114 年 國立中山大學企業管理學系碩士甲班甲組《商用統計學》
第 1 題
A sample of 20 packages of ground pork (in pounds) is listed in ascending order as follows:
0.70 0.75 0.80 0.84 0.86 0.89 0.92 0.95 0.98 1.01
1.01 1.07 1.10 1.12 1.15 1.18 1.22 1.27 1.30 1.34
Based on the data above, which of the following statements is/are correct?
(A) The mean of the sample is approximately 1.02 pounds.
(B) The standard deviation of the sample is approximately 0.16 pounds.
(C) The 40th percentile is 1.30 pounds.
(D) The variance of the sample is approximately 0.03 pounds.
(E) The upper quartile is 0.80 pounds.
登入後即可作答並保存紀錄。
本題考驗樣本資料的敘述統計量計算與解釋,包含平均數、標準差、變異數、百分位數與四分位數。
首先,計算樣本的平均數。樣本共有 筆資料。
將所有資料加總:
因此,選項 (A) 樣本平均數約為 1.02 磅,是正確的。
接著,計算樣本標準差。首先計算樣本變異數。
計算各資料點與平均數的差的平方:
第 2 題
A fair six-sided dice is rolled three times. Based on classical probability principles, which of the following statements is/are correct?
(A) The probability of rolling at least one 6 is 1-125/216.
(B) The probability of rolling three even numbers is 1/8.
(C) The probability of rolling a total of 18 is 1/216.
(D) The probability of rolling exactly two 6 is 5/216.
(E) The probability of rolling a total greater than 4 is 215/216.
登入後即可作答並保存紀錄。
本題考驗獨立事件的機率計算,特別是關於骰子投擲的機率問題。由於骰子是公平的,每一面出現的機率均為 1/6。
(A) 滾動至少一個 6 的機率:
這是計算「至少一」的機率問題,通常用「1 減去沒有一個 6 的機率」來計算。
每次滾動骰子出現 6 的機率是 ,出現非 6 的機率是 。
滾動三次骰子,三次都沒有出現 6 的機率是 。
因此,滾動至少一個 6 的機率是 。
選項 (A) 說機率是 ,這是正確的。
(B) 滾動三個偶數的機率:
偶數有 2, 4, 6,所以一次滾動出現偶數的機率是 。
滾動三次骰子,三次都是偶數的機率是 。
選項 (B) 說機率是 1/8,這是正確的。
(C) 滾動總和為 18 的機率:
骰子是六面骰,點數為 1 到 6。三次滾動的總和最大為 。
只有一種組合可以得到總和為 18,那就是三次都出現 6 (6, 6, 6)。
三次都出現 6 的機率是 。
選項 (C) 說機率是 1/216,這是正確的。
第 3 題
Which of the following descriptions of variables is/are INCORRECT?
(A) "Student ID number" is a nominal variable.
(B) "Bank account balance" is an interval variable.
(C) "Customer satisfaction rating (1 to 5)" is a ordinal variable.
(D) "Number of children in a household" is a ratio variable.
(E) "Type of transportation (car, bus, train)" is a categorical variable.
登入後即可作答並保存紀錄。
本題考驗對不同變數類型的理解,包含名目(nominal)、順序(ordinal)、區間(interval)和比例(ratio)變數,以及類別(categorical)變數。
(A) "Student ID number" (學號):學號通常是數字,但這些數字沒有數學意義,也不能進行加減乘除運算。它只是用來區分不同的學生。因此,學號是一個名目變數 (nominal variable)。此敘述是正確的。
(B) "Bank account balance" (銀行帳戶餘額):銀行帳戶餘額可以有絕對的零點(餘額為零表示沒有錢),並且餘額之間的差距是有意義的(例如 100 元與 200 元差 100 元,200 元與 300 元也差 100 元)。更重要的是,餘額可以進行比例運算(例如 200 元是 100 元的兩倍)。因此,銀行帳戶餘額是一個比例變數 (ratio variable),而不是區間變數 (interval variable)。區間變數的特點是沒有絕對的零點(例如攝氏溫度,0 度並沒有表示沒有溫度)。所以此敘述是錯誤的。
第 4 題
At a university, 15% of undergraduate students study abroad. Among the students who study abroad, 55% are female, while 45% of those who do not study abroad are female. Based on this information, which of the following statements is/are INCORRECT?
(A) The overall percentage of female undergraduate students is 48.00%.
(B) Given that an undergraduate student is female, the probability that she studies abroad is 12.98%.
(C) Given that an undergraduate student studies abroad, the probability that the student is male is 9.45%.
(D) The overall percentage of male undergraduate students is 53.50%.
(E) Given that an undergraduate student is male, the probability that he studies abroad is 6.75%.
登入後即可作答並保存紀錄。
核心觀念
本題考查條件機率、全機率與列聯表分析。
重要公式如下:
- 條件機率:
- 全體女性比例:
其中:
- :學生出國留學
- :學生未出國留學
- :學生為女性
- :學生為男性
題目給定:
因此:
解題方法
為方便計算,假設大學生總數為 人。
| 分類 | 出國留學 | 未出國留學 | 合計 |
|---|---|---|---|
| 女性 | |||
| 男性 | |||
| 合計 |
雖然人數出現小數,但比例計算完全有效。
選項分析
(A) The overall percentage of female undergraduate students is 48.00%.
全體女性比例為:
並非 ,因此 (A) 錯誤。
(B) Given that an undergraduate student is female, the probability that she studies abroad is 12.98%.
要求的是:
根據條件機率:
第 5 題
Which of the following is/are NOT discrete probability distributions?
(A) Poisson probability distribution
(B) Normal probability distribution
(C) Binomial probability distribution
(D) Exponential probability distribution
(E) Chi-square probability distribution
登入後即可作答並保存紀錄。
本題考驗對常見機率分布類型的辨識,特別是離散型 (discrete) 與連續型 (continuous) 機率分布的區別。
離散機率分布是指其隨機變數只能取有限個或可數無限個值的分布。
連續機率分布是指其隨機變數可以取一個連續區間內任意值的分布。
我們逐一檢視選項:
(A) Poisson probability distribution (卜瓦松分布):用於計算在固定時間或空間間隔內,某事件發生次數的機率。事件發生的次數是離散的整數(0, 1, 2, ...)。因此,卜瓦松分布是離散機率分布。
(B) Normal probability distribution (常態分布):用於描述許多自然現象,其隨機變數可以取任意實數值。例如身高、測量誤差等。常態分布的機率密度函數是定義在整個實數軸上,取值是連續的。因此,常態分布是連續機率分布。
(C) Binomial probability distribution (二項分布):用於計算在固定次數的獨立伯努利試驗中,某種結果(成功)發生的次數。
第 6 題
Which of the following statements about hypothesis testing is/are correct?
(A) Type I error occurs when the null hypothesis is rejected even though it is true.
(B) Type II error occurs when the null hypothesis is not rejected even though it is false.
(C) The power of a test is the probability of rejecting the null hypothesis when it is false.
(D) Confidence limit refers to the range within which the true population parameter is expected to fall.
(E) Type III error occurs when the null hypothesis is correctly rejected, but for the wrong reason.
登入後即可作答並保存紀錄。
本題考驗對假設檢定基本概念的理解,包括第一類錯誤、第二類錯誤、檢定力以及信賴區間的定義。
(A) 第一類錯誤 (Type I error, ):當虛無假設 () 為真時,卻拒絕了虛無假設。這個敘述是正確的。
(B) 第二類錯誤 (Type II error, ):當虛無假設 () 為偽時,卻未能拒絕(接受)虛無假設。這個敘述是正確的。
(C) 檢定力 (Power of a test, ):當虛無假設 () 為偽時,能夠正確地拒絕虛無假設的機率。這個敘述是正確的。
(D) 信賴區間 (Confidence interval):信賴區間是用來估計母體參數的範圍。它是一個區間,我們有某個信賴水準(例如 95%)相信母體參數落在此區間內。這個敘述是正確的。
第 7 題
Customers arrive at a service desk randomly and independently. The probability of an arrival is the same for any interval of equal length. The average time interval between customer arrivals is 2 minutes. Which of the following statements is/are correct?
(A) The probability that no customers will arrive in the next 4 minutes is .
(B) The probability that exactly 2 customers will arrive in the next 6 minutes is .
(C) The average number of customers arriving in the next 10 minutes is 5.
(D) The standard deviation of the arrival rate per 10 minutes is 5.
(E) The average number of customers arriving in the next 8 minutes is 4.
登入後即可作答並保存紀錄。
本題考驗對 Poisson 過程的理解。題目描述了顧客到達的隨機性和獨立性,且在等長的區間內到達的機率相同,這符合 Poisson 過程的假設。
已知資訊:
平均時間間隔 (average time interval) 分鐘。
這表示平均每 2 分鐘有 1 位顧客到達。
因此,平均到達率 (average arrival rate) 位顧客/分鐘。
Poisson 分布的機率質量函數為 ,其中 是在時間 內到達的顧客數, 是平均到達率, 是在時間 內的平均到達數。
我們來逐一檢視選項:
(A) 在接下來的 4 分鐘內沒有顧客到達的機率。
時間 分鐘。
在 4 分鐘內的平均到達數為 。
沒有顧客到達的機率,即 :
。
選項 (A) 說機率是 ,這是正確的。
(B) 在接下來的 6 分鐘內恰好有 2 位顧客到達的機率。
時間 分鐘。
在 6 分鐘內的平均到達數為 。
恰好有 2 位顧客到達的機率,即 :
第 8 題
Suppose X and Y are two random variables. Which of the following statements about correlation coefficient and covariance is/are correct?
(A) The correlation coefficient between X and Y is always non-negative.
(B) If the covariance between X and Y is zero, then X and Y are independent.
(C) The covariance between X and Y is equal to the product of their standard deviations and the correlation coefficient.
(D) A correlation coefficient of +1 indicates a perfect positive linear relationship between X and Y.
(E) The covariance between X and Y is always greater than or equal to zero.
登入後即可作答並保存紀錄。
本題考驗對相關係數 (correlation coefficient) 和共變異數 (covariance) 的基本性質的理解。
我們逐一檢視選項:
(A) 相關係數 () 的值介於 -1 到 +1 之間。它可以是負值、正值或零。因此,相關係數不一定是正數。例如,如果 Y 隨著 X 的增加而減少,相關係數就會是負的。
所以,選項 (A)「相關係數永遠為非負值」是錯誤的。
(B) 如果兩個隨機變數的共變異數為零,這意味著它們之間沒有線性關係。然而,這並不保證它們是獨立的。獨立性比線性關係更強。可能存在非線性關係,使得共變異數為零,但變數之間並非獨立。例如,令 X 在 [-1, 0, 1] 上等可能,Y = 。則 , 。。
第 9 題
Suppose X is a continuous random variable that follows a uniform distribution on the interval [a,b]. Which of the following statements about the uniform distribution is/are correct?
(A) The probability density function (pdf) of X is constant over the interval [a,b].
(B) The cumulative distribution function (cdf) of X increases linearly from 0 to 1 over the interval [a,b].
(C) The expected value of X is the midpoint of a and b.
(D) The range of X is equal to the difference between b and a.
(E) The probability that X falls outside the interval [a,b] is greater than zero.
登入後即可作答並保存紀錄。
本題考驗對連續均勻分布 (Continuous Uniform Distribution) 的性質的理解。
對於一個在區間 上服從連續均勻分布的隨機變數 X,其機率密度函數 (pdf) 為:
其累積分布函數 (cdf) 為:
期望值 (Expected Value, Mean) 為:
變異數 (Variance) 為:
現在我們逐一檢視選項:
(A) 機率密度函數 (pdf) 在區間 上是常數。
根據定義, 在 時為常數。此敘述是正確的。
第 10 題
A researcher repeatedly draws random samples of size n from a population with mean and standard deviation . Which of the following statements about the sampling distribution of the sample mean is/are correct?
(A) The sampling distribution of is always normal, regardless of the sample size n.
(B) The standard deviation of the sampling distribution of decreases as the sample size n increases.
(C) The mean of the sampling distribution of is equal to .
(D) The sampling distribution of has a variance equal to .
(E) The shape of the sampling distribution of depends only on the population distribution.
登入後即可作答並保存紀錄。
本題考驗對中央極限定理 (Central Limit Theorem, CLT) 以及樣本平均數抽樣分布性質的理解。
假設母體有一個均值 和標準差 。我們從這個母體中抽取樣本,樣本大小為 。
我們逐一檢視選項:
(A) 抽樣分布的形狀:
中央極限定理指出,如果母體分布是任意的,但樣本大小 足夠大(通常 ),那麼樣本平均數 的抽樣分布近似於常態分布。
如果母體本身就是常態分布,那麼無論樣本大小 如何, 的抽樣分布都是常態分布。
但是,如果母體不是常態分布,且樣本大小 不足夠大,那麼 的抽樣分布就不一定是常態分布。
因此,選項 (A)「抽樣分布永遠是常態分布,不論樣本大小 如何」是錯誤的。
(B) 抽樣分布的標準差 (Standard Error, SE):
樣本平均數 的抽樣分布的標準差,也稱為標準誤,其公式為 。
當樣本大小 增加時, 增加,因此 會減小。
所以,抽樣分布的標準差隨著樣本大小 的增加而減小。
第 11 題
A company records the monthly electricity usage of its offices, which follows a normal distribution with a mean of 500 kWh and a standard deviation of 50 kWh. Based on this information, which of the following statements about electricity usage is/are correct?
(A) Approximately 68% of the monthly electricity usage falls between 450 kWh and 550 kWh.
(B) Approximately 95% of the monthly electricity usage falls between 450 kWh and 550 kWh.
(C) Approximately 99.7% of the monthly electricity usage falls between 350 kWh and 650 kWh.
(D) About 16% of the offices use more than 550 kWh per month.
(E) The probability of usage being exactly 500 kWh is zero.
登入後即可作答並保存紀錄。
本題考驗對常態分布 (Normal Distribution) 特性和經驗法則 (Empirical Rule) 的理解。
已知母體為常態分布,平均數 kWh,標準差 kWh。
經驗法則 (68-95-99.7 Rule) 指出:
- 約 68% 的數據落在平均數的 個標準差範圍內。
- 約 95% 的數據落在平均數的 個標準差範圍內。
- 約 99.7% 的數據落在平均數的 個標準差範圍內。
我們逐一檢視選項:
(A) 落在 450 kWh 和 550 kWh 之間的比例。
根據經驗法則,約 68% 的數據落在 範圍內。
所以,選項 (A) 正確。
(B) 落在 450 kWh 和 550 kWh 之間的比例。
如上所述,450 和 550 是 。
選項 (B) 說約 95% fall between 450 kWh and 550 kWh,這是錯誤的。95% 對應的是 。
(C) 落在 350 kWh 和 650 kWh 之間的比例。
根據經驗法則,約 99.7% 的數據落在 範圍內。
所以,選項 (C) 正確。
第 12 題
The following data are from a simple random sample:
5, 8, 10, 7, 10, 14
Based on the data above, which of the following statements are correct?
(A) The point estimate of the population mean is 9.00.
(B) The point estimate of the population standard deviation is approximately 4.10.
(C) The point estimate of the population mean is 8.67.
(D) The range of the sample is 9.
(E) The median of the sample is 8.50.
登入後即可作答並保存紀錄。
本題考驗對樣本資料的敘述統計量計算,包括樣本平均數、樣本標準差、樣本範圍和樣本中位數。
樣本資料:5, 8, 10, 7, 10, 14。
樣本大小 。
首先,將樣本資料排序:5, 7, 8, 10, 10, 14。
計算樣本平均數 ():
。
因此,選項 (A)「母體平均數的點估計值是 9.00」是正確的。
選項 (C)「母體平均數的點估計值是 8.67」是錯誤的。
計算樣本變異數 ():
:
5 - 9 = -4
7 - 9 = -2
8 - 9 = -1
10 - 9 = 1
10 - 9 = 1
14 - 9 = 5
第 13 題
The state of California has a mean annual rainfall of 60 cm, while New York has a mean annual rainfall of 110 cm. The standard deviation for both states is 12 cm. A sample of 25 years of rainfall for California and a sample of 40 years of rainfall for New York has been taken.
Based on the information above, which of the following statements is correct?
(A) The standard error of the sample mean rainfall for California is greater than that for New York.
(B) The difference between the standard error of California and New York is 0.50.
(C) The probability that the sample mean is within 3 cm of the population mean is the same for both states.
(D) The sample size does not affect the standard error of the sample mean.
(E) The larger the sample size, the smaller the standard error of the sample mean.
登入後即可作答並保存紀錄。
核心觀念
本題考查「樣本平均數的標準誤」:
其中:
- :母體標準差
- :樣本數
- :樣本平均數的標準誤
由公式可知,在母體標準差相同時,樣本數越大,樣本平均數的標準誤越小。
解題方法
加州與紐約的母體標準差皆為 cm,因此分別計算樣本平均數的標準誤。
加州樣本數為 :
紐約樣本數為 :
因此:
紐約的樣本數較大,所以其樣本平均數較穩定、標準誤較小。
選項分析
(A) 加州樣本平均降雨量的標準誤大於紐約。
正確計算為:
因此:
此敘述本身正確。
(B) 加州與紐約標準誤的差為 。
兩者差異為:
第 14 題
A simple random sample of 60 items resulted in a sample mean of 80. The population standard deviation is .
Based on this information, which of the following statements are correct?
(A) The confidence interval for the population mean becomes narrower as the sample size increases.
(B) The confidence interval for a sample size of 120 will be wider than that for a sample size of 60.
(C) Increasing the sample size decreases the margin of error for the population mean.
(D) The confidence interval for the population mean is unaffected by changes in sample size.
(E) The larger the sample size, the greater the uncertainty in estimating the population mean.
登入後即可作答並保存紀錄。
本題考驗對信賴區間 (Confidence Interval, CI) 的性質,特別是樣本大小對信賴區間寬度的影響。
信賴區間的計算公式通常為:
CI = (若母體標準差 已知)
或 CI = (若母體標準差 未知,用樣本標準差 估計)
在此題中,母體標準差 已知,樣本大小 ,樣本平均數 。
信賴區間的寬度主要由「邊際誤差 (Margin of Error, ME)」決定,ME = 。
信賴區間的寬度是 。
我們逐一檢視選項:
(A) 信賴區間隨著樣本大小的增加而變窄。
隨著樣本大小 的增加, 增加,因此 減小。
第 15 題
A sample of 100 items is drawn from a population with a standard deviation of . The sample mean is . The null hypothesis is that the population mean . Based on this information, which of the following statements is correct?
(A) The test statistic is -2.0.
(B) The standard error of the mean for this sample is 2.5.
(C) The null hypothesis states that the sample mean is greater than 155.
(D) A negative test statistic indicates that the sample mean is less than the hypothesized population mean.
(E) The null hypothesis does not make any claim about the sample mean.
登入後即可作答並保存紀錄。
核心觀念
本題考查母體平均數假設檢定中的:
- 標準誤(standard error)
- 已知母體標準差時的 檢定統計量
- 虛無假設的意義
- 檢定統計量正負號的判讀
已知:
其中 是虛無假設所指定的假設母體平均數。
解題方法
因為母體標準差 已知,平均數的檢定統計量為:
先計算樣本平均數的標準誤:
再計算檢定統計量:
因此,樣本平均數 比假設的母體平均數 小,故檢定統計量為負值。
選項分析
(A) The test statistic is -2.0.
正確。由計算:
因此檢定統計量為 。
(B) The standard error of the mean for this sample is 2.5.
正確。標準誤為:
第 16 題
Which of the following statements about ANOVA is correct?
(A) One assumption of ANOVA is that each population has the same mean.
(B) One assumption of ANOVA is that the response variable is normally distributed for each population.
(C) The null hypothesis in ANOVA states that at least one population mean differs from the others.
(D) If ANOVA results indicate no significant difference, a post-hoc test must still be conducted to confirm.
(E) One-way ANOVA is a one-tailed test, while two-way ANOVA is a two-tailed test.
登入後即可作答並保存紀錄。
本題考驗對變異數分析 (Analysis of Variance, ANOVA) 基本概念和假設的理解。
我們逐一檢視選項:
(A) ANOVA 的一項假設是母體具有相同的平均數。
這是錯誤的。ANOVA 的目的是檢定母體平均數是否相等。虛無假設 () 是所有母體平均數相等,對立假設 () 是至少有一個母體平均數不同。所以「母體具有相同的平均數」是虛無假設的內容,而不是一個前提假設。
ANOVA 的假設是:
- 獨立性 (Independence):各組的觀測值是獨立的。
- 常態性 (Normality):各組的母體回應變數服從常態分布。
- 等變異數 (Homoscedasticity):各組母體的變異數相等。
所以,選項 (A) 是錯誤的。
(B) ANOVA 的一項假設是回應變數對於每個母體都是常態分布。
這是正確的。這是 ANOVA 的常態性假設。
第 17 題
Below is the estimated linear regression equation based on 12 observations, where x₁ and x₂ are numerical variables:
ŷ = 35 + 0.75x₁ + 0.4x₂
Where: SST(Total Sum of Squares)=8500; SSR(Regression Sum of Squares)=7650; Sb₁=0.10; Sb₂=0.09. The
b₁ and b₂ are the estimated values of B₁ and B₁ for the variables x₁ and x₂ respectively; Sb₁ and Sb₂ are the
standard errors of the estimated coefficients. Which of the following is/are correct?
(A) R-square =7650/8500
(B) MSR (regression mean square) =7650/2
(C) MSE (mean square error) =850/9
(D) The t-ratio for b₁ is 8.33.
(E) The standard error of the estimate decreases if the model fits the data better.
登入後即可作答並保存紀錄。
本題考驗對複迴歸分析 (Multiple Linear Regression) 中相關統計量的理解,包括判定係數 (R-squared)、均方 (Mean Square)、t 檢定以及標準誤的解釋。
已知資訊:
樣本數
迴歸線方程式:
,
SST (總平方和)
SSR (迴歸平方和)
(變數 的迴歸係數 的標準誤)
(變數 的迴歸係數 的標準誤)
我們逐一檢視選項:
(A) 判定係數 (R-squared):
。
這個敘述是正確的。
(B) MSR (迴歸均方):
MSR = 。
在複迴歸中,迴歸自由度等於自變數的個數 (p)。此模型有兩個自變數 ( 和 ),所以 。
MSR = 。
選項 (B) 說 MSR = 7650/2,這是正確的計算。
第 18 題
A company conducted an experiment to test whether different training programs have a significant impact on employee productivity. Three training programs (Program A, Program B, and Program C) were assigned to employees, and their productivity scores (out of 100) were recorded after completing the training. The following table summarizes the data collected from the experiment:
| Training Program | Productivity Scores |
|---|---|
| Program A | 63, 47, 54, 40 |
| Program B | 82, 72, 88, 66 |
| Program C | 69, 54, 61, 48 |
Based on the data above, which of the following statements are correct?
(A) The F-value from the ANOVA test is approximately 7.87.
(B) The p-value for the ANOVA test is approximately 0.011, which indicates that there are no significant differences between the training programs.
(C) The mean productivity scores for Program A and Program B differ significantly.
(D) The mean productivity scores for Program A and Program C differ significantly.
(E) The pooled standard deviation for the data can be used to compute the F-value directly without additional post-hoc tests.
登入後即可作答並保存紀錄。
核心觀念
本題考驗單因子變異數分析(one-way ANOVA),用來檢定三種訓練方案的平均生產力是否全部相同。
設三組母體平均數為 :
- 虛無假設:
- 對立假設: 至少有一組平均數不同
ANOVA 的檢定統計量為:
其中:
- :組間均方,反映各組平均數彼此差異
- :組內均方,反映同組資料的隨機變異
解題方法與計算
三組資料的平均數為:
總平均數為:
組間平方和:
組內平方和分別為:
因此:
自由度為:
組間均方與組內均方:
所以:
查詢 分配可得:
因為 ,拒絕虛無假設,表示三種訓練方案的平均生產力並非全部相同。接著必須進行事後比較,判斷究竟是哪幾組之間存在顯著差異。
使用 ANOVA 的組內均方 作為共同誤差變異估計。兩組平均數比較時:
第 19 題
Tom is a fitness enthusiast who owns a treadmill at home. He is considering whether to purchase a maintenance contract for his treadmill. Tom believes that the maintenance costs are directly related to the weekly usage of the treadmill. To help him make a decision, Tom collected data on the weekly hours of treadmill usage and corresponding annual maintenance costs (in hundreds of dollars) from other treadmill users in his fitness group:
| Weekly Treadmill Usage (hours) | Annual Maintenance Cost (hundreds of dollars) |
|---|---|
| 13 | 17.0 |
| 10 | 22.0 |
| 20 | 30.0 |
| 28 | 37.0 |
| 32 | 47.0 |
| 17 | 30.5 |
| 24 | 32.5 |
| 31 | 39.0 |
| 40 | 51.5 |
Based on the data above, which of the following statements are correct?
(A) The intercept of the regression equation is 10.53.
(B) The slope of the regression equation is 1.05.
(C) For a treadmill used 30 hours per week, the predicted annual maintenance cost is (2874, 4952), assuming .
(D) Tom should purchase a maintenance contract costing 3000.
(E) The intercept of the regression equation represents the annual maintenance cost when the treadmill is used for 0 hours per week.
登入後即可作答並保存紀錄。
核心觀念
本題考查**簡單線性迴歸分析(Simple Linear Regression)**的參數估計、統計意涵與預測區間建構:
- 模型設定:,其中自變數 為每週跑步機使用時數(Weekly Treadmill Usage, hours),應變數 為年維護費用(Annual Maintenance Cost,單位為百美元,即 1 = \100$)。
- 最小平方法(OLS)估計量:
- 樣本斜率:
- 樣本截距:
- 截距項之統計意涵:在線性迴歸方程式 中,截距 代表當自變數 (即每週使用時數為 0 小時)時,應變數 的估計期望值(基準維護費用)。
- 個別值預測區間(Prediction Interval for an Individual Value at ):
其中 為迴歸估計之殘差標準誤(Standard Error of Estimate)。
解題方法
步驟一:計算樣本基本彙總統計量
樣本數 。
-
自變數 的統計量:
-
應變數 的統計量:
-
交叉乘積和 :
步驟二:求解迴歸方程式
- 斜率 :
- 截距 :
第 20 題
A coffee shop owner is analyzing the sales of coffee on different days of the week to determine if the sales are evenly distributed across all days. A total of 420 cups of coffee were sold in one week, and the number of cups sold on each day is summarized in the table below:
| Day | Cups of Coffee Sold |
|---|---|
| Sunday | 66 |
| Monday | 50 |
| Tuesday | 53 |
| Wednesday | 47 |
| Thursday | 55 |
| Friday | 69 |
| Saturday | 80 |
Based on the data above, which of the following statements are correct?
()
(A) The expected number of cups of coffee sold per day, assuming equal distribution, is 60.
(B) The Chi-square statistic for this test is approximately 14.33.
(C) The p-value for this test is approximately 0.026, indicating that there is no significant difference in coffee sales across the days.
(D) Coffee sales on Saturday are significantly higher compared to the expected value, making it the day with the highest percentage of sales.
(E) At a significance level of 0.05, the null hypothesis that coffee sales are equally distributed across all days is rejected.
登入後即可作答並保存紀錄。
本題考驗對卡方適合度檢定 (Chi-square Goodness-of-Fit Test) 的應用。我們要檢定咖啡銷量是否在每週的各天均勻分布。
1. 設定假設:
虛無假設 ():咖啡銷量在每週的各天均勻分布。
對立假設 ():咖啡銷量在每週的各天不均勻分布。
2. 計算預期頻率 (Expected Frequencies):
總銷售量 = 420 杯。
一週有 7 天。
如果銷量均勻分布,則每天的預期銷售量為:
杯。
選項 (A)「假設均勻分布,每天預期銷售的咖啡杯數是 60」是正確的。
3. 計算卡方檢定統計量 ():
卡方統計量公式為:,其中 是觀察頻率, 是預期頻率。
| Day | Observed () | Expected () | |||
|---|---|---|---|---|---|
| Sunday | 66 | 60 | 6 | 36 | |
| Monday | 50 | 60 | -10 | 100 | |
| Tuesday | 53 | 60 | -7 | 49 | |
| Wednesday | 47 | 60 | -13 | 169 | |
| Thursday | 55 | 60 | -5 | 25 |