Presentation is loading. Please wait.

Presentation is loading. Please wait.

Distribution of a Difference in Means

Similar presentations


Presentation on theme: "Distribution of a Difference in Means"β€” Presentation transcript:

1 Distribution of a Difference in Means
Section 6.4-D Distribution of a Difference in Means

2 Math SAT by Gender The average math SAT score for males is 534 with a standard deviation of The average math SAT score for females is 500 with a standard deviation of If we were to take random samples of 50 males and 50 females and record the difference in means π‘₯ 𝑀 βˆ’ π‘₯ 𝐹 , what shape would the sampling distribution have? Symmetric and bell-shaped Skewed to the right Skewed to the left None of the above Impossible to determine

3 Math SAT by Gender The average math SAT score for males is 534 with a standard deviation of The average math SAT score for females is 500 with a standard deviation of If we were to take random samples of 50 males and 50 females and record the difference in means π‘₯ 𝑀 βˆ’ π‘₯ 𝐹 , where would the sampling distribution be located? 534 500 34 23 18 π‘₯ 𝑀 βˆ’ π‘₯ 𝐹 =534βˆ’500=34

4 Math SAT by Gender The average math SAT score for males is 534 with a standard deviation of The average math SAT score for females is 500 with a standard deviation of If we were to take random samples of 50 males and 50 females and record the difference in means π‘₯ 𝑀 βˆ’ π‘₯ 𝐹 , what will the standard error be? 534 500 34 23 18 π‘₯ 𝑀 βˆ’ π‘₯ 𝐹 ~ 𝑁 πœ‡ 𝑀 βˆ’ πœ‡ 𝐹 , 𝜎 𝑀 𝑛 𝑀 + 𝜎 𝐹 𝑛 𝐹 ~ 𝑁 534βˆ’500, ~ 𝑁 34, 23

5 Confidence Interval for a Difference in Means
Section 6.4-CI Confidence Interval for a Difference in Means

6 Video Games and GPA 210 first-year college students were randomly assigned roommates For the 78 students assigned to roommates who brought a videogame to college: average GPA after the first semester was 2.84, with a sd of For the 132 students assigned to roommates who did not bring a videogame to college, average GPA after the first semester was 3.105, with a sd of How much does getting assigned a roommate who brings a videogame to college affect your first semester GPA? Give a 90% confidence interval.

7 Video Games and GPA 78 students whose roommates brought a videogame to college: average GPA was 2.84, with a sd of 132 students whose roommates did not bring a videogame to college: average GPA was 3.105, with a sd of For a 90% confidence interval, what is t*? a) b) c) d) e) t with 78 – 1 = 77 df, 90% CI: => t* = 1.665

8 Video Games and GPA 78 students whose roommates brought a videogame to college: average GPA was 2.84, with a sd of 132 students whose roommates did not bring a videogame to college: average GPA was 3.105, with a sd of For a 90% CI, what is the relevant sample statistic? a) b) c) d) e) π‘₯ 1 βˆ’ π‘₯ 2 = 2.84 – =

9 Video Games and GPA 78 students whose roommates brought a videogame to college: average GPA was 2.84, with a sd of 132 students whose roommates did not bring a videogame to college: average GPA was 3.105, with a sd of For a 90% CI, what is the standard error? a) b) c) d) e) SE = 𝑠 𝑛 𝑠 𝑛 2 = =0.093

10 Videogames and GPA 78 β‰₯ 30, 132 β‰₯ 30 t with 78 – 1 = 77 df, 90% CI:
78 β‰₯ 30, 132 β‰₯ 30 1. Check conditions: 2. Find t*: t with 78 – 1 = 77 df, 90% CI: => t* = 1.665 3. Calculate statistic: π‘₯ 1 βˆ’ π‘₯ 2 = 2.84 – = – 0.265 SE = 𝑠 𝑛 𝑠 𝑛 2 = =0.093 4. Calculate standard error: 5. Calculate CI: π‘₯ 1 βˆ’ π‘₯ 2 Β± 𝑑 βˆ— βˆ™π‘†πΈ =βˆ’0.265Β±1.665βˆ™0.093 = βˆ’0.265 Β± 0.155 (-0.42, -0.11) 5. Interpret in context: We are 90% confident that getting assigned a roommate who brings a videogame to college decreases a student’s first semester GPA by 0.11 to 0.42 points, on average.

11 Hypothesis Test for a Difference in Means
Section 6.4-HT Hypothesis Test for a Difference in Means

12 The Pygmalion Effect Pygmalion Effect: the greater the expectation placed upon people, the better they perform Teachers were told that certain children (chosen randomly) were expected to be β€œgrowth spurters,” based on the Harvard Test of Inflected Acquisition (a test that didn’t actually exist). The response variable is change in IQ over the course of one year. Source: Rosenthal, R. and Jacobsen, L. (1968). β€œPygmalion in the Classroom: Teacher Expectation and Pupils’ Intellectual Development.” Holt, Rinehart and Winston, Inc.

13 The Pygmalion Effect (a) 2.096 (b) 3.80 (c) 1.813 (d) 0.02 (e) 64 n 𝒙
s Control Students 255 8.42 12.0 β€œGrowth Spurters” 65 12.22 13.3 Does this provide evidence that merely expecting a child to do better actually causes the child to do better? Find the test statistic: (a) 2.096 (b) 3.80 (c) 1.813 (d) 0.02 (e) 64 t= π‘ π‘‘π‘Žπ‘‘π‘–π‘ π‘‘π‘–π‘ βˆ’π‘›π‘’π‘™π‘™ 𝑆𝐸 = π‘₯ 1 βˆ’ π‘₯ 𝑠 𝑛 𝑠 𝑛 2 = 12.22βˆ’ = =2.096

14 The Pygmalion Effect (a) 2.096 (b) 3.80 (c) 0.98 (d) 0.02 (e) 0.04 n 𝒙
s Control Students 255 8.42 12.0 β€œGrowth Spurters” 65 12.22 13.3 Does this provide evidence that merely expecting a child to do better actually causes the child to do better? Find the p-value when the t-statistic is 2.096: (a) (b) 3.80 (c) 0.98 (d) 0.02 (e) 0.04 t with 65 – 1 = 64 df, upper tail p-value = 0.02

15 The Pygmalion Effect n 𝒙 s Control Students 255 8.42 12.0 β€œGrowth Spurters” 65 12.22 13.3 Does this provide evidence that the Pygmalion Effect exists? (that merely expecting a child to do better actually causes the child to do better?) (a) Yes (b) No

16 Pygmalion Effect H0: 1 = 2 Ha: 1 > 2
1 = average change in IQ for β€œgrowth spurters” 1 = average change in IQ for control 1. State hypotheses: n1 = 65 β‰₯ 30, n2 = 255 β‰₯ 30 2. Check conditions: π‘₯ 1 βˆ’ π‘₯ 2 =12.22 – 8.42 = 3.8 3. Calculate statistic: SE = 𝑠 𝑛 𝑠 𝑛 2 = =1.813 4. Calculate standard error: t= π‘ π‘‘π‘Žπ‘‘π‘–π‘ π‘‘π‘–π‘ βˆ’π‘›π‘’π‘™π‘™ 𝑆𝐸 = =2.096 5. Calculate test statistic: 6. Compute p-value: t with 65 – 1 = 64 df, upper tail p-value = 0.02 7. Interpret in context: We have evidence that positive teacher expectations significantly increase IQ scores, on average, in elementary school children.


Download ppt "Distribution of a Difference in Means"

Similar presentations


Ads by Google