CN103413065B - The relatively amount of sampling computer of different groups disease rates - Google Patents
The relatively amount of sampling computer of different groups disease rates Download PDFInfo
- Publication number
- CN103413065B CN103413065B CN201310393749.2A CN201310393749A CN103413065B CN 103413065 B CN103413065 B CN 103413065B CN 201310393749 A CN201310393749 A CN 201310393749A CN 103413065 B CN103413065 B CN 103413065B
- Authority
- CN
- China
- Prior art keywords
- key
- error
- colony
- prevalence rate
- computer
- 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.)
- Expired - Fee Related
Links
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention relates to the computer of a kind of sample size obtaining population risk or risk in etiology is investigated.This computer is made up of input module, computing module and display module, wherein runs following technology formula in computing module:This computer is a kind of intelligent computer, and convenient specialty and layman use.
Description
Technical field
The present invention relates to a kind of computer, be specifically related to a kind of acquisition population risk or ill in etiology is investigated
The computer of the sample size of risk.
Background technology
Etiological study is one of substance of epidemiological study, often meets in Epidemiological study and research practice
Arrive.The most significant step of etiological study determines that disease and assumes the significance,statistical of association between paathogenic factor.Determine
Disease and the relatedness assumed between paathogenic factor, need the colony under comparison this hypothesis factor effect and do not have this factor
The generation of the colony's disease existed is the most variant.In the case of the cause of disease is clear and definite, it is thus necessary to determine that epidemic disease is occurred by different factors
Impact.
In Field of Animal Epidemic Disease Control real work, generally prevalence rate or onset risk to certain epidemic disease of different regions is carried out
Relatively, see whether there are differences, and wish to find out the reason causing this species diversity to exist；Or implement the feelings of different control measure
Under condition, the generation of epidemic disease or popular whether there are differences in colony.This needs from different regions or implements different control measure
Colony in obtain sample by sampling, it is thus achieved that corresponding ratio (in epidemiology usually prevalence rate, onset risk), compare
Whether there is the difference on statistical significance between ratio, thus judge this factor or control measure shadow pathogenetic to epidemic disease
Ring.
Traditional sample size calculates and mostly is to manually compute, and has statistical function button in existing computer more, but this merit
Can be common statistical function, such as read group total, square root etc., statistical formula more complicated in statistics be calculated,
Need professional very familiar to statistical formula, then use the computer commonly with statistical function to calculate, to institute
Obtain result to be corrected according to the confidence interval number table in statistics.Layman is difficult to carry out this work.
Summary of the invention
For the problems referred to above, an object of the present invention is to provide the sample size of a kind of intelligence and calculates equipment, and this calculating sets
The calculating of the standby sample size being specifically designed in etiology investigation as obtaining different groups sickness rate or risk needs extraction.Should
Mechanical discipline personnel and layman all can readily grasp and skilled use.
A kind of method that it is a further object of the present invention to provide disease Study on Etiology, in the method, amount of sampling passes through above-mentioned meter
Calculation equipment carries out calculating acquisition.
The calculating equipment of the present invention includes input module, amount of sampling computing module and display module.Wherein input module bag
Include confidence level, prevalence rate is expected by colony 1, prevalence rate is expected by colony 2 and the input of power of a test and the input of numeral.Amount of sampling
Computing module is provided with the input from described input module, goes to the outfan of display module.This computer can be by handing over
Stream electricity power supply also can be powered by battery.
In etiology investigation, an important job is to compare the disease rates of different groups or ill ratio.
It has been investigated that, in certain inspection validity interval, compared proportions is the most variant, can be according to following sample size
Approximate formula calculate obtain:
Wherein:
N is the sample size required for each group；
ZαFor 1-α/2 percentile of standard normal distribution, it it is the standard normal distribution corresponding when being 1-α of confidence level
Marginal value, Z0.05=1.96 (notes: this value is applicable to two-sided test or two-sided confidence interval)；
ZβFor (1-β) percentile of the standard normal distribution relevant with inspection validity (power of a test) 1-β, inspection is imitated
For degree (1-β) is 80%, 85%, 90% and 95%, the Z of its correspondenceβValue is 0.84,1.04,1.28,1.64；
p1The expection prevalence rate of colony 1
p2The expection prevalence rate of colony 2
P is colony 1 and the meansigma methods of colony 2 two expection prevalence rate: (p1+p2)/2
Q=1-p
q1=1-p1
q2=1-p2
Stochastic sampling from overall, is inferred general characteristic by sample information, can run into such problem in actual applications:
Whether a certain sample rate is not from the overall of certain known rate？Two different sample rates are the most unequal totally from rate？
Answer such problem, need to solve with hypothesis testing.Hypothesis testing, also known as significance test, is to utilize small probability anti-
Demonstration thought, from the opposite (H of problem0) setting out judges problem (H to be solved indirectly1) whether set up.I.e. assuming H0Set up
Under conditions of calculate statistic of test, then according to obtain P value judge.According to the deduction conclusion that P value is made, there is probability
Property, therefore its conclusion can not be the most correct, it may occur however that Type Ⅰ Ⅱ error.
Type Ⅰ error: be to have rejected correct null hypothesis H0, the mistake of this kind of " abandoning true " is referred to as type Ⅰ error.We often say
Inspection level, it is simply that the maximum of the prespecified criminal's of permission type Ⅰ error probability, represent with α.As specified α=0.05, meaning
And work as H0Set up refusal H0Time, in theory 100 inspections averagely have 5 times and such mistake occurs.
Type Ⅱ error: be to receive actual invalid null hypothesis H0, the mistake of this kind of " type B error " is referred to as type Ⅱ error.
Its probability size β represents, β only takes single tail, and its size is the most unknown, could must calculate when knowing two overall difference, α and n
Go out.
Inspection validity is 1-β, and its meaning totally truly has difference for working as two, can find this difference by regulation inspection level α
Ability.Such as 1-β=0.9, it is meant that if two totally truly have difference, in the most every 100 inspections, having 90 times can
Draw the conclusion that difference is statistically significant.
Two sample rates more i.e. can use u-test, it is also possible to χ2Inspection, but real work the most more application χ2Inspection.
χ2Inspection is with χ2It is distributed as theoretical foundation, only one of which parameter, i.e. degree of freedom.Chi-square value has corresponding closing with inspection level P value
System, χ2Being worth the biggest, P value is the least；Otherwise, χ2Being worth the least, P value is the biggest.χ2During inspection, first calculate the χ of statistic of test2Value, then
χ is looked into by degree of freedom2Dividing value table, determines P value, finally compares with determined inspection level, thus judges that difference is the most notable.
Detailed description of the invention
Hereinafter, with reference to accompanying drawing, the sample sample calculation device according to the present invention is illustrated.
Structure:
As it is shown in figure 1, computer of the present invention has input module 1 and display module 3.Described input module is by various buttons
Composition, various buttons include confidence level (CL) key, colony 1 expect prevalence rate (p1) key, colony 2 expect prevalence rate (p2) key,
Allowable error (α) key and power of a test (β) key and ten digital keys, decimal key (.), cancel button (UNDO) key, acknowledgement key
And directionkeys (ENTER).
Confidence level (CL%) key: press this key, there is CL in display screen:, input corresponding confidence water by ten numeral keys
Flat, such as 95%, then input 95, press acknowledgement key and confirm.
Prevalence rate (p1) key is expected by colony 1: press this key, and p1 occurs in display screen:, corresponding pre-by the input of ten numeral keys
Phase prevalence rate, such as 15%, then inputs 0.15, presses acknowledgement key and confirms.
Prevalence rate (p2) key is expected by colony 2: press this key, and p2 occurs in display screen:, corresponding pre-by the input of ten numeral keys
Phase prevalence rate, such as 10%, then inputs 0.10, presses acknowledgement key and confirms.
Allowable error (α) key: press this key, there is α in display screen:, input corresponding allowable errors by ten numeral keys, as
5%, then input 5, press acknowledgement key and confirm.
Power of a test (β) key: press this key, there is β in display screen:, input corresponding allowable errors by ten numeral keys, as
10%, then input 10, press acknowledgement key and confirm.
Cancel button (UNDO) key: press this key, the data being strayed into can be deleted.
The left and right scroll key of directionkeys realizes advance and the retrogressing of the display page.
The display screen of display module 3 correspondence shows the numeral that corresponding various button is pressed.
Function:
Below, the function composition of computer is illustrated.
Fig. 2 is the block diagram of calculator function structure, as it can be seen, sample sample calculation utensil have input unit 3, display part 4,
ROM (Read only Memory) 5, RAM (Random Access Memory) 6 and CPU (Central Processing
Unit) 7 function part such as grade, each function part is connected by bus 9.
Input unit 3 has above-mentioned various button group, exports the information pressed to CPU.
Display part 4 has above-mentioned display 2, shows various information in the display according to the signal from CPU7.
ROM5 preserves various set up an office process and the concrete amount of sampling calculating public affairs involved with sample sample calculation device
The calculation process of formula etc. operate relevant various programs and for realizing the program of the various functions that sample calculation device is had
Deng.In the present embodiment, storage has sampling sample size calculation procedure, CPU7 read the program ROM5 from ROM5,
It is performed after RAM6 launches.
RAM6 is temporarily to remain able to write the various programs that CPU7 performs or the number relating to the execution of these programs at any time
According to the memorizer waited.RAM6 such as has storage to have the information of each parameter inputted by user or data or phase in the present embodiment
Answer the operation result etc. of Sample Size Calculation.
CPU7 and the instruction corresponding execution process based on established procedure inputted, carry out each instruction to function part or number
According to transmission, specifically, CPU7 reads, according to the operation signal inputted from input unit 3, the journey that preserved in ROM5
Sequence, performs process according to this program, thus, CPU7 controls for the display showing result to suitable display part 4 output
Signal, and show the display information of correspondence.
Accompanying drawing explanation
Fig. 1: be the front elevation of sample amount of sampling computer
Fig. 2: be the block diagram representing sampling sample size computer schematic configuration
Fig. 3: be in present embodiment picture conversion schematic diagram
Detailed description of the invention
Operational instances 1:
Below, use the flow process shown in Fig. 3 and picture conversion, CPU7 is performed to the operation example of sample amount of sampling computer
Illustrate, show user operation in the left side of figure, the picture in the right side of figure display display screen.
Standby process was carried out before user operation button:
(1) purpose according to investigation collects the essential information of respondent, and presses follow procedure operation.
(2) confidence level key is pressed, display screen display CL:；
(3) confidence level such as 95% selected by the input of ten numeral keys, then display screen display CL:95, presses acknowledgement key
Confirm；
(4) press colony 1 and expect prevalence rate key, display screen display P1:；
(5) by ten numeral keys's input corresponding prevalence rates such as 15%, then 0.15, display screen display P1:0.15 are inputted,
Press acknowledgement key to confirm；
(6) press colony 2 and expect prevalence rate key, display screen display P2:；
(7) by ten numeral keys's input corresponding prevalence rates such as 10%, then display screen display P2:0.10, presses acknowledgement key
Confirm；
(8) power of a test key is pressed, display screen display β:；
(9) by ten numeral keys's input corresponding power of a tests such as 80%, then inputting 80, display screen shows β: 80, presses really
Recognize key to confirm；
The operation result such as 685 of display display CPU7.
Example 2:
Certain county is that raising dairy cattle industry is the most flourishing, is also the most serious place of brucellosis.Local raising dairy cattle mainly includes
Two ways, one is large-scale cultivation, i.e. cattle farm scale is big, has the milking equipment of oneself, and this has veterinary, and oneself is joined
Kind, management regulation and being isolated from the outside；Another kind is dairy village or village specializing in a certain trade, and the most multiple milk cattle cultivating families are gathered in one
Rise, share milking equipment, local breeding station and veterinary provide service.According to this toward brucellosis testing result, estimate scale field brucellosis
Positive rate is about 4%, and other feeding manner milch cow brucellosis positive rates are about 7%.If confidence level 95%, it is ensured that 90%
In the presence of degree of holding determines difference, need to extract how many samples？
Standby process was carried out before user operation button:
(1) confidence level key is pressed, display screen display CL:；
(2) confidence level 95% selected by the input of ten numeral keys, then display screen display CL:95, presses acknowledgement key true
Recognize；
(3) press colony 1 and expect prevalence rate key, display screen display P1:；
(4) by ten numeral keys's input corresponding prevalence rates such as 7%, then input 0.07, display screen display P1:0.07, press
Lower acknowledgement key confirms；
(5) press colony 2 and expect prevalence rate key, display screen display P2:；
(6) by ten numeral keys's input corresponding prevalence rates such as 4%, then display screen display P2:0.04, presses acknowledgement key
Confirm；
(7) power of a test key is pressed, display screen display β:；
(8) by ten numeral keys's input corresponding power of a tests such as 90%, then inputting 90, display screen shows β: 90, presses really
Recognize key to confirm；
The operation result such as 1211 of display display CPU7, the sample size of the most each colonial need extraction is 1211 milk
Cattle.
There is described herein the preferred embodiment of the present invention, including the known best pattern realizing invention of inventor.
After reading the description above, the variation of those preferred implementations will be apparent for persons skilled in the art
's.Inventor expects that those of skill in the art can use these to make a variation suitably.Therefore, the present invention include that applicable law allows
All modifications of the theme stated in appended claims and equivalent, additionally, present invention resides in all possible
Any combination of the above-mentioned element in variation.Unless had at this in other different explanations or context to have negate clearly.
Claims (2)
1. the computer of the sample size obtaining population risk or risk in etiology is investigated, it is characterised in that
Described computer includes that input module, computing module and display module, wherein said input module include confidence level key, group
Body 1 expects that prevalence rate key, colony 2 expect prevalence rate key, allowable error key and power of a test key and ten digital keys, arithmetic point
Key, cancel button key, acknowledgement key and directionkeys；The computing formula run in described computing module is
Wherein:
N is the sample size required for each group；
ZαFor 1-α/2 percentile of standard normal distribution, it it is facing of the standard normal distribution corresponding when being 1-α of confidence level
Dividing value；
ZβFor (1-β) percentile of the standard normal distribution relevant with inspection validity 1-β, for inspection validity (1-β) it is
80%, for 85%, 90% and 95%, the Z of its correspondenceβValue is 0.84,1.04,1.28,1.64；
p1Expection prevalence rate for colony 1；
p2Expection prevalence rate for colony 2；
P is colony 1 and the meansigma methods of colony 2 two expection prevalence rate: (p1+p2)/2；
Q=1-p；
q1=1-p1；
q2=1-p2；
Hypothesis testing, also known as significance test, is to utilize small probability apagoge thought, indirectly sentences from opposite H0 of problem
Whether disconnected problem H1 to be solved is set up, and i.e. calculates statistic of test under conditions of assuming H0 establishment, then according to the P obtained
Value judges；Having probability according to the deduction conclusion that P value is made, therefore its conclusion can not be the most correct, it may occur however that two
Class mistake, type Ⅰ error: be to have rejected correct null hypothesis H0, the mistake of this kind of " abandoning true " is referred to as type Ⅰ error, and we often say
Inspection level, it is simply that the maximum of the prespecified criminal's of permission type Ⅰ error probability, represent with α；Type Ⅱ error: be to receive
Actual invalid null hypothesis H0, the mistake of this kind of " type B error " is referred to as type Ⅱ error, and its probability size β represents.
2. the method obtaining the sample size of sampling in D Ety investigation, in the method, the amount of sampling of sample passes through right
Require that computer described in 1 carries out calculating to obtain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310393749.2A CN103413065B (en) | 2013-09-02 | 2013-09-02 | The relatively amount of sampling computer of different groups disease rates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310393749.2A CN103413065B (en) | 2013-09-02 | 2013-09-02 | The relatively amount of sampling computer of different groups disease rates |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103413065A CN103413065A (en) | 2013-11-27 |
| CN103413065B true CN103413065B (en) | 2016-11-23 |
Family
ID=49606076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310393749.2A Expired - Fee Related CN103413065B (en) | 2013-09-02 | 2013-09-02 | The relatively amount of sampling computer of different groups disease rates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103413065B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1424651A (en) * | 2002-04-19 | 2003-06-18 | 刘振民 | Generation 3 counting tools |
| CN102184470A (en) * | 2011-04-28 | 2011-09-14 | 上海同城信息科技有限公司 | Method and device for processing selected information of sample points in land price survey |
| WO2012151212A1 (en) * | 2011-05-01 | 2012-11-08 | University Of Rochester | Multifocal hepatocellular carcinoma microrna expression patterns and uses thereof |
| CN102855384A (en) * | 2012-07-27 | 2013-01-02 | 中国农业科学院油料作物研究所 | Quantitative evaluation method for peanut aflatoxin B1 pollution on human health risk |
-
2013
- 2013-09-02 CN CN201310393749.2A patent/CN103413065B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1424651A (en) * | 2002-04-19 | 2003-06-18 | 刘振民 | Generation 3 counting tools |
| CN102184470A (en) * | 2011-04-28 | 2011-09-14 | 上海同城信息科技有限公司 | Method and device for processing selected information of sample points in land price survey |
| WO2012151212A1 (en) * | 2011-05-01 | 2012-11-08 | University Of Rochester | Multifocal hepatocellular carcinoma microrna expression patterns and uses thereof |
| CN102855384A (en) * | 2012-07-27 | 2013-01-02 | 中国农业科学院油料作物研究所 | Quantitative evaluation method for peanut aflatoxin B1 pollution on human health risk |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103413065A (en) | 2013-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zadoks et al. | Comparison of Staphylococcus aureus isolates from bovine and human skin, milking equipment, and bovine milk by phage typing, pulsed-field gel electrophoresis, and binary typing | |
| Almond et al. | The 1918 influenza pandemic and subsequent health outcomes: an analysis of SIPP data | |
| Santman-Berends et al. | An estimation of the clinical mastitis incidence per 100 cows per year based on routinely collected herd data | |
| Birnbaum et al. | The analysis of disease clusters, part I: state of the art | |
| Fregel et al. | The maternal aborigine colonization of La Palma (Canary Islands) | |
| Sherlaw-Johnson et al. | Withdrawing low risk women from cervical screening programmes: mathematical modelling studyCommentary: trials versus models in appraising screening programmes | |
| CN111145848A (en) | Method, device, medium and equipment for detecting adverse reaction events in clinical test | |
| Diab et al. | Case report: Abortion and disseminated infection by Coccidioides posadasii in an alpaca (Vicugna pacos) fetus in Southern California | |
| CN103413065B (en) | The relatively amount of sampling computer of different groups disease rates | |
| CN106951710B (en) | CAP data system and method based on privilege information learning support vector machine | |
| Riffe et al. | COVerAGE-DB: A database of age-structured COVID-19 cases and deaths | |
| CN103425897B (en) | Estimate the amount of sampling computer of Animal diseases prevalence rate | |
| Zhang et al. | A GEE approach to determine sample size for pre-and post-intervention experiments with dropout | |
| CN207149265U (en) | A kind of child's health account management platform | |
| McCoy et al. | Variability of the date of HIV diagnosis: a comparison of self-report, medical record, and HIV/AIDS surveillance data | |
| CN202221571U (en) | Health monitoring service system for health maintenance | |
| Welderufael et al. | Simultaneous genetic evaluation of simulated mastitis susceptibility and recovery ability using a bivariate threshold sire model | |
| CN103425619B (en) | Prove without epidemic disease or the amount of sampling computer of discovery epidemic disease | |
| Johnston et al. | Improving validity of on-farm research | |
| Abrams et al. | Parametric overdispersed frailty models for current status data | |
| Lasater | An examination of the relationships among dogmatism, cognitive and behavioral changes, and persuasive communications within the context of a dental health program | |
| Siregar et al. | Knowledge and Attitudes about Breast Self-Examination (BSE) in Women of Childbearing Age (WCA) in Sigulang Village, Padangsidimpuan District | |
| Haugaard et al. | Prediction of clinical mastitis outcomes within and between environments using whole-genome markers | |
| Keselman et al. | Analysis ofvariance (ANOVA) | |
| Elghareeb | Screening for Vulvovaginal Candidiasis of Pregnant Women and Effectiveness of Learning Package on the Knowledge and Clinical Feature in Egypt |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161123 Termination date: 20170902 |