JP2007102668A - Statistic comparison processor - Google Patents
Statistic comparison processor Download PDFInfo
- Publication number
- JP2007102668A JP2007102668A JP2005294546A JP2005294546A JP2007102668A JP 2007102668 A JP2007102668 A JP 2007102668A JP 2005294546 A JP2005294546 A JP 2005294546A JP 2005294546 A JP2005294546 A JP 2005294546A JP 2007102668 A JP2007102668 A JP 2007102668A
- Authority
- JP
- Japan
- Prior art keywords
- data
- comparison
- acquired
- subject
- target person
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 claims abstract description 41
- 239000000470 constituent Substances 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 22
- 238000013075 data extraction Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 7
- 238000003672 processing method Methods 0.000 claims description 4
- 238000013517 stratification Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 description 46
- 238000012360 testing method Methods 0.000 description 35
- 238000005259 measurement Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 4
- 230000036772 blood pressure Effects 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000001953 Hypotension Diseases 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000012866 low blood pressure Diseases 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000035485 pulse pressure Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
本発明は、時や評価対象を違えて対象者から取得された第１と第２のデータを統計比較する技術に関し、特に、第１と第２のデータを取得した対象者の集合の構成者に部分的な相違がある場合に適用して好適な技術に関する。 The present invention relates to a technique for statistically comparing first and second data acquired from a subject at different times and evaluation targets, and in particular, a member of a set of subjects who have acquired first and second data. The present invention relates to a technique that is suitable for application when there is a partial difference.
複数の対象者を集めて、市場調査、世論調査、健康調査等といった様々な目的でアンケート調査やデータ測定が行われている。また、街頭アンケートのような対象者を任意に選定した形式の他に、組織の構成員を対象として組織メンバの意識等を評価することも行われている。
このような調査では、イベントや施策の前後でアンケート質問やデータ測定を行って、当該イベント等の効果を計る等の目的でアンケート回答や測定値を比較したい場合がある。
A number of subjects are gathered, and questionnaire surveys and data measurements are conducted for various purposes such as market research, public opinion surveys, and health surveys. Further, in addition to a format in which a target person is arbitrarily selected such as a street questionnaire, evaluation of organizational member consciousness and the like is also performed for members of the organization.
In such a survey, there are cases where it is desired to compare questionnaire responses and measured values for the purpose of measuring questionnaire questions and data before and after an event or measure and measuring the effect of the event.
しかしながら、このような調査の実施において、例えば調査時刻が異なった場合、対象者（回答者、被験者）が同じメンバにならないことが多い。また、このような対象者集合の構成者が部分的に異なってしまうことは、調査によって評価してもらう対象物が異なった場合においても生ずる。
このように部分的に構成者が異なる対象者集合から得られた２つのアンケート回答や測定値の変化は、統計的には、母集団（対象者集合）の平均の最尤推定値はその構成者の平均値となるため、単純に平均をとって比較されてしまうことが多い。
However, in conducting such a survey, for example, when the survey time is different, the target person (respondent, subject) often does not become the same member. In addition, the fact that the members of such a set of subjects are partially different also occurs when the objects to be evaluated by the survey are different.
In this way, two questionnaire responses and changes in measured values obtained from a set of subjects with different constituents are statistically calculated from the average maximum likelihood estimate of the population (target set). In many cases, the average value is simply averaged and compared.
変化を統計的に見るための手法として、χ二乗適合度検定、Ｆ検定などの検定手法がある。
しかしながら、χ二乗適合度検定をそのまま使っても、変化したことが判別できても、それが実質の変化なのか、メンバ（対象者集合の構成者）が変わったことによる変化なのかは、判断できない。
また、変動がメンバによるものか、測定や回答時の条件によるものかをＦ検定によって求める方法もあるものの、メンバが同じである必要があるため判定できない。
There are test methods such as chi-square goodness-of-fit test and F test as a method for statistically viewing the change.
However, even if the χ-square goodness-of-fit test is used as it is, it can be determined whether it has changed, or whether it is a change due to a change in the members (members of the target set). Can not.
Further, although there is a method of obtaining whether the variation is due to the member or the condition at the time of measurement and answering by F test, it is not possible to determine because the members need to be the same.
ここで、アンケートシステムにおいて、必要なプロフィールの回答を増やすために、単純に対象者を増やすのではなく、プロフィールごとに個別の質問を行うようにして、コストを押さえながら回答を増やすシステムが提案されている（特許文献１参照。）。しかしながら、この提案は、アンケートや実験が一旦終了してしまった後はデータの比較精度を向上することができない。
また、時間的な変化を伴う故障診断のため、シミュレーション結果と時系列データを比較する提案もなされているが、この提案は前後のデータの比較ではない（特許文献２参照。）。
In addition, there is a proposal for comparing simulation results with time-series data for failure diagnosis accompanied by temporal changes, but this proposal is not a comparison of previous and subsequent data (see Patent Document 2).
単純平均の比較やχ二乗適合度検定を単純に適用した場合、対象者集合のメンバに変更があったために回答内容や測定値が変化したのか、回答内容や測定値に実際の変化があったのかが区別できないという課題がある。また、回答内容や測定値に変化があったにもかかわらず、メンバが変わったことに相殺されて、回答内容や測定値の実際の変化を正しく検出ができないという課題がある。
また、Ｆ検定は、一部のデータが欠けても検定は可能なものの、検定精度が大幅に下がるため、メンバのほとんどが同じでなければ、極端に検定精度が低くなるため、Ｆ検定を単純に適用しても実質的に比較ができないという課題がある。
When simple average comparison or chi-square goodness-of-fit test was simply applied, whether the response content or measurement value changed due to a change in the target set member, or the response content or measurement value actually changed There is a problem that cannot be distinguished. In addition, there is a problem that even though there is a change in the answer content and the measured value, the actual change in the answer content and the measured value cannot be correctly detected by offsetting the change in the member.
In addition, although the F test can be performed even if some data is missing, the test accuracy is greatly reduced. If most of the members are not the same, the test accuracy is extremely low. There is a problem that even if it is applied to the above, it cannot be substantially compared.
本発明は上記従来の事情に鑑みなされたものであり、回答者や被験者などの対象者集合の構成者を同じメンバで構成することができない場合にも、前後のアンケート回答等について統計量の比較を正しく行うことができるようにすることを目的としている。 The present invention has been made in view of the above-mentioned conventional circumstances, and even when the constituent members of the target group such as respondents and subjects cannot be composed of the same members, comparison of statistics about the questionnaire responses before and after, etc. The purpose is to be able to do correctly.
本発明は、複数の対象者から取得した第１と第２のデータを統計的に比較処理する技術であり、当該比較処理を行う統計比較処理装置、当該統計比較処理装置をコンピュータにより構成するプログラム、当該統計比較処理装置により実施される統計比較処理方法と言った種々な態様で実現される。 The present invention is a technique for statistically comparing first and second data acquired from a plurality of subjects, a statistical comparison processing device for performing the comparison processing, and a program for configuring the statistical comparison processing device by a computer The statistical comparison processing method implemented by the statistical comparison processing apparatus is realized in various modes.
本発明の一態様である統計比較処理装置では、比較データ抽出手段が、第１のデータを取得した第１対象者集合と第２のデータを取得した第２対象者集合との構成者に部分的に変更がある状況に対して、当該第１のデータについて第１対象者集合と第２対象者集合とに共通して属した共通対象者から取得した第１のデータと当該第１対象者集合にだけ属した一時的対象者から取得した第１のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第１のデータを比較用第１データとして選択する一方、当該第１のデータについて当該所定の統計的な有意差がない場合には当該第１対象者集合から取得した全ての第１のデータを比較用第１データとして選択し、また、当該第２のデータについて前記共通対象者から取得した第２のデータと前記第２対象者集合にだけ属した一時的対象者から取得した第２のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第２のデータを比較用第２データとして選択する一方、当該第２のデータについて当該所定の統計的な有意差がない場合には前記第２対象者集合から取得した全ての第２のデータを比較用第２データとして選択し、データ比較手段が、選択した比較用第１データと比較用第２データと統計処理して両データ間の差を算出する。 In the statistical comparison processing device according to one aspect of the present invention, the comparison data extraction unit includes a portion of the first target person group that has acquired the first data and the second target person group that has acquired the second data. First data obtained from a common target person belonging to both the first target person group and the second target person group for the first data and the first target person When there is a predetermined statistically significant difference from the first data acquired from the temporary target person belonging only to the set, the first data acquired from the common target person is used as the first data for comparison. On the other hand, if there is no predetermined statistically significant difference for the first data, all the first data acquired from the first subject set is selected as the first data for comparison, and Take the second data from the common target When there is a predetermined statistically significant difference between the second data obtained and the second data obtained from a temporary subject belonging only to the second subject set, the subject was obtained from the common subject. While the second data is selected as the second data for comparison, if there is no predetermined statistically significant difference for the second data, all the second data acquired from the second subject set is selected. The second comparison data is selected, and the data comparison means performs statistical processing on the selected first comparison data and second comparison data to calculate a difference between the two data.
したがって、第１のデータを取得した第１対象者集合と第２のデータを取得した第２対象者集合との構成者に部分的に変更がある状況に対して、上記のような本発明特有の選択ルールに基づいて選択した比較用第１データと比較用第２データとを統計処理することで、第１のデータと第２のデータとを精度よく比較処理することができる。 Therefore, in the situation where the members of the first target person group who acquired the first data and the second target person group who acquired the second data are partially changed, the present invention is unique to the present invention as described above. By statistically processing the first comparison data and the second comparison data selected based on the selection rule, the first data and the second data can be compared with high accuracy.
ここで、本発明では統計処理方法として、典型的にはχ二乗適合度検定を用いるが、コロモゴロフ・スミノフの検定、ウィルコクソンのＵ検定など、公知の他の方法を用いることもできる。
また、本発明では、上記所定の統計的な有意差として、第１のデータと第２のデータとについて同じ値を用いることも或いは異なる値を用いることもでき、要は、処理の必要性や目的等に応じて任意に設定すればよい。
Here, in the present invention, a chi-square goodness-of-fit test is typically used as a statistical processing method, but other known methods such as Kolomogorov-Smirnoff test and Wilcoxon U test can also be used.
In the present invention, as the predetermined statistical significance difference, the same value or different values can be used for the first data and the second data. What is necessary is just to set arbitrarily according to the objective.
また、本発明は種々なデータの統計比較処理に用いることができ、例えば、第１のデータと第２のデータが時間を違えて対象者から取得した質問に対する回答データ（例えば同じアンケート質問に対する回答）、第１のデータと第２のデータが評価対象を違えて対象者から取得した質問に対する回答データ（例えば評価対象物を違えて行ったイエス／ノーの回答）、第１のデータと第２のデータが対象者を測定することで取得したデータ（例えば対象者から測定した血圧データ）の処理に用いて好適である。 In addition, the present invention can be used for statistical comparison processing of various data. For example, answer data for a question acquired from a subject at different times between the first data and the second data (for example, answer to the same questionnaire question) ), Answer data (for example, yes / no answers made with different evaluation objects), the first data and the second data with respect to the question obtained from the subject with different evaluation targets, the first data and the second data This data is suitable for processing data acquired by measuring the subject (for example, blood pressure data measured from the subject).
本発明は、時や評価対象を違えて対象者から取得された第１と第２のデータを統計比較するに際して、第１と第２のデータを取得した対象者集合の構成者に部分的な相違がある場合に、第１データ及び第２のデータの構成者に基づいた統計的な有意差を判定し、これに応じて、第１データ及び第２のデータから比較に用いる比較用第１データ及び比較用第２のデータを選択して統計比較処理を行うようにしたため、構成者に部分的な変更に対しても高精度な統計比較処理結果を得ることができる。 In the present invention, when statistically comparing the first and second data acquired from the subject at different times and evaluation targets, the present invention is partially applied to the members of the subject set who acquired the first and second data. If there is a difference, a statistically significant difference based on the constituents of the first data and the second data is determined, and the first comparison data used for comparison is determined from the first data and the second data accordingly. Since the data and the second comparison data are selected and the statistical comparison process is performed, it is possible to obtain a highly accurate statistical comparison process result even for a partial change.
本発明を一実施例に基づいて具体的に説明する。
図１には本例に係る統計比較処理装置の構成を示してあり、本例では統計処理方法としてχ二乗適合度検定を用いている。
まず、本例の統計比較処理装置を説明するに先立って、対象者集合のメンバ（構成者）に部分的な相違がある場合に、第１データ及び第２のデータから比較に用いる比較用第１データ及び比較用第２のデータを選択する方法について図２〜図４を参照して説明する。
The present invention will be specifically described based on an example.
FIG. 1 shows the configuration of a statistical comparison processing apparatus according to this example. In this example, a chi-square goodness-of-fit test is used as a statistical processing method.
First, prior to describing the statistical comparison processing apparatus of this example, when there is a partial difference in the members (members) of the set of subjects, the first comparison data used for comparison is compared with the first data and the second data. A method of selecting one data and second data for comparison will be described with reference to FIGS.
例えば、イベントを行う前のアンケート回答とイベント後のアンケート回答といったように、第１のデータと第２のデータとを時間を違えて回答者から取得した質問に対するアンケート回答データを例にとると、図２に示すように、アンケート回答に回答した回答者（メンバ）の集合は、時間的に前のアンケートに回答したメンバ集合１と時間的に後のアンケートに回答したメンバ集合２とがある。
時間的に前後のアンケートに回答したメンバの集合に部分的にメンバの変更があると、メンバ集合１は、時間的に前のアンケートと後のアンケートの両方に回答した共通回答者（共通メンバ）３と、時間的に前のアンケートだけに回答した一時的回答者（その時点のみのメンバ）４とから成っている。また同様に、メンバ集合２は、時間的に前のアンケートと後のアンケートの両方に回答した共通回答者（共通メンバ）３と、時間的に後のアンケートだけに回答した一時的回答者（その時点のみのメンバ）５とから成っている。
For example, taking questionnaire response data for a question acquired from a respondent at different times, such as the questionnaire response before the event and the questionnaire response after the event, As shown in FIG. 2, there are two sets of respondents (members) who answered the questionnaire response: a member set 1 that answered the previous questionnaire in time and a member set 2 that answered the later questionnaire.
If there is a partial change in the set of members who answered the previous and subsequent questionnaires, the member set 1 is the common respondent who responded to both the previous and subsequent questionnaires (common members). 3 and temporary respondents (members only at that time) 4 who answered only the previous questionnaire in time. Similarly, the
このようなメンバ構成の相違に対して、図３に示すような回答内容（観測値）の統計的分布に基づいて図４に示す選択ルールを規定している。
図３は、時間的前のアンケート（事前調査）に対する回答分布に共通メンバと一時的メンバとの間で比較的大きな差があり（ａ）、時間的後のアンケート（事後調査）に対する回答分布に共通メンバと一時的メンバとの間で殆ど差がない（ｂ）場合を示している。
この分布の差は、任意に設定した値を基準として、設定値より大きな差がる場合は「有意差あり」、設定値より小さな差の場合は「有意差なし」とする。
For such a difference in member configuration, the selection rule shown in FIG. 4 is defined based on the statistical distribution of response contents (observed values) as shown in FIG.
FIG. 3 shows that there is a relatively large difference in the response distribution for the pre-temporal questionnaire (preliminary survey) between the common member and the temporary member (a), and the response distribution for the post-temporal questionnaire (post-survey) The case where there is almost no difference between a common member and a temporary member is shown (b).
This difference in distribution is determined to be “significantly different” if there is a difference larger than the set value, and “no significant difference” if the difference is smaller than the set value, based on an arbitrarily set value.
このような有意差の有無に応じた場合分けをすると、事前調査回答（第１のデータ）の分布に有意差があり且つ事後調査回答（第２のデータ）の分布に有意差がある第１の場合、事前調査回答（第１のデータ）の分布に有意差があり且つ事後調査回答（第２のデータ）の分布に有意差がない第２の場合、事前調査回答（第１のデータ）の分布に有意差がなく且つ事後調査回答（第２のデータ）の分布に有意差がある第３の場合、事前調査回答（第１のデータ）の分布に有意差がなく且つ事後調査回答（第２のデータ）の分布に有意差がない第４の場合に分けることができる。 When the case is classified according to the presence or absence of such a significant difference, there is a significant difference in the distribution of the preliminary survey responses (first data) and the significant difference in the distribution of the follow-up survey responses (second data). In the case of the second case, there is a significant difference in the distribution of the preliminary survey responses (first data) and there is no significant difference in the distribution of the follow-up survey responses (second data). In the second case, the preliminary survey responses (first data) In the third case, there is no significant difference in distribution of distribution and the distribution of follow-up survey responses (second data) is significant, and there is no significant difference in the distribution of prior survey responses (first data) and follow-up survey responses ( The second case can be divided into a fourth case in which there is no significant difference in distribution.
本発明では、図４に示すように、第１の場合には事前調査回答（第１のデータ）と事後調査回答（第２のデータ）とからそれらの共通メンバの回答だけを選択し、第２の場合には事前調査回答（第１のデータ）からはその共通メンバの回答だけを選択するとともに事後調査回答（第２のデータ）はその共通メンバと一時的メンバの分け隔てなく全ての回答を選択し、第３の場合には事前調査回答（第１のデータ）からはその共通メンバと一時的メンバの分け隔てなく全ての回答を選択するとともに事後調査回答（第２のデータ）からはその共通メンバの回答だけを選択し、第４の場合には事前調査回答（第１のデータ）と事後調査回答（第２のデータ）とからそれらの共通メンバと一時的メンバの分け隔てなく全ての回答を選択する選択ルールを策定している。
なお、選択された回答データは、事前調査回答（第１のデータ）と事後調査回答（第２のデータ）との間に差があるかを統計処理するために用いられる。
In the present invention, as shown in FIG. 4, in the first case, only the answers of those common members are selected from the preliminary survey response (first data) and the subsequent survey response (second data). In the case of 2, only the response of the common member is selected from the preliminary survey response (first data), and the post-survey survey response (second data) is all responses regardless of the common member and the temporary member. In the third case, from the preliminary survey response (first data), select all the responses without separating the common member and the temporary member, and from the follow-up survey response (second data) Select only the answers of the common members. In the fourth case, all of the common members and temporary members are separated from the preliminary survey responses (first data) and the follow-up survey responses (second data). Select route to select answer Which formulated.
The selected response data is used for statistically processing whether there is a difference between the preliminary survey response (first data) and the follow-up survey response (second data).
本例に係る統計比較処理装置は、図１に示すように、イベント等の前に収集したアンケート回答データや測定データを記録する事前データ記憶手段１１、当該イベント等の後に収集したアンケート回答データや実験観測データを記録する事後データ記憶手段１２、これら前後のデータで共通するメンバの回答データや観測データと一時的メンバの回答データや観測データとを分離するメンバデータ層別手段１３、事前及び事後のそれぞれで共通メンバと一時的メンバとの間のデータに統計的な差があるかどうかを調べるメンバ間比較手段１４、メンバ間比較手段１６の結果に基づいて事前及び事後のそれぞれで比較に用いることのできる比較用データを抽出する比較データ抽出手段１５、比較データ抽出手段１５で抽出された事前及び事後のデータを統計的に差があるかどうかを調べる前後データ比較手段１６、前後データ比較手段１６の比較処理結果を出力もしくは記録する出力手段１７を有している。
なお、比較データ抽出手段１５には図４に示す選択ルールが予め設定されており、比較データ抽出手段１５は当該選択ルールに従って比較用の事前データと比較用の事後データとを抽出する。
As shown in FIG. 1, the statistical comparison processing apparatus according to this example includes a pre-data storage means 11 for recording questionnaire response data and measurement data collected before an event, questionnaire response data collected after the event, Post-event data storage means 12 for recording experimental observation data, member data stratification means 13 for separating the response data and observation data of members common to the preceding and subsequent data from the response data and observation data of temporary members, pre- and post-event Are used for comparison before and after the comparison based on the results of the member comparison means 14 and the member comparison means 16 for checking whether or not there is a statistical difference in data between the common member and the temporary member. Comparison data extraction means 15 for extracting the comparison data that can be performed, the pre- and post-extraction extracted by the comparison data extraction means 15 Longitudinal data comparing means 16 for the chromatography data determine whether statistically there is a difference, it has an output means 17 for outputting or recording the comparison results before and after the
The selection rule shown in FIG. 4 is set in advance in the comparison
図５には、本例の統計比較処理装置が行う処理の手順を示してある。
事前データ記憶手段１１と事後データ記憶手段１２とにそれぞれ事前データと事後データとが記録されている状態で、メンバデータ層別手段１３が、事前データと事後データに付加されている回答者情報や被験者情報により、事前データと事後データで共通するメンバのデータを抽出する（ステップＳ１）。なお、オンラインアンケートの場合、無記名であっても個別の識別子などによって回答者を特定できるようにしておくことで、回答者が同じことを特定できるようにするようにしてもよい。
FIG. 5 shows a procedure of processing performed by the statistical comparison processing apparatus of this example.
With the pre-data and post-data stored in the pre-data storage means 11 and the post-data storage means 12, respectively, the member data stratification means 13 has the respondent information added to the pre-data and post-data, Based on the subject information, common member data is extracted from the previous data and the subsequent data (step S1). In the case of an online questionnaire, respondents may be identified by the individual identifiers or the like, even if they are anonymous, so that the respondents can identify the same thing.
次いで、メンバ間比較手段１４が、事前データ内で前後で共通するメンバと事前のみの一時的メンバとの間のデータの間で統計的に有意差があるかどうかを検定し（ステップＳ２）、また、事後データ内で前後で共通するメンバと事後のみの一時的メンバとの間のデータの間で統計的に有意差があるかどうかを検定する（ステップＳ３）。
次いで、比較データ抽出手段１５が、事前データメンバ間検定（ステップＳ２）と事後データメンバ間検定（ステップＳ３）の結果に基づいて、有意差があるか否かにより選択ルールに従って前後の比較に用いる比較用事前データと比較用事後データを抽出する（ステップＳ４）。
Next, the member comparison means 14 tests whether or not there is a statistically significant difference between the data between the members common before and after in the preliminary data and the temporary members only in advance (step S2). Further, it is tested whether or not there is a statistically significant difference between data between members that are common in the posterior data before and after and temporary members that are only posterior (step S3).
Next, the comparison data extraction means 15 is used for comparison before and after according to the selection rule depending on whether or not there is a significant difference based on the results of the pre-data member test (step S2) and the post-data member test (step S3). Pre-comparison data and post-comparison data for comparison are extracted (step S4).
次いで、前後データ比較手段１６が、抽出された比較用の事前データと事後データの間で統計的に有意差があるかどうかを検定する（ステップＳ６）。
そして、出力手段１７が前後データ比較手段１６の検定結果を出力または記録する（ステップＳ６）。
なお、事前データメンバ間検定（ステップＳ２）と、事後データメンバ間検定（ステップＳ３）と、前後比較（ステップＳ５）は、同様な統計処理を行うので、同じ統計処理機能を呼び出すように共通化してもよい。
Next, the before-and-after
Then, the output means 17 outputs or records the test result of the before and after data comparison means 16 (step S6).
Note that the pre-data member test (step S2), the post-data member test (step S3), and the pre- and post-comparison (step S5) perform the same statistical processing, so they are standardized to call the same statistical processing function. May be.
図６〜図１０を参照して、本例の統計比較処理装置により、或る質問に対して３つの回答を選択肢として記載したアンケートをイベントの前後で実施した回答データの処理を説明する。
図６には、イベントの事前回答結果及び事後回答結果を示してあり、共通メンバは１〜２６の番号を付し、事前アンケートの一時的メンバは２７〜５１の番号を付し、事後アンケートの一時的メンバは５２〜７５の番号を付して示し、それぞれが回答した選択肢番号「１」又は「２」又は「３」を示してある。
なお、本例のアンケートでは、事前アンケートのメンバ総数は５１人、事後アンケートのメンバ総数は５０人であるが、これら前後のメンバ数が同じであってもよく、本発明ではメンバ総数の同一性について特段の限定はない。
With reference to FIG. 6 to FIG. 10, processing of answer data in which a questionnaire in which three answers are given as options for a certain question is performed before and after the event by the statistical comparison processing apparatus of this example will be described.
FIG. 6 shows the pre-answer result and post-answer result of the event. Common members are numbered 1 to 26, temporary members of the pre-survey are numbered 27 to 51, The temporary members are shown with
In the questionnaire of this example, the total number of members in the pre-survey is 51, and the total number of members in the post-survey is 50. However, the number of members before and after these may be the same. There is no particular limitation about.
当該回答結果に基づいて図５に示す処理を実行し、その事前データメンバ間検定処理（ステップＳ２）の結果を図７に示してある。
すなわち、回答毎の比率が共通メンバと事前のみの一時的メンバとの間で変わらないと仮定し、 χ二乗適合度検定により有意差をみると、式（１）に示すように、事前メンバ間の場合は、危険率を５％で判定して有意差がないため、メンバ間に有意差があるとは言えないという結果になった。
The processing shown in FIG. 5 is executed based on the answer result, and the result of the preliminary data member verification processing (step S2) is shown in FIG.
That is, assuming that the ratio for each answer does not change between the common member and the temporary member only in advance, and looking at the significant difference by the chi-square goodness-of-fit test, as shown in Equation (1), In the case of, the risk rate was judged at 5% and there was no significant difference, so it could not be said that there was a significant difference between the members.
そして、事後データメンバ間検定処理（ステップＳ３）の結果を図８に示してある。
同様に、回答毎の比率が共通メンバと事後のみの一時的メンバとの間で変わらないと仮定し、 χ二乗適合度検定により有意差をみると、式（２）に示すように、事後メンバ間の場合は、危険率５％で有意差があり、メンバ間には差があるという結果になった。
The result of the post-data member verification process (step S3) is shown in FIG.
Similarly, assuming that the ratio of each answer does not change between the common member and the temporary member only after the fact, and looking at the significant difference by the chi-square goodness-of-fit test, as shown in the formula (2), the posterior member In the case of between, there was a significant difference at a risk rate of 5%, and there was a difference between members.
上記のように事前データでは有意差なし、事後データでは有意差ありという結果だったので、図４に示す選択ルールに従って、事前データは全て利用し、事後データは共通メンバのデータのみを前後比較処理（ステップＳ５）に利用する。本例では、事前データはメンバ１〜５１まで、事後データはメンバ１〜２６までの回答データを利用する。
なお、事前データの全平均は２．０１９６０８、事後データの全平均は２．０２で変化はないように見える。事後データの共通メンバのみの平均は２．３４６１５４である。
As shown above, there was no significant difference in the preliminary data, and there was a significant difference in the posterior data, so all the preliminary data was used according to the selection rule shown in FIG. This is used for (step S5). In this example, response data from
It should be noted that the total average of the prior data is 2.019608 and the total average of the posterior data is 2.02, which does not seem to change. The average of only the common members of the posterior data is 2.346154.
上記選択された回答データに基づいて前後比較処理（ステップＳ５）を行った結果を図９に示してある。
同様に、回答毎の比率が前後間で変わらないと仮定し、χ二乗適合度検定により有意差をみると、式（３）に示すように、危険率５％で有意差があり、前後間で差がある(変化があった)とみなせる結果になった。
FIG. 9 shows the result of performing the front-rear comparison process (step S5) based on the selected answer data.
Similarly, assuming that the ratio for each answer does not change between before and after, and looking at the significant difference by the chi-square goodness-of-fit test, there is a significant difference at a risk rate of 5% as shown in Equation (3). The result was that there was a difference (there was a change).
因みに、図１０には、本発明のような選択ルールを用いずに、事前データと事後データとの全てを用いて比較処理を行った結果を示してある。
同様に、回答毎の比率が前後間で変わらないと仮定し、χ二乗適合度検定により、有意差をみると、式（４）に示すように、全データを使った前後間の比較では有意差はなく、前後での変化はなかったものとみなされるため、上記の本例と較べると、前後の変化を見落とす結果になってしまう。
したがって、本発明を適用することにより、回答者もしくは被験者の変化の影響を排除して、事前データと事後データとの正しい比較が可能になる。
Incidentally, FIG. 10 shows the result of performing the comparison process using all the previous data and the subsequent data without using the selection rule as in the present invention.
Similarly, assuming that the ratio for each answer does not change between before and after, and looking at the significant difference by chi-square goodness-of-fit test, as shown in equation (4), the comparison between before and after using all data is significant. Since there is no difference and it is considered that there was no change before and after, the result is that the change before and after is overlooked compared to this example.
Therefore, by applying the present invention, it is possible to correctly compare the prior data and the subsequent data by eliminating the influence of the change of the respondent or the subject.
図１１〜図１６を参照して、本例の統計比較処理装置により、評価対象を違えた２つのアンケートをこれらアンケート間でメンバが部分的に異なる対象者集合に実施した回答データの処理を説明する。
図１１には、両アンケートの回答結果を示してあり、共通メンバは１〜２０の番号を付し、一方（対象Ａについて）のアンケートの一時的メンバは２１〜４０の番号を付し、他方（対象Ｂについて）のアンケートの一時的メンバは４１〜６０の番号を付して示し、それぞれが回答（選択）した結果「０：ＹＥＳ」又は「１：ＮＯ」を示してある。
なお、本例は、例えば、政党Ａを指示するかどうか、政党Ｂを指示するかどうかという別々の調査の結果を比べるような場合や、製品Ａを購入したいと思うかと、製品Ｂを購入したいと思うかという調査結果を比べる場合に相当する。
With reference to FIG. 11 to FIG. 16, the statistical data processing apparatus of this example will explain the processing of answer data in which two questionnaires with different evaluation targets are executed on a set of target persons whose members are partially different between these questionnaires To do.
FIG. 11 shows the answer results of both questionnaires, common members are numbered 1 to 20, temporary members of one questionnaire (for target A) are numbered 21 to 40, and the other Temporary members of the questionnaire for (subject B) are shown with
In this example, for example, if you want to compare the results of separate surveys on whether to instruct political party A or whether to instruct political party B, or if you want to purchase product A, you want to purchase product B This is equivalent to comparing survey results.
当該回答結果に基づいて、一方のアンケート回答データ（対象Ａ）を事前データとして扱い、他方のアンケート回答データ（対象Ｂ）を事前データとして扱って、図５に示す処理を実行し、その事前データメンバ間検定処理（ステップＳ２）の結果を図１２に示してある。
回答毎の比率が共通メンバと対象Ａのみの一時的メンバとの間で変わらないと仮定し、χ二乗適合度検定により有意差をみると、式（５）に示すように、対象Ａの評価におけるメンバ間の比較では、危険率５％として有意差があり、メンバ間に差があるという結果になった。
Based on the response result, one questionnaire response data (target A) is treated as prior data, the other questionnaire response data (target B) is treated as prior data, and the processing shown in FIG. 5 is executed. The result of the inter-member verification process (step S2) is shown in FIG.
Assuming that the ratio for each answer does not change between the common member and the temporary member of only the target A, and looking at the significant difference by the chi-square goodness-of-fit test, the evaluation of the target A is as shown in Equation (5) In comparison between members, there was a significant difference as a risk rate of 5%, and there was a difference between members.
そして、事後データメンバ間検定処理（ステップＳ３）の結果を図１３に示してある。
同様に、回答毎の比率が共通メンバと対象Ｂのみの一時的メンバとの間で変わらないと仮定し、χ二乗適合度検定により有意差をみると、式（６）に示すように、対象Ｂの評価におけるメンバ間の比較では、危険率を５％で判定して、有意差がなく、メンバ間には差があるとは言えないという結果になった。
The result of the post-data member verification process (step S3) is shown in FIG.
Similarly, assuming that the ratio for each answer does not change between the common member and the temporary member of only the target B, and looking at the significant difference by the chi-square goodness-of-fit test, as shown in the equation (6), the target In comparison between members in the evaluation of B, the risk rate was determined at 5%, and there was no significant difference, and it could be said that there was no difference between the members.
そして、比較データ抽出処理（ステップＳ４）では、図１４に示すように図４と同様な選択ルールに従って、比較用データを抽出する。
すなわち、上記の結果、対象Ａのデータでは有意差あり、対象Ｂのデータでは有意差なしという結果だったので、対象Ａのデータは共通メンバのデータのみを利用し、対象Ｂのデータは全てのデータを利用する。
本例では、対象Ａのデータはメンバ１〜２０まで、対象Ｂのデータはメンバ１〜２０と４１〜６０までのデータを利用する。
Then, in the comparison data extraction process (step S4), as shown in FIG. 14, the comparison data is extracted according to the same selection rule as in FIG.
That is, as a result of the above, since there was a significant difference in the data of the target A and no significant difference in the data of the target B, the data of the target A used only the data of the common member, and the data of the target B was all Use data.
In this example, the data of the target A uses
上記選択されたデータに基づいて前後比較処理（ステップＳ５）を行った結果を図１５に示してある。
同様に、回答毎の比率が前後間で変わらないと仮定し、χ二乗適合度検定により有意差をみると、式（７）に示すように、危険率５％で有意差がなく、対象ＡＢ間で差がない(変化がなかった)とみなせる結果になった。
FIG. 15 shows the result of performing the front-back comparison process (step S5) based on the selected data.
Similarly, assuming that the ratio for each answer does not change between before and after, and looking at the significant difference by chi-square goodness-of-fit test, as shown in Equation (7), there is no significant difference at a risk rate of 5%, and the target AB The result was that there was no difference between them (no change).
因みに、図１６には、本発明のような選択ルールを用いずに、対象Ａのデータと対象Ｂのデータとの全てを用いて比較処理を行った結果を示してある。
同様に、回答毎の比率が対象間で変わらないと仮定し、χ二乗適合度検定により、有意差をみると、式（８）に示すように、全データを使った比較では有意差があり、対象間での変化があったものとみなされる。
Incidentally, FIG. 16 shows the result of performing the comparison process using all of the data of the target A and the data of the target B without using the selection rule as in the present invention.
Similarly, assuming that the ratio for each answer does not change between subjects, and looking at the significant difference by chi-square goodness-of-fit test, there is a significant difference in the comparison using all data as shown in Equation (8). , Are considered to have changed between subjects.
以上のように、本発明を用いることにより、回答者もしくは被験者の変化の影響を排除して、正しい対象間の比較が可能になる。
また、本発明はアンケートの回答に限らず、例えば脈拍や血圧のような対象者から直接的に取得する測定値データに関しても、例えば、測定値を高血圧、正常、低血圧というようにいくつかのカテゴリに分類すれば、そのまま適用が可能である。
As described above, by using the present invention, it is possible to eliminate the influence of changes in respondents or subjects and to compare correct subjects.
In addition, the present invention is not limited to questionnaire responses, and for example, measurement value data obtained directly from a subject such as a pulse or blood pressure, for example, some measurement values such as high blood pressure, normal, and low blood pressure If it is classified into categories, it can be applied as it is.
１：事前データメンバ、 ２：事後データメンバ、
３：共通メンバ、 ４：事前一時的メンバ、
５：事後一時的メンバ、 １１：事前データ記憶手段、
１２：事後データ記憶手段、 １３：メンバデータ層別手段、
１４：メンバ間比較手段、 １５：比較データ抽出手段、
１６：前後データ比較手段、 １７：出力手段、
1: Pre-data member, 2: Post-data member,
3: common member, 4: pre-temporary member,
5: Post-temporary member 11: Prior data storage means
12: Subsequent data storage means, 13: Member data stratification means,
14: member comparison means, 15: comparison data extraction means,
16: before and after data comparison means, 17: output means,
Claims (8)
第１のデータを取得した第１対象者集合と第２のデータを取得した第２対象者集合との構成者に部分的に変更がある状況に対して、当該第１のデータについて第１対象者集合と第２対象者集合とに共通して属した共通対象者から取得した第１のデータと当該第１対象者集合にだけ属した一時的対象者から取得した第１のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第１のデータを比較用第１データとして選択する一方、当該第１のデータについて当該所定の統計的な有意差がない場合には当該第１対象者集合から取得した全ての第１のデータを比較用第１データとして選択し、また、当該第２のデータについて前記共通対象者から取得した第２のデータと前記第２対象者集合にだけ属した一時的対象者から取得した第２のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第２のデータを比較用第２データとして選択する一方、当該第２のデータについて当該所定の統計的な有意差がない場合には前記第２対象者集合から取得した全ての第２のデータを比較用第２データとして選択する比較データ抽出手段と、
前記比較データ抽出手段が選択した比較用第１データと比較用第２データと統計処理して両データ間の差を算出するデータ比較手段と、
を備えることを特徴とする統計比較処理装置。 A statistical comparison processing device that statistically compares the first and second data acquired from a plurality of subjects,
In a situation where there is a partial change in the constituents of the first set of subjects who acquired the first data and the second set of subjects who acquired the second data, the first target for the first data Between the first data acquired from a common target person belonging to both the person set and the second target person set and the first data acquired from a temporary target person belonging only to the first target person set If there is a predetermined statistical significant difference, the first data acquired from the common subject is selected as the first data for comparison, while the predetermined statistical significant difference is selected for the first data. If not, all the first data acquired from the first target user group is selected as the first data for comparison, and the second data acquired from the common target person for the second data and the first data Is it a temporary subject belonging only to the second subject set? When there is a predetermined statistically significant difference with the acquired second data, the second data acquired from the common target person is selected as the second data for comparison, while the second data is Comparison data extracting means for selecting all second data acquired from the second subject set as second data for comparison when there is no predetermined statistically significant difference;
Data comparison means for statistically processing the first data for comparison and the second data for comparison selected by the comparison data extraction means to calculate a difference between the two data;
A statistical comparison processing device comprising:
前記第１のデータと第２のデータから、前記共通対象者から取得した第１のデータと第２のデータ、前記第１対象者集合の一時的対象者から取得した第１のデータ、及び、前記第２対象者集合の一時的対象者から取得した第２のデータを分離するメンバデータ層別手段と、
前記共通対象者から取得した第１のデータと前記第１対象者集合の一時的対象者から取得した第１のデータとの間に前記所定の統計的な有意差があるか否かを判定するとともに、当該共通対象者から取得した第２のデータと前記第２対象者集合の一時的対象者から取得した第２のデータとの間に前記所定の統計的な有意差があるか否かを判定するメンバ間比較手段と、を更に備え、
前記比較データ抽出手段は、前記メンバ間比較手段の判定結果に応じて前記比較用第１データと比較用第２データを選択することを特徴とする統計比較処理装置。 In the statistical comparison processing apparatus according to claim 1,
From the first data and the second data, the first data and the second data obtained from the common subject, the first data obtained from the temporary subject of the first subject set, and Member data stratification means for separating second data acquired from temporary subjects of the second subject set;
It is determined whether there is the predetermined statistical significance between the first data acquired from the common target person and the first data acquired from a temporary target person of the first target person set. And whether there is a predetermined statistically significant difference between the second data acquired from the common target person and the second data acquired from the temporary target person of the second target person set. A member comparison means for judging,
The comparison data extraction unit selects the first comparison data and the second comparison data according to the determination result of the member comparison unit.
前記第１対象者集合と第２対象者集合から取得した第１のデータと第２のデータを統計的比較処理のために保持するデータ記憶手段と、
前記データ比較手段が算出したデータ間の差に係る情報を出力する出力手段と、を更に備えることを特徴とする統計比較処理装置。 In the statistical comparison processing apparatus according to claim 2,
Data storage means for holding the first data and the second data acquired from the first subject set and the second subject set for statistical comparison processing;
An output means for outputting information relating to the difference between the data calculated by the data comparison means;
前記第１のデータと第２のデータとは時間を違えて対象者から取得した質問に対する回答データであることを特徴とする統計比較処理装置。 In the statistical comparison processing apparatus according to any one of claims 1 to 3,
The statistical comparison processing apparatus, wherein the first data and the second data are answer data to a question acquired from a subject at different times.
前記第１のデータと第２のデータとは評価対象を違えて対象者から取得した質問に対する回答データであることを特徴とする統計比較処理装置。 In the statistical comparison processing apparatus according to any one of claims 1 to 3,
The statistical comparison processing apparatus according to claim 1, wherein the first data and the second data are answer data to a question acquired from a subject with different evaluation targets.
前記第１のデータと第２のデータとは対象者を測定することで取得したデータであることを特徴とする統計比較処理装置。 In the statistical comparison processing apparatus according to any one of claims 1 to 3,
The statistical comparison processing apparatus, wherein the first data and the second data are data obtained by measuring a subject.
コンピュータに、
第１のデータを取得した第１対象者集合と第２のデータを取得した第２対象者集合との構成者に部分的に変更がある状況に対して、当該第１のデータについて第１対象者集合と第２対象者集合とに共通して属した共通対象者から取得した第１のデータと当該第１対象者集合にだけ属した一時的対象者から取得した第１のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第１のデータを比較用第１データとして選択する一方、当該第１のデータについて当該所定の統計的な有意差がない場合には当該第１対象者集合から取得した全ての第１のデータを比較用第１データとして選択し、また、当該第２のデータについて前記共通対象者から取得した第２のデータと前記第２対象者集合にだけ属した一時的対象者から取得した第２のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第２のデータを比較用第２データとして選択する一方、当該第２のデータについて当該所定の統計的な有意差がない場合には前記第２対象者集合から取得した全ての第２のデータを比較用第２データとして選択する比較データ抽出手段と、
前記比較データ抽出手段が選択した比較用第１データと比較用第２データと統計処理して両データ間の差を算出するデータ比較手段と、
を構成することを特徴とする統計比較処理プログラム。 A statistical comparison processing device for statistically comparing the first and second data acquired from a plurality of subjects is a program comprising a computer,
On the computer,
In a situation where there is a partial change in the constituents of the first set of subjects who acquired the first data and the second set of subjects who acquired the second data, the first target for the first data Between the first data acquired from a common target person belonging to both the person set and the second target person set and the first data acquired from a temporary target person belonging only to the first target person set If there is a predetermined statistical significant difference, the first data acquired from the common subject is selected as the first data for comparison, while the predetermined statistical significant difference is selected for the first data. If not, all the first data acquired from the first target user group is selected as the first data for comparison, and the second data acquired from the common target person for the second data and the first data Is it a temporary subject belonging only to the second subject set? When there is a predetermined statistically significant difference with the acquired second data, the second data acquired from the common target person is selected as the second data for comparison, while the second data is Comparison data extracting means for selecting all second data acquired from the second subject set as second data for comparison when there is no predetermined statistically significant difference;
Data comparison means for statistically processing the first data for comparison and the second data for comparison selected by the comparison data extraction means to calculate a difference between the two data;
The statistical comparison processing program characterized by comprising.
前記比較データ抽出手段が、第１のデータを取得した第１対象者集合と第２のデータを取得した第２対象者集合との構成者に部分的に変更がある状況に対して、当該第１のデータについて第１対象者集合と第２対象者集合とに共通して属した共通対象者から取得した第１のデータと当該第１対象者集合にだけ属した一時的対象者から取得した第１のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第１のデータを比較用第１データとして選択する一方、当該第１のデータについて当該所定の統計的な有意差がない場合には当該第１対象者集合から取得した全ての第１のデータを比較用第１データとして選択し、また、当該第２のデータについて前記共通対象者から取得した第２のデータと前記第２対象者集合にだけ属した一時的対象者から取得した第２のデータとの間に所定の統計的な有意差がある場合には当該共通対象者から取得した第２のデータを比較用第２データとして選択する一方、当該第２のデータについて当該所定の統計的な有意差がない場合には前記第２対象者集合から取得した全ての第２のデータを比較用第２データとして選択し、
前記データ比較手段が、前記比較データ抽出手段が選択した比較用第１データと比較用第２データと統計処理して両データ間の差を算出することを特徴とする統計比較処理方法。 A statistical comparison processing device comprising a comparison data extraction means and a data comparison means is a method for statistically comparing first and second data acquired from a plurality of subjects,
For the situation where the comparison data extraction means has a partial change in the constituents of the first subject group that has acquired the first data and the second subject group that has acquired the second data, The first data obtained from a common subject who belonged to both the first subject set and the second subject set for one data and the temporary subject who belonged only to the first subject set When there is a predetermined statistically significant difference from the first data, the first data acquired from the common target person is selected as the first data for comparison, while the predetermined data is selected for the first data. If there is no statistically significant difference, all the first data acquired from the first target person set is selected as the first data for comparison, and the second data is acquired from the common target person Second data and the second set of subjects When there is a predetermined statistically significant difference from the second data acquired from the temporary subject who only belonged, the second data obtained from the common subject is selected as the second data for comparison. On the other hand, when there is no predetermined statistical significance for the second data, all the second data acquired from the second subject set is selected as the second data for comparison,
A statistical comparison processing method, wherein the data comparison means statistically processes the comparison first data and the comparison second data selected by the comparison data extraction means to calculate a difference between the two data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2005294546A JP4670575B2 (en) | 2005-10-07 | 2005-10-07 | Statistical comparison processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2005294546A JP4670575B2 (en) | 2005-10-07 | 2005-10-07 | Statistical comparison processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2007102668A true JP2007102668A (en) | 2007-04-19 |
| JP4670575B2 JP4670575B2 (en) | 2011-04-13 |
Family
ID=38029524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2005294546A Expired - Fee Related JP4670575B2 (en) | 2005-10-07 | 2005-10-07 | Statistical comparison processor |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP4670575B2 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013018160A1 (en) * | 2011-07-29 | 2013-02-07 | アクアエンタープライズ株式会社 | Valuation assistance system and valuation assistance program |
| JP5629363B1 (en) * | 2013-10-17 | 2014-11-19 | 長嶋 克佳 | Questionnaire counting device, method, and program |
| JP2018136604A (en) * | 2017-02-20 | 2018-08-30 | 株式会社マクロミル | Evaluation system |
| JP2021033884A (en) * | 2019-08-28 | 2021-03-01 | Kddi株式会社 | Program, apparatus and method for determining change of behavior of user group |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001318589A (en) * | 2000-05-12 | 2001-11-16 | Fujitsu Ltd | Training effect judging system |
| JP2002099667A (en) * | 2000-09-22 | 2002-04-05 | Nikkei Business Publications Inc | Exhibition effect measuring method and measurement system for implementing the same |
| JP2003196470A (en) * | 2001-12-27 | 2003-07-11 | Recruit Co Ltd | Customer control method and system |
| JP2004030170A (en) * | 2002-06-25 | 2004-01-29 | East Side Co Ltd | Device and method for collecting questionnaires, and program and storage medium |
| JP2004252604A (en) * | 2003-02-19 | 2004-09-09 | Okinawa Pref Gov | Sightseeing estimation method and program therefor, and health recreation type sightseeing touring method using them |
-
2005
- 2005-10-07 JP JP2005294546A patent/JP4670575B2/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001318589A (en) * | 2000-05-12 | 2001-11-16 | Fujitsu Ltd | Training effect judging system |
| JP2002099667A (en) * | 2000-09-22 | 2002-04-05 | Nikkei Business Publications Inc | Exhibition effect measuring method and measurement system for implementing the same |
| JP2003196470A (en) * | 2001-12-27 | 2003-07-11 | Recruit Co Ltd | Customer control method and system |
| JP2004030170A (en) * | 2002-06-25 | 2004-01-29 | East Side Co Ltd | Device and method for collecting questionnaires, and program and storage medium |
| JP2004252604A (en) * | 2003-02-19 | 2004-09-09 | Okinawa Pref Gov | Sightseeing estimation method and program therefor, and health recreation type sightseeing touring method using them |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013018160A1 (en) * | 2011-07-29 | 2013-02-07 | アクアエンタープライズ株式会社 | Valuation assistance system and valuation assistance program |
| JP5629363B1 (en) * | 2013-10-17 | 2014-11-19 | 長嶋 克佳 | Questionnaire counting device, method, and program |
| JP2015079386A (en) * | 2013-10-17 | 2015-04-23 | 長嶋 克佳 | Questionnaire collection device, method, and program |
| JP2018136604A (en) * | 2017-02-20 | 2018-08-30 | 株式会社マクロミル | Evaluation system |
| JP2021033884A (en) * | 2019-08-28 | 2021-03-01 | Kddi株式会社 | Program, apparatus and method for determining change of behavior of user group |
| JP7075173B2 (en) | 2019-08-28 | 2022-05-25 | Kddi株式会社 | Programs, devices and methods for determining behavioral changes in user groups |
Also Published As
| Publication number | Publication date |
|---|---|
| JP4670575B2 (en) | 2011-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lutzke et al. | Priming critical thinking: Simple interventions limit the influence of fake news about climate change on Facebook | |
| Gao et al. | Psychometric evaluation of the USE (usefulness, satisfaction, and ease of use) questionnaire for reliability and validity | |
| Thomson et al. | Investigating an alternate form of the cognitive reflection test | |
| Green et al. | Identifying bully victims: definitional versus behavioral approaches. | |
| Marszalek et al. | Sample size in psychological research over the past 30 years | |
| US10504376B2 (en) | System and method for improving the quality of computer generated exams | |
| Colton et al. | Some misconceptions about R2 | |
| Moody | Rule-based methods for ECG quality control | |
| Seale-Carlisle et al. | Confidence and response time as indicators of eyewitness identification accuracy in the lab and in the real world | |
| JP4670575B2 (en) | Statistical comparison processor | |
| Ross et al. | Beyond “fake news”: The role of analytic thinking in the detection of inaccuracy and partisan bias in news headlines | |
| Gómez-Benito et al. | Efficacy of effect size measures in logistic regression: An application for detecting DIF | |
| US20180129777A1 (en) | Method and apparatus for estimating the quantity of microorganisms within a taxonomic unit in a sample | |
| Collisson et al. | How popular are pop stars? The false consensus of perceived celebrity popularity. | |
| O'Connor et al. | The stability of individual differences in basic mathematics‐related skills in young children at the start of formal education | |
| Semeraro et al. | Fit for the frontline? Identification of mission-critical auditory tasks (MCATs) carried out by infantry and combat-support personnel | |
| JP2011233044A (en) | Device, method and program for subjective evaluation | |
| TWI524294B (en) | Online learning style automated diagnostic system, online learning style automated diagnostic method and computer readable recording medium | |
| Singmann et al. | Investigating the other-race effect of Germans towards Turks and Arabs using multinomial processing tree models | |
| US20170161798A1 (en) | System and method for assessing data for a specified product/service | |
| US20200098076A1 (en) | Systems and methods for measuring and scoring the effectiveness of a message | |
| KR101496348B1 (en) | A quantitative measure of consumer-relevant sensory difference for food quality maintenance | |
| Kerber et al. | Trait and situational attributions in a naturalistic setting: Familiarity, liking, and attribution validity | |
| Getmantsev et al. | A novel health risk model based on intraday physical activity time series collected by smartphones | |
| Kress et al. | Team cognition and reframing behavior: The impact of team cognition on problem reframing, team dynamics and design performance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| RD04 | Notification of resignation of power of attorney |
Free format text: JAPANESE INTERMEDIATE CODE: A7424 Effective date: 20070928 |
|
| RD04 | Notification of resignation of power of attorney |
Free format text: JAPANESE INTERMEDIATE CODE: A7424 Effective date: 20071024 |
|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20080924 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20101012 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20101019 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20101112 |
|
| RD02 | Notification of acceptance of power of attorney |
Free format text: JAPANESE INTERMEDIATE CODE: A7422 Effective date: 20101112 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20101221 |
|
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20110103 |
|
| R150 | Certificate of patent or registration of utility model |
Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20140128 Year of fee payment: 3 |
|
| LAPS | Cancellation because of no payment of annual fees |