diff --git a/analyze.py b/analyze.py
new file mode 100644
index 0000000..20e5888
--- /dev/null
+++ b/analyze.py
@@ -0,0 +1,18 @@
+from typing import List
+
+import numpy as np
+import scipy.stats as stats
+
+
+def analyze(name: str, data: List[np.ndarray]):
+    F, p = stats.f_oneway(*data)
+    print(f"F-stats for {name}: {F}")
+    print(f"p-value for {name}: {p}")
+
+    if p > 0.05:
+        print("statistically insignificant\n")
+        return
+
+    print("statistically significant")
+    tukey_results = stats.tukey_hsd(*data)
+    print(tukey_results)
diff --git a/analyze_occupation.py b/analyze_occupation.py
index 5aa446c..f322934 100644
--- a/analyze_occupation.py
+++ b/analyze_occupation.py
@@ -1,5 +1,6 @@
 import numpy as np
-import scipy.stats as stats
+
+from analyze import analyze
 
 dataset = np.load("clean.npy")
 print(f"dataset shape: {dataset.shape}, analyzing column 6 (sex)")
@@ -12,22 +13,19 @@ print("\t5 - none")
 print("")
 
 
-def analyze(name: str, col: np.ndarray):
+def analyze_occupation(name: str, col: np.ndarray):
     occupation_col = dataset[:, 6]
-    F, p = stats.f_oneway(col[occupation_col == 0], col[occupation_col == 1], col[occupation_col == 2], col[occupation_col == 3], col[occupation_col == 4], col[occupation_col == 5])
-    print(f"F-stats for {name}: {F}")
-    print(f"p-value for {name}: {p}")
-
-    if p > 0.05:
-        print("statistically insignificant\n")
-        return
-
-    print("statistically significant")
-    tukey_results = stats.tukey_hsd(col[occupation_col == 0], col[occupation_col == 1], col[occupation_col == 2], col[occupation_col == 3], col[occupation_col == 4], col[occupation_col == 5])
-    print(tukey_results)
+    analyze(name, [
+        col[occupation_col == 0],
+        col[occupation_col == 1],
+        col[occupation_col == 2],
+        col[occupation_col == 3],
+        col[occupation_col == 4],
+        col[occupation_col == 5]
+    ])
 
 
-analyze("gpa", dataset[:, 2])
-analyze("math", dataset[:, 3])
-analyze("slovak", dataset[:, 4])
-analyze("english", dataset[:, 5])
+analyze_occupation("gpa", dataset[:, 2])
+analyze_occupation("math", dataset[:, 3])
+analyze_occupation("slovak", dataset[:, 4])
+analyze_occupation("english", dataset[:, 5])
diff --git a/analyze_sex.py b/analyze_sex.py
index 50c763b..c47e489 100644
--- a/analyze_sex.py
+++ b/analyze_sex.py
@@ -1,5 +1,6 @@
 import numpy as np
-import scipy.stats as stats
+
+from analyze import analyze
 
 dataset = np.load("clean.npy")
 print(f"dataset shape: {dataset.shape}, analyzing column 1 (sex)")
@@ -8,19 +9,12 @@ print("\t1 - male")
 print("")
 
 
-def analyze(name: str, col: np.ndarray):
+def analyze_sex(name: str, col: np.ndarray):
     sex_col = dataset[:, 1]
-    F, p = stats.f_oneway(col[sex_col == 0], col[sex_col == 1])
-    print(f"F-stats for {name}: {F}")
-    print(f"p-value for {name}: {p}")
-
-    if p > 0.05:
-        print("statistically insignificant\n")
-        return
-
-    print("statistically significant")
-    tukey_results = stats.tukey_hsd(col[sex_col == 0], col[sex_col == 1])
-    print(tukey_results)
+    analyze(name, [
+        col[sex_col == 0],
+        col[sex_col == 1]
+    ])
 
 
 analyze("gpa", dataset[:, 2])