Skip to contents

Computes the joint inclusion probability matrix using the Hajek (1964) approximation based on conditional Poisson (rejective) sampling theory: $$\pi_{ij} \approx \pi_i \pi_j \left[1 - \frac{(1-\pi_i)(1-\pi_j)}{D}\right]$$ where \(D = \sum_k \pi_k (1 - \pi_k)\).

Usage

hajek_jip(pik, sample_idx = NULL, eps = 1e-06, ...)

Arguments

pik

Numeric vector of inclusion probabilities (\(0 \le \pi_k \le 1\)).

sample_idx

Unique integer vector of 1-based indices for the sampled units, or NULL (default) for the full population matrix. When non-NULL, returns the submatrix for those units only, without allocating the full N x N matrix. The returned matrix has at most 10,000 rows, as for joint_inclusion_prob(), so a population above that size needs sample_idx.

eps

Boundary tolerance (default 1e-6). Units with \(\pi_k \ge 1 - \varepsilon\) are treated as certainty selections, and units with \(\pi_k \le \varepsilon\) are treated as zero.

...

Additional arguments (ignored). Present so that the function matches the joint_fn signature required by register_method(). sampled_only is refused, since it belongs to joint_inclusion_prob(). Use sample_idx here instead.

Value

A symmetric matrix of joint inclusion probabilities: N x N when sample_idx is NULL, or length(sample_idx) x length(sample_idx) otherwise. Diagonal entries are \(\pi_i\). Rows and columns are named after names(pik), as in joint_inclusion_prob(). A submatrix of unnamed pik is labeled with the indices in sample_idx.

Details

The Hajek approximation is simpler and computationally lighter than the high-entropy approximation (he_jip()), but generally slightly less accurate. It is derived from the asymptotic theory of rejective (conditional Poisson) sampling, where the design is obtained by conditioning independent Bernoulli trials (Poisson sampling) on the total sample size.

The formula is valid for any high-entropy design, but is most accurate when the design is close to rejective sampling. For CPS, the maximum-entropy design, and for other high-entropy designs such as Sampford's, he_jip() tends to give tighter results. Both CPS and Sampford have exact joint probabilities in joint_inclusion_prob(). In practice, both approximations agree closely for moderate to large populations with well-spread inclusion probabilities.

Like he_jip(), this function matches the joint_fn signature required by register_method():

register_method("my_method", sample_fn = my_fn, joint_fn = hajek_jip)

Properties

  • Symmetric: \(\pi_{ij} = \pi_{ji}\)

  • Diagonal: \(\pi_{ii} = \pi_i\) (set directly)

  • Bounded: \(0 \le \pi_{ij} \le \min(\pi_i, \pi_j)\) (clamped)

  • Marginal defect: \(|\sum_{j \ne i} \pi_{ij} - (n-1)\pi_i| = O(1/N)\) for well-spread \(\pi_k\)

References

Hajek, J. (1964). Asymptotic theory of rejective sampling with varying probabilities from a finite population. Annals of Mathematical Statistics, 35(4), 1491–1523.

See also

he_jip() for the high-entropy approximation, joint_inclusion_prob() for design-based dispatch, register_method() for custom method registration.

Examples

pik <- inclusion_prob(c(2, 3, 4, 5, 6, 7, 8, 9), n = 4)

# Full N x N matrix
pikl <- hajek_jip(pik)
round(pikl, 4)
#>        [,1]   [,2]   [,3]   [,4]   [,5]   [,6]   [,7]   [,8]
#> [1,] 0.1818 0.0317 0.0453 0.0603 0.0769 0.0949 0.1144 0.1354
#> [2,] 0.0317 0.2727 0.0714 0.0942 0.1190 0.1458 0.1745 0.2053
#> [3,] 0.0453 0.0714 0.3636 0.1306 0.1636 0.1990 0.2367 0.2767
#> [4,] 0.0603 0.0942 0.1306 0.4545 0.2107 0.2545 0.3008 0.3496
#> [5,] 0.0769 0.1190 0.1636 0.2107 0.5455 0.3124 0.3669 0.4240
#> [6,] 0.0949 0.1458 0.1990 0.2545 0.3124 0.6364 0.4350 0.4998
#> [7,] 0.1144 0.1745 0.2367 0.3008 0.3669 0.4350 0.7273 0.5772
#> [8,] 0.1354 0.2053 0.2767 0.3496 0.4240 0.4998 0.5772 0.8182

# Compare with high-entropy approximation
he <- he_jip(pik)
max(abs(pikl - he))
#> [1] 0.02273801