
def eq_qp(g, c, sup):
m = len(sup)
a = [[2.0 * g[i][k] for k in sup] + [1.0] for i in sup]
a.append([1.0] * m + [0.0])
b = [2.0 * c[i] for i in sup] + [1.0]
return solve(a, b)[:m]
def simplex_ls(g, c, tol=1e-10):
# 精确有效集法:min w'Gw - 2c'w,w >= 0,权重和为 1
j = len(c)
k0 = min(range(j), key=lambda k: g[k][k] - 2.0 * c[k])
w = [0.0] * j
w[k0] = 1.0
sup = [k0]
for _ in range(4 * j + 20):
gr = [2.0 * (math.fsum([g[i][k] * w[k] for k in sup]) - c[i])
for i in range(j)]
nu = -math.fsum([gr[k] for k in sup]) / len(sup)
out = [k for k in range(j) if k not in sup]
if not out:
break
kb = min(out, key=lambda k: gr[k] + nu)
if gr[kb] + nu >= -tol:
break
sup = sorted(sup + [kb])
while True:
z = eq_qp(g, c, sup)
if min(z) > 0.0:
for k, v in zip(sup, z):
w[k] = v
break
step = min(w[k] / (w[k] - v) for k, v in zip(sup, z)
if v <= 0.0)
for k, v in zip(sup, z):
w[k] = w[k] + step * (v - w[k])
sup = [k for k in sup if w[k] > 1e-12]
for k in range(j):
if k not in sup:
w[k] = 0.0
return w
def synth(ys, g, tr, donors):
gs = [[g[i][k] for k in donors] for i in donors]
cs = [g[i][tr] for i in donors]
w = simplex_ls(gs, cs)
weeks = len(ys[tr])
gap = [ys[tr][t] - dot(w, [ys[d][t] for d in donors])
for t in range(weeks)]
return w, gap
def ratio(gap, t0=T0):
return rmspe(gap[t0:]) / rmspe(gap[:t0])
def placebo(ys, g, tr, pool, t0=T0):
# 逐个捐赠站当处理站;处理站本身不进入安慰剂的捐赠池
out = {}
for j in pool:
dn = [k for k in pool if k != j]
out[j] = synth(ys, g, j, dn)[1]
return out
if __name__ == "__main__":
donors = list(range(1, NS))
twins, est = [], {"before-after": [], "single twin": [],
"synthetic": []}
pre = {"single twin": [], "synthetic": []}
for r in range(200):
ys, cf, pars, ss, mk = panel(r)
p0 = pars[0]
n = len([d for d in donors
if all(abs(pars[d][k] / p0[k] - 1.0) <= 0.10
for k in range(3))])
twins.append(n)
est["before-after"].append(mean(ys[0][T0:]) -
mean(ys[0][T0 - 12:T0]))
g = gram(ys, T0)
w, gap = synth(ys, g, 0, donors)
est["synthetic"].append(mean(gap[T0:]))
pre["synthetic"].append(rmspe(gap[:T0]))
best = None
for d in donors:
sh = mean(ys[0][:T0]) - mean(ys[d][:T0])
gp = [ys[0][t] - ys[d][t] - sh for t in range(T0 + POST)]
f = rmspe(gp[:T0])
if best is None or f < best[0]:
best = (f, gp)
est["single twin"].append(mean(best[1][T0:]))
pre["single twin"].append(best[0])
have = len([n for n in twins if n > 0]) / len(twins)
print("literal twins within 10% on 3 traits: mean {:.3f} per panel,"
.format(mean(twins)))
print(" share of panels with at least one: {:.3f}".format(have))
print("method preRMSPE bias lift RMSE")
for k, xs in est.items():
pr = "{:8.2f}".format(mean(pre[k])) if k in pre else " n/a"
print("{:<14s} {} {:+6.2f} {:9.2f}".format(
k, pr, mean(xs) - 12.0, rmspe([x - 12.0 for x in xs])))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《合成控制法与单站改版因果、捐赠站加权重建反事实与安慰剂置换检验母典》第 7 章「东西方原典考辨:《墨子·小取》「以类取,以类予」与密尔的差异法」(版本 1.0.0). 5D Library. DOI 待发布
DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-304 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026304,
author = {Fan, Yafu},
title = {Synthetic Control and the Causal Effect of a Single-Site Redesign: Rebuilding the Counterfactual from Weighted Donor Sites and Placebo Permutation Tests},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}