## 1998 Household Survey on Land：Sampling Procedure and Reliability of Estimate

### 1 Outline of Sampling Design

The 1998 Housing and Land Survey was conducted based on the stratified two-stage group sampling method with the first sampling unit of enumeration districts designated in the 1995 Population Census, and the secondary sampling unit of enumeration unit districts established by dividing those sampled enumeration districts.

The sampled enumeration districts were decided applying different sampling rate by region in order to achieve enough accuracy in the survey results for prefectures, cities, rural districts, towns, words in 13 large cities, metropolitan areas and urban areas respectively.

Furthermore, among the enumeration districts of the 1995 Population Census, districts where a prison, or a detention house, etc is located (the enumeration districts with the suffix number 5), districts for the Self-Defense Forces (with the suffix number 6), districts for the US Forces stationing in Japan (with the suffix number 7) and water-surface districts (with the suffix number 9) are excluded from the subjects of sampling.

### 2 Sampling Method of Enumeration Unit Districts

##### a. Stratifying the enumeration districts of the Population Census

Based on the results of the 1995 Population Census, 28 strata were established, where 26 strata were established on the criteria by stratum as per the Table 1, mainly on the “ratio by the relation of ownership of dwellings” and “size of dwellings” plus stratum of temporal housing districts (Note 1) and that of new group housing districts (Note 2).

##### b. Sampling of Enumeration Districts

A systematic sampling at a fixed sampling rate was made on every city and word as for cities and words of 13 large cities and made on every prefecture as for towns and villages.

The sampling rate was decided as per the Table 2 referring to the size of population in order to distribute number of samples necessary for the result tables as mentioned above.

##### c. Designation of the enumeration districts where Form B is distributed

In order to achieve enough accuracy of results for the survey items in Form B, the enumeration districts where Form B is distributed were designated by a systematic sampling at a fixed sampling rate every city with prefectural government, ordinance-designated city and other area as for both Kanagawa Prefecture and Fukuoka Prefecture, and every city with prefectural government and other area as for other prefectures than Kanagawa and Fukuoka.

##### d. Sampling of Enumeration Unit Districts

One of two unit districts, into which an enumeration district is divided, is sampled at random as an enumeration unit district.

However, the enumeration districts where dwellings are 35 or less were not divided. The enumeration districts where dwellings are 66 or over were divided into three or more so that one unit district contains more or less 25 dwellings.

Note 1) | TThose districts where approximately 40 or more of temporal housing were constructed due to the Great Hanshin Earthquake. |

Note 2) | Those districts where 50 or more of housing were constructed in group after the 1995 Population Census. |

Note 3) | The number of the population of municipalities used when applying sampling rate is based on the 1995 Population Census over the administrative districts as of October 1, 1997. |

But the result tables are expressed in accordance with the administrative districts as of October 1, 1999.

### 3 Method of Estimation of Results

The survey results of every enumeration unit district of the 1998 Housing and Land Survey were multiplied by the reciprocal number of the sampling rate applicable to the enumeration district which includes the enumeration unit district in question and also by the reciprocal number of the sampling rate applicable to the enumeration unit district in the enumeration district concerned, then added up. Then ratio estimate was made on the population municipality by municipality as of October 1, 1999.

### 4 Reliability of the Estimates

The survey results of the 1998 Housing and Land Survey are estimates by sampling survey and, therefore, contain sampling error so that the results do not always coincide with a result which would be obtainable by a complete survey.

The Table 3 shows the ratio of standard error for the estimate for all Japan used in this Report. As for the ratio of standard error for tabulated items other than Table 3, generally the Table 4 is applicable though such ratio varies depending on the characteristics of the tabulated items even when resulting in the same estimate.

The ratio of standard error shown in the Table 3 was calculated item by item of tabulation using an approximate expression of variance of estimates, while the Table 4 provides an evaluation made on average basis fitting a curve on plotted results of the calculation.

The ratio of standard error is criteria to show the range of existence of a value, which would be obtainable by a complete survey (the true value). That is, with the estimate in the center and a range equivalent to the standard error (the estimate multiplied by the ratio of standard error) on both sides, the true value is expected within the whole range at 68% of probability. With a range equivalent to 2 times of the standard error on both sides, the true value is now expected within the whole range at 95% of probability.

### ATTACHED TABLES

**Results for Japan**

Table 1 | Criteria and codes for stratification of enumeration districts (Eds) for Population Census | ViewDownload |
---|---|---|

Table 2 | Sampling rate of designated enumeration district (Eds) | ViewDownload |

Table 3 | Ratio of Standard Error by Major Item (%) | ViewDownload |

Table 4 | Rate of Standard Error by size of estimate (%) | ViewDownload |

**Results for Prefectures**

Table 1 | Criteria and codes for stratification of enumeration districts (Eds) for Population Census | ViewDownload |
---|---|---|

Table 2 | Sampling rate of designated enumeration district (Eds) | ViewDownload |

Table 3 | Ratio of Standard Error by Major Item (%) | ViewDownload |

Table 4 | Rate of Standard Error by size of estimate (%) | ViewDownload |

**Results for Ordinance-Designated Cities**

Table 1 | Criteria and codes for stratification of enumeration districts (Eds) for Population Census | ViewDownload |
---|---|---|

Table 2 | Sampling rate of designated enumeration district (Eds) | ViewDownload |

Table 3 | Ratio of Standard Error by Major Item (%) | ViewDownload |

Table 4 | Rate of Standard Error by size of estimate (%) | ViewDownload |

**Results for Cities with Prefectural Government**

Table 1 | Criteria and codes for stratification of enumeration districts (Eds) for Population Census | ViewDownload |
---|---|---|

Table 2 | Sampling rate of designated enumeration district (Eds) | ViewDownload |

Table 3 | Ratio of Standard Error by Major Item (%) | ViewDownload |

Table 4 | Rate of Standard Error by size of estimate (%) | ViewDownload |