Aggregate

VAR_POP

BigQuery

Menghitung variance (ragam) populasi dari nilai numerik. Menggunakan formula pembagi N, cocok ketika data merepresentasikan seluruh populasi.

Tipe hasil: FLOAT64Diperbarui: 7 Jan 2026

Syntax

SQL

VAR_POP(expression)

Parameter

expressionnumericwajib

Kolom atau ekspresi numerik yang akan dihitung variance populasinya

Contoh Penggunaan

Population Variance vs Sample Variance

SQL

1 SELECT
2   VAR_POP(score) as population_variance,
3   VAR_SAMP(score) as sample_variance,
4   VARIANCE(score) as variance_alias,
5   COUNT(*) as n
6 FROM `project.dataset.all_test_scores`;

Membandingkan population dan sample variance.

Hasil

population_variance	sample_variance	variance_alias	n
156.25	163.93	163.93	1000

VAR_POP untuk Complete Dataset

SQL

1 SELECT
2   machine_id,
3   AVG(output_quantity) as avg_output,
4   VAR_POP(output_quantity) as output_variance,
5   STDDEV_POP(output_quantity) as output_stddev
6 FROM `project.dataset.production_log`
7 WHERE production_date >= DATE_SUB(CURRENT_DATE(), INTERVAL 30 DAY)
8 GROUP BY machine_id
9 ORDER BY output_variance DESC;

Variance populasi dari output produksi (data lengkap 30 hari).

Hasil

machine_id	avg_output	output_variance	output_stddev
M001	1250	15625	125
M002	1180	8464	92
M003	1320	4900	70

Relationship: VAR_POP and STDDEV_POP

SQL

1 SELECT
2   category,
3   VAR_POP(price) as variance_pop,
4   STDDEV_POP(price) as stddev_pop,
5   POWER(STDDEV_POP(price), 2) as stddev_squared,
6   ABS(VAR_POP(price) - POWER(STDDEV_POP(price), 2)) < 0.0001 as are_equal
7 FROM `project.dataset.products`
8 GROUP BY category;

Membuktikan bahwa VAR_POP = STDDEV_POP^2.

Hasil

category	variance_pop	stddev_pop	stddev_squared	are_equal
Electronics	3422500000000	1850000	3422500000000	TRUE
Fashion	102400000000	320000	102400000000	TRUE

Fungsi Terkait

STDDEVSTDDEV_POPSTDDEV_SAMPVARIANCEVAR_SAMPCORRCOVAR_POPCOVAR_SAMPPERCENTILE_CONTPERCENTILE_DISC

Kembali ke BigQuery Functions

1	SELECT
2	VAR_POP(score) as population_variance,
3	VAR_SAMP(score) as sample_variance,
4	VARIANCE(score) as variance_alias,
5	COUNT(*) as n
6	FROM `project.dataset.all_test_scores`;

1	SELECT
2	machine_id,
3	AVG(output_quantity) as avg_output,
4	VAR_POP(output_quantity) as output_variance,
5	STDDEV_POP(output_quantity) as output_stddev
6	FROM `project.dataset.production_log`
7	WHERE production_date >= DATE_SUB(CURRENT_DATE(), INTERVAL 30 DAY)
8	GROUP BY machine_id
9	ORDER BY output_variance DESC;

1	SELECT
2	category,
3	VAR_POP(price) as variance_pop,
4	STDDEV_POP(price) as stddev_pop,
5	POWER(STDDEV_POP(price), 2) as stddev_squared,
6	ABS(VAR_POP(price) - POWER(STDDEV_POP(price), 2)) < 0.0001 as are_equal
7	FROM `project.dataset.products`
8	GROUP BY category;