Question

You are a consultant to the marketing department of a business preparing to launch an ad campaign for a new product. The company can afford to run ads during one TV show, and has decided not to sponsor a show with sexual content. Do these results indicate that viewer memory for ads may differ depending on program content? Conduct an appropriate hypothesis test at the a= 0.05 level. Show your working, which test statistic are u using? Assume population standard deviations are equal. What would you recommend?

Sex and violence TheJournal of Applied Psychology reported on a study that examined whether the content of TV shows influenced the ability of viewers to recall brand names of items featured in the commercials. The researchers randomly assigned volunteers to watch one of three programs, each containing the same nine commercials. One of the programs had violent content another sexual content, and the third neutral content. After the shows ended, the subjects were asked to recall the brands of products that were advertised. Here are summaries of the results: Program Type Violent Sexual Neutral No. of subjects Brands recalled108 108 108 2.08 1.71 3.17 Mean SD 1.87 1.76 1.77

Answer 1

Since we need to compare more than three population mean so one way ANOVA will be used.

Hypotheses are:

$H_{0}:\mu_{1}=\mu_{2}=\mu_{3}$

Ha: At least one population mean differ.

Here we have

108, T1 2.08 +1.713.17 2.08, 72 - 1.71,73 3.17,si 1.87, s 1.762, s2 = 1.772, 2.32

Now :

SStreatments _ n! (zi-i)2 + n2(T2-x)2 + n3Tz-x)2-124.4376

and

SSerror = (n1-1) sỉ + (n2 - + (R3-1)s-1040.8318 1) s

Therefore

SStotal-SStreatments SSerror-1165.2694

Since there are 3 different groups so we have k=3. Therefore degree of freedoms are:

dftreat ments-k-1 = 3-1 = 2

dferrorN - k-324- 3321

dftotal - 323

-------------

Now

-622188 sst re at ments MStreatmentsdftreatments

Serror = error = 3.2425 MSerror dferror eTTo eTTo

F test statistics is

Streatments19.1887 M Serror

So p-value of the test is 0.0000. Since P-value is less than 0.05 so we reject the null hypothesis. That is we can conclude that viewer memory for ads may differ depending on program content.