係我 聽日考試 遲D先解答 但講真我UG唔係Stat 冇聽過呢兩樣野 有冇多D background information
我本來都唔知有呢啲嘢(可能因為我未上design and anal of experiments啦) 係之前係個網度見到啲infographic有講,所以先查過少少呢啲資料,感覺係psyc人用多
個巴打啲terminology好似有少少nonstandard嘅... 簡單啲黎講就係要estimate (mu1-mu2)/sigma 係咩(assume normality啦應該係) 有幾個point estimate,一個叫d,一個叫g,一個叫大楷delta
個巴打用緊嘅係g,減咗兩個xbar再除pooled sd,不過出嚟個結果會bias所以佢會乘返嗰個數去correct
至於點解會有兩個唔同嘅ci我就唔知
我都無聽過
不過個巴打好似想從一個estimate搵另一個estimate
從一個estimate既ci搵另一個estimate既ci
無聽過 x3
p.s. 我有做ALE meta analysis
其實你喺第四個冇聽過
其實我係做psy meta analysis
但我都唔係好識呢類stat formula
我只知 SMD X 岩岩講果揪野就會= g, vice versa
但我唔明點解佢地既CI照樣咁做就唔得
Google搵到D咁既野 https://www.meta-analysis.com/downloads/Meta-analysis%20Effect%20sizes%20based%20on%20means.pdf
應該解決到你既問題
Stat既野真係學極都學唔熟,過幾年又有新既least square出黎應用