Psychology Research Guide

import pandas as pd
import pingouin as pg
from scipy import stats

# Load data
df = pd.read_csv("experiment_data.csv")

# Step 1: Descriptive statistics by condition
descriptives = df.groupby("condition").agg(
    n=("dv", "count"),
    mean=("dv", "mean"),
    sd=("dv", "std"),
    median=("dv", "median"),
).round(3)

# Step 2: Check assumptions
# Normality
for condition in df["condition"].unique():
    subset = df[df["condition"] == condition]["dv"]
    stat, p = stats.shapiro(subset)
    print(f"{condition}: Shapiro-Wilk W={stat:.3f}, p={p:.3f}")

# Homogeneity of variance
levene_stat, levene_p = stats.levene(
    df[df["condition"] == "treatment"]["dv"],
    df[df["condition"] == "control"]["dv"],
)

# Step 3: Primary analysis with effect size and CI
result = pg.ttest(
    df[df["condition"] == "treatment"]["dv"],
    df[df["condition"] == "control"]["dv"],
    paired=False,
    alternative="two-sided",
)
print(result[["T", "dof", "p-val", "cohen-d", "CI95%", "BF10"]])

# Step 4: Bayesian analysis (increasingly expected)
bf10 = float(result["BF10"].values[0])
print(f"Bayes Factor BF10 = {bf10:.2f}")
if bf10 > 10:
    print("Strong evidence for H1")
elif bf10 > 3:
    print("Moderate evidence for H1")
elif bf10 > 1:
    print("Anecdotal evidence for H1")
else:
    print("Evidence favors H0")

# One-way ANOVA
aov = pg.anova(dv="score", between="group", data=df, detailed=True)
print(aov)

# Effect size (eta-squared and omega-squared)
print(f"Eta-squared: {aov['np2'].values[0]:.3f}")

# Post-hoc pairwise comparisons with correction
posthoc = pg.pairwise_tukey(dv="score", between="group", data=df)
print(posthoc)

# Mixed ANOVA (between + within)
mixed = pg.mixed_anova(
    dv="score", between="group", within="time",
    subject="participant_id", data=df_long
)
print(mixed)

# Scale reliability
from pingouin import cronbach_alpha

items = df[["item1", "item2", "item3", "item4", "item5"]]
alpha, ci = cronbach_alpha(items)
print(f"Cronbach's alpha = {alpha:.3f}, 95% CI = [{ci[0]:.3f}, {ci[1]:.3f}]")

# Confirmatory Factor Analysis (using semopy)
from semopy import Model

model_spec = """
factor1 =~ item1 + item2 + item3
factor2 =~ item4 + item5 + item6
"""
model = Model(model_spec)
model.fit(df)
print(model.inspect())

# Fit indices
stats_result = model.calc_stats()
print(f"CFI = {stats_result.loc['CFI', 'Value']:.3f}")
print(f"RMSEA = {stats_result.loc['RMSEA', 'Value']:.3f}")
print(f"SRMR = {stats_result.loc['SRMR', 'Value']:.3f}")

Standard reporting patterns:

t-test:
"Participants in the gratitude condition (M = 5.23, SD = 1.12) reported
significantly higher life satisfaction than those in the control condition
(M = 4.67, SD = 1.08), t(398) = 4.89, p < .001, d = 0.49, 95% CI [0.29, 0.69]."

ANOVA:
"There was a significant main effect of group on performance,
F(2, 297) = 8.43, p < .001, eta-p-squared = .054."

Correlation:
"Life satisfaction was positively correlated with gratitude,
r(198) = .42, p < .001, 95% CI [.30, .53]."

Always include: test statistic, df, p-value, effect size, confidence interval.