Q&A
Q1:the standard error of measurement of the total score was calculated for both the test-retest and the interrater conditions to determine the consistency of scoring in absoloute terms and to evaluate the minimal detectable change.
Ans:DGI再測信度和施測者間條件檢驗總分的標準誤(SE of measurement, SEM)以判斷分數在絕對數值中的一致性，及評估最少偵測變化(Minimal Detectable Change)。
Q2:the Bland and Altman method of plotting the difference of scores against total scores of each participant of the 2 testing times //showed good realibility.
Q3:the mean differences in interrater scoring are plotted against the mean scores of the 2 raters for the same participant in figure 1B.
Ans: Q2 & Q3 are the same meaning of telling us the ICC scores of the interrater and test-retest have increased when we look in the Bland and & Alman plot and Table 2.e.g item 5:icc scores 0.56(test-retest )< icc scores 0.83 (interrater)
against difference(Y axis) vs mean (X axis)
Q4:for item 5,and for item 7 ,the realibility for the test-retest conditionwas lower than that of the interrater condition.
Ans:That is means the realibility
Q5:on item 8,there was total agreement in both test-retest and the interrater condition indicating that instructions for item 8 were specific enough to leave little doubt about scoring.
Ans:total agreement = 完全一致
Q6:the criterion for statistical significance was P less than .05.
Ans:
P值是論文中最常用的一個統計學指標，可是其誤用、解釋錯誤的現象卻很常見。因此，很有必要說明p值的意義、用法及常見錯誤。
釐清自己的觀念:
1.角色--
2.貢獻--對病患的成效有多少,能排除其他介入的因素來確定OTR 在臨床給予的治療?
2007年11月30日 星期五
2007年11月29日 星期四
11/30 reading and revise articles
敏感性(sensitivity)與特異性(specificity)
乃臨床診斷正確性之評價指標﹐亦可以引用到製造業對策之評價﹐以下表說明之：
sensitivity（敏感性）：疾病發現之能力﹐計算式：a/(a+c) 最佳狀況為100%
specificity（特異性）：無病發現之能力﹐計算是：d/(b+d) 最佳狀況為100%
如上所示﹐乃健康者與罹患者之BioMark定量分布圖﹐圖中重疊區的上緣是疾病的指標﹐下緣則是健康的指標﹐一般而言均假設兩者間有重疊。
重疊區包括假陽性(False Positive)是誤判健康者為罹患者﹐假陰性(False Negative)則是誤判罹患者為健康者。
降低上緣值固可以提高診斷的敏感度﹐但此時診斷的特異性會降地（亦即假陽性增加）﹐兩者之間有取捨之關係。診斷之目的在於正確之判斷﹐通常在95%信賴區間外之情況﹐吾人視之為異常！
參考資料：http://homepage3.nifty.com/m_nw/dataac10j.htm
False positive rate (α) = FP / (FP + TN) = 18 / (18 + 182) = 9% = 1 - specificity
False negative rate (β) = FN / (TP + FN) = 1 / (2 + 1) = 33% = 1 - sensitivity
Power = 1 − β
sensitivity =number of true positives /(number of true positives +number of false positives )
@A sensitivity of 100% means that the test recognizes all sick people as such.
@Sensitivity alone does not tell us how well the test predicts other classes (that is, about the negative cases). In the binary classification, as illustrated above, this is the corresponding specificity test, or equivalently, the sensitivity for the other classes.
@Sensitivity is not the same as the positive predictive value (ratio of true positives to combined true and false positives), which is as much a statement about the proportion of actual positives in the population being tested as it is about the test.
@The calculation of sensitivity does not take into account indeterminate test results. If a test cannot be repeated, the options are to exclude indeterminate samples from analyses (but the number of exclusions should be stated when quoting sensitivity), or, alternatively, indeterminate samples can be treated as false negatives (which gives the worst-case value for sensitivity and may therefore underestimate it).
--------------------------------------------------------------------------------
一個診斷工具不會同時具有良好的Sensitivity & Specificity
通常Sensitivity好的工具Specificity會較差，而Specificity好的工具Sensitivity較差。
Sensitivity（以下簡稱Sen.）與Specificity（以下簡稱Spe.）是對診斷工具而言的。
然而對病人而言，重要的不是診斷工具的Sen.與Spe.
而是該診斷結果對病人的意義。亦即：
陽性預測值 Positive Predictive Value (PPV.) 與
陰性預測值 Negative Predictive Value (NPV.)
所謂的陽性預測值，就是檢查結果是陽性，而確實是得病而不是偽陽性的機率。
而陰性預測值，就是檢查結果是陰性，而確實沒有得病而不是偽陰性的機率。
11/29 revise the article(chinese)!
Mission:
1. revise the translation of the article,reading some chinese article to improve the writing skill with more qualify.
2. will go to Far Eastern Hospital for bringing back the data of p't!
1. revise the translation of the article,reading some chinese article to improve the writing skill with more qualify.
2. will go to Far Eastern Hospital for bringing back the data of p't!
2007年11月27日 星期二
11/28 NTUH assessment
Categorical variable, 分類變量
變數(variable)
在搜集資料時，首先要根據研究目的確定同質觀察單位，再對每個觀察單位的某項特徵進行測量或觀察，這種特徵稱為變數。如上述的“身高”、“體重”、“療效”就是變數。變數的觀察結果或測量值稱為變數值(variable value) ，變數按其值的性質可分為不同類型。
分類變數（categorical variable）：表現為互不相容的類別或屬性，亦稱定性變數。分類變數可分為無序與有序兩類。
無序分類變數（unordered categorical variable）是指所分類別或屬性之間無程度和順序的差別。又可分為二項分類和多項分類，如性別（男、女）；血型（O、A、B、AB）等。 無序分類變數的分析應先按類別分組，計各組的觀察單位數，編制分類資料的頻數表，所得資料稱為計數資料。
有序分類變數（ordinal categorical variable）是各類別之間有程度的差別。如尿糖化驗結果按－、±、+、++、+++分類；療效按治癒、好轉、無效、惡化分組。有序分類變數的分析應先按等級順序分組，計各組的觀察單位數，編制各等級的頻數表，所得資料稱為等級資料。
Mission:
1.Today i have finished 2ADL and 1BIB.
2.Tomorrow need to phone to Far eastern hospital for taking back the detail of p't
變數(variable)
在搜集資料時，首先要根據研究目的確定同質觀察單位，再對每個觀察單位的某項特徵進行測量或觀察，這種特徵稱為變數。如上述的“身高”、“體重”、“療效”就是變數。變數的觀察結果或測量值稱為變數值(variable value) ，變數按其值的性質可分為不同類型。
分類變數（categorical variable）：表現為互不相容的類別或屬性，亦稱定性變數。分類變數可分為無序與有序兩類。
無序分類變數（unordered categorical variable）是指所分類別或屬性之間無程度和順序的差別。又可分為二項分類和多項分類，如性別（男、女）；血型（O、A、B、AB）等。 無序分類變數的分析應先按類別分組，計各組的觀察單位數，編制分類資料的頻數表，所得資料稱為計數資料。
有序分類變數（ordinal categorical variable）是各類別之間有程度的差別。如尿糖化驗結果按－、±、+、++、+++分類；療效按治癒、好轉、無效、惡化分組。有序分類變數的分析應先按等級順序分組，計各組的觀察單位數，編制各等級的頻數表，所得資料稱為等級資料。
Mission:
1.Today i have finished 2ADL and 1BIB.
2.Tomorrow need to phone to Far eastern hospital for taking back the detail of p't
11/27 Reading & Translation article & figure out the basic concept of statistical
標準差standard deviation,SD:一組數值自平均值分散開來的程度
一個較大的標準差代表大部分的數值和其平均值之間差異較大;一個較小的標準差代表這些數值較接近平均值。
標準誤standard error,SE是一種 standard deviation
但通常的 standard deviation 是指原始資料的標準差;standard error 是指統計量或估計量的標準差
1.相當於統計母群的標準差。其公式隨統計項目不同而異。例如：樣本平均的標準誤＝樣本的標準差／根號（樣本大小）。The standard error is the estimated standard deviation of a statistic. The formula depends on what statistic you are talking about. For example, the standard error of a sample mean is just the sample standard deviation divided by the square root of the sample size.
http://www.cmh.edu/stats/definitions/stderr.htm
2.如果我們從同個母群中取出多個樣本，那我們必然可得到多個樣本數值的平均。若我們計算這些樣本數平均相對於未知母群平均的標準差，即稱為「標準誤」。標準誤是用來測量樣本平均的變異性。然而，我們可以用以下公式來計算標準誤：(即不需用到未知的母群平均) 標準誤 = 標準差/根號(樣本數-1)。Standard error. If we took several samples of the same thing we would, of course, be able to compute several means, one for each sample. If we computed the standard deviation of these sample means as an estimate of their variation around the true but unknown population mean, that standard deviation of means is called the standard error. Standard error measures the variability of sample means. However, since we normally have only one sample but still wish to assess its variability, we can compute estimated standard error by this formula:
SE = sd/SQRT(n - 1)
where sd is the standard deviation for a variable and n is sample size. Often estimated standard error is just called 'standard error.'
http://www2.chass.ncsu.edu/garson/pa765/normal.htm
測量標準誤(standard error of measurement,SEM):=測驗誤差的標準差
1.可以顯示對個別病患進行測量之誤差,也可計算95%信賴區間(confidence interval,CI)之SEM藉以表示個案之真實結果有95%的機會將落在此區間。
例:一個人接受某一測驗N 次 所得的分數應是以其真實分數為中心而構成的常態分配,這個分配的標準差就是測量標準誤。
2.另一個解釋-->:測驗分數之誤差程度的量數與其信度之間成反比的關係
亦即信度愈高 測量標準誤愈小;反之 信度愈低 測量標準誤愈大。
分數的分析理論，是比較「母群」的施測結果和預期結果，但在實行比較時，我們通常只能比較樣本的結果。（例如：我們記錄了100位個案的收縮壓，並計算其平均和標準差，我們就能知道單個個體數據離樣本平均的距離。但如果我們重複執行此測驗多次，就能了解單個個體數據離所有樣本平均的平均值的差距。)「所有樣本平均的平均值」的“標準差”就稱為 SEM。在正負一個測量標準誤之外的數據被解釋為和其它大部分數據(67%)有差異。
The theoretical (i.e. statistical) analysis of scores depends on comparisons between obtained scores (or statistics) and expected scores (or statistics) from the population based on happenstance (chance). But in practice our comparisons are based almost without exception on scores obtained from samples, not on populations. For example, if we record systolic blood pressure in a large number of volunteers (n=100) and calculate the mean and standard deviation of our sample scores, we would know on average how far away any particular individual's score was from the (sample) average. But now if we repeat the effort (i.e. the measurement of systolic blood pressure in multiple separate samples of 100 individuals) over and over again (say, 100 times) we would know on average how far away any particular sample's average score was from the mean of all the (100) samples tested. The "standard deviation" of the mean of all the sample means (i.e. the population mean) is the standard error of measurement (SEM). Scores that fall beyond ± 1 SEMs are interpreted as unlike most (~67%) of the other scores.
http://symptomresearch.nih.gov/chapter_23/sec29/cahs29pg1.htm
相關性分析correlation coefficient
若我們想知道兩個連續變數之間的關係,例如身高和體重,是不是兩個會一起變化,就要用相關性分析
相關就是兩個變數會一起變化,如果一起變大及變小,就是正相關,如果一個變大另一個就變小,則是負相關。例如體重和腰圍的關係。
低度相關就是兩個變數各變各的,例如血脂肪和血鈣濃度的關係。
表示相關程度的數字,就是相關係數,介於-1至1之間,愈接近-1(負相關) 或1(正相關),相關程度愈高;愈接近0,相關程度愈低。常用的有Pearson相關係數(母數方法)及Spearman相關係數(無母數方法).前者需要較大的樣本及較多數學假設,所以Spearman相關係數的適用範圍較廣。
MCID (最小臨床重要差異值)
Jaeschke最早定義「最小臨床重要差異值 MCID」為："在病人有獲利且執行上沒有困難或副作用的情況下，所得到臨床上最小的分數改變。" 而在那之後MCID的定義有些改變。例如："被認為有用或重要的最小分數差異"；"降低最小的風險，讓答應接受治療的病人事前知道不接受治療的風險"。這些定義顯示了MCID建構的多個層面；有些著重在潛在危險的改變，有些著重在治療決策的影響，有些則單純著重改變的大小。最常見的定義是：MCID為重要改變的最低界線。
Jaeschke first defined an MCID as being “the smallest difference in score in the domain of interest which patients perceive as beneficial and which would mandate, in the absence of troublesome side effects and excessive cost, a change in the patient's management” [6]. Since then the definition has varied. We see definitions such as “the smallest difference in a score that is considered to be worthwhile or important” [4], the “minimum absolute risk reduction for which patients would take a treatment given their understanding of the risk without that treatment” [7], or the mean score for patients with an optimal result minus the mean score for a group with a suboptimal result [8]. The definitions show the varied constructs with the common label of MCID; some weighing change against potential risks, others weighing the impact on treatment decision making, others weighing the impact on the magnitude of change alone. The common thread is that it is the lower boundary of change that has been defined, in some way, to be important.
MCID 的主要功能是協助研究及臨床人員解釋, 評量分數變化或差異之意義。
研究上，療效的判斷常以是否「統計顯著(statistical significance)」判定之，然而具有統計顯著之差異值，不一定具有「臨床意義(clinical significance)」。
MCID值可作為判斷群組分數改變/差異（組內(within-group)/組間(between-group)）是否具有臨床重要意義的最小閾值，決定評量工具的MCID值，可協助臨床及研究人員判斷研究結果所造成的差異是否具備「臨床意義」！MCID值的另一用途是判斷評估工具是否具備反應性(responsiveness)(within-group)。
一個較大的標準差代表大部分的數值和其平均值之間差異較大;一個較小的標準差代表這些數值較接近平均值。
標準誤standard error,SE是一種 standard deviation
但通常的 standard deviation 是指原始資料的標準差;standard error 是指統計量或估計量的標準差
1.相當於統計母群的標準差。其公式隨統計項目不同而異。例如：樣本平均的標準誤＝樣本的標準差／根號（樣本大小）。The standard error is the estimated standard deviation of a statistic. The formula depends on what statistic you are talking about. For example, the standard error of a sample mean is just the sample standard deviation divided by the square root of the sample size.
http://www.cmh.edu/stats/definitions/stderr.htm
2.如果我們從同個母群中取出多個樣本，那我們必然可得到多個樣本數值的平均。若我們計算這些樣本數平均相對於未知母群平均的標準差，即稱為「標準誤」。標準誤是用來測量樣本平均的變異性。然而，我們可以用以下公式來計算標準誤：(即不需用到未知的母群平均) 標準誤 = 標準差/根號(樣本數-1)。Standard error. If we took several samples of the same thing we would, of course, be able to compute several means, one for each sample. If we computed the standard deviation of these sample means as an estimate of their variation around the true but unknown population mean, that standard deviation of means is called the standard error. Standard error measures the variability of sample means. However, since we normally have only one sample but still wish to assess its variability, we can compute estimated standard error by this formula:
SE = sd/SQRT(n - 1)
where sd is the standard deviation for a variable and n is sample size. Often estimated standard error is just called 'standard error.'
http://www2.chass.ncsu.edu/garson/pa765/normal.htm
測量標準誤(standard error of measurement,SEM):=測驗誤差的標準差
1.可以顯示對個別病患進行測量之誤差,也可計算95%信賴區間(confidence interval,CI)之SEM藉以表示個案之真實結果有95%的機會將落在此區間。
例:一個人接受某一測驗N 次 所得的分數應是以其真實分數為中心而構成的常態分配,這個分配的標準差就是測量標準誤。
2.另一個解釋-->:測驗分數之誤差程度的量數與其信度之間成反比的關係
亦即信度愈高 測量標準誤愈小;反之 信度愈低 測量標準誤愈大。
分數的分析理論，是比較「母群」的施測結果和預期結果，但在實行比較時，我們通常只能比較樣本的結果。（例如：我們記錄了100位個案的收縮壓，並計算其平均和標準差，我們就能知道單個個體數據離樣本平均的距離。但如果我們重複執行此測驗多次，就能了解單個個體數據離所有樣本平均的平均值的差距。)「所有樣本平均的平均值」的“標準差”就稱為 SEM。在正負一個測量標準誤之外的數據被解釋為和其它大部分數據(67%)有差異。
The theoretical (i.e. statistical) analysis of scores depends on comparisons between obtained scores (or statistics) and expected scores (or statistics) from the population based on happenstance (chance). But in practice our comparisons are based almost without exception on scores obtained from samples, not on populations. For example, if we record systolic blood pressure in a large number of volunteers (n=100) and calculate the mean and standard deviation of our sample scores, we would know on average how far away any particular individual's score was from the (sample) average. But now if we repeat the effort (i.e. the measurement of systolic blood pressure in multiple separate samples of 100 individuals) over and over again (say, 100 times) we would know on average how far away any particular sample's average score was from the mean of all the (100) samples tested. The "standard deviation" of the mean of all the sample means (i.e. the population mean) is the standard error of measurement (SEM). Scores that fall beyond ± 1 SEMs are interpreted as unlike most (~67%) of the other scores.
http://symptomresearch.nih.gov/chapter_23/sec29/cahs29pg1.htm
相關性分析correlation coefficient
若我們想知道兩個連續變數之間的關係,例如身高和體重,是不是兩個會一起變化,就要用相關性分析
相關就是兩個變數會一起變化,如果一起變大及變小,就是正相關,如果一個變大另一個就變小,則是負相關。例如體重和腰圍的關係。
低度相關就是兩個變數各變各的,例如血脂肪和血鈣濃度的關係。
表示相關程度的數字,就是相關係數,介於-1至1之間,愈接近-1(負相關) 或1(正相關),相關程度愈高;愈接近0,相關程度愈低。常用的有Pearson相關係數(母數方法)及Spearman相關係數(無母數方法).前者需要較大的樣本及較多數學假設,所以Spearman相關係數的適用範圍較廣。
MCID (最小臨床重要差異值)
Jaeschke最早定義「最小臨床重要差異值 MCID」為："在病人有獲利且執行上沒有困難或副作用的情況下，所得到臨床上最小的分數改變。" 而在那之後MCID的定義有些改變。例如："被認為有用或重要的最小分數差異"；"降低最小的風險，讓答應接受治療的病人事前知道不接受治療的風險"。這些定義顯示了MCID建構的多個層面；有些著重在潛在危險的改變，有些著重在治療決策的影響，有些則單純著重改變的大小。最常見的定義是：MCID為重要改變的最低界線。
Jaeschke first defined an MCID as being “the smallest difference in score in the domain of interest which patients perceive as beneficial and which would mandate, in the absence of troublesome side effects and excessive cost, a change in the patient's management” [6]. Since then the definition has varied. We see definitions such as “the smallest difference in a score that is considered to be worthwhile or important” [4], the “minimum absolute risk reduction for which patients would take a treatment given their understanding of the risk without that treatment” [7], or the mean score for patients with an optimal result minus the mean score for a group with a suboptimal result [8]. The definitions show the varied constructs with the common label of MCID; some weighing change against potential risks, others weighing the impact on treatment decision making, others weighing the impact on the magnitude of change alone. The common thread is that it is the lower boundary of change that has been defined, in some way, to be important.
MCID 的主要功能是協助研究及臨床人員解釋, 評量分數變化或差異之意義。
研究上，療效的判斷常以是否「統計顯著(statistical significance)」判定之，然而具有統計顯著之差異值，不一定具有「臨床意義(clinical significance)」。
MCID值可作為判斷群組分數改變/差異（組內(within-group)/組間(between-group)）是否具有臨床重要意義的最小閾值，決定評量工具的MCID值，可協助臨床及研究人員判斷研究結果所造成的差異是否具備「臨床意義」！MCID值的另一用途是判斷評估工具是否具備反應性(responsiveness)(within-group)。
2007年11月25日 星期日
11/26 Reading article & translation
Q & A
Q1:what is the meaning of 95% confidence intervals?
何謂信賴區間(confidence interval)？利用樣本抽樣,將抽出的樣本在一定可性度之下,利用抽樣分配建立一區間,採用此區間預測母體分配特性。
在了解了抽樣分配(sampling distribution)的概念及其兩個重要定理後，我們即可從事推論統計兩大任務之一：由樣本得到的統計值（statistic）來推估母群體之數值或母數(parameters)。在日常生活中常看到的民意調查或選舉調查，就是這種估計的運用。
估計的方法有兩種：一為點估計(a point estimate)，也就是從樣本得到的統計值來估計母群體的數值。如果您做了一個民意調查後，報告說全部選民中有 42%的人會投給某候選人，此即為點估計的例子(就是估計有 42%選民會投給此人)。另一為區間估計(an interval estimate)。此涉及信賴區間（confidence intervals）的估計步驟。信賴區間是估計在一個範圍內的數值，而非單一數值。
區間估計提供我們感興趣參數可能的範圍，例如：μ的 95%信賴區間（95% Confidence Interval, 95% CI）告訴我們此區間有 95%的機會會涵蓋真實母群體平均數。
影響區間大小的因素包括信心水準與母族群的變異數或標準偏差
意義：如為常態分布時,有95%的機會測量到的樣本數據會落在信賴區間範圍內
信賴區間 (Confidence Interval, CI) 有95%的信心確定，群體的正確數值會落在這個數值範圍內 Quantifies the uncertainty in measurement. It is usually reported as a 95% CI which is the range of values within which we can be 95% sure that the true value for the whole population lies.
95％信賴區間:95％信賴區間是從樣本數據計算出來的一個區間，保證在所有樣本當中，有95％會把真正的母體參數包含在區間之中。
Q2:How to decrease the different in the Bland and Altman method?
ANS:That will need to figure out the meaning of the difference in this paragragh at first,because it is too small variable that not so important to decrease the different.
Q3:some examples inside the article need all mention out or chose the most important one to explaination
ANS:main point(theme of article) <----> explain clearly ,if it is the main point ,you may need to make it clearly ,until the reader understand whart you mention!!
Q4:What is the means of positive correlation in concurrent validity?
同時效度(concurrent validity):自編的測驗與同時間的效標測驗，求其相關。目的在估計或診斷目前的實際情況。
Concurrent validity is a parameter used in sociology, psychology, and other psychometric or behavioral sciences. Concurrent validity is demonstrated where a test correlates well with a measure that has previously been validated. The two measures may be for the same construct, or for different, but presumably related, constructs.
positive correlation :An obvious concern relates to the validity of the test against which you are comparing your test.
http://allpsych.com/researchmethods/validityreliability.html
Q1:what is the meaning of 95% confidence intervals?
何謂信賴區間(confidence interval)？利用樣本抽樣,將抽出的樣本在一定可性度之下,利用抽樣分配建立一區間,採用此區間預測母體分配特性。
在了解了抽樣分配(sampling distribution)的概念及其兩個重要定理後，我們即可從事推論統計兩大任務之一：由樣本得到的統計值（statistic）來推估母群體之數值或母數(parameters)。在日常生活中常看到的民意調查或選舉調查，就是這種估計的運用。
估計的方法有兩種：一為點估計(a point estimate)，也就是從樣本得到的統計值來估計母群體的數值。如果您做了一個民意調查後，報告說全部選民中有 42%的人會投給某候選人，此即為點估計的例子(就是估計有 42%選民會投給此人)。另一為區間估計(an interval estimate)。此涉及信賴區間（confidence intervals）的估計步驟。信賴區間是估計在一個範圍內的數值，而非單一數值。
區間估計提供我們感興趣參數可能的範圍，例如：μ的 95%信賴區間（95% Confidence Interval, 95% CI）告訴我們此區間有 95%的機會會涵蓋真實母群體平均數。
影響區間大小的因素包括信心水準與母族群的變異數或標準偏差
意義：如為常態分布時,有95%的機會測量到的樣本數據會落在信賴區間範圍內
信賴區間 (Confidence Interval, CI) 有95%的信心確定，群體的正確數值會落在這個數值範圍內 Quantifies the uncertainty in measurement. It is usually reported as a 95% CI which is the range of values within which we can be 95% sure that the true value for the whole population lies.
95％信賴區間:95％信賴區間是從樣本數據計算出來的一個區間，保證在所有樣本當中，有95％會把真正的母體參數包含在區間之中。
Q2:How to decrease the different in the Bland and Altman method?
ANS:That will need to figure out the meaning of the difference in this paragragh at first,because it is too small variable that not so important to decrease the different.
Q3:some examples inside the article need all mention out or chose the most important one to explaination
ANS:main point(theme of article) <----> explain clearly ,if it is the main point ,you may need to make it clearly ,until the reader understand whart you mention!!
Q4:What is the means of positive correlation in concurrent validity?
同時效度(concurrent validity):自編的測驗與同時間的效標測驗，求其相關。目的在估計或診斷目前的實際情況。
Concurrent validity is a parameter used in sociology, psychology, and other psychometric or behavioral sciences. Concurrent validity is demonstrated where a test correlates well with a measure that has previously been validated. The two measures may be for the same construct, or for different, but presumably related, constructs.
positive correlation :An obvious concern relates to the validity of the test against which you are comparing your test.
http://allpsych.com/researchmethods/validityreliability.html
2007年11月22日 星期四
11/23 NTUH assessment & Translation reading paper
Mission:
1.Check the data base of the p't and help 蕙君invite p't to participate her cognition treatment!
2.translation about the second article,and find out some statistical method!
個人分數之正確性
測量標準誤(Standard error of measurement, SEM)之估計，來推估真實分數
測量標準誤之觀念，類似於統計之常態分配，即一個人之真實分數可透過許多次類似的測驗，以平均數代表其真實分數，而標準差就是每次測驗所得分數之誤差範圍。然而在實際應用上，我們並無法對每個受測者進行如此多次之測驗，所以需透過群體之標準差與信度係數來估計出測量標準誤。
Bland-Altman plot:
A scatterplot of variable means plotted on the horizontal axis and the differences plotted on the vertical axis which shows the amount of disagreement between the two measures (via the differences) and lets you see how this disagreement relates to the magnitude of the measurements. This plot includes approximate 95% limits (based on an assumption of normal differences). If differences observed in this plot are not deemed scientifically (or clinical) important (according to the researcher’s own expertise), this is a confirmation of agreement. (The decision as to what constitutes a clinically important difference should be made in advance of the analysis.)
1.Check the data base of the p't and help 蕙君invite p't to participate her cognition treatment!
2.translation about the second article,and find out some statistical method!
個人分數之正確性
測量標準誤(Standard error of measurement, SEM)之估計，來推估真實分數
測量標準誤之觀念，類似於統計之常態分配，即一個人之真實分數可透過許多次類似的測驗，以平均數代表其真實分數，而標準差就是每次測驗所得分數之誤差範圍。然而在實際應用上，我們並無法對每個受測者進行如此多次之測驗，所以需透過群體之標準差與信度係數來估計出測量標準誤。
Bland-Altman plot:
A scatterplot of variable means plotted on the horizontal axis and the differences plotted on the vertical axis which shows the amount of disagreement between the two measures (via the differences) and lets you see how this disagreement relates to the magnitude of the measurements. This plot includes approximate 95% limits (based on an assumption of normal differences). If differences observed in this plot are not deemed scientifically (or clinical) important (according to the researcher’s own expertise), this is a confirmation of agreement. (The decision as to what constitutes a clinically important difference should be made in advance of the analysis.)
2007年11月21日 星期三
11/22 Reading and translation articles
Question:
1.信度之間有2項種類1.test-retest & interrater reliability 之間的關連性,是否會是因2者分數高是否其關連性高,代表其信度越高.
老師的回答:基本上信度為看評量工具的穩定性,因此可以單獨分開解釋這兩者的功能:1.test-retest為看評估工具的經過再測後其穩定性是否會一樣.2.interrater reliability 則為不同施測者在施測工具後其兩者的一致性.
2.如何將評估工具發展成較客觀性的?需要的步驟以及考慮的面向為何?
老師的回答:考慮你要評估的目的是什麼!考慮其差別(沒聽得很清楚)以及測量的內容,以便變成更簡單和容易操作的評估工具.
3.Given a normal distribution and no change,68%of the time an observed score will fall within 1SE of measurement of a person 's true score, and 95%of the time it should fall within 1.96SE of measurement of the true score.
深藍色區域是距平均值小於一個標準差之內的數值範圍。在常態分佈中，此範圍所佔比率為全部數值之 68%。根據常態分佈，兩個標準差之內（藍，棕）的比率合起來為 95%。根據常態分佈，三個標準差之內（深藍，橙，黃）的比率合起來為 99% 。
常態分佈/常態分布/常態分配(Normal Distribution)又稱高斯分佈(Gauss Distribution)，一般研究變數常會呈現常態分佈或近似常態分佈，如身高、體重、收入、支出、意見程度、評量誤差(error of measurement)。常態分佈的特徵是以數值資料平均值(μ )為中心，分佈曲線呈鈴形(bell shape)，中心點位置其數值出現的頻率(次數)最多，離中心點位置左右(可延伸到無窮大± ∞ )的數值出現頻率漸少，曲線左右對稱，即大於平均值和小於平均值的出現頻率相等。
4.They used K coefficient values for the item analyses, which may have been influenced by the low variability of their subjects who were skewed toward the higher end of the scale.
老師的回答:利用kappa coefficient 去做個別項目一致性分析,較低的差異度代表有高的一致性或信度,因其評估的分數多集中在較高分數的範圍內.因此是由於他們所施測的族群不同,得到的分數也會不一樣,其他的可能會很高或者低的分數呈現出來.
Kappa 一致性係數（Kappa Coefficient of Agreement, K）是屬於無母數統計的範疇，適用於類別尺度變數，主要目的是探討不同測量者對一組不同物件分類結果的一致狀況。Kappa 一致性統計量的形成有一基本假設：判斷者在有意識的情況下所進行的判斷，其一致性不應低於隨機指派的結果。
慢性中風個案動態步態指標之信效度
Reliability and Validity of the Dynamic Gait Index in Persons with Chronic Stroke
論文各部分之重點：
前言：
I為何需要從事此研究（還有哪些問題未解決？其重要性為何？或此問題未解決，將導致哪些問題？）
大多數患者中風後，仍然在移動和步態活動中有平衡的問題；而這些問題通常在急性後期出現，以及限制一般功能和參與日常活動。因此在計畫治療和評估結果時，平衡的信賴程度和準確度是最基礎的。尤其中風病患評估動態平衡時非常重要的因素，因為他們時常在移動時跌倒。
雖然中風病患在動、靜態站姿上有良好的平衡表現以及感覺輸入的改變，但是在步態活動時評估個案的動態平衡仍然缺少的。Shumwa-Cook和Woollacout共同發展動態步態指標DGI以便評估老年人在步態活動的功能穩定性以及跌到的危機。
II研究目的（be specific，作者欲解決哪些問題？）
中風病患多數擁有感覺和神經動作組織性的問題以及動作中衝量的控制困難。DGI
此次的研究目的是要評量中風病患之施測者間信度(interrater reliability)、再測信度(test-retest
reiablity)以及同時建構效度(concurrent construct validity)。
方法（※需說明作者「如何設計研究」以驗證各「研究目的」）：
樣本：
25位中風病患，其中18位為男生和7位為女生。研究的平均年齡±標準誤差為61.6±13.1年(範圍26.6-75.4年)以及平均發病時間為4.2±7.5年(範圍0.5-35.3年)。19位病患在屋外是使用行走輔助器材，但只有6位在家裡使用。9位為左側偏癱,14位為右側偏癱。3為病患有使用三腳拐當作行動輔助器材以及剩餘的病患則是使用拐扙。所有病人都必須經過評量BI來判斷其功能獨立性，以及可以依照和明白治療師的指令。
※ 2位治療師(施測者1,JJ;施測者2,DC),兩者在評估神經性問題的病患都擁有十年的經驗以及曾有在其他病患族群使用DGI。
程序：
評估（測量）工具：
DGI含8個4點(0-1-2-3)量尺項目，滿分為24分， 8個行走項目為:（1）行走20呎；（2）改變行走速度，快變慢；（3）行走時同時頭轉向左和右；（4）行走時同時頭向上和向下；（5）行走時同時180度向後轉停；（6）行走時同時跨越鞋盒；（7）行走時同時繞過鞋盒；（8）上下4個樓梯。老年人若分數等於或小於19分者，有較高的機會發生跌倒。DGI總分數越低表示平衡失調越嚴重。
Berg平衡量表(Berg Balance Scale ,BBS)
BBS原先用來評估老年人的平衡能力以及跌到的危機率。其中Berg平衡量表共評估14 項功能性活動，且要求個案在一個姿勢下維持其平衡和同時項目的困難增加。BBS裡面特定的項目要素有相似的步態規定，如無支持獨立站姿和弓箭步站姿。其他的要素如從坐到站和無支持站姿。每項活動之評分為0 至4 分(最好表現為56 分)。BBS是ㄧ個證據充分以及在老年人、多發性硬化症和中風病患中擁有高的心理測量學特性。以中風病患為列，其研究的施測者間和施測者內信度顯示分數分別為.97和.98。分數愈高者表示受試者之平衡能力愈好，但分數為小於或等於44表示有很高的機率跌倒。
特定活動平衡信心量表(activities—specific balance confidence scale，ABC scale) ABC為16項自我報告問卷，詢問病患自己對於在日常生活活動上的平衡表現給予數值刻度(範圍0-100)評分。分數為0顯示在活動表現上為無信賴，分數100則表示完全信賴。Botner和其他專家表示在中風病患研究中，ABC有高的再測信度以及輕度到中度的線性相關係數與BBS和步態速度(分別為r =.36 ,r =.48)。在前庭失能病患中，介於DGI和ABC總分有中度的相關係數(r =.58)。
行走時間測量Timed walking test此項測驗個案需要在適當的速度下，在限定的時間內行走10公尺。行走時間測量發現在中風病患中有高的再測信度。步態速度反映出行走能力的要素以及用於評估神經性失能的個案的移動能力。
計時起走測驗(Timed Up and Go Test; TUG)
TUG為一簡易功能性的測驗，評估個案在行定的時間內起立、行走三公尺、向後轉身以及再次的坐下。此項測驗在中風病人中有良好的再測信度。
資料分析：各研究目的，以何種統計驗證之。
信度之中有兩種:施測者間信度(interrater reliability)和再測信度(test-retest
reliability)，是由組內相關系數-模式2，1(intraclass correlation coefficient , model 2 , 1)
計算出來。基於先前的參考文獻，他們建議組內相關系數的分數介於0.8-1.0顯示出良好的信度，0.6-0.8為可接受，0.4-0.6為中等以及少於0.4為較差。
同時建構效度(concurrent construct validity)
我們假設DGI與BBS、ABC有中度正相關；與行走時間測驗、TUG有中度的負相關
1.信度之間有2項種類1.test-retest & interrater reliability 之間的關連性,是否會是因2者分數高是否其關連性高,代表其信度越高.
老師的回答:基本上信度為看評量工具的穩定性,因此可以單獨分開解釋這兩者的功能:1.test-retest為看評估工具的經過再測後其穩定性是否會一樣.2.interrater reliability 則為不同施測者在施測工具後其兩者的一致性.
2.如何將評估工具發展成較客觀性的?需要的步驟以及考慮的面向為何?
老師的回答:考慮你要評估的目的是什麼!考慮其差別(沒聽得很清楚)以及測量的內容,以便變成更簡單和容易操作的評估工具.
3.Given a normal distribution and no change,68%of the time an observed score will fall within 1SE of measurement of a person 's true score, and 95%of the time it should fall within 1.96SE of measurement of the true score.
深藍色區域是距平均值小於一個標準差之內的數值範圍。在常態分佈中，此範圍所佔比率為全部數值之 68%。根據常態分佈，兩個標準差之內（藍，棕）的比率合起來為 95%。根據常態分佈，三個標準差之內（深藍，橙，黃）的比率合起來為 99% 。
常態分佈/常態分布/常態分配(Normal Distribution)又稱高斯分佈(Gauss Distribution)，一般研究變數常會呈現常態分佈或近似常態分佈，如身高、體重、收入、支出、意見程度、評量誤差(error of measurement)。常態分佈的特徵是以數值資料平均值(μ )為中心，分佈曲線呈鈴形(bell shape)，中心點位置其數值出現的頻率(次數)最多，離中心點位置左右(可延伸到無窮大± ∞ )的數值出現頻率漸少，曲線左右對稱，即大於平均值和小於平均值的出現頻率相等。
4.They used K coefficient values for the item analyses, which may have been influenced by the low variability of their subjects who were skewed toward the higher end of the scale.
老師的回答:利用kappa coefficient 去做個別項目一致性分析,較低的差異度代表有高的一致性或信度,因其評估的分數多集中在較高分數的範圍內.因此是由於他們所施測的族群不同,得到的分數也會不一樣,其他的可能會很高或者低的分數呈現出來.
Kappa 一致性係數（Kappa Coefficient of Agreement, K）是屬於無母數統計的範疇，適用於類別尺度變數，主要目的是探討不同測量者對一組不同物件分類結果的一致狀況。Kappa 一致性統計量的形成有一基本假設：判斷者在有意識的情況下所進行的判斷，其一致性不應低於隨機指派的結果。
慢性中風個案動態步態指標之信效度
Reliability and Validity of the Dynamic Gait Index in Persons with Chronic Stroke
論文各部分之重點：
前言：
I為何需要從事此研究（還有哪些問題未解決？其重要性為何？或此問題未解決，將導致哪些問題？）
大多數患者中風後，仍然在移動和步態活動中有平衡的問題；而這些問題通常在急性後期出現，以及限制一般功能和參與日常活動。因此在計畫治療和評估結果時，平衡的信賴程度和準確度是最基礎的。尤其中風病患評估動態平衡時非常重要的因素，因為他們時常在移動時跌倒。
雖然中風病患在動、靜態站姿上有良好的平衡表現以及感覺輸入的改變，但是在步態活動時評估個案的動態平衡仍然缺少的。Shumwa-Cook和Woollacout共同發展動態步態指標DGI以便評估老年人在步態活動的功能穩定性以及跌到的危機。
II研究目的（be specific，作者欲解決哪些問題？）
中風病患多數擁有感覺和神經動作組織性的問題以及動作中衝量的控制困難。DGI
此次的研究目的是要評量中風病患之施測者間信度(interrater reliability)、再測信度(test-retest
reiablity)以及同時建構效度(concurrent construct validity)。
方法（※需說明作者「如何設計研究」以驗證各「研究目的」）：
樣本：
25位中風病患，其中18位為男生和7位為女生。研究的平均年齡±標準誤差為61.6±13.1年(範圍26.6-75.4年)以及平均發病時間為4.2±7.5年(範圍0.5-35.3年)。19位病患在屋外是使用行走輔助器材，但只有6位在家裡使用。9位為左側偏癱,14位為右側偏癱。3為病患有使用三腳拐當作行動輔助器材以及剩餘的病患則是使用拐扙。所有病人都必須經過評量BI來判斷其功能獨立性，以及可以依照和明白治療師的指令。
※ 2位治療師(施測者1,JJ;施測者2,DC),兩者在評估神經性問題的病患都擁有十年的經驗以及曾有在其他病患族群使用DGI。
程序：
評估（測量）工具：
DGI含8個4點(0-1-2-3)量尺項目，滿分為24分， 8個行走項目為:（1）行走20呎；（2）改變行走速度，快變慢；（3）行走時同時頭轉向左和右；（4）行走時同時頭向上和向下；（5）行走時同時180度向後轉停；（6）行走時同時跨越鞋盒；（7）行走時同時繞過鞋盒；（8）上下4個樓梯。老年人若分數等於或小於19分者，有較高的機會發生跌倒。DGI總分數越低表示平衡失調越嚴重。
Berg平衡量表(Berg Balance Scale ,BBS)
BBS原先用來評估老年人的平衡能力以及跌到的危機率。其中Berg平衡量表共評估14 項功能性活動，且要求個案在一個姿勢下維持其平衡和同時項目的困難增加。BBS裡面特定的項目要素有相似的步態規定，如無支持獨立站姿和弓箭步站姿。其他的要素如從坐到站和無支持站姿。每項活動之評分為0 至4 分(最好表現為56 分)。BBS是ㄧ個證據充分以及在老年人、多發性硬化症和中風病患中擁有高的心理測量學特性。以中風病患為列，其研究的施測者間和施測者內信度顯示分數分別為.97和.98。分數愈高者表示受試者之平衡能力愈好，但分數為小於或等於44表示有很高的機率跌倒。
特定活動平衡信心量表(activities—specific balance confidence scale，ABC scale) ABC為16項自我報告問卷，詢問病患自己對於在日常生活活動上的平衡表現給予數值刻度(範圍0-100)評分。分數為0顯示在活動表現上為無信賴，分數100則表示完全信賴。Botner和其他專家表示在中風病患研究中，ABC有高的再測信度以及輕度到中度的線性相關係數與BBS和步態速度(分別為r =.36 ,r =.48)。在前庭失能病患中，介於DGI和ABC總分有中度的相關係數(r =.58)。
行走時間測量Timed walking test此項測驗個案需要在適當的速度下，在限定的時間內行走10公尺。行走時間測量發現在中風病患中有高的再測信度。步態速度反映出行走能力的要素以及用於評估神經性失能的個案的移動能力。
計時起走測驗(Timed Up and Go Test; TUG)
TUG為一簡易功能性的測驗，評估個案在行定的時間內起立、行走三公尺、向後轉身以及再次的坐下。此項測驗在中風病人中有良好的再測信度。
資料分析：各研究目的，以何種統計驗證之。
信度之中有兩種:施測者間信度(interrater reliability)和再測信度(test-retest
reliability)，是由組內相關系數-模式2，1(intraclass correlation coefficient , model 2 , 1)
計算出來。基於先前的參考文獻，他們建議組內相關系數的分數介於0.8-1.0顯示出良好的信度，0.6-0.8為可接受，0.4-0.6為中等以及少於0.4為較差。
同時建構效度(concurrent construct validity)
我們假設DGI與BBS、ABC有中度正相關；與行走時間測驗、TUG有中度的負相關
11/21 Far Eastern Hospital
Mission:
1.Today just have received 2 papers of BIB and ADL,because the Wednesday is the day of group therapy for stroke people!And the data of ICD cost one hour to figure out from thier computer!
The step are :1.病患就診查詢 2.任一病患 3.輸入病歷號碼 4.選擇2351 (復健門診)5.關閉F12 6.ICD碼 or with the step 5 we also can check the date that they begin come to rehabilitation!
2.Participant in the course about Introduction to memory by 顏乃欣主任!
1.Today just have received 2 papers of BIB and ADL,because the Wednesday is the day of group therapy for stroke people!And the data of ICD cost one hour to figure out from thier computer!
The step are :1.病患就診查詢 2.任一病患 3.輸入病歷號碼 4.選擇2351 (復健門診)5.關閉F12 6.ICD碼 or with the step 5 we also can check the date that they begin come to rehabilitation!
2.Participant in the course about Introduction to memory by 顏乃欣主任!
2007年11月20日 星期二
intraclass correlation coefficient（組內相關係數）
intraclass correlation coefficient（組內相關係數）
Explain the use of intraclass correlation in relation to inter-rater reliability.
組內相關係數用來測量施測者間信度。ICC可被表示為組間的變異和總變異的比值。Intraclass correlation (ICC) is used to measure inter-rater reliability. ICC may be conceptualized as the ratio of between-groups variance to total variance.
資料建立：ICC的目的是用來評論施測者間的影響和受測族群間的關係。Data setup:The purpose of ICC is to assess the inter-rater (column) effect in relation to the grouping (row) effect, using two-way ANOVA.
解釋：當受測目標間沒有差異時，ICC的值會接近1，顯示總變異全來自受測者自身的不同。Interpretation: ICC will approach 1.0 when there is no variance within targets, indicating total variation in measurements on the Likert scale is due solely to the target (ex., subject, neighborhood) variable.
模型：ICC會隨著以下幾種原因而改變：評估者是包括所有施測者或是由可能的施測者中隨機抽來的；受測者是否包括所有受測者或是只是由隨機抽樣選出；信度的驗證是建立在個別的評估者上或是所有評者的平均。Models: ICC varies depending on whether the judges are all judges of interest or are conceived as a random sample of possible judges, and whether all targets are rated or only a random sample, and whether reliability is to be measured based on individual ratings or mean ratings of all judges. Shrout and Fleiss (1979).
ICC公式由來：令A代表個案真實的改變，令B代表由施測者間信度不良所造成的誤差，則ICC=A/(A+B)。B是個案間差異(一群施測者施測同樣個案時所給的不同分數)的均方(一組數的平方的平均值)，由ANOVA計算。個案間變異的均方則為(A的k倍+B)Derivation of the ICC formula, following Ebel (1951: 409-411): Let A be the true variance in subjects' ratings due to the normal expectation that different subjects will have true different scores on the rating variable. Let B be the error variance in subjects' ratings attributable to inter-rater unreliability. The intent of ICC is to form the ratio, ICC = A/(A + B). B is simply the mean-square estimate of within-subjects variance (variance in the ratings for a given subject by a group of raters), computed in ANOVA. The mean-square estimate of between-subjects variance equals k times A (the true component) plus B (the inter-rater error component), since each mean contains a true component and an error component.
將B用MSwithin、A用(MSbetween –B)/k表示(因為MSbetween = kA + B)，則公式就可化為：
ICC = rI = (MSbetween - MSwithin)/( MSbetween + [k - 1] MSwithin)。
此時MSbtween 反應了不同的個案的真實分數也就不同。MSwithin則表示由施測者間的誤差造成的分數不同。k代表了(施測者人數/受測者人數）。
Given B = MSwithin, and given MSbetween = kA + B, substituting these equalities into the intended equation (ICC = A/[A+B]), the equation for ICC reduces to the formula for the most-used version of intraclass correlation (Haggard, 1958: 60) : ICC = rI = (MSbetween - MSwithin)/( MSbetween + [k - 1] MSwithin) where MSbetween is the mean-square estimate of between-subjects variance, reflecting the normal expectation that different subjects will have true different scores on the rating variable
MSwithin is the mean-square estimate of within-subjects variance, or error attributed to inter-rater unreliability in rating the same person or target (row). k is the number of raters/ratings per target (person, neighborhood, etc.) = number of columns.
當MSbetween 等於MSwithin時，ICC等於0，顯示此時分組方式不會對ICC造成影響。
ICC is 0 when within-groups variance equals between-groups variance, indicative of the grouping variable having no effect.
http://www2.chass.ncsu.edu/garson/pa765/reliab.htm#intraclass
(ICC)= 高≥ 0.8> 中≥ 0.6>低； Spearman’s ρ/Pearson’s γ= 高≥0.9>中≥0.7>低
(Reference：Volume 36 * Number 2 (Supplement) * April-June 2001 )
Explain the use of intraclass correlation in relation to inter-rater reliability.
組內相關係數用來測量施測者間信度。ICC可被表示為組間的變異和總變異的比值。Intraclass correlation (ICC) is used to measure inter-rater reliability. ICC may be conceptualized as the ratio of between-groups variance to total variance.
資料建立：ICC的目的是用來評論施測者間的影響和受測族群間的關係。Data setup:The purpose of ICC is to assess the inter-rater (column) effect in relation to the grouping (row) effect, using two-way ANOVA.
解釋：當受測目標間沒有差異時，ICC的值會接近1，顯示總變異全來自受測者自身的不同。Interpretation: ICC will approach 1.0 when there is no variance within targets, indicating total variation in measurements on the Likert scale is due solely to the target (ex., subject, neighborhood) variable.
模型：ICC會隨著以下幾種原因而改變：評估者是包括所有施測者或是由可能的施測者中隨機抽來的；受測者是否包括所有受測者或是只是由隨機抽樣選出；信度的驗證是建立在個別的評估者上或是所有評者的平均。Models: ICC varies depending on whether the judges are all judges of interest or are conceived as a random sample of possible judges, and whether all targets are rated or only a random sample, and whether reliability is to be measured based on individual ratings or mean ratings of all judges. Shrout and Fleiss (1979).
ICC公式由來：令A代表個案真實的改變，令B代表由施測者間信度不良所造成的誤差，則ICC=A/(A+B)。B是個案間差異(一群施測者施測同樣個案時所給的不同分數)的均方(一組數的平方的平均值)，由ANOVA計算。個案間變異的均方則為(A的k倍+B)Derivation of the ICC formula, following Ebel (1951: 409-411): Let A be the true variance in subjects' ratings due to the normal expectation that different subjects will have true different scores on the rating variable. Let B be the error variance in subjects' ratings attributable to inter-rater unreliability. The intent of ICC is to form the ratio, ICC = A/(A + B). B is simply the mean-square estimate of within-subjects variance (variance in the ratings for a given subject by a group of raters), computed in ANOVA. The mean-square estimate of between-subjects variance equals k times A (the true component) plus B (the inter-rater error component), since each mean contains a true component and an error component.
將B用MSwithin、A用(MSbetween –B)/k表示(因為MSbetween = kA + B)，則公式就可化為：
ICC = rI = (MSbetween - MSwithin)/( MSbetween + [k - 1] MSwithin)。
此時MSbtween 反應了不同的個案的真實分數也就不同。MSwithin則表示由施測者間的誤差造成的分數不同。k代表了(施測者人數/受測者人數）。
Given B = MSwithin, and given MSbetween = kA + B, substituting these equalities into the intended equation (ICC = A/[A+B]), the equation for ICC reduces to the formula for the most-used version of intraclass correlation (Haggard, 1958: 60) : ICC = rI = (MSbetween - MSwithin)/( MSbetween + [k - 1] MSwithin) where MSbetween is the mean-square estimate of between-subjects variance, reflecting the normal expectation that different subjects will have true different scores on the rating variable
MSwithin is the mean-square estimate of within-subjects variance, or error attributed to inter-rater unreliability in rating the same person or target (row). k is the number of raters/ratings per target (person, neighborhood, etc.) = number of columns.
當MSbetween 等於MSwithin時，ICC等於0，顯示此時分組方式不會對ICC造成影響。
ICC is 0 when within-groups variance equals between-groups variance, indicative of the grouping variable having no effect.
http://www2.chass.ncsu.edu/garson/pa765/reliab.htm#intraclass
(ICC)= 高≥ 0.8> 中≥ 0.6>低； Spearman’s ρ/Pearson’s γ= 高≥0.9>中≥0.7>低
(Reference：Volume 36 * Number 2 (Supplement) * April-June 2001 )
11/20 NTUH & Reading
Mission:
1.Today just finished one paper of BADL and BIB!
2.Read new paper that title is Reliability and validity of the Dynamic Gait Index in persons with chronic stroke!
3.Finding and recheck the number of ICD9 from the old files,but didnt have anyone matched with it.
4.Find out the meaning of the statistical method ,such as Bland and Altman method,concurrent construct validity!
The Bland & Altman plot (Bland & Altman, 1986 and 1999) is a statistical method to compare two measurements techniques. In this graphical method the differences (or alternatively the ratios) between the two techniques are plotted against the averages of the two techniques.
The Bland & Altman plot is useful to reveal a relationship between the differences and the averages (examples 1 & 2), to look for any systematic bias (example 3) and to identify possible outliers. If there is a consistent bias, it can be adjusted for by subtracting the mean difference from the new method.
If the differences within mean ± 1.96 SD are not clinically important, the two methods may be used interchangeably
Repeatability
The Bland and Altman plot may also be used to assess the repeatability of a method by comparing repeated measurements using one single method on a series of subjects. The graph can then also be used to check whether the variability or precision of a method is related to the size of the characteristic being measured.
Since for the repeated measurements the same method is used, the mean difference should be zero. Therefore the Coefficient of Repeatability (CR) can be calculated as 1.96 (or 2) times the standard deviations of the differences between the two measurements (d2 and d1):
This coefficient can be read from the Bland & Altman plot, but can also be calculated using Summary statistics. E.g. if the names of the variables for 2 repeated measurements for FSH concentration are FSH1 and FSH2, then you define a new variable as FSH2-FSH1 and calculate the summary statistics for it. By multiplying the calculated standard deviation by 2 you obtain the coefficient of repeatability.
1.Today just finished one paper of BADL and BIB!
2.Read new paper that title is Reliability and validity of the Dynamic Gait Index in persons with chronic stroke!
3.Finding and recheck the number of ICD9 from the old files,but didnt have anyone matched with it.
4.Find out the meaning of the statistical method ,such as Bland and Altman method,concurrent construct validity!
The Bland & Altman plot (Bland & Altman, 1986 and 1999) is a statistical method to compare two measurements techniques. In this graphical method the differences (or alternatively the ratios) between the two techniques are plotted against the averages of the two techniques.
The Bland & Altman plot is useful to reveal a relationship between the differences and the averages (examples 1 & 2), to look for any systematic bias (example 3) and to identify possible outliers. If there is a consistent bias, it can be adjusted for by subtracting the mean difference from the new method.
If the differences within mean ± 1.96 SD are not clinically important, the two methods may be used interchangeably
Repeatability
The Bland and Altman plot may also be used to assess the repeatability of a method by comparing repeated measurements using one single method on a series of subjects. The graph can then also be used to check whether the variability or precision of a method is related to the size of the characteristic being measured.
Since for the repeated measurements the same method is used, the mean difference should be zero. Therefore the Coefficient of Repeatability (CR) can be calculated as 1.96 (or 2) times the standard deviations of the differences between the two measurements (d2 and d1):
This coefficient can be read from the Bland & Altman plot, but can also be calculated using Summary statistics. E.g. if the names of the variables for 2 repeated measurements for FSH concentration are FSH1 and FSH2, then you define a new variable as FSH2-FSH1 and calculate the summary statistics for it. By multiplying the calculated standard deviation by 2 you obtain the coefficient of repeatability.
2007年11月19日 星期一
Validity (效度) & Reliability(信度)
Validity (效度) has three kinds:
1.content validity(內容效度):the suitable degree of the assessment's content,such as the special characteristic is it suitable to the element of the assessment!
2.Criterion-related validity(效標關連效度):concurrent valididy & predictive validity
3.construct validity(建構效度):
Reliability(信度)has four types:
1.inter-rater reliability(施測者間信度):
2.test-retest reliability(再測信度):intra-rater reliability(施測者內信度):
3.split-half reliability(折半信度):
4.alternative form reliability(複本信度):
1.content validity(內容效度):the suitable degree of the assessment's content,such as the special characteristic is it suitable to the element of the assessment!
2.Criterion-related validity(效標關連效度):concurrent valididy & predictive validity
3.construct validity(建構效度):
Reliability(信度)has four types:
1.inter-rater reliability(施測者間信度):
2.test-retest reliability(再測信度):intra-rater reliability(施測者內信度):
3.split-half reliability(折半信度):
4.alternative form reliability(複本信度):
2007年11月18日 星期日
11/19 Key in data & revision the paper
Mission:
1.Key in data & revision the paper!
2.Arrange the definition of Validity and Reliability.
1.Key in data & revision the paper!
2.Arrange the definition of Validity and Reliability.
2007年11月15日 星期四
11/16 NTUH clinical assessment
Mission:
1.Recently the functional level of p't are so severe to let us testing ,such as OA,body weakness and others..
2. today i have finished 4ADL and 1 BIB
1.Recently the functional level of p't are so severe to let us testing ,such as OA,body weakness and others..
2. today i have finished 4ADL and 1 BIB
11/15 NTUH clinical assessment
Mission:
1. Today morning i have finished 3BIB and 4 ADL, afternoon have 2BIB and 3ADL.
1. Today morning i have finished 3BIB and 4 ADL, afternoon have 2BIB and 3ADL.
2007年11月14日 星期三
11/14 Key in the data base
Mission:
1.Today have a course about Brain function and brain pathology that presented by 葉炳強教授.
2.Key in the databases.
1.Today have a course about Brain function and brain pathology that presented by 葉炳強教授.
2.Key in the databases.
11/13 Far eastern Memorial Hospital
Mission:
1.Today i have finished 18 papers (ADL & BIB).
2.Thusday(11/15) have 2 p't need to assess,930am and 11am!
3.Next week (11/21)wednesday go to Far eastern Hospital again!
1.Today i have finished 18 papers (ADL & BIB).
2.Thusday(11/15) have 2 p't need to assess,930am and 11am!
3.Next week (11/21)wednesday go to Far eastern Hospital again!
2007年11月12日 星期一
11/12 Key in the data base & NTUH clinical assessment
Mission:
1.Today i have finished 4 ADL in NTUH clinical field, because new case are too weak to have an assessment!!
2.Tomorrow morning need to disscuss with Sir about the latest paper!
3.Tomorrow 11/13 afternoon and night will go to Far eastern Memorial Hospital!
1.Today i have finished 4 ADL in NTUH clinical field, because new case are too weak to have an assessment!!
2.Tomorrow morning need to disscuss with Sir about the latest paper!
3.Tomorrow 11/13 afternoon and night will go to Far eastern Memorial Hospital!
2007年11月11日 星期日
11/9 Far Eastern Memorial hospital
Mission:
1.Today I have finished 7 papers(4 ADL & 3 BIB).
2.Next Tuesday (11/13)afternoon will go there again.
3.There(PT) have a group activity for CVA p't, so the department of OT will just have few CVA p't.
1.Today I have finished 7 papers(4 ADL & 3 BIB).
2.Next Tuesday (11/13)afternoon will go there again.
3.There(PT) have a group activity for CVA p't, so the department of OT will just have few CVA p't.
2007年11月7日 星期三
2007年11月6日 星期二
11/6 NTUH clinical assessment & Check up
As the tiltle,
1.Today have finished 3 BIB and 1 ADL.
2. And also finished the first check up list (3pieces).
1.Today have finished 3 BIB and 1 ADL.
2. And also finished the first check up list (3pieces).
2007年11月5日 星期一
2007年11月2日 星期五
2007年11月1日 星期四
11/1 Far Eastern Hospital
Mission:
1.At Far Eastern Hospital have finished ADL and BIB each 5.
2.Next Friday(11/9) will plan to go there for whole day.
3.This week Saturday need to come here work for half day to key in data and tomorrow whole also need to key in data whole day.
Question:
1.The person who have ataxia also need to assess that also have difference in balance function.
1.At Far Eastern Hospital have finished ADL and BIB each 5.
2.Next Friday(11/9) will plan to go there for whole day.
3.This week Saturday need to come here work for half day to key in data and tomorrow whole also need to key in data whole day.
Question:
1.The person who have ataxia also need to assess that also have difference in balance function.
訂閱：
文章 (Atom)