When studing the Rasch model in designing scale, a wonderful idea was yielded.
Why we cannot design a scale for evaluating someone's ability about that using chopsticks.
Dr. Roberto was told to learn using chopstick in Taiwan. After practising it over many weeks and knowing it very well. \
Why we do not design a scale in evaluating abilities of persons and comparing it as well as obtaining a logit value of that ability level to reveal the result of practising chopstick in Taiwan.
That is also said that what is the performance of using chopstick by Dr. Roberto, which can be evaluated and brought back to tell his father what is the level of the performance. That is not only said I have known it. The amount of that performance results should be qualitified.
2008年8月29日 星期五
What is the main purpose when traveling study in Chi-Mei
We propose a flow to describe what is the main purpose when traveling study in Chi-Mei, which is from the beginning of wishing to know the medical quality to the end of that so-called foundation of medical quality: tools used via Rasch model.
Why? because that Rasch model can help evaluating, monitoring, predicting and detecting abnormal responses through fit statistics of quality control.
2008年8月27日 星期三
Google earth helps a project to be sucessful
We used google earth approach to launch a project regarding a newly-set up hospital designed to be submited.
2008年8月25日 星期一
Quality indicator management to improve achievement ( Economic analysis on 4 quadrants)
We discussed on "
quality indicator management to improve achievement", which was using the economic analysis to interprter it.
The effects are displayed with the areas of A,B,C and D, given the patient minimum requirement for quality on Line 1 or even upgrading to Line 2 which will let the area of A or B in term of the quality curve of C1 to be disappeared.
Therefore, as encountering the possible developement on patient's requirement upgrading all the time, we should be also takeing efforts on the quality(i.e. curve 1) to be upgraded as to curve 2 in a bit to let the advandage of competition areas to keep on existed.
In the analysis, the quality level will be decided by cost (investment), indicator management, custormers' satisfaction level(revenues of a hospital). That will be necessary for us to efficiently invest our efforts, money or time(X axis) on indicator management, which will then be let the performance of hospital revenue and custormers' satisfaction level higher and higher and eventually attain another higher level of quality curve as c2 in quadrant 1, which will also be allowing another newly-developed areas such as C and D ( so called Access) to be appeared.
The lesson on this analysis tells us that an efficient indicator management in a hospital plays an important role, not only for the suitable indicator we recruit but also for the analysis tools we implement. If then, the cost(on right X axis) we invest will be be a cost-effectiveness compared with the revenue (on left X axis).
quality indicator management to improve achievement", which was using the economic analysis to interprter it.The effects are displayed with the areas of A,B,C and D, given the patient minimum requirement for quality on Line 1 or even upgrading to Line 2 which will let the area of A or B in term of the quality curve of C1 to be disappeared.
Therefore, as encountering the possible developement on patient's requirement upgrading all the time, we should be also takeing efforts on the quality(i.e. curve 1) to be upgraded as to curve 2 in a bit to let the advandage of competition areas to keep on existed.
In the analysis, the quality level will be decided by cost (investment), indicator management, custormers' satisfaction level(revenues of a hospital). That will be necessary for us to efficiently invest our efforts, money or time(X axis) on indicator management, which will then be let the performance of hospital revenue and custormers' satisfaction level higher and higher and eventually attain another higher level of quality curve as c2 in quadrant 1, which will also be allowing another newly-developed areas such as C and D ( so called Access) to be appeared.
The lesson on this analysis tells us that an efficient indicator management in a hospital plays an important role, not only for the suitable indicator we recruit but also for the analysis tools we implement. If then, the cost(on right X axis) we invest will be be a cost-effectiveness compared with the revenue (on left X axis).
2008年8月22日 星期五
A famous cronic desease hospital's health care to be visited
we have visited a hospital in charge of the cronic disease and feel impresive very much about its success.
Rasch and Continuous Variableshttp://www.rasch.org/rmt/rmt211.pdf
Question: Can Rasch analyze continuous response-level data, such as time and distance?
Answer: There are Rasch models for continuous observations, but processes are rarely truly continuous.
Rasch is formulated in terms of distinguishable qualitative advances.
How much better, faster, more accurate, does a performance need to be for it to be noticeably better?
Think of the same thing in human weight. Our weight varies all day long, so it is not until it has changed by 2 kilos that we really notice a difference. ( Just for the sample-average)
The basic approach in Rasch is to start by categorizing really begining increments.
If those are analyzed successfully, we can then reduce the size of the increments until we reach the level where further reduction introduces more randomness than information into the data.
There are several indicators of over-categorization.
One is that the model polytomous category probability curves start to look a mess, instead of an advancing range of hills. Another is that, as the number of categories increase, the sample-person “test” reliability falls far behind the value predicted by the Spearman-Brown Prophecy Formula.
Going from 2 categories (one decisioner item) to 3 categories (two decisions per item) is some
what like doubling the test length, but not so efficient.
So given the reliability, R(m), for an m-category rating scale, we would predict the reliability for an (m+1) category rating scale to be appreciably better, in the range:R(m) < color="#cc0000">keep track of the reliability as we increase the number of categories. When reliability not longer shows a reasonable increasing (or starts to decrease) we have overcategorized. John M. Linacre
Rasch and Continuous Variableshttp://www.rasch.org/rmt/rmt211.pdf
Question: Can Rasch analyze continuous response-level data, such as time and distance?
Answer: There are Rasch models for continuous observations, but processes are rarely truly continuous.
Rasch is formulated in terms of distinguishable qualitative advances.
How much better, faster, more accurate, does a performance need to be for it to be noticeably better?
Think of the same thing in human weight. Our weight varies all day long, so it is not until it has changed by 2 kilos that we really notice a difference. ( Just for the sample-average)
The basic approach in Rasch is to start by categorizing really begining increments.
If those are analyzed successfully, we can then reduce the size of the increments until we reach the level where further reduction introduces more randomness than information into the data.
There are several indicators of over-categorization.
One is that the model polytomous category probability curves start to look a mess, instead of an advancing range of hills. Another is that, as the number of categories increase, the sample-person “test” reliability falls far behind the value predicted by the Spearman-Brown Prophecy Formula.
Going from 2 categories (one decisioner item) to 3 categories (two decisions per item) is some
what like doubling the test length, but not so efficient.
So given the reliability, R(m), for an m-category rating scale, we would predict the reliability for an (m+1) category rating scale to be appreciably better, in the range:R(m) < color="#cc0000">keep track of the reliability as we increase the number of categories. When reliability not longer shows a reasonable increasing (or starts to decrease) we have overcategorized. John M. Linacre
2008年8月19日 星期二
quality control technique required to supervise and validate test items andperson responses.
The analysis of fit evaluates how well our data cooperate with the construction of measurement.
Analysis of fit gives us a tool to monitor the responses of persons anditems .
We can evaluate any set of items or persons to determine wheremisfit occurs .
Fit analysis provides the quality control techniquerequired to supervise and validate test items andperson responses.
When fit is within our guidelines, we have the control required to feel confident about item calibration and person measurement.
When misfit is discovered we can locate its occasions and begin further study of the items or persons involved.
The analysis of fit is never completed because continued use of the instrument requires that we constantly monitor item and person responses to maintain quality control .
Analysis of fit gives us a tool to monitor the responses of persons anditems .
We can evaluate any set of items or persons to determine wheremisfit occurs .
Fit analysis provides the quality control techniquerequired to supervise and validate test items andperson responses.
When fit is within our guidelines, we have the control required to feel confident about item calibration and person measurement.
When misfit is discovered we can locate its occasions and begin further study of the items or persons involved.
The analysis of fit is never completed because continued use of the instrument requires that we constantly monitor item and person responses to maintain quality control .
Many physicians in Chi-Mei can speek spanish language...
We have met several physicians in Chi-Mei who can speak flunt spanish. Dr. Roberto have had a chat with them. A very delight experience that is remeriable has kept in my mind...
2008年8月15日 星期五
BSC comparing performances using many-faceted Rasch model
A paper of "Comparisons of Hospital Balanced Scorecard Performances Using Many-Facet Rasch Model: Predict and Detect" was reviewed.
We know that the balanced scorecard (BSC) has been implemented worldwide in every hospital. Many executives are encouraged to compare, and even predict or detect performances WITHIN and BETWEEN hospitals year by year.
The many-facet Rasch Model (MFRM) could be applied to analyze BSC data.
The same scenario can be designed as the indication management for assessment on examinees, judges and items, which are inspected and monitored periodly and continuously to let medical quality upgraged through the process of learning, practising and habit-shapping.
A picture is worth a thousand words is a proverb that refers to the idea that complex stories can be described with just a single still image, or that an image may be more influential than a substantial amount of text. It also aptly characterizes the goals of visualization where large amounts of data must be absorbed quickly.
Innovative job descriptions
We talked about the job description and how to design the employees' role and directions of future learning. An innovative way regarding the talents for employees is proposed and dicussed.
"Amazing" was the answer and response from "Dr. Roberto".
2008年8月13日 星期三
Control chart in quality management
For indication management in nursing department, we got the idea of control chart using in quality management.
2008年8月11日 星期一
Many-faceted Rasch model for analysizing data
http://www.winsteps.com/
The many-faceted Rasch model was introduce in this morning, the related judge's perception in an assessment will be reliazed, especially for detecting the judge bias in that evaluation.
Maybe the technique will be helping us know somethings regarding patients judged by the professionals.
The many-faceted Rasch model was introduce in this morning, the related judge's perception in an assessment will be reliazed, especially for detecting the judge bias in that evaluation.
Maybe the technique will be helping us know somethings regarding patients judged by the professionals.
2008年8月8日 星期五
This week's lessons
1> The analysis after organizing data from a survey to an appropriate spreadsheet by VBA for nutrition's components was presented.
2> The deffience between Client and Customer was discussed.
3> The leadership types regarding the willness and ability were talked on the four topics of force, participation, delegation and free-hand.
4>The dept. of pathology was introduced and costed us almost a half day on the Chinese dia de padre ( Aug. 8)
5> The presentation of the full-month learning in Chi-Mei was also fulfilled on Aug. 7 morning.
6> We have planed to introduce the many-faceted Rasch model in the next week, for details will be seen in the next week's blog.
7> attending the health communication commitee of Chi-Mei, we knew much more affairs regarding the contents and operations for the health promotion implemented in Chi-Mei hospital.
2008年8月7日 星期四
2008年8月5日 星期二
I presented somethings regarding NICARAGUA HEALTH SYSTEM to nursing dept. of Chi-Mei
Today is an amazing day on which I presented something regarding
NICARAGUA HEALTH SYSTEM to Chi-Mei's nursing dept. of which staff and superintendents also tell me so much magements with regard with the qualtity administration in that hospital.
NICARAGUA HEALTH SYSTEM to Chi-Mei's nursing dept. of which staff and superintendents also tell me so much magements with regard with the qualtity administration in that hospital.
2008年8月4日 星期一
Roberto has known how to apply statistical technique in Excel dataset to administration affairs
Using Excel spreadsheets to test group difference whether exhibites statisticaly significant is an wonderful achievement in recent week in Chi-Mei..
Preparing the presentation for the learning fruits in Chi-Mei will be held on Aug. 7 at 9:00 - 10:00. The Power-Point format slides regarding the 3 topics have been readily prepared.
訂閱：
文章 (Atom)
