def __init__(self, X):
"""
X : model
Model which will be fitted to the data.
"""
# prepare input
self.X = X = asmodel(X)
self.n_cases = len(X)
if not isbalanced(X):
raise NotImplementedError("Unbalanced models")
self.X_ = X.full
self.full_model = fm = X.df_error == 0
if fm:
self.E_MS = hopkins_ems(X)
elif hasrandom(X):
err = "Models containing random effects need to be fully " "specified."
raise NotImplementedError(err)
self.max_len = int(2 ** _max_array_size // X.df ** 2)
if _lmf_lsq == 0:
pass
elif _lmf_lsq == 1:
self.Xsinv = X.Xsinv
else:
raise ValueError("version")
def __init__(self, X):
super(hopkins_ems, self).__init__()
if X.df_error > 0:
err = "Hopkins E(MS) estimate requires a fully specified model"
raise ValueError(err)
if not isbalanced(X):
logging.warn("X is not balanced")
for e in X.effects:
self[e] = _find_hopkins_ems(e, X)
def anova(self, title="ANOVA", empty=True, ems=False):
"""
returns an ANOVA table for the linear model
"""
X = self.X
values = self.beta * self.X.full
if X.df_error == 0:
e_ms = hopkins_ems(X)
elif hasrandom(X):
err = "Models containing random effects need to be fully " "specified."
raise NotImplementedError(err)
else:
e_ms = False
# table head
table = fmtxt.Table("l" + "r" * (5 + ems))
if title:
table.title(title)
if not isbalanced(X):
table.caption("Warning: model is unbalanced, use anova class")
table.cell()
headers = ["SS", "df", "MS"]
if ems:
headers += ["E(MS)"]
headers += ["F", "p"]
for hd in headers:
table.cell(hd, r"\textbf", just="c")
table.midrule()
# MS for factors (Needed for models involving random effects)
MSs = {}
SSs = {}
for e in X.effects:
idx = X.full_index[e]
SSs[e] = SS = np.sum(values[:, idx].sum(1) ** 2)
MSs[e] = SS / e.df
# table body
results = {}
for e in X.effects:
MS = MSs[e]
if e_ms:
e_EMS = e_ms[e]
df_d = sum(c.df for c in e_EMS)
MS_d = sum(MSs[c] for c in e_EMS)
e_ms_name = " + ".join(repr(c) for c in e_EMS)
else:
df_d = self.df_res
MS_d = self.MS_res
e_ms_name = "Res"
# F-test
if MS_d != False:
F = MS / MS_d
p = 1 - scipy.stats.distributions.f.cdf(F, e.df, df_d)
stars = test.star(p)
tex_stars = fmtxt.Stars(stars)
F_tex = [F, tex_stars]
else:
F_tex = None
p = None
# add to table
if e_ms_name or empty:
table.cell(e.name)
table.cell(SSs[e])
table.cell(e.df, fmt="%i")
table.cell(MS)
if ems:
table.cell(e_ms_name)
table.cell(F_tex, mat=True)
table.cell(fmtxt.p(p))
# store results
results[e.name] = {"SS": SS, "df": e.df, "MS": MS, "E(MS)": e_ms_name, "F": F, "p": p}
# Residuals
if self.df_res > 0:
table.cell("Residuals")
table.cell(self.SS_res)
table.cell(self.df_res, fmt="%i")
table.cell(self.MS_res)
return table