2003 Corporation Survey on Land SAMPLING PROCEDURE AND RELIABILITY OF ESTIMATES

2003 Corporation Survey on Land

SAMPLING PROCEDURE AND RELIABILITY OF ESTIMATE

1 Outline of Sampling Design

In the 2003 Corporations Survey on Land, target corporations were extracted using the stratified sampling method from corporations listed in the "Corporations List for the 2001 Establishment and Enterprise Census" by the Ministry of Internal Affairs and Communications (formerly the Ministry of Public Management, Home Affairs, Posts and Telecommunications) and the "Corporations List for the 2002 Survey of the Status of Land Acquisition by Corporations" by the Ministry of Land, Infrastructure and Transport (in addition, the "Corporations List for the 2002 Financial Statements Statistics of Corporations by Industry" by the Ministry of Finance was also used for corporations with capital funding of 100 million yen or more).

In this sampling design, the following percentages were set as accuracy targets of the result table for the size of land owned by a corporation. Descriptions of each group by type of industry and capital funding are shown in Table 1.

The ratio of the standard error for the result table by type of industry for Japan (10 groups) × amount of capital (5 groups) shall be 15% or less.
The ratio of the standard error for the result table by prefecture where the head office is located × type of industry (10 groups) shall be 20% or less.
The ratio of the standard error for the result tableby type of industry for Japan (49 groups) shall be 15% or less.

Based on these percentages of the accuracy targets, the Survey was conducted for all corporations owning land with a total size of one million square meters or more (hereinafter referred to as "Corporation owning Large Land") or with capital of 100 million yen or more in the 1998 Corporations Survey on Land . Companies with capital of less than 100 million yen and corporations other than companies/corporations mentioned above were surveyed using the sampling method.

2 Sampling Procedure

(1) Sampling Frame

  For companies with capital of 100 million yen or more, sampling frames were constructed from the "Corporations List for the 2002 Survey of the Status of Land Acquisition by Corporations," the "Corporations List for the 2002 Financial Statements Statistics of Corporations by Industry" and the "Corporations List for the 2001 Establishment and Enterprise Census." Furthermore, newly established corporations since the data were added.

  For companies with capital of less than 100 million yen, sampling frames were constructed from independent establishments and headquarters out of the "Corporations List for the 2001 Establishment and Enterprise Census."

  For corporations other than companies, sampling frames were constructed by adding corporations from various lists of organizations based on independent establishments and headquarters from the "Corporations List for the 2001 Establishment and Enterprise Census.".

(2) Sampling Process

  While the number of companies with capital of 100 million yen or more are few in number, the Survey was conducted for all of these considering their extensive impact on the precision of the survey.

  For companies with capital of less than 100 million yen, firstly all companies of some industry groups × amount-of-capital groups were surveyed as they were considered to have a substantial impact on accuracy. For the groups subjected to the sample survey, distribution of sample was decided to make the standard error of each stratum by type of industry for Japan (10 groups) × amount of capital (5 groups) to be 15% or less using the results for tenure size in the "1998 Corporations Survey on Land." Secondly, this number of samples was prorated according to the number of corporations in the stratum by prefecture where the headquarters located × type of industry (49 grou- ps) × amount of capital (5 groups). This was then compared to the number of samples which is necessary to make the standard error of each stratum by prefecture where the headquarters located × type of industry (10 groups) × type of industry in Japan (49 groups) to be of a certain rate or less, and adjusted to avoid excess or deficiency.

  For corporations other than companies, all of the corporations owning large amounts of land were surveyed. For corporations other than those mentioned above, the extraction ratio was decided as shown in Table 2.

3 Method of Estimate of Results

The results of the Survey were multiplied by the reciprocal number of the sampling rate for each stratum of sampling frame and also by the reciprocal number of collection rate, and then these figures were aggregated. Approximately 380 thousand corporations responded with valid answers. In this process, for the stratum in which the number of corporations was 0, a collection rate was obtained by combining with groups with a similar amount of capital, those of a similar type of industry, or those with a similar average tenure size in the results of the "1998 Corporations Survey on Land." For the groups subject to the survey for all corporations, the sampling rate was regarded as 1 and a similar estimate was conducted.

From the above, the estimate of statistics is given by the following formula:

4 Reliability of the Estimate

  Table 1 of Reference 3 at the end of this volume shows the ratio of standard error for the estimates used in this report. Here, the ratio of standard error is a guide for showing the range of existence of a value, which would be obtainable in a complete survey (hereinafter referred to as 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 to be within the entire range at 68% of probability. With a range equivalent to 2 times the standard error on both sides, the true value is now expected to be within the entire range at 95% of probability.

  It should be mentioned that the ratio of standard error by major item (Table 1 of Reference 3) was calculated using the formula shown below. However, the ratio of standard error by decile groups of owned land size and average land size was calculated in resampling method. The ratio of standard error by size of estimate (Table 2 of Reference 3) is an evaluation made on an average basis by fitting a curve to the size of the estimate and the ratio of standard error that corresponds to this size.

  Also, it can be applied only for the statistics such as the number of corporations, the total size of owned land and the number of lots, and can not be applied by itself for the mean value such as the average owned size of land per one corporation, etc.

• ATTACHED TABLES

Results for Japan

Table 1	Classification for targeted accuracy - Type of industry-
Table 2	Sampling rate for corporations other than companies
Table 3	Standard error rate for each main item (%)
Table 4	Ratio of standard error (%) by size of estimate

Results for Prefectures

Table 1	Classification for targeted accuracy - Type of industry-
Table 2	Sampling rate for corporations other than companies
Table 3	Standard error rate for each main item (%)
Table 4	Ratio of standard error (%) by size of estimate

Results for Ordinance-Designated Cities

Table 1	Classification for targeted accuracy - Type of industry-
Table 2	Sampling rate for corporations other than companies
Table 3	Standard error rate for each main item (%)
Table 4	Ratio of standard error (%) by size of estimate

Results for Cities with Prefectural Government

Table 1	Classification for targeted accuracy - Type of industry-
Table 2	Sampling rate for corporations other than companies
Table 3	Standard error rate for each main item (%)
Table 4	Ratio of standard error (%) by size of estimate

| Back to Ministry of Land, Infrastructure and Transport Home Page | Back to Land and Real Property in Japan | Return |

All Rights Reserved, Copyright (C) 2006, Ministry of Land, Infrastructure and Transport