Download presentation
Presentation is loading. Please wait.
Published byBrooke Logan Modified over 6 years ago
1
Introduction to Statistics for the Social Sciences SBS200, COMM200, GEOG200, PA200, POL200, or SOC200 Lecture Section 001, Fall 2015 Room 150 Harvill Building 10: :50 Mondays, Wednesdays & Fridays. Welcome
3
By the end of lecture today 10/30/15
Logic of hypothesis testing Steps for hypothesis testing Levels of significance (Levels of alpha) what does p < 0.05 mean? what does p < 0.01 mean? Two-sample t-tests
4
Before next exam (November 20th)
Please read chapters in OpenStax textbook Please read Chapters 2, 3, and 4 in Plous Chapter 2: Cognitive Dissonance Chapter 3: Memory and Hindsight Bias Chapter 4: Context Dependence
5
Homework Assignment No Homework due Monday, November 2nd
6
Confidence Interval of 95% Has and alpha of 5% α = .05
Critical t close to -2.58 Confidence Interval of 99% Has and alpha of 1% α = .01 99% Critical t close to -2.58 Area outside confidence interval is alpha Confidence Interval of 95% Has and alpha of 5% α = .05 95% Critical t close to -1.96 Critical t close to 1.96 Area in the tails is called alpha Confidence Interval of 90% Has and alpha of 10% α = . 10 Critical t close to -1.64 90% Critical t close to 1.64 Area associated with most extreme scores is called alpha
7
Review of the homework assignment
8
Melvin Melvin Mark Difference not due sample size because both samples same size Difference not due population variability because same population Yes! Difference is due to sloppiness and random error in Melvin’s sample Melvin
9
6 – 5 = 4.0 .25 Two tailed test 1.96 (α = .05) 1 1 = = .25 16 4 √ 4.0
z- score : because we know the population standard deviation Ho: µ = 5 Bags of potatoes from that plant are not different from other plants Ha: µ ≠ 5 Bags of potatoes from that plant are different from other plants Two tailed test 1.96 (α = .05) 1 1 = = .25 6 – 5 16 4 √ = 4.0 .25 4.0 -1.96 1.96
10
Because the observed z (4.0 ) is bigger than critical z (1.96)
These three will always match Yes Yes Probability of Type I error is always equal to alpha Yes .05 1.64 No Because observed z (4.0) is still bigger than critical z (1.64) 2.58 No Because observed z (4.0) is still bigger than critical z(2.58) there is a difference there is not there is no difference there is 1.96 2.58
11
89 - 85 Two tailed test (α = .05) n – 1 =16 – 1 = 15
-2.13 2.13 t- score : because we don’t know the population standard deviation Two tailed test (α = .05) n – 1 =16 – 1 = 15 Critical t(15) = 2.131 2.667 6 √ 16
12
Because the observed z (2.67) is bigger than critical z (2.13)
These three will always match Yes Yes Probability of Type I error is always equal to alpha Yes .05 1.753 No Because observed t (2.67) is still bigger than critical t (1.753) 2.947 Yes Because observed t (2.67) is not bigger than critical t(2.947) No These three will always match No No consultant did improve morale she did not consultant did not improve morale she did 2.131 2.947
13
Value of observed statistic
Finish with statistical summary z = 4.0; p < 0.05 Or if it *were not* significant: z = 1.2 ; n.s. Start summary with two means (based on DV) for two levels of the IV Describe type of test (z-test versus t-test) with brief overview of results n.s. = “not significant” p<0.05 = “significant” The average weight of bags of potatoes from this particular plant is 6 pounds, while the average weight for population is 5 pounds. A z-test was completed and this difference was found to be statistically significant. We should fix the plant. (z = 4.0; p<0.05) Value of observed statistic
14
Value of observed statistic
Finish with statistical summary t(15) = 2.67; p < 0.05 Or if it *were not* significant: t(15) = 1.07; n.s. Start summary with two means (based on DV) for two levels of the IV Describe type of test (z-test versus t-test) with brief overview of results n.s. = “not significant” p<0.05 = “significant” The average job-satisfaction score was 89 for the employees who went On the retreat, while the average score for population is 85. A t-test was completed and this difference was found to be statistically significant. We should hire the consultant. (t(15) = 2.67; p<0.05) Value of observed statistic df
15
Hypothesis testing Is this a single sample or two sample test?
Is it a z or a t test or an ANOVA? Hypothesis testing Is it a one-tail test or a two tail test? Step 1: Identify the research problem Did the sheriff keep her promise to change response times from the previous average of 30 minutes? Step 2: Describe the null and alternative hypotheses Ho: The response times are not changed H1: The response times did change As the new chief of police, I am going to change response times for traffic accidents. Before I started the average response time was 30 minutes 15
16
Hypothesis testing Two-tailed test n = 10 df = 9 alpha = 0.05
Gather the data: We measured the time for police to respond to 10 accidents Two-tailed test One or two tailed test? What is our sample size What is size of our degrees of freedom? What is our alpha What is our critical t value? n = 10 (df = 9) Alpha = .05 Decision rule: critical t = 1.83 n = 10 df = 9 alpha = 0.05 16
17
Hypothesis testing Two-tailed test Alpha of 0.05
Gather the data: We measured the time for police to respond to 10 accidents One or two tailed test? What is our sample size What is size of our degrees of freedom? What is our alpha What is our critical t value? Decision rule: critical t = 2.262 Two-tailed test Alpha of 0.05 Critical t (9) = 2.262 17
18
Average time for response before 30 minutes
Step 3: Calculations: Average time for response before 30 minutes Average time for response after 24 minutes Observed t = Step 4: Make decision whether or not to reject null hypothesis Observed t = Critical t = 2.262 -2.71 is farther out on the curve than 2.262 so, we do not reject the null hypothesis Step 5: Conclusion: There appears to be a significant difference between the sheriff’s times and 30 minutes 18
19
Hypothesis testing: Did the sheriff keep her promise to reduce response times to less than 30 minutes? Start summary with two means (based on DV) for two levels of the IV notice we are comparing a sample mean with a population mean: single sample t-test Finish with statistical summary t(9) = -5.71; p < 0.05 Describe type of test (t-test versus anova) with brief overview of results Or if it had been different results that *were not* significant: t(9) = -1.71; ns The mean response time for following the sheriff’s new plan was 24 minutes, while the mean response time prior to the new plan was 30 minutes. A t-test was completed and there appears to be a significant difference in the response time following the implementation of the new plan t(9) = -2.71; p < 0.05 Type of test with degrees of freedom n.s. = “not significant” p<0.05 = “significant” n.s. = “not significant” p<0.05 = “significant” Value of observed statistic 19
20
A note on z scores, and t score:
. . A note on z scores, and t score: Numerator is always distance between means (how far away the distributions are or “effect size”) Denominator is always measure of variability (how wide or much overlap there is between distributions) Difference between means Difference between means Variability of curve(s) (within group variability) Variability of curve(s)
21
A note on variability versus effect size Difference between means
. A note on variability versus effect size Difference between means Difference between means Variability of curve(s) Variability of curve(s) (within group variability)
22
A note on variability versus effect size Difference between means
. A note on variability versus effect size Difference between means Difference between means . Variability of curve(s) Variability of curve(s) (within group variability)
23
Effect size is considered relative to variability of distributions
. Effect size is considered relative to variability of distributions 1. Larger variance harder to find significant difference Treatment Effect x Treatment Effect 2. Smaller variance easier to find significant difference x
24
Effect size is considered relative to variability of distributions
. Effect size is considered relative to variability of distributions Treatment Effect x Difference between means Treatment Effect x Variability of curve(s) (within group variability)
25
Thank you! See you next time!!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.