diff --git a/vlib/math/stats/stats.v b/vlib/math/stats/stats.v
index ed071d6bacb640..6462a743ced615 100644
--- a/vlib/math/stats/stats.v
+++ b/vlib/math/stats/stats.v
@@ -434,7 +434,7 @@ pub fn covariance_mean[T](data1 []T, data2 []T, mean1 T, mean2 T) T {
 	for i in 0 .. n {
 		delta1 := data1[i] - mean1
 		delta2 := data2[i] - mean2
-		covariance += T((delta1 * delta2 - covariance) / (i + T(1)))
+		covariance += T((delta1 * delta2 - covariance) / (T(i) + T(1)))
 	}
 	return covariance
 }
@@ -459,8 +459,11 @@ pub fn lag1_autocorrelation_mean[T](data []T, mean T) T {
 	for i := 1; i < data.len; i++ {
 		delta0 := data[i - 1] - mean
 		delta1 := data[i] - mean
-		q += T((delta0 * delta1 - q) / (i + T(1)))
-		v += T((delta1 * delta1 - v) / (T(i) + T(1)))
+		d01 := delta0 * delta1
+		d11 := delta1 * delta1
+		ti1 := T(i) + T(1)
+		q += T((d01 - q) / ti1)
+		v += T((d11 - v) / ti1)
 	}
 	return T(q / v)
 }
@@ -486,7 +489,9 @@ pub fn kurtosis_mean_stddev[T](data []T, mean T, sd T) T {
 	*/
 	for i, v in data {
 		x := (v - mean) / sd
-		avg += T((x * x * x * x - avg) / (i + T(1)))
+		x4 := x * x * x * x
+		ti1 := (T(i) + T(1))
+		avg += T((x4 - avg) / ti1)
 	}
 	return avg - T(3)
 }
@@ -511,7 +516,8 @@ pub fn skew_mean_stddev[T](data []T, mean T, sd T) T {
 	*/
 	for i, v in data {
 		x := (v - mean) / sd
-		skew += T((x * x * x - skew) / (i + T(1)))
+		x3 := x * x * x
+		skew += T((x3 - skew) / (T(i) + T(1)))
 	}
 	return skew
 }
diff --git a/vlib/math/stats/stats_test.v b/vlib/math/stats/stats_test.v
index 7c9dcb30886457..dbdafc789449e9 100644
--- a/vlib/math/stats/stats_test.v
+++ b/vlib/math/stats/stats_test.v
@@ -428,13 +428,15 @@ fn test_covariance() {
 fn test_lag1_autocorrelation() {
 	mut data := [10.0, 4.45, 5.9, 2.7]
 	mut o := stats.lag1_autocorrelation(data)
+	mut e := 0.0
 	assert math.alike(o, -0.5542285481446095)
 	data = [-3.0, 67.31, 4.4, 1.89]
 	o = stats.lag1_autocorrelation(data)
 	assert math.alike(o, -0.5102510654033415)
 	data = [12.0, 7.88, 76.122, 54.83]
 	o = stats.lag1_autocorrelation(data)
-	assert math.alike(o, 0.10484450460892072)
+	e = 0.10484450460892072
+	assert math.veryclose(o, e), diff(o, e)
 
 	// test for int, i64, f32 array
 	assert stats.lag1_autocorrelation[int]([1, 2, 3, 1]) == 0
@@ -444,7 +446,7 @@ fn test_lag1_autocorrelation() {
 }
 
 fn diff(actual f64, expected f64) string {
-	return '\nactual:\n${actual}\nexpected:\n${expected}'
+	return '\n  actual:${actual:40.35f}\nexpected:${expected:40.35f}\n    diff:${actual - expected:40.35f}'
 }
 
 fn test_kurtosis() {
@@ -464,27 +466,30 @@ fn test_kurtosis() {
 	assert stats.kurtosis[int]([1, 2, 3, 1]) == 1
 	assert stats.kurtosis[i64]([i64(1), 2, 3, 1]) == 1
 	o = stats.kurtosis[f32]([f32(1.0), 3, 5, 7, 3])
-	assert math.alike(o, -1.044378399848938)
+	e = -1.044378399848938
+	assert math.alike(o, e), diff(o, e)
 }
 
 fn test_skew() {
 	mut data := [10.0, 4.45, 5.9, 2.7]
 	mut o := stats.skew(data)
 	mut e := 0.5754021106320453
-	assert math.veryclose(o, e), diff(o, e)
+	assert math.close(o, e), diff(o, e)
 	data = [-3.0, 67.31, 4.4, 1.89]
 	o = stats.skew(data)
 	e = 1.1248733711136492
 	assert math.veryclose(o, e), diff(o, e)
 	data = [12.0, 7.88, 76.122, 54.83]
 	o = stats.skew(data)
-	assert math.alike(o, 0.19007911706827735)
+	e = 0.19007911706827735
+	assert math.veryclose(o, e), diff(o, e)
 
 	// test for int, i64, f32 array
 	assert stats.skew[int]([1, 2, 3, 1]) == 2
 	assert stats.skew[i64]([i64(1), 2, 3, 1]) == 2
 	o = stats.skew[f32]([f32(1.0), 3, 5, 7, 3])
-	assert math.alike(o, 0.27154541015625)
+	e = 0.27154541015625
+	assert math.close(o, e), diff(o, e)
 }
 
 fn test_quantile() {